diff options
224 files changed, 7981 insertions, 3427 deletions
diff --git a/.githubmap b/.githubmap index 5265fa59bed..c8ae6e284a2 100644 --- a/.githubmap +++ b/.githubmap @@ -9,6 +9,7 @@ # a2batic Kanika Murarka <kmurarka@redhat.com> aaSharma14 Aashish Sharma <aasharma@redhat.com> +abhishek-kane Abhishek Kane <abhishek.kane@ibm.com> <abhishek.kane@gmail.com> aclamk Adam Kupczyk <akupczyk@redhat.com> adamemerson Adam C. Emerson <aemerson@redhat.com> adk3798 Adam King <adking@redhat.com> @@ -13,6 +13,7 @@ Aashish Sharma <aasharma@redhat.com> <66050535+aaSharma14@users.noreply.github.c Aashish Sharma <aasharma@redhat.com> <aasharma@li-e74156cc-2f67-11b2-a85c-e98659a63c5c.ibm.com> Aashish Sharma <aasharma@redhat.com> <aashishsharma@fedora.redhat.com> Aashish Sharma <aasharma@redhat.com> <aashishsharma@localhost.localdomain> +Abhishek Kane <abhishek.kane@ibm.com> <abhishek.kane@gmail.com> Abhishek Lekshmanan <abhishek.lekshmanan@cern.ch> <abhishek.l@cern.ch> Abhishek Lekshmanan <abhishek@suse.com> <abhishek.lekshmanan@gmail.com> Abhishek Lekshmanan <abhishek@suse.com> <alekshmanan@suse.com> diff --git a/.organizationmap b/.organizationmap index e59e6ae24e1..ac9b0ea70fe 100644 --- a/.organizationmap +++ b/.organizationmap @@ -345,6 +345,7 @@ Huawei <contact@huawei.com> Yehu <yehu5@huawei.com> Huayun <contact@huayun.com> Zheng Yin <zhengyin@huayun.com> Huazhong University of Science and Technology <contact@hust.edu.cn> Luo Runbing <runsisi@hust.edu.cn> HXT Semiconductor <contact@hxt-semitech.org> Jiang Yutang <yutang2.jiang@hxt-semitech.com> +IBM <contact@IBM.com> Abhishek Kane <abhishek.kane@ibm.com> IBM <contact@IBM.com> Adam Kupczyk <akupczyk@ibm.com> IBM <contact@IBM.com> Afreen Misbah <afreen@ibm.com> IBM <contact@IBM.com> Aliaksei Makarau <aliaksei.makarau@ibm.com> diff --git a/.peoplemap b/.peoplemap index 418e8505fb4..ed70830c092 100644 --- a/.peoplemap +++ b/.peoplemap @@ -16,6 +16,7 @@ # # git log --pretty='%aN <%aE>' $range | git -c mailmap.file=.peoplemap check-mailmap --stdin | sort | uniq | sed -e 's/\(.*\) \(<.*\)/\2 \1/' | uniq --skip-field=1 --all-repeated | sed -e 's/\(.*>\) \(.*\)/\2 \1/' # +Abhishek Kane <abhishek.kane@ibm.com> <abhishek.kane@gmail.com> Abhishek Lekshmanan <abhishek.lekshmanan@cern.ch> <abhishek@suse.com> Adam Kupczyk <akupczyk@ibm.com> <akupczyk@redhat.com> <akupczyk@mirantis.com> Alexandre Marangone <amarango@redhat.com> Alexandre Marangone <alexandre.marangone@inktank.com> diff --git a/container/Containerfile b/container/Containerfile index c954ebed1be..9a5a88e76a1 100644 --- a/container/Containerfile +++ b/container/Containerfile @@ -212,6 +212,7 @@ RUN rpm -q $(cat packages.txt) && rm -f /var/lib/rpm/__db* && rm -f *packages.tx # Set some envs in the container for quickly inspecting details about the build at runtime ENV CEPH_IS_DEVEL="${CI_CONTAINER}" \ CEPH_REF="${CEPH_REF}" \ + CEPH_VERSION="${CEPH_REF}" \ CEPH_OSD_FLAVOR="${OSD_FLAVOR}" \ FROM_IMAGE="${FROM_IMAGE}" diff --git a/doc/_ext/ceph_commands.py b/doc/_ext/ceph_commands.py index 0697c71f0e1..d96eab08853 100644 --- a/doc/_ext/ceph_commands.py +++ b/doc/_ext/ceph_commands.py @@ -94,7 +94,7 @@ class CmdParam(object): self.goodchars = goodchars self.positional = positional != 'false' - assert who == None + assert who is None def help(self): advanced = [] diff --git a/doc/cephadm/services/osd.rst b/doc/cephadm/services/osd.rst index 831bd238c79..90ebd86f897 100644 --- a/doc/cephadm/services/osd.rst +++ b/doc/cephadm/services/osd.rst @@ -198,6 +198,18 @@ There are a few ways to create new OSDs: .. warning:: When deploying new OSDs with ``cephadm``, ensure that the ``ceph-osd`` package is not already installed on the target host. If it is installed, conflicts may arise in the management and control of the OSD that may lead to errors or unexpected behavior. +* OSDs created via ``ceph orch daemon add`` are by default not added to the orchestrator's OSD service, they get added to 'osd' service. To attach an OSD to a different, existing OSD service, issue a command of the following form: + + .. prompt:: bash * + + ceph orch osd set-spec-affinity <service_name> <osd_id(s)> + + For example: + + .. prompt:: bash # + + ceph orch osd set-spec-affinity osd.default_drive_group 0 1 + Dry Run ------- diff --git a/doc/cephadm/services/rgw.rst b/doc/cephadm/services/rgw.rst index ed0b149365a..3df8ed2fc56 100644 --- a/doc/cephadm/services/rgw.rst +++ b/doc/cephadm/services/rgw.rst @@ -173,6 +173,32 @@ Then apply this yaml document: Note the value of ``rgw_frontend_ssl_certificate`` is a literal string as indicated by a ``|`` character preserving newline characters. +Disabling multisite sync traffic +-------------------------------- + +There is an RGW config option called ``rgw_run_sync_thread`` that tells the +RGW daemon to not transmit multisite replication data. This is useful if you want +that RGW daemon to be dedicated to I/O rather than multisite sync operations. +The RGW spec file includes a setting ``disable_multisite_sync_traffic`` that when +set to "True" will tell cephadm to set ``rgw_run_sync_thread`` to false for all +RGW daemons deployed for that RGW service. For example + +.. code-block:: yaml + + service_type: rgw + service_id: foo + placement: + label: rgw + spec: + rgw_realm: myrealm + rgw_zone: myzone + rgw_zonegroup: myzg + disable_multisite_sync_traffic: True + +.. note:: This will only stop the RGW daemon(s) from sending replication data. + The daemon can still receive replication data unless it has been removed + from the zonegroup and zone replication endpoints. + Service specification --------------------- diff --git a/doc/cephfs/disaster-recovery-experts.rst b/doc/cephfs/disaster-recovery-experts.rst index 7677b42f47e..b01a3dfde6a 100644 --- a/doc/cephfs/disaster-recovery-experts.rst +++ b/doc/cephfs/disaster-recovery-experts.rst @@ -21,43 +21,46 @@ Advanced: Metadata repair tools Journal export -------------- -Before attempting dangerous operations, make a copy of the journal like so: +Before attempting any dangerous operation, make a copy of the journal by +running the following command: -:: +.. prompt:: bash # - cephfs-journal-tool journal export backup.bin + cephfs-journal-tool journal export backup.bin -Note that this command may not always work if the journal is badly corrupted, -in which case a RADOS-level copy should be made (http://tracker.ceph.com/issues/9902). +If the journal is badly corrupted, this command might not work. If the journal +is badly corrupted, make a RADOS-level copy +(http://tracker.ceph.com/issues/9902). Dentry recovery from journal ---------------------------- If a journal is damaged or for any reason an MDS is incapable of replaying it, -attempt to recover what file metadata we can like so: +attempt to recover file metadata by running the following command: -:: +.. prompt:: bash # - cephfs-journal-tool event recover_dentries summary + cephfs-journal-tool event recover_dentries summary -This command by default acts on MDS rank 0, pass --rank=<n> to operate on other ranks. +By default, this command acts on MDS rank ``0``. Pass the option ``--rank=<n>`` +to the ``cephfs-journal-tool`` command to operate on other ranks. -This command will write any inodes/dentries recoverable from the journal -into the backing store, if these inodes/dentries are higher-versioned -than the previous contents of the backing store. If any regions of the journal -are missing/damaged, they will be skipped. +This command writes all inodes and dentries recoverable from the journal into +the backing store, but only if these inodes and dentries are higher-versioned +than the existing contents of the backing store. Any regions of the journal +that are missing or damaged will be skipped. -Note that in addition to writing out dentries and inodes, this command will update -the InoTables of each 'in' MDS rank, to indicate that any written inodes' numbers -are now in use. In simple cases, this will result in an entirely valid backing +In addition to writing out dentries and inodes, this command updates the +InoTables of each ``in`` MDS rank, to indicate that any written inodes' numbers +are now in use. In simple cases, this will result in an entirely valid backing store state. .. warning:: - The resulting state of the backing store is not guaranteed to be self-consistent, - and an online MDS scrub will be required afterwards. The journal contents - will not be modified by this command, you should truncate the journal + The resulting state of the backing store is not guaranteed to be + self-consistent, and an online MDS scrub will be required afterwards. The + journal contents will not be modified by this command. Truncate the journal separately after recovering what you can. Journal truncation diff --git a/doc/conf.py b/doc/conf.py index 4fdc9a53b75..5293ff1b212 100644 --- a/doc/conf.py +++ b/doc/conf.py @@ -76,7 +76,7 @@ html_show_sphinx = False html_static_path = ["_static"] html_sidebars = { '**': ['smarttoc.html', 'searchbox.html'] - } +} html_css_files = ['css/custom.css'] @@ -133,13 +133,23 @@ extensions = [ 'sphinxcontrib.mermaid', 'sphinxcontrib.openapi', 'sphinxcontrib.seqdiag', - ] +] ditaa = shutil.which("ditaa") if ditaa is not None: # in case we don't have binfmt_misc enabled or jar is not registered - ditaa_args = ['-jar', ditaa] - ditaa = 'java' + _jar_paths = [ + '/usr/share/ditaa/lib/ditaa.jar', # Gentoo + '/usr/share/ditaa/ditaa.jar', # deb + '/usr/share/java/ditaa.jar', # rpm + ] + _jar_paths = [p for p in _jar_paths if os.path.exists(p)] + if _jar_paths: + ditaa = 'java' + ditaa_args = ['-jar', _jar_paths[0]] + else: + # keep ditaa from shutil.which + ditaa_args = [] extensions += ['sphinxcontrib.ditaa'] else: extensions += ['plantweb.directive'] diff --git a/doc/dev/developer_guide/testing_integration_tests/tests-integration-testing-teuthology-workflow.rst b/doc/dev/developer_guide/testing_integration_tests/tests-integration-testing-teuthology-workflow.rst index 34dfd521eaa..6964012ef31 100644 --- a/doc/dev/developer_guide/testing_integration_tests/tests-integration-testing-teuthology-workflow.rst +++ b/doc/dev/developer_guide/testing_integration_tests/tests-integration-testing-teuthology-workflow.rst @@ -6,7 +6,8 @@ Integration Tests using Teuthology Workflow Infrastructure -------------- -Components: +Components +********** 1. `ceph-ci`_: Clone of the main Ceph repository, used for triggering Jenkins Ceph builds for development. @@ -44,7 +45,27 @@ Components: Each Teuthology test *run* contains multiple test *jobs*. Each job runs in an environment isolated from other jobs, on a different collection of test nodes. -To test a change in Ceph, follow these steps: +Workflow Overview +***************** + +.. image:: workflow.png + + +To test a change in Ceph, start by pushing a branch with your changes to the +`ceph-ci`_ repository. This will automatically trigger the Jenkins process +to build Ceph binaries - the status of the build can be observed on `Shaman`_. +These built packages will be uploaded on `Chacra`_. + +To schedule a Teuthology integration test against this new build, you will +need access to the Sepia lab. Once you have access, log into the Teuthology +machine and complete the one-time initial Teuthology setup required to run +Teuthology commands. After the setup, use the ``teuthology-suite`` command to schedule +a Teuthology run. In this command, use the ``-c <ceph-ci branch name>`` option to +specify your build. The results of your test can be observed on `Pulpito`_. +Log into a `developer playground machine`_ to review the Teuthology run's archive logs. + + +The rest of the document will explain these steps in detail: 1. Getting binaries - Build Ceph. 2. Scheduling Test Run: @@ -98,6 +119,31 @@ Ceph binaries must be built for your branch before you can use teuthology to run .. _the Chacra site: https://shaman.ceph.com/api/search/?status=ready&project=ceph +Pushing to the ceph-ci repository +********************************* + +Follow these steps to push to the ceph-ci repository. After pushing, a new build will +automatically be scheduled. + +1. Add the ceph-ci repository as a remote to your local clone of the Ceph repository: + + .. prompt:: bash $ + + git remote add ceph-ci git@github.com:ceph/ceph-ci.git + + $ git remote -v + origin git@github.com:ceph/ceph.git (fetch) + origin git@github.com:ceph/ceph.git (push) + ceph-ci git@github.com:ceph/ceph-ci.git (fetch) + ceph-ci git@github.com:ceph/ceph-ci.git (push) + +2. Push your branch upstream by running a command of the following form: + + .. prompt:: bash $ + + $ git push ceph-ci wip-yourname-feature-x + + Naming the ceph-ci branch ************************* Prepend your branch with your name before you push it to ceph-ci. For example, @@ -110,15 +156,14 @@ the name of that stable branch in your ceph-ci branch name. For example, the ``feature-x`` PR branch should be named ``wip-feature-x-nautilus``. *This is not just a convention. This ensures that your branch is built in the correct environment.* -You can choose to only trigger a CentOS 9.Stream build (excluding other distro like ubuntu) -by adding "centos9-only" at the end of the ceph-ci branch name. For example, -``wip-$yourname-feature-centos9-only``. This helps to get quicker builds and save resources -when you don't require binaries for other distros. - Delete the branch from ceph-ci when you no longer need it. If you are logged in to GitHub, all your branches on ceph-ci can be found here: https://github.com/ceph/ceph-ci/branches. +.. note:: You can choose to only trigger a CentOS 9.Stream build (excluding other + distro like ubuntu) by adding "centos9-only" at the end of the ceph-ci branch name. + For example, ``wip-$yourname-feature-centos9-only``. This helps to get quicker builds + and save resources when you don't require binaries for other distros. Scheduling Test Run ------------------- diff --git a/doc/dev/developer_guide/testing_integration_tests/workflow.png b/doc/dev/developer_guide/testing_integration_tests/workflow.png Binary files differnew file mode 100644 index 00000000000..610baf683bc --- /dev/null +++ b/doc/dev/developer_guide/testing_integration_tests/workflow.png diff --git a/doc/man/8/cephadm.rst b/doc/man/8/cephadm.rst index b2cad6cb505..3c23a9867f7 100644 --- a/doc/man/8/cephadm.rst +++ b/doc/man/8/cephadm.rst @@ -13,7 +13,7 @@ Synopsis | [--log-dir LOG_DIR] [--logrotate-dir LOGROTATE_DIR] | [--unit-dir UNIT_DIR] [--verbose] [--timeout TIMEOUT] | [--retry RETRY] [--no-container-init] -| {version,pull,inspect-image,ls,list-networks,adopt,rm-daemon,rm-cluster,run,shell,enter,ceph-volume,unit,logs,bootstrap,deploy,check-host,prepare-host,add-repo,rm-repo,install,list-images} +| {version,pull,inspect-image,ls,list-networks,adopt,rm-daemon,rm-cluster,run,shell,enter,ceph-volume,unit,logs,bootstrap,deploy,check-host,prepare-host,add-repo,rm-repo,install,list-images,update-osd-service} | ... @@ -106,6 +106,7 @@ Synopsis | **cephadm** **list-images** +| **cephadm** **update-osd-service** [-h] [--fsid FSID] --osd-ids OSD_IDS --service-name SERVICE_NAME Description @@ -535,6 +536,18 @@ list-images List the default container images for all services in ini format. The output can be modified with custom images and passed to --config flag during bootstrap. +update-osd-service +------------------ + +Update the OSD service for specific OSDs + +Arguments: + +* [--fsid FSID] cluster FSID +* --osd-ids OSD_IDS Comma-separated OSD IDs +* --service-name SERVICE_NAME OSD service name + + Availability ============ diff --git a/doc/rados/operations/stretch-mode.rst b/doc/rados/operations/stretch-mode.rst index e8be5e13e6a..7a4fa46117d 100644 --- a/doc/rados/operations/stretch-mode.rst +++ b/doc/rados/operations/stretch-mode.rst @@ -119,13 +119,29 @@ See https://tracker.ceph.com/issues/68338 for more information. Stretch Mode ============ -Stretch mode is designed to handle deployments in which you cannot guarantee the -replication of data across two data centers. This kind of situation can arise -when the cluster's CRUSH rule specifies that three copies are to be made, but -then a copy is placed in each data center with a ``min_size`` of 2. Under such -conditions, a placement group can become active with two copies in the first -data center and no copies in the second data center. +Stretch mode is designed to handle netsplit scenarios between two data zones as well +as the loss of one data zone. It handles the netsplit scenario by choosing the surviving zone +that has the better connection to the ``tiebreaker monitor``. It handles the loss of one zone by +reducing the ``size`` to ``2`` and ``min_size`` to ``1``, allowing the cluster to continue operating +with the remaining zone. When the lost zone comes back, the cluster will recover the lost data +and return to normal operation. + +Connectivity Monitor Election Strategy +--------------------------------------- +When using stretch mode, the monitor election strategy must be set to ``connectivity``. +This strategy tracks network connectivity between the monitors and is +used to determine which zone should be favored when the cluster is in a netsplit scenario. + +See `Changing Monitor Elections`_ + +Stretch Peering Rule +-------------------- +One critical behavior of stretch mode is its ability to prevent a PG from going active if the acting set +contains only replicas from a single zone. This safeguard is crucial for mitigating the risk of data +loss during site failures because if a PG were allowed to go active with replicas only in a single site, +writes could be acknowledged despite a lack of redundancy. In the event of a site failure, all data in the +affected PG would be lost. Entering Stretch Mode --------------------- @@ -271,7 +287,7 @@ possible, if needed). .. _Changing Monitor elections: ../change-mon-elections Exiting Stretch Mode -===================== +-------------------- To exit stretch mode, run the following command: .. prompt:: bash $ diff --git a/doc/radosgw/account.rst b/doc/radosgw/account.rst index 6dab997d93e..0e4ede5a50a 100644 --- a/doc/radosgw/account.rst +++ b/doc/radosgw/account.rst @@ -174,6 +174,11 @@ An existing user can be adopted into an account with ``user modify``:: .. note:: Account membership is permanent. Once added, users cannot be removed from their account. +.. note:: The IAM User API imposes additional requirements on the format + of ``UserName``, which is enforced when migrating users into an account. + If migration fails with "UserName contains invalid characters", the + ``--display-name`` should be modified to match ``[\w+=,.@-]+``. + .. warning:: Ownership of the user's notification topics will not be transferred to the account. Notifications will continue to work, but the topics will no longer be visible to SNS Topic APIs. Topics and diff --git a/doc/radosgw/bucket_logging.rst b/doc/radosgw/bucket_logging.rst index cb9f8465d20..f3e790f5705 100644 --- a/doc/radosgw/bucket_logging.rst +++ b/doc/radosgw/bucket_logging.rst @@ -15,6 +15,12 @@ The log bucket can accumulate logs from multiple buckets. It is recommended to c a different "prefix" for each bucket, so that the logs of different buckets will be stored in different objects in the log bucket. +.. note:: + + - The log bucket must be created before enabling logging on a bucket + - The log bucket cannot be the same as the bucket being logged + - The log bucket cannot have logging enabled on it + .. toctree:: :maxdepth: 1 @@ -29,6 +35,7 @@ Adding a log object to the log bucket is done "lazily", meaning, that if no more remain outside of the log bucket even after the configured time has passed. To counter that, you can flush all logging objects on a given source bucket to log them, regardless if enough time passed or if no more records are written to the object. +Flushing will happen automatically when logging is disabled on a bucket, its logging configuration is changed, or the bucket is deleted. Standard ```````` @@ -72,7 +79,7 @@ has the following format: :: - <prefix><bucket owner>/<source region>/<bucket name>/<year>/<month>/<day>/<year-month-day-hour-minute-second>-<16 bytes unique-id> + <prefix><bucket owner>/<source region>/[tenant:]<bucket name>/<year>/<month>/<day>/<year-month-day-hour-minute-second>-<16 bytes unique-id> For example: @@ -90,7 +97,7 @@ Journal minimum amount of data used for journaling bucket changes (this is a Ceph extension). - bucket owner (or dash if empty) - - bucket name (or dash if empty) + - bucket name (or dash if empty). in the format: ``[tenant:]<bucket name>`` - time in the following format: ``[day/month/year:hour:minute:second timezone]`` - object key (or dash if empty) - operation in the following format: ``WEBSITE/REST.<HTTP method>.<resource>`` @@ -111,7 +118,7 @@ Standard based on `AWS Logging Record Format`_. - bucket owner (or dash if empty) - - bucket name (or dash if empty) + - bucket name (or dash if empty). in the format: ``[tenant:]<bucket name>`` - time - remote IP (not supported, always a dash) - user or account (or dash if empty) diff --git a/doc/radosgw/config-ref.rst b/doc/radosgw/config-ref.rst index edc6a90b0f9..405bc727208 100644 --- a/doc/radosgw/config-ref.rst +++ b/doc/radosgw/config-ref.rst @@ -75,10 +75,11 @@ aggressiveness of lifecycle processing: .. confval:: rgw_lc_max_wp_worker These values can be tuned based upon your specific workload to further increase the -aggressiveness of lifecycle processing. For a workload with a larger number of buckets (thousands) -you would look at increasing the :confval:`rgw_lc_max_worker` value from the default value of 3 whereas for a -workload with a smaller number of buckets but higher number of objects (hundreds of thousands) -per bucket you would consider decreasing :confval:`rgw_lc_max_wp_worker` from the default value of 3. +aggressiveness of lifecycle processing. For a workload with a large number of buckets (thousands) +you would raise the number of workers by increasing :confval:`rgw_lc_max_worker` +from the default value of 3. Whereas for a workload with a higher number of objects per bucket +(hundreds of thousands) you would raise the number of parallel threads +by increasing :confval:`rgw_lc_max_wp_worker` from the default value of 3. .. note:: When looking to tune either of these specific values please validate the current Cluster performance and Ceph Object Gateway utilization before increasing. diff --git a/doc/releases/index.rst b/doc/releases/index.rst index a8015c65465..1393770878f 100644 --- a/doc/releases/index.rst +++ b/doc/releases/index.rst @@ -23,7 +23,6 @@ security fixes. Squid (v19.2.*) <squid> Reef (v18.2.*) <reef> - Quincy (v17.2.*) <quincy> .. ceph_releases:: releases.yml current @@ -40,6 +39,7 @@ receive bug fixes or backports). :maxdepth: 1 :hidden: + Quincy (v17.2.*) <quincy> Pacific (v16.2.*) <pacific> Octopus (v15.2.*) <octopus> Nautilus (v14.2.*) <nautilus> diff --git a/doc/releases/releases.yml b/doc/releases/releases.yml index 948f9eab278..6a76cc7c92c 100644 --- a/doc/releases/releases.yml +++ b/doc/releases/releases.yml @@ -32,6 +32,7 @@ releases: quincy: target_eol: 2024-06-01 + actual_eol: 2025-01-13 releases: - version: 17.2.8 released: 2024-11-25 diff --git a/examples/rgw/boto3/head_bucket_stats.py b/examples/rgw/boto3/head_bucket_stats.py new file mode 100755 index 00000000000..1de40d63f4a --- /dev/null +++ b/examples/rgw/boto3/head_bucket_stats.py @@ -0,0 +1,27 @@ +#!/usr/bin/python + +import boto3 +import sys + +if len(sys.argv) != 2: + print('Usage: ' + sys.argv[0] + ' <bucket>') + sys.exit(1) + +# bucket name as first argument +bucketname = sys.argv[1] + +# endpoint and keys from vstart +endpoint = 'http://127.0.0.1:8000' +access_key='0555b35654ad1656d804' +secret_key='h7GhxuBLTrlhVUyxSPUKUV8r/2EI4ngqJxD7iBdBYLhwluN30JaT3Q==' + +client = boto3.client('s3', + endpoint_url=endpoint, + aws_access_key_id=access_key, + aws_secret_access_key=secret_key) + +# reading bucket stats via HeadBucket + +response = client.head_bucket(Bucket=bucketname, ReadStats=True) + +print('Objects:', response['ObjectCount'], 'Bytes:', response['BytesUsed']) diff --git a/examples/rgw/boto3/service-2.sdk-extras.json b/examples/rgw/boto3/service-2.sdk-extras.json index b81667ecd09..4618543d61b 100644 --- a/examples/rgw/boto3/service-2.sdk-extras.json +++ b/examples/rgw/boto3/service-2.sdk-extras.json @@ -379,7 +379,36 @@ }, "documentation":"<p>A filter for all log object. Filter for the object by its key (prefix, suffix and regex).</p>", "locationName":"Filter" - } + }, + "HeadBucketRequest": { + "members": { + "ReadStats":{ + "shape":"ReadStats", + "documentation":"<p>Read additional usage statistics for <code>ObjectCount</code> and <code>BytesUsed</code> in the response.</p> <note> <p>This request parameter is a Ceph RGW extension.</p> </note>", + "location":"querystring", + "locationName":"read-stats" + } + } + }, + "HeadBucketOutput":{ + "members":{ + "ObjectCount":{ + "shape":"ObjectCount", + "documentation": "<p>Total number of objects/versions in the bucket.</p>", + "location": "header", + "locationName": "x-rgw-object-count" + }, + "BytesUsed":{ + "shape":"BytesUsed", + "documentation": "<p>Total size in bytes of all objects/versions in the bucket.</p>", + "location": "header", + "locationName": "x-rgw-bytes-used" + } + } + }, + "ReadStats":{"type":"boolean"}, + "ObjectCount":{"type":"integer"}, + "BytesUsed":{"type":"integer"} }, "documentation":"<p/>" } diff --git a/monitoring/ceph-mixin/config.libsonnet b/monitoring/ceph-mixin/config.libsonnet index a15b88422fc..e917b4c2dac 100644 --- a/monitoring/ceph-mixin/config.libsonnet +++ b/monitoring/ceph-mixin/config.libsonnet @@ -9,12 +9,12 @@ CephNodeNetworkPacketDropsPerSec: 10, CephRBDMirrorImageTransferBandwidthThreshold: 0.8, CephRBDMirrorImagesPerDaemonThreshold: 100, - NVMeoFMaxGatewaysPerGroup: 4, - NVMeoFMaxGatewaysPerCluster: 4, + NVMeoFMaxGatewaysPerGroup: 8, + NVMeoFMaxGatewaysPerCluster: 32, NVMeoFHighGatewayCPU: 80, NVMeoFMaxSubsystemsPerGateway: 128, - NVMeoFMaxNamespaces: 1024, - NVMeoFHighClientCount: 32, + NVMeoFMaxNamespaces: 2048, + NVMeoFHighClientCount: 128, NVMeoFHighHostCPU: 80, // // Read/Write latency is defined in ms diff --git a/monitoring/ceph-mixin/prometheus_alerts.yml b/monitoring/ceph-mixin/prometheus_alerts.yml index 3440d761351..7c0da4d51a4 100644 --- a/monitoring/ceph-mixin/prometheus_alerts.yml +++ b/monitoring/ceph-mixin/prometheus_alerts.yml @@ -776,18 +776,18 @@ groups: type: "ceph_default" - alert: "NVMeoFTooManyGateways" annotations: - description: "You may create many gateways, but 4 is the tested limit" + description: "You may create many gateways, but 32 is the tested limit" summary: "Max supported gateways exceeded on cluster {{ $labels.cluster }}" - expr: "count(ceph_nvmeof_gateway_info) by (cluster) > 4.00" + expr: "count(ceph_nvmeof_gateway_info) by (cluster) > 32.00" for: "1m" labels: severity: "warning" type: "ceph_default" - alert: "NVMeoFMaxGatewayGroupSize" annotations: - description: "You may create many gateways in a gateway group, but 4 is the tested limit" + description: "You may create many gateways in a gateway group, but 8 is the tested limit" summary: "Max gateways within a gateway group ({{ $labels.group }}) exceeded on cluster {{ $labels.cluster }}" - expr: "count(ceph_nvmeof_gateway_info) by (cluster,group) > 4.00" + expr: "count(ceph_nvmeof_gateway_info) by (cluster,group) > 8.00" for: "1m" labels: severity: "warning" @@ -832,7 +832,7 @@ groups: annotations: description: "Although you may continue to create namespaces in {{ $labels.gateway_host }}, the configuration may not be supported" summary: "The number of namespaces defined to the gateway exceeds supported values on cluster {{ $labels.cluster }}" - expr: "sum by(gateway_host, cluster) (label_replace(ceph_nvmeof_subsystem_namespace_count,\"gateway_host\",\"$1\",\"instance\",\"(.*?)(?::.*)?\")) > 1024.00" + expr: "sum by(gateway_host, cluster) (label_replace(ceph_nvmeof_subsystem_namespace_count,\"gateway_host\",\"$1\",\"instance\",\"(.*?)(?::.*)?\")) > 2048.00" for: "1m" labels: severity: "warning" @@ -848,9 +848,9 @@ groups: type: "ceph_default" - alert: "NVMeoFHighClientCount" annotations: - description: "The supported limit for clients connecting to a subsystem is 32" + description: "The supported limit for clients connecting to a subsystem is 128" summary: "The number of clients connected to {{ $labels.nqn }} is too high on cluster {{ $labels.cluster }}" - expr: "ceph_nvmeof_subsystem_host_count > 32.00" + expr: "ceph_nvmeof_subsystem_host_count > 128.00" for: "1m" labels: severity: "warning" diff --git a/monitoring/ceph-mixin/tests_alerts/test_alerts.yml b/monitoring/ceph-mixin/tests_alerts/test_alerts.yml index b3b29308d08..83b4ff80375 100644 --- a/monitoring/ceph-mixin/tests_alerts/test_alerts.yml +++ b/monitoring/ceph-mixin/tests_alerts/test_alerts.yml @@ -2331,12 +2331,69 @@ tests: values: '1+0x20' - series: 'ceph_nvmeof_gateway_info{addr="1.1.1.5",cluster="mycluster"}' values: '1+0x20' + - series: 'ceph_nvmeof_gateway_info{addr="1.1.1.6",cluster="mycluster"}' + values: '1+0x20' + - series: 'ceph_nvmeof_gateway_info{addr="1.1.1.7",cluster="mycluster"}' + values: '1+0x20' + - series: 'ceph_nvmeof_gateway_info{addr="1.1.1.8",cluster="mycluster"}' + values: '1+0x20' + - series: 'ceph_nvmeof_gateway_info{addr="1.1.1.9",cluster="mycluster"}' + values: '1+0x20' + - series: 'ceph_nvmeof_gateway_info{addr="1.1.1.10",cluster="mycluster"}' + values: '1+0x20' + - series: 'ceph_nvmeof_gateway_info{addr="1.1.1.11",cluster="mycluster"}' + values: '1+0x20' + - series: 'ceph_nvmeof_gateway_info{addr="1.1.1.12",cluster="mycluster"}' + values: '1+0x20' + - series: 'ceph_nvmeof_gateway_info{addr="1.1.1.13",cluster="mycluster"}' + values: '1+0x20' + - series: 'ceph_nvmeof_gateway_info{addr="1.1.1.14",cluster="mycluster"}' + values: '1+0x20' + - series: 'ceph_nvmeof_gateway_info{addr="1.1.1.15",cluster="mycluster"}' + values: '1+0x20' + - series: 'ceph_nvmeof_gateway_info{addr="1.1.1.16",cluster="mycluster"}' + values: '1+0x20' + - series: 'ceph_nvmeof_gateway_info{addr="1.1.1.17",cluster="mycluster"}' + values: '1+0x20' + - series: 'ceph_nvmeof_gateway_info{addr="1.1.1.18",cluster="mycluster"}' + values: '1+0x20' + - series: 'ceph_nvmeof_gateway_info{addr="1.1.1.19",cluster="mycluster"}' + values: '1+0x20' + - series: 'ceph_nvmeof_gateway_info{addr="1.1.1.20",cluster="mycluster"}' + values: '1+0x20' + - series: 'ceph_nvmeof_gateway_info{addr="1.1.1.21",cluster="mycluster"}' + values: '1+0x20' + - series: 'ceph_nvmeof_gateway_info{addr="1.1.1.22",cluster="mycluster"}' + values: '1+0x20' + - series: 'ceph_nvmeof_gateway_info{addr="1.1.1.23",cluster="mycluster"}' + values: '1+0x20' + - series: 'ceph_nvmeof_gateway_info{addr="1.1.1.24",cluster="mycluster"}' + values: '1+0x20' + - series: 'ceph_nvmeof_gateway_info{addr="1.1.1.25",cluster="mycluster"}' + values: '1+0x20' + - series: 'ceph_nvmeof_gateway_info{addr="1.1.1.26",cluster="mycluster"}' + values: '1+0x20' + - series: 'ceph_nvmeof_gateway_info{addr="1.1.1.27",cluster="mycluster"}' + values: '1+0x20' + - series: 'ceph_nvmeof_gateway_info{addr="1.1.1.28",cluster="mycluster"}' + values: '1+0x20' + - series: 'ceph_nvmeof_gateway_info{addr="1.1.1.29",cluster="mycluster"}' + values: '1+0x20' + - series: 'ceph_nvmeof_gateway_info{addr="1.1.1.30",cluster="mycluster"}' + values: '1+0x20' + - series: 'ceph_nvmeof_gateway_info{addr="1.1.1.31",cluster="mycluster"}' + values: '1+0x20' + - series: 'ceph_nvmeof_gateway_info{addr="1.1.1.32",cluster="mycluster"}' + values: '1+0x20' + - series: 'ceph_nvmeof_gateway_info{addr="1.1.1.33",cluster="mycluster"}' + values: '1+0x20' + promql_expr_test: - - expr: count(ceph_nvmeof_gateway_info) by (cluster) > 4.00 + - expr: count(ceph_nvmeof_gateway_info) by (cluster) > 32.00 eval_time: 1m exp_samples: - labels: '{cluster="mycluster"}' - value: 5 + value: 33 alert_rule_test: - eval_time: 5m alertname: NVMeoFTooManyGateways @@ -2347,7 +2404,7 @@ tests: type: ceph_default exp_annotations: summary: "Max supported gateways exceeded on cluster mycluster" - description: "You may create many gateways, but 4 is the tested limit" + description: "You may create many gateways, but 32 is the tested limit" # NVMeoFMaxGatewayGroupSize - interval: 1m @@ -2362,16 +2419,24 @@ tests: values: '1+0x20' - series: 'ceph_nvmeof_gateway_info{group="group-1",addr="1.1.1.12",cluster="mycluster"}' values: '1+0x20' + - series: 'ceph_nvmeof_gateway_info{group="group-1",addr="1.1.1.10",cluster="mycluster"}' + values: '1+0x20' + - series: 'ceph_nvmeof_gateway_info{group="group-1",addr="1.1.1.14",cluster="mycluster"}' + values: '1+0x20' + - series: 'ceph_nvmeof_gateway_info{group="group-1",addr="1.1.1.11",cluster="mycluster"}' + values: '1+0x20' + - series: 'ceph_nvmeof_gateway_info{group="group-1",addr="1.1.1.13",cluster="mycluster"}' + values: '1+0x20' - series: 'ceph_nvmeof_gateway_info{group="group-2",addr="1.1.1.4",cluster="mycluster"}' values: '1+0x20' - series: 'ceph_nvmeof_gateway_info{group="group-2",addr="1.1.1.5",cluster="mycluster"}' values: '1+0x20' promql_expr_test: - - expr: count(ceph_nvmeof_gateway_info) by (cluster, group) > 4.00 + - expr: count(ceph_nvmeof_gateway_info) by (cluster, group) > 8.00 eval_time: 1m exp_samples: - labels: '{cluster="mycluster",group="group-1"}' - value: 5 + value: 9 alert_rule_test: - eval_time: 5m alertname: NVMeoFMaxGatewayGroupSize @@ -2383,7 +2448,7 @@ tests: type: ceph_default exp_annotations: summary: "Max gateways within a gateway group (group-1) exceeded on cluster mycluster" - description: "You may create many gateways in a gateway group, but 4 is the tested limit" + description: "You may create many gateways in a gateway group, but 8 is the tested limit" # NVMeoFSingleGatewayGroup - interval: 1m @@ -2767,12 +2832,14 @@ tests: values: '200+0x10' - series: 'ceph_nvmeof_subsystem_namespace_count{instance="node-1:10008",nqn="nqn10",cluster="mycluster"}' values: '200+0x10' + - series: 'ceph_nvmeof_subsystem_namespace_count{instance="node-1:10008",nqn="nqn11",cluster="mycluster"}' + values: '200+0x10' promql_expr_test: - - expr: sum by(gateway_host, cluster) (label_replace(ceph_nvmeof_subsystem_namespace_count,"gateway_host","$1","instance","(.*):.*")) > 1024 + - expr: sum by(gateway_host, cluster) (label_replace(ceph_nvmeof_subsystem_namespace_count,"gateway_host","$1","instance","(.*):.*")) > 2048 eval_time: 1m exp_samples: - labels: '{gateway_host="node-1", cluster="mycluster"}' - value: 2000 + value: 2200 alert_rule_test: - eval_time: 5m alertname: NVMeoFTooManyNamespaces @@ -2815,15 +2882,15 @@ tests: - interval: 1m input_series: - series: 'ceph_nvmeof_subsystem_host_count{nqn="nqn1",cluster="mycluster"}' - values: '2 2 2 4 4 8 8 8 10 10 20 20 32 34 34 38 38 40 44 44' + values: '2 4 8 10 20 30 40 50 62 74 80 95 100 110 130 130 130 130 130 130' - series: 'ceph_nvmeof_subsystem_host_count{nqn="nqn2",cluster="mycluster"}' - values: '2 2 2 8 8 8 16 16 16 16 16 16 16 16 16 16 16 16 16 16' + values: '2 8 16 16 16 16 16 16 16 16 20 20 32 34 34 36 37 37 37 37' promql_expr_test: - - expr: ceph_nvmeof_subsystem_host_count > 32.00 + - expr: ceph_nvmeof_subsystem_host_count > 128.00 eval_time: 15m exp_samples: - labels: '{__name__="ceph_nvmeof_subsystem_host_count",nqn="nqn1",cluster="mycluster"}' - value: 38 + value: 130 alert_rule_test: - eval_time: 20m alertname: NVMeoFHighClientCount @@ -2835,7 +2902,7 @@ tests: type: ceph_default exp_annotations: summary: "The number of clients connected to nqn1 is too high on cluster mycluster" - description: "The supported limit for clients connecting to a subsystem is 32" + description: "The supported limit for clients connecting to a subsystem is 128" # NVMeoFMissingListener - interval: 1m diff --git a/qa/crontab/teuthology-cronjobs b/qa/crontab/teuthology-cronjobs index c979e5b105f..c558a1382ef 100644 --- a/qa/crontab/teuthology-cronjobs +++ b/qa/crontab/teuthology-cronjobs @@ -52,7 +52,6 @@ TEUTHOLOGY_SUITE_ARGS="--non-interactive --newest=100 --ceph-repo=https://git.ce 00 05 * * 0,2,4 $CW $SS 1 --ceph main --suite smoke -p 100 --force-priority 08 05 * * 0 $CW $SS 1 --ceph squid --suite smoke -p 100 --force-priority 16 05 * * 0 $CW $SS 1 --ceph reef --suite smoke -p 100 --force-priority -24 05 * * 0 $CW $SS 1 --ceph quincy --suite smoke -p 100 --force-priority ## ********** windows tests on main branch - weekly # 00 03 * * 1 CEPH_BRANCH=main; MACHINE_NAME=smithi; $CW teuthology-suite -v -c $CEPH_BRANCH -n 100 -m $MACHINE_NAME -s windows -k distro -e $CEPH_QA_EMAIL @@ -122,7 +121,6 @@ TEUTHOLOGY_SUITE_ARGS="--non-interactive --newest=100 --ceph-repo=https://git.ce 16 00 * * 1 $CW $SS 1 --ceph quincy --suite upgrade-clients/client-upgrade-pacific-quincy --suite-branch pacific -p 820 24 00 * * 1 $CW $SS 120000 --ceph quincy --suite upgrade:octopus-x -p 820 32 00 * * 1 $CW $SS 120000 --ceph quincy --suite upgrade:pacific-x -p 820 -40 00 * * 1 $CW $SS 1 --ceph quincy --suite upgrade/quincy-p2p -p 820 ### upgrade runs for reef release ###### on smithi diff --git a/qa/standalone/osd/osd-bluefs-volume-ops.sh b/qa/standalone/osd/osd-bluefs-volume-ops.sh index aedfbc9b5cb..f7424de8ce1 100755 --- a/qa/standalone/osd/osd-bluefs-volume-ops.sh +++ b/qa/standalone/osd/osd-bluefs-volume-ops.sh @@ -72,7 +72,7 @@ function TEST_bluestore() { truncate $dir/0/block -s 4294967296 # 4GB ceph-bluestore-tool --path $dir/0 bluefs-bdev-expand || return 1 - truncate $dir/1/block -s 4311744512 # 4GB + 16MB + truncate $dir/1/block -s 11811160064 # 11GB to get bdev label at 10737418240 ceph-bluestore-tool --path $dir/1 bluefs-bdev-expand || return 1 truncate $dir/2/block -s 4295099392 # 4GB + 129KB ceph-bluestore-tool --path $dir/2 bluefs-bdev-expand || return 1 diff --git a/qa/standalone/scrub/osd-recovery-scrub.sh b/qa/standalone/scrub/osd-recovery-scrub.sh index 843e9b9901b..7b77a60f35b 100755 --- a/qa/standalone/scrub/osd-recovery-scrub.sh +++ b/qa/standalone/scrub/osd-recovery-scrub.sh @@ -163,7 +163,7 @@ function wait_for_scrub_mod() { fi sleep 1 # are we still the primary? - local current_primary=`bin/ceph pg $pgid query | jq '.acting[0]' ` + local current_primary=`./bin/ceph pg $pgid query | jq '.acting[0]' ` if [ $orig_primary != $current_primary ]; then echo $orig_primary no longer primary for $pgid return 0 @@ -194,7 +194,7 @@ function pg_scrub_mod() { local last_scrub=$(get_last_scrub_stamp $pgid) # locate the primary - local my_primary=`bin/ceph pg $pgid query | jq '.acting[0]' ` + local my_primary=`./bin/ceph pg $pgid query | jq '.acting[0]' ` local recovery=false ceph pg scrub $pgid #ceph --format json pg dump pgs | jq ".pg_stats | .[] | select(.pgid == \"$pgid\") | .state" diff --git a/qa/standalone/scrub/osd-scrub-test.sh b/qa/standalone/scrub/osd-scrub-test.sh index 85a45a421c1..385479258f2 100755 --- a/qa/standalone/scrub/osd-scrub-test.sh +++ b/qa/standalone/scrub/osd-scrub-test.sh @@ -603,17 +603,16 @@ function TEST_dump_scrub_schedule() { declare -A expct_dmp_duration=( ['dmp_last_duration']="0" ['dmp_last_duration_neg']="not0" ) wait_any_cond $pgid 10 $saved_last_stamp expct_dmp_duration "WaitingAfterScrub_dmp " sched_data || return 1 - sleep 2 - # # step 2: set noscrub and request a "periodic scrub". Watch for the change in the 'is the scrub # scheduled for the future' value # - ceph tell osd.* config set osd_shallow_scrub_chunk_max "3" || return 1 - ceph tell osd.* config set osd_scrub_sleep "2.0" || return 1 ceph osd set noscrub || return 1 sleep 2 + ceph tell osd.* config set osd_shallow_scrub_chunk_max "3" || return 1 + ceph tell osd.* config set osd_scrub_sleep "2.0" || return 1 + sleep 8 saved_last_stamp=${sched_data['query_last_stamp']} ceph tell $pgid schedule-scrub @@ -692,28 +691,28 @@ function wait_initial_scrubs() { # set a long schedule for the periodic scrubs. Wait for the # initial 'no previous scrub is known' scrubs to finish for all PGs. - bin/ceph tell osd.* config set osd_scrub_min_interval 7200 - bin/ceph tell osd.* config set osd_deep_scrub_interval 14400 - bin/ceph tell osd.* config set osd_max_scrubs 32 - bin/ceph tell osd.* config set osd_scrub_sleep 0 - bin/ceph tell osd.* config set osd_shallow_scrub_chunk_max 10 - bin/ceph tell osd.* config set osd_scrub_chunk_max 10 + ceph tell osd.* config set osd_scrub_min_interval 7200 + ceph tell osd.* config set osd_deep_scrub_interval 14400 + ceph tell osd.* config set osd_max_scrubs 32 + ceph tell osd.* config set osd_scrub_sleep 0 + ceph tell osd.* config set osd_shallow_scrub_chunk_max 10 + ceph tell osd.* config set osd_scrub_chunk_max 10 for pg in "${!pg_to_prim_dict[@]}"; do (( extr_dbg >= 1 )) && echo "Scheduling initial scrub for $pg" - bin/ceph tell $pg scrub || return 1 + ceph tell $pg scrub || return 1 done sleep 1 - (( extr_dbg >= 1 )) && bin/ceph pg dump pgs --format=json-pretty | \ + (( extr_dbg >= 1 )) && ceph pg dump pgs --format=json-pretty | \ jq '.pg_stats | map(select(.last_scrub_duration == 0)) | map({pgid: .pgid, last_scrub_duration: .last_scrub_duration})' tout=20 while [ $tout -gt 0 ] ; do sleep 0.5 - (( extr_dbg >= 2 )) && bin/ceph pg dump pgs --format=json-pretty | \ + (( extr_dbg >= 2 )) && ceph pg dump pgs --format=json-pretty | \ jq '.pg_stats | map(select(.last_scrub_duration == 0)) | map({pgid: .pgid, last_scrub_duration: .last_scrub_duration})' - not_done=$(bin/ceph pg dump pgs --format=json-pretty | \ + not_done=$(ceph pg dump pgs --format=json-pretty | \ jq '.pg_stats | map(select(.last_scrub_duration == 0)) | map({pgid: .pgid, last_scrub_duration: .last_scrub_duration})' | wc -l ) # note that we should ignore a header line if [ "$not_done" -le 1 ]; then @@ -782,14 +781,14 @@ function TEST_abort_periodic_for_operator() { wait_initial_scrubs pg_pr || return 1 # limit all OSDs to one scrub at a time - bin/ceph tell osd.* config set osd_max_scrubs 1 - bin/ceph tell osd.* config set osd_stats_update_period_not_scrubbing 1 + ceph tell osd.* config set osd_max_scrubs 1 + ceph tell osd.* config set osd_stats_update_period_not_scrubbing 1 # configure for slow scrubs - bin/ceph tell osd.* config set osd_scrub_sleep 3 - bin/ceph tell osd.* config set osd_shallow_scrub_chunk_max 2 - bin/ceph tell osd.* config set osd_scrub_chunk_max 2 - (( extr_dbg >= 2 )) && bin/ceph tell osd.2 dump_scrub_reservations --format=json-pretty + ceph tell osd.* config set osd_scrub_sleep 3 + ceph tell osd.* config set osd_shallow_scrub_chunk_max 2 + ceph tell osd.* config set osd_scrub_chunk_max 2 + (( extr_dbg >= 2 )) && ceph tell osd.2 dump_scrub_reservations --format=json-pretty # the first PG to work with: local pg1="1.0" @@ -812,7 +811,7 @@ function TEST_abort_periodic_for_operator() { fi # the common primary is allowed two concurrent scrubs - bin/ceph tell osd."${pg_pr[$pg1]}" config set osd_max_scrubs 2 + ceph tell osd."${pg_pr[$pg1]}" config set osd_max_scrubs 2 echo "The two PGs to manipulate are $pg1 and $pg2" set_query_debug "$pg1" @@ -821,31 +820,31 @@ function TEST_abort_periodic_for_operator() { local is_act for i in $( seq 1 3 ) do - is_act=$(bin/ceph pg "$pg1" query | jq '.scrubber.active') + is_act=$(ceph pg "$pg1" query | jq '.scrubber.active') if [[ "$is_act" = "false" ]]; then break fi echo "Still waiting for pg $pg1 to finish scrubbing" sleep 0.7 done - bin/ceph pg dump pgs + ceph pg dump pgs if [[ "$is_act" != "false" ]]; then - bin/ceph pg "$pg1" query + ceph pg "$pg1" query echo "PG $pg1 appears to be still scrubbing" return 1 fi sleep 0.5 echo "Initiating a periodic scrub of $pg1" - (( extr_dbg >= 2 )) && bin/ceph pg "$pg1" query -f json-pretty | jq '.scrubber' - bin/ceph tell $pg1 schedule-deep-scrub || return 1 + (( extr_dbg >= 2 )) && ceph pg "$pg1" query -f json-pretty | jq '.scrubber' + ceph tell $pg1 schedule-deep-scrub || return 1 sleep 1 - (( extr_dbg >= 2 )) && bin/ceph pg "$pg1" query -f json-pretty | jq '.scrubber' + (( extr_dbg >= 2 )) && ceph pg "$pg1" query -f json-pretty | jq '.scrubber' for i in $( seq 1 14 ) do sleep 0.5 - stt=$(bin/ceph pg "$pg1" query | jq '.scrubber') + stt=$(ceph pg "$pg1" query | jq '.scrubber') is_active=$(echo $stt | jq '.active') is_reserving_replicas=$(echo $stt | jq '.is_reserving_replicas') if [[ "$is_active" = "true" && "$is_reserving_replicas" = "false" ]]; then @@ -854,49 +853,49 @@ function TEST_abort_periodic_for_operator() { echo "Still waiting for pg $pg1 to start scrubbing: $stt" done if [[ "$is_active" != "true" || "$is_reserving_replicas" != "false" ]]; then - bin/ceph pg "$pg1" query -f json-pretty | jq '.scrubber' + ceph pg "$pg1" query -f json-pretty | jq '.scrubber' echo "The scrub is not active or is reserving replicas" return 1 fi - (( extr_dbg >= 2 )) && bin/ceph pg "$pg1" query -f json-pretty | jq '.scrubber' + (( extr_dbg >= 2 )) && ceph pg "$pg1" query -f json-pretty | jq '.scrubber' # PG 1 is scrubbing, and has reserved the replicas - soem of which are shared # by PG 2. As the max-scrubs was set to 1, that should prevent PG 2 from # reserving its replicas. - (( extr_dbg >= 1 )) && bin/ceph tell osd.* dump_scrub_reservations --format=json-pretty + (( extr_dbg >= 1 )) && ceph tell osd.* dump_scrub_reservations --format=json-pretty # now - the 2'nd scrub - which should be blocked on reserving set_query_debug "$pg2" - bin/ceph tell "$pg2" schedule-deep-scrub + ceph tell "$pg2" schedule-deep-scrub sleep 0.5 (( extr_dbg >= 2 )) && echo "====================================================================================" - (( extr_dbg >= 2 )) && bin/ceph pg "$pg2" query -f json-pretty | jq '.scrubber' - (( extr_dbg >= 2 )) && bin/ceph pg "$pg1" query -f json-pretty | jq '.scrubber' + (( extr_dbg >= 2 )) && ceph pg "$pg2" query -f json-pretty | jq '.scrubber' + (( extr_dbg >= 2 )) && ceph pg "$pg1" query -f json-pretty | jq '.scrubber' sleep 1 (( extr_dbg >= 2 )) && echo "====================================================================================" - (( extr_dbg >= 2 )) && bin/ceph pg "$pg2" query -f json-pretty | jq '.scrubber' - (( extr_dbg >= 2 )) && bin/ceph pg "$pg1" query -f json-pretty | jq '.scrubber' + (( extr_dbg >= 2 )) && ceph pg "$pg2" query -f json-pretty | jq '.scrubber' + (( extr_dbg >= 2 )) && ceph pg "$pg1" query -f json-pretty | jq '.scrubber' # make sure pg2 scrub is stuck in the reserving state - local stt2=$(bin/ceph pg "$pg2" query | jq '.scrubber') + local stt2=$(ceph pg "$pg2" query | jq '.scrubber') local pg2_is_reserving pg2_is_reserving=$(echo $stt2 | jq '.is_reserving_replicas') if [[ "$pg2_is_reserving" != "true" ]]; then echo "The scheduled scrub for $pg2 should have been stuck" - bin/ceph pg dump pgs + ceph pg dump pgs return 1 fi # now - issue an operator-initiated scrub on pg2. # The periodic scrub should be aborted, and the operator-initiated scrub should start. echo "Instructing $pg2 to perform a high-priority scrub" - bin/ceph tell "$pg2" scrub + ceph tell "$pg2" scrub for i in $( seq 1 10 ) do sleep 0.5 - stt2=$(bin/ceph pg "$pg2" query | jq '.scrubber') + stt2=$(ceph pg "$pg2" query | jq '.scrubber') pg2_is_active=$(echo $stt2 | jq '.active') pg2_is_reserving=$(echo $stt2 | jq '.is_reserving_replicas') if [[ "$pg2_is_active" = "true" && "$pg2_is_reserving" != "true" ]]; then diff --git a/qa/standalone/scrub/scrub-helpers.sh b/qa/standalone/scrub/scrub-helpers.sh index 0b14d6028b6..dd37b643e08 100644 --- a/qa/standalone/scrub/scrub-helpers.sh +++ b/qa/standalone/scrub/scrub-helpers.sh @@ -320,7 +320,7 @@ function build_pg_dicts { # if the infile name is '-', fetch the dump directly from the ceph cluster if [[ $infile == "-" ]]; then - local -r ceph_cmd="bin/ceph pg dump pgs_brief -f=json-pretty" + local -r ceph_cmd="ceph pg dump pgs_brief -f=json-pretty" local -r ceph_cmd_out=$(eval $ceph_cmd) local -r ceph_cmd_rc=$? if [[ $ceph_cmd_rc -ne 0 ]]; then diff --git a/qa/suites/rados/monthrash/workloads/rados_mon_osdmap_prune.yaml b/qa/suites/rados/monthrash/workloads/rados_mon_osdmap_prune.yaml index 372bf2561fa..8b3c4c11ac6 100644 --- a/qa/suites/rados/monthrash/workloads/rados_mon_osdmap_prune.yaml +++ b/qa/suites/rados/monthrash/workloads/rados_mon_osdmap_prune.yaml @@ -15,6 +15,7 @@ overrides: # causing tests to fail due to health warns, even if # the tests themselves are successful. - \(OSDMAP_FLAGS\) + - \(PG_DEGRADED\) tasks: - workunit: clients: diff --git a/qa/suites/rados/verify/clusters/fixed-4.yaml b/qa/suites/rados/verify/clusters/fixed-4.yaml new file mode 120000 index 00000000000..aa88300715a --- /dev/null +++ b/qa/suites/rados/verify/clusters/fixed-4.yaml @@ -0,0 +1 @@ +.qa/clusters/fixed-4.yaml
\ No newline at end of file diff --git a/qa/suites/rados/verify/validater/valgrind.yaml b/qa/suites/rados/verify/validater/valgrind.yaml index e2dc29b5f7e..17cf141b0cd 100644 --- a/qa/suites/rados/verify/validater/valgrind.yaml +++ b/qa/suites/rados/verify/validater/valgrind.yaml @@ -27,6 +27,7 @@ overrides: - \(SLOW_OPS\) - slow request - OSD bench result + - OSD_DOWN valgrind: mon: [--tool=memcheck, --leak-check=full, --show-reachable=yes] osd: [--tool=memcheck] diff --git a/qa/suites/upgrade/quincy-x/parallel/0-start.yaml b/qa/suites/upgrade/quincy-x/parallel/0-start.yaml index 40fbcefe728..62fb6427f72 100644 --- a/qa/suites/upgrade/quincy-x/parallel/0-start.yaml +++ b/qa/suites/upgrade/quincy-x/parallel/0-start.yaml @@ -32,13 +32,22 @@ overrides: osd: osd shutdown pgref assert: true log-ignorelist: - - \(POOL_APP_NOT_ENABLED\) + - do not have an application enabled + - application not enabled + - or freeform for custom applications + - POOL_APP_NOT_ENABLED + - is down - OSD_DOWN - mons down - mon down - MON_DOWN - out of quorum + - PG_AVAILABILITY - PG_DEGRADED - Reduced data availability - Degraded data redundancy + - pg .* is stuck inactive + - pg .* is .*degraded + - FS_DEGRADED - OSDMAP_FLAGS + - OSD_UPGRADE_FINISHED diff --git a/qa/suites/upgrade/quincy-x/parallel/1-tasks.yaml b/qa/suites/upgrade/quincy-x/parallel/1-tasks.yaml index e27c7c0f092..f7167975aa9 100644 --- a/qa/suites/upgrade/quincy-x/parallel/1-tasks.yaml +++ b/qa/suites/upgrade/quincy-x/parallel/1-tasks.yaml @@ -1,11 +1,8 @@ overrides: ceph: log-ignorelist: - - mons down - - mon down - - MON_DOWN - - out of quorum - - PG_AVAILABILITY + - Telemetry requires re-opt-in + - telemetry module includes new collections tasks: - install: branch: quincy diff --git a/qa/suites/upgrade/quincy-x/stress-split/1-start.yaml b/qa/suites/upgrade/quincy-x/stress-split/1-start.yaml index 005514292ce..5641471629e 100644 --- a/qa/suites/upgrade/quincy-x/stress-split/1-start.yaml +++ b/qa/suites/upgrade/quincy-x/stress-split/1-start.yaml @@ -1,17 +1,25 @@ overrides: ceph: log-ignorelist: - - \(POOL_APP_NOT_ENABLED\) + - do not have an application enabled + - application not enabled + - or freeform for custom applications + - POOL_APP_NOT_ENABLED + - is down - OSD_DOWN - mons down - mon down - MON_DOWN - out of quorum + - PG_AVAILABILITY - PG_DEGRADED - Reduced data availability - Degraded data redundancy + - pg .* is stuck inactive + - pg .* is .*degraded + - FS_DEGRADED - OSDMAP_FLAGS - - PG_AVAILABILITY + - OSD_UPGRADE_FINISHED tasks: - install: branch: quincy diff --git a/qa/suites/upgrade/reef-x/parallel/0-start.yaml b/qa/suites/upgrade/reef-x/parallel/0-start.yaml index 146bd57960d..62fb6427f72 100644 --- a/qa/suites/upgrade/reef-x/parallel/0-start.yaml +++ b/qa/suites/upgrade/reef-x/parallel/0-start.yaml @@ -32,4 +32,22 @@ overrides: osd: osd shutdown pgref assert: true log-ignorelist: - - PG_DEGRADED + - do not have an application enabled + - application not enabled + - or freeform for custom applications + - POOL_APP_NOT_ENABLED + - is down + - OSD_DOWN + - mons down + - mon down + - MON_DOWN + - out of quorum + - PG_AVAILABILITY + - PG_DEGRADED + - Reduced data availability + - Degraded data redundancy + - pg .* is stuck inactive + - pg .* is .*degraded + - FS_DEGRADED + - OSDMAP_FLAGS + - OSD_UPGRADE_FINISHED diff --git a/qa/suites/upgrade/reef-x/parallel/1-tasks.yaml b/qa/suites/upgrade/reef-x/parallel/1-tasks.yaml index ce4e0cc228b..b5160c2dd00 100644 --- a/qa/suites/upgrade/reef-x/parallel/1-tasks.yaml +++ b/qa/suites/upgrade/reef-x/parallel/1-tasks.yaml @@ -1,12 +1,8 @@ overrides: ceph: log-ignorelist: - - mons down - - mon down - - MON_DOWN - - out of quorum - - PG_AVAILABILITY - - PG_DEGRADED + - Telemetry requires re-opt-in + - telemetry module includes new collections tasks: - install: branch: reef diff --git a/qa/suites/upgrade/reef-x/parallel/overrides/ignorelist_health.yaml b/qa/suites/upgrade/reef-x/parallel/overrides/ignorelist_health.yaml index 5e995da7d2c..fa93b2f2ece 100644 --- a/qa/suites/upgrade/reef-x/parallel/overrides/ignorelist_health.yaml +++ b/qa/suites/upgrade/reef-x/parallel/overrides/ignorelist_health.yaml @@ -1,20 +1,19 @@ overrides: ceph: log-ignorelist: - - \(MDS_ALL_DOWN\) - - \(MDS_UP_LESS_THAN_MAX\) - - \(OSD_SLOW_PING_TIME + - MDS_ALL_DOWN + - MDS_UP_LESS_THAN_MAX + - OSD_SLOW_PING_TIME - reached quota + - running out of quota - overall HEALTH_ - - \(CACHE_POOL_NO_HIT_SET\) - - \(POOL_FULL\) - - \(SMALLER_PGP_NUM\) - - \(SLOW_OPS\) - - \(CACHE_POOL_NEAR_FULL\) - - \(POOL_APP_NOT_ENABLED\) - - \(PG_AVAILABILITY\) - - \(OBJECT_MISPLACED\) + - CACHE_POOL_NO_HIT_SET + - pool\(s\) full + - POOL_FULL + - SMALLER_PGP_NUM + - SLOW_OPS + - CACHE_POOL_NEAR_FULL + - OBJECT_MISPLACED - slow request - - \(MON_DOWN\) - noscrub - nodeep-scrub diff --git a/qa/suites/upgrade/reef-x/stress-split/1-start.yaml b/qa/suites/upgrade/reef-x/stress-split/1-start.yaml index 992f9e1bc36..59ccfe2cd02 100644 --- a/qa/suites/upgrade/reef-x/stress-split/1-start.yaml +++ b/qa/suites/upgrade/reef-x/stress-split/1-start.yaml @@ -1,11 +1,25 @@ overrides: ceph: log-ignorelist: + - do not have an application enabled + - application not enabled + - or freeform for custom applications + - POOL_APP_NOT_ENABLED + - is down + - OSD_DOWN - mons down - mon down - MON_DOWN - out of quorum - PG_AVAILABILITY + - PG_DEGRADED + - Reduced data availability + - Degraded data redundancy + - pg .* is stuck inactive + - pg .* is .*degraded + - FS_DEGRADED + - OSDMAP_FLAGS + - OSD_UPGRADE_FINISHED tasks: - install: branch: reef diff --git a/qa/suites/upgrade/reef-x/stress-split/overrides/ignorelist_health.yaml b/qa/suites/upgrade/reef-x/stress-split/overrides/ignorelist_health.yaml index 5e995da7d2c..fa93b2f2ece 100644 --- a/qa/suites/upgrade/reef-x/stress-split/overrides/ignorelist_health.yaml +++ b/qa/suites/upgrade/reef-x/stress-split/overrides/ignorelist_health.yaml @@ -1,20 +1,19 @@ overrides: ceph: log-ignorelist: - - \(MDS_ALL_DOWN\) - - \(MDS_UP_LESS_THAN_MAX\) - - \(OSD_SLOW_PING_TIME + - MDS_ALL_DOWN + - MDS_UP_LESS_THAN_MAX + - OSD_SLOW_PING_TIME - reached quota + - running out of quota - overall HEALTH_ - - \(CACHE_POOL_NO_HIT_SET\) - - \(POOL_FULL\) - - \(SMALLER_PGP_NUM\) - - \(SLOW_OPS\) - - \(CACHE_POOL_NEAR_FULL\) - - \(POOL_APP_NOT_ENABLED\) - - \(PG_AVAILABILITY\) - - \(OBJECT_MISPLACED\) + - CACHE_POOL_NO_HIT_SET + - pool\(s\) full + - POOL_FULL + - SMALLER_PGP_NUM + - SLOW_OPS + - CACHE_POOL_NEAR_FULL + - OBJECT_MISPLACED - slow request - - \(MON_DOWN\) - noscrub - nodeep-scrub diff --git a/qa/tasks/ceph.py b/qa/tasks/ceph.py index 9b04e3dc675..8f666d2fa9b 100644 --- a/qa/tasks/ceph.py +++ b/qa/tasks/ceph.py @@ -1206,8 +1206,18 @@ def cluster(ctx, config): args.extend([ run.Raw('|'), 'head', '-n', '1', ]) - stdout = mon0_remote.sh(args) - return stdout or None + r = mon0_remote.run( + stdout=BytesIO(), + args=args, + stderr=StringIO(), + ) + stdout = r.stdout.getvalue().decode() + if stdout: + return stdout + stderr = r.stderr.getvalue() + if stderr: + return stderr + return None if first_in_ceph_log('\[ERR\]|\[WRN\]|\[SEC\]', config['log_ignorelist']) is not None: diff --git a/qa/tasks/cephadm.py b/qa/tasks/cephadm.py index dab61c2c700..0cde6050718 100644 --- a/qa/tasks/cephadm.py +++ b/qa/tasks/cephadm.py @@ -475,12 +475,16 @@ def ceph_log(ctx, config): run.Raw('|'), 'head', '-n', '1', ]) r = ctx.ceph[cluster_name].bootstrap_remote.run( - stdout=StringIO(), + stdout=BytesIO(), args=args, + stderr=StringIO(), ) - stdout = r.stdout.getvalue() - if stdout != '': + stdout = r.stdout.getvalue().decode() + if stdout: return stdout + stderr = r.stderr.getvalue() + if stderr: + return stderr return None # NOTE: technically the first and third arg to first_in_ceph_log diff --git a/qa/tasks/nvmeof.py b/qa/tasks/nvmeof.py index c58a7267b4e..691a6f7dd86 100644 --- a/qa/tasks/nvmeof.py +++ b/qa/tasks/nvmeof.py @@ -315,7 +315,7 @@ class NvmeofThrasher(Thrasher, Greenlet): def _get_devices(self, remote): GET_DEVICE_CMD = "sudo nvme list --output-format=json | " \ - "jq -r '.Devices | sort_by(.NameSpace) | .[] | select(.ModelNumber == \"Ceph bdev Controller\") | .DevicePath'" + "jq -r '.Devices[].Subsystems[] | select(.Controllers | all(.ModelNumber == \"Ceph bdev Controller\")) | .Namespaces | sort_by(.NSID) | .[] | .NameSpace'" devices = remote.sh(GET_DEVICE_CMD).split() return devices diff --git a/qa/tasks/rgw_multisite.py b/qa/tasks/rgw_multisite.py index e83a54efc2b..f93ca017fa2 100644 --- a/qa/tasks/rgw_multisite.py +++ b/qa/tasks/rgw_multisite.py @@ -361,6 +361,8 @@ def create_zonegroup(cluster, gateways, period, config): if endpoints: # replace client names with their gateway endpoints config['endpoints'] = extract_gateway_endpoints(gateways, endpoints) + if not config.get('api_name'): # otherwise it will be set to an empty string + config['api_name'] = config['name'] zonegroup = multisite.ZoneGroup(config['name'], period) # `zonegroup set` needs --default on command line, and 'is_master' in json args = is_default_arg(config) diff --git a/qa/tasks/rook.py b/qa/tasks/rook.py index 6cb75173966..fae5ef3bf00 100644 --- a/qa/tasks/rook.py +++ b/qa/tasks/rook.py @@ -8,7 +8,7 @@ import json import logging import os import yaml -from io import BytesIO +from io import BytesIO, StringIO from tarfile import ReadError from tasks.ceph_manager import CephManager @@ -235,10 +235,14 @@ def ceph_log(ctx, config): r = ctx.rook[cluster_name].remote.run( stdout=BytesIO(), args=args, + stderr=StringIO(), ) stdout = r.stdout.getvalue().decode() if stdout: return stdout + stderr = r.stderr.getvalue() + if stderr: + return stderr return None if first_in_ceph_log('\[ERR\]|\[WRN\]|\[SEC\]', diff --git a/qa/workunits/nvmeof/basic_tests.sh b/qa/workunits/nvmeof/basic_tests.sh index 794353348b4..9e7a1f5134e 100755 --- a/qa/workunits/nvmeof/basic_tests.sh +++ b/qa/workunits/nvmeof/basic_tests.sh @@ -39,7 +39,7 @@ connect_all() { sudo nvme connect-all --traddr=$NVMEOF_DEFAULT_GATEWAY_IP_ADDRESS --transport=tcp -l 3600 sleep 5 expected_devices_count=$1 - actual_devices=$(sudo nvme list --output-format=json | grep -o "$SPDK_CONTROLLER" | wc -l) + actual_devices=$(sudo nvme list --output-format=json | jq -r ".Devices[].Subsystems[] | select(.Controllers | all(.ModelNumber == \"$SPDK_CONTROLLER\")) | .Namespaces[].NameSpace" | wc -l) if [ "$actual_devices" -ne "$expected_devices_count" ]; then sudo nvme list --output-format=json return 1 @@ -74,7 +74,7 @@ test_run connect test_run list_subsys 1 test_run disconnect_all test_run list_subsys 0 -devices_count=$(( $NVMEOF_NAMESPACES_COUNT * $NVMEOF_SUBSYSTEMS_COUNT)) +devices_count=$(( $NVMEOF_NAMESPACES_COUNT * $NVMEOF_SUBSYSTEMS_COUNT )) test_run connect_all $devices_count gateways_count=$(( $(echo "$NVMEOF_GATEWAY_IP_ADDRESSES" | tr -cd ',' | wc -c) + 1 )) multipath_count=$(( $gateways_count * $NVMEOF_SUBSYSTEMS_COUNT)) diff --git a/qa/workunits/nvmeof/fio_test.sh b/qa/workunits/nvmeof/fio_test.sh index 03fb58693bd..f7f783afc67 100755 --- a/qa/workunits/nvmeof/fio_test.sh +++ b/qa/workunits/nvmeof/fio_test.sh @@ -34,7 +34,7 @@ done fio_file=$(mktemp -t nvmeof-fio-XXXX) all_drives_list=$(sudo nvme list --output-format=json | - jq -r '.Devices | sort_by(.NameSpace) | .[] | select(.ModelNumber == "Ceph bdev Controller") | .DevicePath') + jq -r '.Devices[].Subsystems[] | select(.Controllers | all(.ModelNumber == "Ceph bdev Controller")) | .Namespaces | sort_by(.NSID) | .[] | .NameSpace') # When the script is passed --start_ns and --end_ns (example: `nvmeof_fio_test.sh --start_ns 1 --end_ns 3`), # then fio runs on namespaces only in the defined range (which is 1 to 3 here). diff --git a/src/ceph-volume/ceph_volume/main.py b/src/ceph-volume/ceph_volume/main.py index f8eca65ec49..4f27f429e89 100644 --- a/src/ceph-volume/ceph_volume/main.py +++ b/src/ceph-volume/ceph_volume/main.py @@ -11,8 +11,16 @@ try: from importlib.metadata import entry_points def get_entry_points(group: str): # type: ignore - return entry_points().get(group, []) # type: ignore + eps = entry_points() + if hasattr(eps, 'select'): + # New importlib.metadata uses .select() + return eps.select(group=group) + else: + # Fallback to older EntryPoints that returns dicts + return eps.get(group, []) # type: ignore + except ImportError: + # Fallback to `pkg_resources` for older versions from pkg_resources import iter_entry_points as entry_points # type: ignore def get_entry_points(group: str): # type: ignore diff --git a/src/cephadm/cephadm.py b/src/cephadm/cephadm.py index d2ddf564116..a8616980e4d 100755 --- a/src/cephadm/cephadm.py +++ b/src/cephadm/cephadm.py @@ -111,6 +111,7 @@ from cephadmlib.file_utils import ( unlink_file, write_new, write_tmp, + update_meta_file, ) from cephadmlib.net_utils import ( build_addrv_params, @@ -3453,6 +3454,7 @@ def list_daemons( detail: bool = True, legacy_dir: Optional[str] = None, daemon_name: Optional[str] = None, + type_of_daemon: Optional[str] = None, ) -> List[Dict[str, str]]: host_version: Optional[str] = None ls = [] @@ -3489,6 +3491,8 @@ def list_daemons( if os.path.exists(data_dir): for i in os.listdir(data_dir): if i in ['mon', 'osd', 'mds', 'mgr', 'rgw']: + if type_of_daemon and type_of_daemon != i: + continue daemon_type = i for j in os.listdir(os.path.join(data_dir, i)): if '-' not in j: @@ -3525,6 +3529,8 @@ def list_daemons( if daemon_name and name != daemon_name: continue (daemon_type, daemon_id) = j.split('.', 1) + if type_of_daemon and type_of_daemon != daemon_type: + continue unit_name = get_unit_name(fsid, daemon_type, daemon_id) @@ -4705,6 +4711,34 @@ def command_list_images(ctx: CephadmContext) -> None: # print default images cp_obj.write(sys.stdout) + +def update_service_for_daemon(ctx: CephadmContext, + available_daemons: list, + update_daemons: list) -> None: + """ Update the unit.meta file of daemon with required service name for valid daemons""" + + data = {'service_name': ctx.service_name} + # check if all the daemon names are valid + if not set(update_daemons).issubset(set(available_daemons)): + raise Error(f'Error EINVAL: one or more daemons of {update_daemons} does not exist on this host') + for name in update_daemons: + path = os.path.join(ctx.data_dir, ctx.fsid, name, 'unit.meta') + update_meta_file(path, data) + print(f'Successfully updated daemon {name} with service {ctx.service_name}') + + +@infer_fsid +def command_update_osd_service(ctx: CephadmContext) -> int: + """update service for provided daemon""" + update_daemons = [f'osd.{osd_id}' for osd_id in ctx.osd_ids.split(',')] + daemons = list_daemons(ctx, detail=False, type_of_daemon='osd') + if not daemons: + raise Error(f'Daemon {ctx.osd_ids} does not exists on this host') + available_daemons = [d['name'] for d in daemons] + update_service_for_daemon(ctx, available_daemons, update_daemons) + return 0 + + ################################## @@ -5571,6 +5605,14 @@ def _get_parser(): parser_list_images = subparsers.add_parser( 'list-images', help='list all the default images') parser_list_images.set_defaults(func=command_list_images) + + parser_update_service = subparsers.add_parser( + 'update-osd-service', help='update service for provided daemon') + parser_update_service.set_defaults(func=command_update_osd_service) + parser_update_service.add_argument('--fsid', help='cluster FSID') + parser_update_service.add_argument('--osd-ids', required=True, help='Comma-separated OSD IDs') + parser_update_service.add_argument('--service-name', required=True, help='OSD service name') + return parser diff --git a/src/cephadm/cephadmlib/daemons/monitoring.py b/src/cephadm/cephadmlib/daemons/monitoring.py index 9a9402632b0..4ba00daaefb 100644 --- a/src/cephadm/cephadmlib/daemons/monitoring.py +++ b/src/cephadm/cephadmlib/daemons/monitoring.py @@ -16,7 +16,13 @@ from ..daemon_form import register as register_daemon_form from ..daemon_identity import DaemonIdentity from ..deployment_utils import to_deployment_container from ..exceptions import Error -from ..net_utils import get_fqdn, get_hostname, get_ip_addresses, wrap_ipv6 +from ..net_utils import ( + get_fqdn, + get_hostname, + get_ip_addresses, + wrap_ipv6, + EndPoint, +) @register_daemon_form @@ -89,11 +95,6 @@ class Monitoring(ContainerDaemonForm): 'image': DefaultImages.ALERTMANAGER.image_ref, 'cpus': '2', 'memory': '2GB', - 'args': [ - '--cluster.listen-address=:{}'.format( - port_map['alertmanager'][1] - ), - ], 'config-json-files': [ 'alertmanager.yml', ], @@ -248,11 +249,14 @@ class Monitoring(ContainerDaemonForm): ip = meta['ip'] if 'ports' in meta and meta['ports']: port = meta['ports'][0] - if daemon_type == 'prometheus': - config = fetch_configs(ctx) + config = fetch_configs(ctx) + if daemon_type in ['prometheus', 'alertmanager']: ip_to_bind_to = config.get('ip_to_bind_to', '') if ip_to_bind_to: ip = ip_to_bind_to + web_listen_addr = str(EndPoint(ip, port)) + r += [f'--web.listen-address={web_listen_addr}'] + if daemon_type == 'prometheus': retention_time = config.get('retention_time', '15d') retention_size = config.get( 'retention_size', '0' @@ -276,9 +280,11 @@ class Monitoring(ContainerDaemonForm): r += ['--web.route-prefix=/prometheus/'] else: r += [f'--web.external-url={scheme}://{host}:{port}'] - r += [f'--web.listen-address={ip}:{port}'] if daemon_type == 'alertmanager': - config = fetch_configs(ctx) + clus_listen_addr = str( + EndPoint(ip, self.port_map[daemon_type][1]) + ) + r += [f'--cluster.listen-address={clus_listen_addr}'] use_url_prefix = config.get('use_url_prefix', False) peers = config.get('peers', list()) # type: ignore for peer in peers: @@ -294,13 +300,11 @@ class Monitoring(ContainerDaemonForm): if daemon_type == 'promtail': r += ['--config.expand-env'] if daemon_type == 'prometheus': - config = fetch_configs(ctx) try: r += [f'--web.config.file={config["web_config"]}'] except KeyError: pass if daemon_type == 'node-exporter': - config = fetch_configs(ctx) try: r += [f'--web.config.file={config["web_config"]}'] except KeyError: diff --git a/src/cephadm/cephadmlib/file_utils.py b/src/cephadm/cephadmlib/file_utils.py index 27e70e31756..4dd88cc3671 100644 --- a/src/cephadm/cephadmlib/file_utils.py +++ b/src/cephadm/cephadmlib/file_utils.py @@ -5,6 +5,7 @@ import datetime import logging import os import tempfile +import json from contextlib import contextmanager from pathlib import Path @@ -157,3 +158,26 @@ def unlink_file( except Exception: if not ignore_errors: raise + + +def update_meta_file(file_path: str, update_key_val: dict) -> None: + """Update key in the file with provided value""" + try: + with open(file_path, 'r') as fh: + data = json.load(fh) + file_stat = os.stat(file_path) + except FileNotFoundError: + raise + except Exception: + logger.exception(f'Failed to update {file_path}') + raise + data.update( + {key: value for key, value in update_key_val.items() if key in data} + ) + + with write_new( + file_path, + owner=(file_stat.st_uid, file_stat.st_gid), + perms=(file_stat.st_mode & 0o777), + ) as fh: + fh.write(json.dumps(data, indent=4) + '\n') diff --git a/src/cephadm/cephadmlib/net_utils.py b/src/cephadm/cephadmlib/net_utils.py index 9a7f138b1c6..bfa61d933ef 100644 --- a/src/cephadm/cephadmlib/net_utils.py +++ b/src/cephadm/cephadmlib/net_utils.py @@ -24,12 +24,22 @@ class EndPoint: def __init__(self, ip: str, port: int) -> None: self.ip = ip self.port = port + self.is_ipv4 = True + try: + if ip and ipaddress.ip_network(ip).version == 6: + self.is_ipv4 = False + except Exception: + logger.exception('Failed to check ip address version') def __str__(self) -> str: - return f'{self.ip}:{self.port}' + if self.is_ipv4: + return f'{self.ip}:{self.port}' + return f'[{self.ip}]:{self.port}' def __repr__(self) -> str: - return f'{self.ip}:{self.port}' + if self.is_ipv4: + return f'{self.ip}:{self.port}' + return f'[{self.ip}]:{self.port}' def attempt_bind(ctx, s, address, port): diff --git a/src/cephadm/tests/test_deploy.py b/src/cephadm/tests/test_deploy.py index c5094db335f..1736639ed55 100644 --- a/src/cephadm/tests/test_deploy.py +++ b/src/cephadm/tests/test_deploy.py @@ -316,7 +316,7 @@ def test_deploy_a_monitoring_container(cephadm_fs, funkypatch): runfile_lines = f.read().splitlines() assert 'podman' in runfile_lines[-1] assert runfile_lines[-1].endswith( - 'quay.io/titans/prometheus:latest --config.file=/etc/prometheus/prometheus.yml --storage.tsdb.path=/prometheus --storage.tsdb.retention.time=15d --storage.tsdb.retention.size=0 --web.external-url=http://10.10.10.10:9095 --web.listen-address=1.2.3.4:9095' + 'quay.io/titans/prometheus:latest --config.file=/etc/prometheus/prometheus.yml --storage.tsdb.path=/prometheus --web.listen-address=1.2.3.4:9095 --storage.tsdb.retention.time=15d --storage.tsdb.retention.size=0 --web.external-url=http://10.10.10.10:9095' ) assert '--user 8765' in runfile_lines[-1] assert f'-v /var/lib/ceph/{fsid}/prometheus.fire/etc/prometheus:/etc/prometheus:Z' in runfile_lines[-1] diff --git a/src/common/CMakeLists.txt b/src/common/CMakeLists.txt index ea3cce16609..c607839a8d2 100644 --- a/src/common/CMakeLists.txt +++ b/src/common/CMakeLists.txt @@ -13,6 +13,7 @@ if(WIN32) endif() add_subdirectory(io_exerciser) +add_subdirectory(json) add_subdirectory(options) set(common_srcs diff --git a/src/common/bit_vector.hpp b/src/common/bit_vector.hpp index 961d9a0192e..c5fd491ed29 100644 --- a/src/common/bit_vector.hpp +++ b/src/common/bit_vector.hpp @@ -29,8 +29,8 @@ private: static const uint8_t MASK = static_cast<uint8_t>((1 << _bit_count) - 1); // must be power of 2 - BOOST_STATIC_ASSERT((_bit_count != 0) && !(_bit_count & (_bit_count - 1))); - BOOST_STATIC_ASSERT(_bit_count <= BITS_PER_BYTE); + static_assert((_bit_count != 0) && !(_bit_count & (_bit_count - 1))); + static_assert(_bit_count <= BITS_PER_BYTE); template <typename DataIterator> class ReferenceImpl { diff --git a/src/common/ceph_time.h b/src/common/ceph_time.h index 01feff4c063..0b05be5372e 100644 --- a/src/common/ceph_time.h +++ b/src/common/ceph_time.h @@ -342,6 +342,23 @@ public: } }; +// Please note time_guard is not thread safety -- multiple threads +// updating same diff_accumulator can corrupt it. +template <class ClockT = mono_clock> +class time_guard { + const typename ClockT::time_point start; + timespan& diff_accumulator; + +public: + time_guard(timespan& diff_accumulator) + : start(ClockT::now()), + diff_accumulator(diff_accumulator) { + } + ~time_guard() { + diff_accumulator += ClockT::now() - start; + } +}; + namespace time_detail { // So that our subtractions produce negative spans rather than // arithmetic underflow. diff --git a/src/common/config_cacher.h b/src/common/config_cacher.h index 91b8152dde1..f23195955a1 100644 --- a/src/common/config_cacher.h +++ b/src/common/config_cacher.h @@ -18,21 +18,30 @@ #include "common/config_obs.h" #include "common/config.h" +/** + * A simple class to cache a single configuration value. + * Points to note: + * - as get_tracked_conf_keys() must return a pointer to a null-terminated + * array of C-strings, 'keys' - an array - is used to hold the sole key + * that this observer is interested in. + * - the const cast should be removed once we change the + * get_tracked_conf_keys() to return const char* const * (or something + * similar). + */ template <typename ValueT> class md_config_cacher_t : public md_config_obs_t { ConfigProxy& conf; - const char* const option_name; + const char* keys[2]; std::atomic<ValueT> value_cache; const char** get_tracked_conf_keys() const override { - const static char* keys[] = { option_name, nullptr }; - return keys; + return const_cast<const char**>(keys); } void handle_conf_change(const ConfigProxy& conf, const std::set<std::string>& changed) override { - if (changed.count(option_name)) { - value_cache.store(conf.get_val<ValueT>(option_name)); + if (changed.contains(keys[0])) { + value_cache.store(conf.get_val<ValueT>(keys[0])); } } @@ -40,10 +49,10 @@ public: md_config_cacher_t(ConfigProxy& conf, const char* const option_name) : conf(conf), - option_name(option_name) { + keys{option_name, nullptr} { conf.add_observer(this); std::atomic_init(&value_cache, - conf.get_val<ValueT>(option_name)); + conf.get_val<ValueT>(keys[0])); } ~md_config_cacher_t() { diff --git a/src/common/io_exerciser/CMakeLists.txt b/src/common/io_exerciser/CMakeLists.txt index 07091df86e1..ab2e64fc222 100644 --- a/src/common/io_exerciser/CMakeLists.txt +++ b/src/common/io_exerciser/CMakeLists.txt @@ -5,9 +5,11 @@ add_library(object_io_exerciser STATIC Model.cc ObjectModel.cc RadosIo.cc + EcIoSequence.cc ) target_link_libraries(object_io_exerciser - librados + librados global + json_structures )
\ No newline at end of file diff --git a/src/common/io_exerciser/DataGenerator.cc b/src/common/io_exerciser/DataGenerator.cc index 9aa77eeb6e9..701c32fa9ec 100644 --- a/src/common/io_exerciser/DataGenerator.cc +++ b/src/common/io_exerciser/DataGenerator.cc @@ -2,32 +2,28 @@ // vim: ts=8 sw=2 smarttab #include "DataGenerator.h" -#include "ObjectModel.h" +#include <chrono> +#include <iostream> +#include <stdexcept> +#include "ObjectModel.h" #include "common/debug.h" #include "common/dout.h" - #include "fmt/format.h" #include "fmt/ranges.h" -#include <chrono> -#include <iostream> -#include <stdexcept> - #define dout_subsys ceph_subsys_rados #define dout_context g_ceph_context using DataGenerator = ceph::io_exerciser::data_generation::DataGenerator; -using SeededRandomGenerator = ceph::io_exerciser::data_generation - ::SeededRandomGenerator; -using HeaderedSeededRandomGenerator = ceph::io_exerciser::data_generation - ::HeaderedSeededRandomGenerator; +using SeededRandomGenerator = + ceph::io_exerciser::data_generation ::SeededRandomGenerator; +using HeaderedSeededRandomGenerator = + ceph::io_exerciser::data_generation ::HeaderedSeededRandomGenerator; std::unique_ptr<DataGenerator> DataGenerator::create_generator( - GenerationType generationType, const ObjectModel& model) -{ - switch(generationType) - { + GenerationType generationType, const ObjectModel& model) { + switch (generationType) { case GenerationType::SeededRandom: return std::make_unique<SeededRandomGenerator>(model); case GenerationType::HeaderedSeededRandom: @@ -39,28 +35,25 @@ std::unique_ptr<DataGenerator> DataGenerator::create_generator( return nullptr; } -bufferlist DataGenerator::generate_wrong_data(uint64_t offset, uint64_t length) -{ +bufferlist DataGenerator::generate_wrong_data(uint64_t offset, + uint64_t length) { bufferlist retlist; uint64_t block_size = m_model.get_block_size(); char buffer[block_size]; - for (uint64_t block_offset = offset; - block_offset < offset + length; - block_offset++) - { + for (uint64_t block_offset = offset; block_offset < offset + length; + block_offset++) { std::memset(buffer, 0, block_size); retlist.append(ceph::bufferptr(buffer, block_size)); } return retlist; } -bool DataGenerator::validate(bufferlist& bufferlist, uint64_t offset, uint64_t length) -{ +bool DataGenerator::validate(bufferlist& bufferlist, uint64_t offset, + uint64_t length) { return bufferlist.contents_equal(generate_data(offset, length)); } -ceph::bufferptr SeededRandomGenerator::generate_block(uint64_t block_offset) -{ +ceph::bufferptr SeededRandomGenerator::generate_block(uint64_t block_offset) { uint64_t block_size = m_model.get_block_size(); char buffer[block_size]; @@ -70,29 +63,26 @@ ceph::bufferptr SeededRandomGenerator::generate_block(uint64_t block_offset) constexpr size_t generation_length = sizeof(uint64_t); - for (uint64_t i = 0; i < block_size; i+=(2*generation_length), rand1++, rand2--) - { + for (uint64_t i = 0; i < block_size; + i += (2 * generation_length), rand1++, rand2--) { std::memcpy(buffer + i, &rand1, generation_length); std::memcpy(buffer + i + generation_length, &rand2, generation_length); } size_t remainingBytes = block_size % (generation_length * 2); - if (remainingBytes > generation_length) - { + if (remainingBytes > generation_length) { size_t remainingBytes2 = remainingBytes - generation_length; std::memcpy(buffer + block_size - remainingBytes, &rand1, remainingBytes); std::memcpy(buffer + block_size - remainingBytes2, &rand2, remainingBytes2); - } - else if (remainingBytes > 0) - { + } else if (remainingBytes > 0) { std::memcpy(buffer + block_size - remainingBytes, &rand1, remainingBytes); } return ceph::bufferptr(buffer, block_size); } -ceph::bufferptr SeededRandomGenerator::generate_wrong_block(uint64_t block_offset) -{ +ceph::bufferptr SeededRandomGenerator::generate_wrong_block( + uint64_t block_offset) { uint64_t block_size = m_model.get_block_size(); char buffer[block_size]; @@ -102,141 +92,134 @@ ceph::bufferptr SeededRandomGenerator::generate_wrong_block(uint64_t block_offse constexpr size_t generation_length = sizeof(uint64_t); - for (uint64_t i = 0; i < block_size; i+=(2*generation_length), rand1++, rand2--) - { + for (uint64_t i = 0; i < block_size; + i += (2 * generation_length), rand1++, rand2--) { std::memcpy(buffer + i, &rand1, generation_length); std::memcpy(buffer + i + generation_length, &rand2, generation_length); } size_t remainingBytes = block_size % (generation_length * 2); - if (remainingBytes > generation_length) - { + if (remainingBytes > generation_length) { size_t remainingBytes2 = remainingBytes - generation_length; std::memcpy(buffer + block_size - remainingBytes, &rand1, remainingBytes); std::memcpy(buffer + block_size - remainingBytes2, &rand2, remainingBytes2); - } - else if (remainingBytes > 0) - { + } else if (remainingBytes > 0) { std::memcpy(buffer + block_size - remainingBytes, &rand1, remainingBytes); } return ceph::bufferptr(buffer, block_size); } -bufferlist SeededRandomGenerator::generate_data(uint64_t offset, uint64_t length) -{ +bufferlist SeededRandomGenerator::generate_data(uint64_t offset, + uint64_t length) { bufferlist retlist; - for (uint64_t block_offset = offset; block_offset < offset + length; block_offset++) - { + for (uint64_t block_offset = offset; block_offset < offset + length; + block_offset++) { retlist.append(generate_block(block_offset)); } return retlist; } -bufferlist SeededRandomGenerator::generate_wrong_data(uint64_t offset, uint64_t length) -{ +bufferlist SeededRandomGenerator::generate_wrong_data(uint64_t offset, + uint64_t length) { bufferlist retlist; - for (uint64_t block_offset = offset; block_offset < offset + length; block_offset++) - { + for (uint64_t block_offset = offset; block_offset < offset + length; + block_offset++) { retlist.append(generate_wrong_block(block_offset)); } return retlist; } -HeaderedSeededRandomGenerator - ::HeaderedSeededRandomGenerator(const ObjectModel& model, - std::optional<uint64_t> unique_run_id) : - SeededRandomGenerator(model), - unique_run_id(unique_run_id.value_or(generate_unique_run_id())) -{ - -} +HeaderedSeededRandomGenerator ::HeaderedSeededRandomGenerator( + const ObjectModel& model, std::optional<uint64_t> unique_run_id) + : SeededRandomGenerator(model), + unique_run_id(unique_run_id.value_or(generate_unique_run_id())) {} -uint64_t HeaderedSeededRandomGenerator::generate_unique_run_id() -{ +uint64_t HeaderedSeededRandomGenerator::generate_unique_run_id() { std::mt19937_64 random_generator = - std::mt19937_64(duration_cast<std::chrono::milliseconds>( - std::chrono::system_clock::now().time_since_epoch()).count()); + std::mt19937_64(duration_cast<std::chrono::milliseconds>( + std::chrono::system_clock::now().time_since_epoch()) + .count()); - return random_generator(); + return random_generator(); } -ceph::bufferptr HeaderedSeededRandomGenerator::generate_block(uint64_t block_offset) -{ +ceph::bufferptr HeaderedSeededRandomGenerator::generate_block( + uint64_t block_offset) { SeedBytes seed = m_model.get_seed(block_offset); - TimeBytes current_time = duration_cast<std::chrono::milliseconds>( - std::chrono::system_clock::now().time_since_epoch()).count(); + TimeBytes current_time = + duration_cast<std::chrono::milliseconds>( + std::chrono::system_clock::now().time_since_epoch()) + .count(); - ceph::bufferptr bufferptr = SeededRandomGenerator::generate_block(block_offset); + ceph::bufferptr bufferptr = + SeededRandomGenerator::generate_block(block_offset); - std::memcpy(bufferptr.c_str() + uniqueIdStart(), &unique_run_id, uniqueIdLength()); + std::memcpy(bufferptr.c_str() + uniqueIdStart(), &unique_run_id, + uniqueIdLength()); std::memcpy(bufferptr.c_str() + seedStart(), &seed, seedLength()); std::memcpy(bufferptr.c_str() + timeStart(), ¤t_time, timeLength()); return bufferptr; } -ceph::bufferptr HeaderedSeededRandomGenerator::generate_wrong_block(uint64_t block_offset) -{ +ceph::bufferptr HeaderedSeededRandomGenerator::generate_wrong_block( + uint64_t block_offset) { return HeaderedSeededRandomGenerator::generate_block(block_offset % 8); } const HeaderedSeededRandomGenerator::UniqueIdBytes - HeaderedSeededRandomGenerator::readUniqueRunId(uint64_t block_offset, - const bufferlist& bufferlist) -{ +HeaderedSeededRandomGenerator::readUniqueRunId(uint64_t block_offset, + const bufferlist& bufferlist) { UniqueIdBytes read_unique_run_id = 0; - std::memcpy(&read_unique_run_id, - &bufferlist[(block_offset * m_model.get_block_size()) + uniqueIdStart()], - uniqueIdLength()); + std::memcpy( + &read_unique_run_id, + &bufferlist[(block_offset * m_model.get_block_size()) + uniqueIdStart()], + uniqueIdLength()); return read_unique_run_id; } const HeaderedSeededRandomGenerator::SeedBytes - HeaderedSeededRandomGenerator::readSeed(uint64_t block_offset, - const bufferlist& bufferlist) -{ +HeaderedSeededRandomGenerator::readSeed(uint64_t block_offset, + const bufferlist& bufferlist) { SeedBytes read_seed = 0; - std::memcpy(&read_seed, - &bufferlist[(block_offset * m_model.get_block_size()) + seedStart()], - seedLength()); + std::memcpy( + &read_seed, + &bufferlist[(block_offset * m_model.get_block_size()) + seedStart()], + seedLength()); return read_seed; } const HeaderedSeededRandomGenerator::TimeBytes - HeaderedSeededRandomGenerator::readDateTime(uint64_t block_offset, - const bufferlist& bufferlist) -{ +HeaderedSeededRandomGenerator::readDateTime(uint64_t block_offset, + const bufferlist& bufferlist) { TimeBytes read_time = 0; - std::memcpy(&read_time, - &bufferlist[(block_offset * m_model.get_block_size()) + timeStart()], - timeLength()); + std::memcpy( + &read_time, + &bufferlist[(block_offset * m_model.get_block_size()) + timeStart()], + timeLength()); return read_time; } bool HeaderedSeededRandomGenerator::validate(bufferlist& bufferlist, - uint64_t offset, uint64_t length) -{ + uint64_t offset, uint64_t length) { std::vector<uint64_t> invalid_block_offsets; - for (uint64_t block_offset = offset; block_offset < offset + length; block_offset++) - { - bool valid_block - = validate_block(block_offset, - (bufferlist.c_str() + ((block_offset - offset) * - m_model.get_block_size()))); - if (!valid_block) - { + for (uint64_t block_offset = offset; block_offset < offset + length; + block_offset++) { + bool valid_block = validate_block( + block_offset, (bufferlist.c_str() + + ((block_offset - offset) * m_model.get_block_size()))); + if (!valid_block) { invalid_block_offsets.push_back(block_offset); } } - if (!invalid_block_offsets.empty()) - { + if (!invalid_block_offsets.empty()) { printDebugInformationForOffsets(offset, invalid_block_offsets, bufferlist); } @@ -244,59 +227,51 @@ bool HeaderedSeededRandomGenerator::validate(bufferlist& bufferlist, } bool HeaderedSeededRandomGenerator::validate_block(uint64_t block_offset, - const char* buffer_start) -{ + const char* buffer_start) { // We validate the block matches what we generate byte for byte // however we ignore the time section of the header ceph::bufferptr bufferptr = generate_block(block_offset); bool valid = strncmp(bufferptr.c_str(), buffer_start, timeStart()) == 0; - valid = valid ? strncmp(bufferptr.c_str() + timeEnd(), - buffer_start + timeEnd(), - m_model.get_block_size() - timeEnd()) == 0 : valid; + valid = valid + ? strncmp(bufferptr.c_str() + timeEnd(), buffer_start + timeEnd(), + m_model.get_block_size() - timeEnd()) == 0 + : valid; return valid; } const HeaderedSeededRandomGenerator::ErrorType - HeaderedSeededRandomGenerator::getErrorTypeForBlock(uint64_t read_offset, - uint64_t block_offset, - const bufferlist& bufferlist) -{ - try - { - UniqueIdBytes read_unique_run_id = readUniqueRunId(block_offset - read_offset, - bufferlist); - if (unique_run_id != read_unique_run_id) - { +HeaderedSeededRandomGenerator::getErrorTypeForBlock( + uint64_t read_offset, uint64_t block_offset, const bufferlist& bufferlist) { + try { + UniqueIdBytes read_unique_run_id = + readUniqueRunId(block_offset - read_offset, bufferlist); + if (unique_run_id != read_unique_run_id) { return ErrorType::RUN_ID_MISMATCH; } SeedBytes read_seed = readSeed(block_offset - read_offset, bufferlist); - if (m_model.get_seed(block_offset) != read_seed) - { + if (m_model.get_seed(block_offset) != read_seed) { return ErrorType::SEED_MISMATCH; } if (std::strncmp(&bufferlist[((block_offset - read_offset) * - m_model.get_block_size()) + bodyStart()], + m_model.get_block_size()) + + bodyStart()], generate_block(block_offset).c_str() + bodyStart(), - m_model.get_block_size() - bodyStart()) != 0) - { + m_model.get_block_size() - bodyStart()) != 0) { return ErrorType::DATA_MISMATCH; } - } - catch(const std::exception& e) - { + } catch (const std::exception& e) { return ErrorType::DATA_NOT_FOUND; } return ErrorType::UNKNOWN; } -void HeaderedSeededRandomGenerator - ::printDebugInformationForBlock(uint64_t read_offset, uint64_t block_offset, - const bufferlist& bufferlist) -{ - ErrorType blockError = getErrorTypeForBlock(read_offset, block_offset, bufferlist); +void HeaderedSeededRandomGenerator ::printDebugInformationForBlock( + uint64_t read_offset, uint64_t block_offset, const bufferlist& bufferlist) { + ErrorType blockError = + getErrorTypeForBlock(read_offset, block_offset, bufferlist); TimeBytes read_time = 0; std::time_t ttp; @@ -304,433 +279,361 @@ void HeaderedSeededRandomGenerator char read_bytes[m_model.get_block_size()]; char generated_bytes[m_model.get_block_size()]; - if (blockError == ErrorType::DATA_MISMATCH || blockError == ErrorType::UNKNOWN) - { + if (blockError == ErrorType::DATA_MISMATCH || + blockError == ErrorType::UNKNOWN) { read_time = readDateTime(block_offset - read_offset, bufferlist); - std::chrono::system_clock::time_point time_point{std::chrono::milliseconds{read_time}}; + std::chrono::system_clock::time_point time_point{ + std::chrono::milliseconds{read_time}}; ttp = std::chrono::system_clock::to_time_t(time_point); - std::memcpy(&read_bytes, - &bufferlist[((block_offset - read_offset) * m_model.get_block_size())], - m_model.get_block_size() - bodyStart()); - std::memcpy(&generated_bytes, - generate_block(block_offset).c_str(), + std::memcpy( + &read_bytes, + &bufferlist[((block_offset - read_offset) * m_model.get_block_size())], + m_model.get_block_size() - bodyStart()); + std::memcpy(&generated_bytes, generate_block(block_offset).c_str(), m_model.get_block_size() - bodyStart()); } std::string error_string; - switch(blockError) - { - case ErrorType::RUN_ID_MISMATCH: - { - UniqueIdBytes read_unique_run_id = readUniqueRunId((block_offset - read_offset), - bufferlist); - error_string = fmt::format("Header (Run ID) mismatch detected at block {} " - "(byte offset {}) Header expected run id {} but found id {}. " - "Block data corrupt or not written from this instance of this application.", - block_offset, - block_offset * m_model.get_block_size(), - unique_run_id, - read_unique_run_id); - } - break; - - case ErrorType::SEED_MISMATCH: - { + switch (blockError) { + case ErrorType::RUN_ID_MISMATCH: { + UniqueIdBytes read_unique_run_id = + readUniqueRunId((block_offset - read_offset), bufferlist); + error_string = fmt::format( + "Header (Run ID) mismatch detected at block {} " + "(byte offset {}) Header expected run id {} but found id {}. " + "Block data corrupt or not written from this instance of this " + "application.", + block_offset, block_offset * m_model.get_block_size(), unique_run_id, + read_unique_run_id); + } break; + + case ErrorType::SEED_MISMATCH: { SeedBytes read_seed = readSeed((block_offset - read_offset), bufferlist); - if (m_model.get_seed_offsets(read_seed).size() == 0) - { - error_string = fmt::format("Data (Seed) mismatch detected at block {}" - " (byte offset {}). Header expected seed {} but found seed {}. " - "Read data was not from any other recognised block in the object.", - block_offset, - block_offset * m_model.get_block_size(), - m_model.get_seed(block_offset), - read_seed); - } - else - { + if (m_model.get_seed_offsets(read_seed).size() == 0) { + error_string = fmt::format( + "Data (Seed) mismatch detected at block {}" + " (byte offset {}). Header expected seed {} but found seed {}. " + "Read data was not from any other recognised block in the object.", + block_offset, block_offset * m_model.get_block_size(), + m_model.get_seed(block_offset), read_seed); + } else { std::vector<int> seed_offsets = m_model.get_seed_offsets(read_seed); - error_string = fmt::format("Data (Seed) mismatch detected at block {}" - " (byte offset {}). Header expected seed {} but found seed {}." - " Read data was from a different block(s): {}", - block_offset, - block_offset * m_model.get_block_size(), - m_model.get_seed(block_offset), - read_seed, + error_string = fmt::format( + "Data (Seed) mismatch detected at block {}" + " (byte offset {}). Header expected seed {} but found seed {}." + " Read data was from a different block(s): {}", + block_offset, block_offset * m_model.get_block_size(), + m_model.get_seed(block_offset), read_seed, fmt::join(seed_offsets.begin(), seed_offsets.end(), "")); } - } - break; - - case ErrorType::DATA_MISMATCH: - { - error_string = fmt::format("Data (Body) mismatch detected at block {}" - " (byte offset {}). Header data matches, data body does not." - " Data written at {}\nExpected data: \n{:02x}\nRead data:{:02x}", - block_offset, - block_offset * m_model.get_block_size(), + } break; + + case ErrorType::DATA_MISMATCH: { + error_string = fmt::format( + "Data (Body) mismatch detected at block {}" + " (byte offset {}). Header data matches, data body does not." + " Data written at {}\nExpected data: \n{:02x}\nRead data:{:02x}", + block_offset, block_offset * m_model.get_block_size(), std::ctime(&ttp), - fmt::join(generated_bytes, generated_bytes + m_model.get_block_size(), ""), + fmt::join(generated_bytes, generated_bytes + m_model.get_block_size(), + ""), fmt::join(read_bytes, read_bytes + m_model.get_block_size(), "")); - } - break; + } break; - case ErrorType::DATA_NOT_FOUND: - { + case ErrorType::DATA_NOT_FOUND: { uint64_t bufferlist_length = bufferlist.to_str().size(); - error_string = fmt::format("Data (Body) could not be read at block {}" - " (byte offset {}) offset in bufferlist returned from read: {}" - " ({} bytes). Returned bufferlist length: {}.", - block_offset, - block_offset * m_model.get_block_size(), + error_string = fmt::format( + "Data (Body) could not be read at block {}" + " (byte offset {}) offset in bufferlist returned from read: {}" + " ({} bytes). Returned bufferlist length: {}.", + block_offset, block_offset * m_model.get_block_size(), (block_offset - read_offset), (block_offset - read_offset) * m_model.get_block_size(), bufferlist_length); - } - break; + } break; case ErrorType::UNKNOWN: - [[ fallthrough ]]; - - default: - { - error_string = fmt::format("Data mismatch detected at block {}" - " (byte offset {}).\nExpected data:\n{:02x}\nRead data:\n{:02x}", - block_offset, - block_offset * m_model.get_block_size(), - fmt::join(generated_bytes, generated_bytes + m_model.get_block_size(), ""), + [[fallthrough]]; + + default: { + error_string = fmt::format( + "Data mismatch detected at block {}" + " (byte offset {}).\nExpected data:\n{:02x}\nRead data:\n{:02x}", + block_offset, block_offset * m_model.get_block_size(), + fmt::join(generated_bytes, generated_bytes + m_model.get_block_size(), + ""), fmt::join(read_bytes, read_bytes + m_model.get_block_size(), "")); - } - break; + } break; } dout(0) << error_string << dendl; } -void HeaderedSeededRandomGenerator - ::printDebugInformationForRange(uint64_t read_offset, - uint64_t start_block_offset, - uint64_t range_length_in_blocks, - ErrorType rangeError, - const bufferlist& bufferlist) -{ - switch(rangeError) - { - case ErrorType::RUN_ID_MISMATCH: - printDebugInformationForRunIdMismatchRange(read_offset, start_block_offset, - range_length_in_blocks, bufferlist); - break; - case ErrorType::SEED_MISMATCH: - printDebugInformationForSeedMismatchRange(read_offset, start_block_offset, - range_length_in_blocks, bufferlist); - break; - case ErrorType::DATA_MISMATCH: - printDebugInformationDataBodyMismatchRange(read_offset, start_block_offset, - range_length_in_blocks, bufferlist); - break; - case ErrorType::DATA_NOT_FOUND: - printDebugInformationDataNotFoundRange(read_offset, start_block_offset, - range_length_in_blocks, bufferlist); - break; - case ErrorType::UNKNOWN: - [[ fallthrough ]]; - default: - printDebugInformationCorruptRange(read_offset, start_block_offset, - range_length_in_blocks, bufferlist); - break; +void HeaderedSeededRandomGenerator ::printDebugInformationForRange( + uint64_t read_offset, uint64_t start_block_offset, + uint64_t range_length_in_blocks, ErrorType rangeError, + const bufferlist& bufferlist) { + switch (rangeError) { + case ErrorType::RUN_ID_MISMATCH: + printDebugInformationForRunIdMismatchRange( + read_offset, start_block_offset, range_length_in_blocks, bufferlist); + break; + case ErrorType::SEED_MISMATCH: + printDebugInformationForSeedMismatchRange( + read_offset, start_block_offset, range_length_in_blocks, bufferlist); + break; + case ErrorType::DATA_MISMATCH: + printDebugInformationDataBodyMismatchRange( + read_offset, start_block_offset, range_length_in_blocks, bufferlist); + break; + case ErrorType::DATA_NOT_FOUND: + printDebugInformationDataNotFoundRange( + read_offset, start_block_offset, range_length_in_blocks, bufferlist); + break; + case ErrorType::UNKNOWN: + [[fallthrough]]; + default: + printDebugInformationCorruptRange(read_offset, start_block_offset, + range_length_in_blocks, bufferlist); + break; } } -void HeaderedSeededRandomGenerator - ::printDebugInformationForRunIdMismatchRange(uint64_t read_offset, - uint64_t start_block_offset, - uint64_t range_length_in_blocks, - const bufferlist& bufferlist) -{ +void HeaderedSeededRandomGenerator ::printDebugInformationForRunIdMismatchRange( + uint64_t read_offset, uint64_t start_block_offset, + uint64_t range_length_in_blocks, const bufferlist& bufferlist) { uint64_t range_start = start_block_offset; uint64_t range_length = 0; - UniqueIdBytes initial_read_unique_run_id = readUniqueRunId(start_block_offset - read_offset, - bufferlist); + UniqueIdBytes initial_read_unique_run_id = + readUniqueRunId(start_block_offset - read_offset, bufferlist); for (uint64_t i = start_block_offset; - i < start_block_offset + range_length_in_blocks; i++) - { - ceph_assert(getErrorTypeForBlock(read_offset, i, bufferlist) - == ErrorType::RUN_ID_MISMATCH); + i < start_block_offset + range_length_in_blocks; i++) { + ceph_assert(getErrorTypeForBlock(read_offset, i, bufferlist) == + ErrorType::RUN_ID_MISMATCH); - UniqueIdBytes read_unique_run_id = readUniqueRunId(i - read_offset, bufferlist); + UniqueIdBytes read_unique_run_id = + readUniqueRunId(i - read_offset, bufferlist); if (initial_read_unique_run_id != read_unique_run_id || - i == (start_block_offset + range_length_in_blocks - 1)) - { - if (range_length == 1) - { + i == (start_block_offset + range_length_in_blocks - 1)) { + if (range_length == 1) { printDebugInformationForBlock(read_offset, i, bufferlist); - } - else if (range_length > 1) - { - dout(0) << fmt::format("Data (Run ID) Mismatch detected from block {} ({} bytes)" - " and spanning a range of {} blocks ({} bytes). " - "Expected run id {} for range but found id {}" - " for all blocks in range. " - "Block data corrupt or not written from this instance of this application.", - range_start, - range_start * m_model.get_block_size(), - range_length, - range_length * m_model.get_block_size(), - unique_run_id, - initial_read_unique_run_id) << dendl; + } else if (range_length > 1) { + dout(0) + << fmt::format( + "Data (Run ID) Mismatch detected from block {} ({} bytes)" + " and spanning a range of {} blocks ({} bytes). " + "Expected run id {} for range but found id {}" + " for all blocks in range. " + "Block data corrupt or not written from this instance of " + "this application.", + range_start, range_start * m_model.get_block_size(), + range_length, range_length * m_model.get_block_size(), + unique_run_id, initial_read_unique_run_id) + << dendl; } range_start = i; range_length = 1; initial_read_unique_run_id = read_unique_run_id; - } - else - { + } else { range_length++; } } - if (range_length == 1) - { - printDebugInformationForBlock(read_offset, - start_block_offset + range_length_in_blocks - 1, - bufferlist); - } - else if (range_length > 1) - { - dout(0) << fmt::format("Data (Run ID) Mismatch detected from block {}" - " ({} bytes) and spanning a range of {} blocks ({} bytes). " - "Expected run id {} for range but found id for all blocks in range. " - "Block data corrupt or not written from this instance of this application.", - range_start, - range_start * m_model.get_block_size(), - range_length, - range_length * m_model.get_block_size(), - unique_run_id, - initial_read_unique_run_id) + if (range_length == 1) { + printDebugInformationForBlock( + read_offset, start_block_offset + range_length_in_blocks - 1, + bufferlist); + } else if (range_length > 1) { + dout(0) << fmt::format( + "Data (Run ID) Mismatch detected from block {}" + " ({} bytes) and spanning a range of {} blocks ({} bytes). " + "Expected run id {} for range but found id for all blocks " + "in range. " + "Block data corrupt or not written from this instance of " + "this application.", + range_start, range_start * m_model.get_block_size(), + range_length, range_length * m_model.get_block_size(), + unique_run_id, initial_read_unique_run_id) << dendl; } } -void HeaderedSeededRandomGenerator - ::printDebugInformationForSeedMismatchRange(uint64_t read_offset, - uint64_t start_block_offset, - uint64_t range_length_in_blocks, - const bufferlist& bufferlist) -{ +void HeaderedSeededRandomGenerator ::printDebugInformationForSeedMismatchRange( + uint64_t read_offset, uint64_t start_block_offset, + uint64_t range_length_in_blocks, const bufferlist& bufferlist) { uint64_t range_start = start_block_offset; uint64_t range_length = 0; // Assert here if needed, as we can't support values // that can't be converted to a signed integer. - ceph_assert(m_model.get_block_size() < (std::numeric_limits<uint64_t>::max() / 2)); + ceph_assert(m_model.get_block_size() < + (std::numeric_limits<uint64_t>::max() / 2)); std::optional<int64_t> range_offset = 0; for (uint64_t i = start_block_offset; - i < start_block_offset + range_length_in_blocks; i++) - { - ceph_assert(getErrorTypeForBlock(read_offset, i, bufferlist) - == ErrorType::SEED_MISMATCH); + i < start_block_offset + range_length_in_blocks; i++) { + ceph_assert(getErrorTypeForBlock(read_offset, i, bufferlist) == + ErrorType::SEED_MISMATCH); SeedBytes read_seed = readSeed(i - read_offset, bufferlist); std::vector<int> seed_found_offsets = m_model.get_seed_offsets(read_seed); if ((seed_found_offsets.size() == 1 && - (static_cast<int64_t>(seed_found_offsets.front() - i) == range_offset)) || - range_length == 0) - { - if (range_length == 0) - { + (static_cast<int64_t>(seed_found_offsets.front() - i) == + range_offset)) || + range_length == 0) { + if (range_length == 0) { range_start = i; - if (seed_found_offsets.size() > 0) - { + if (seed_found_offsets.size() > 0) { range_offset = seed_found_offsets.front() - i; - } - else - { + } else { range_offset = std::nullopt; } } range_length++; - } - else - { - if (range_length == 1) - { + } else { + if (range_length == 1) { printDebugInformationForBlock(read_offset, i - 1, bufferlist); - } - else if (range_length > 1 && range_offset.has_value()) - { - dout(0) << fmt::format("Data (Seed) Mismatch detected from block {}" - " ({} bytes) and spanning a range of {} blocks ({} bytes). " - "Returned data located starting from block {} ({} bytes) " - "and spanning a range of {} blocks ({} bytes).", - range_start, - range_start * m_model.get_block_size(), - range_length, range_length * m_model.get_block_size(), - static_cast<uint64_t>(*range_offset) + range_start, - (static_cast<uint64_t>(*range_offset) + range_start) - * m_model.get_block_size(), - range_length, - range_length * m_model.get_block_size()) - << dendl; - } - else - { - dout(0) << fmt::format("Data (Seed) Mismatch detected from block {}" - " ({} bytes) and spanning a range of {} blocks ({} bytes). " - "Data seed mismatch spanning a range of {} blocks ({} bytes).", - range_start, - range_start * m_model.get_block_size(), - range_length, range_length * m_model.get_block_size(), - range_length, - range_length * m_model.get_block_size()) - << dendl; + } else if (range_length > 1 && range_offset.has_value()) { + dout(0) + << fmt::format( + "Data (Seed) Mismatch detected from block {}" + " ({} bytes) and spanning a range of {} blocks ({} bytes). " + "Returned data located starting from block {} ({} bytes) " + "and spanning a range of {} blocks ({} bytes).", + range_start, range_start * m_model.get_block_size(), + range_length, range_length * m_model.get_block_size(), + static_cast<uint64_t>(*range_offset) + range_start, + (static_cast<uint64_t>(*range_offset) + range_start) * + m_model.get_block_size(), + range_length, range_length * m_model.get_block_size()) + << dendl; + } else { + dout(0) + << fmt::format( + "Data (Seed) Mismatch detected from block {}" + " ({} bytes) and spanning a range of {} blocks ({} bytes). " + "Data seed mismatch spanning a range of {} blocks ({} " + "bytes).", + range_start, range_start * m_model.get_block_size(), + range_length, range_length * m_model.get_block_size(), + range_length, range_length * m_model.get_block_size()) + << dendl; } range_length = 1; range_start = i; - if (seed_found_offsets.size() > 0) - { + if (seed_found_offsets.size() > 0) { range_offset = seed_found_offsets.front() - i; - } - else - { + } else { range_offset = std::nullopt; } } } - if (range_length == 1) - { - printDebugInformationForBlock(read_offset, - start_block_offset + range_length_in_blocks - 1, - bufferlist); - } - else if (range_length > 1 && range_offset.has_value()) - { - dout(0) << fmt::format("Data (Seed) Mismatch detected from block {} ({} bytes) " - "and spanning a range of {} blocks ({} bytes). " - "Returned data located starting from block {} ({} bytes) " - "and spanning a range of {} blocks ({} bytes).", - range_start, - range_start * m_model.get_block_size(), - range_length, - range_length * m_model.get_block_size(), - *range_offset + range_start, - (*range_offset + range_start) * m_model.get_block_size(), - range_length, - range_length * m_model.get_block_size()) + if (range_length == 1) { + printDebugInformationForBlock( + read_offset, start_block_offset + range_length_in_blocks - 1, + bufferlist); + } else if (range_length > 1 && range_offset.has_value()) { + dout(0) << fmt::format( + "Data (Seed) Mismatch detected from block {} ({} bytes) " + "and spanning a range of {} blocks ({} bytes). " + "Returned data located starting from block {} ({} bytes) " + "and spanning a range of {} blocks ({} bytes).", + range_start, range_start * m_model.get_block_size(), + range_length, range_length * m_model.get_block_size(), + *range_offset + range_start, + (*range_offset + range_start) * m_model.get_block_size(), + range_length, range_length * m_model.get_block_size()) << dendl; - } - else - { - dout(0) << fmt::format("Data (Seed) Mismatch detected from block {} ({} bytes) " - "and spanning a range of {} blocks ({} bytes). " - "and spanning a range of {} blocks ({} bytes).", - range_start, - range_start * m_model.get_block_size(), - range_length, - range_length * m_model.get_block_size(), - range_length, - range_length * m_model.get_block_size()) + } else { + dout(0) << fmt::format( + "Data (Seed) Mismatch detected from block {} ({} bytes) " + "and spanning a range of {} blocks ({} bytes). " + "and spanning a range of {} blocks ({} bytes).", + range_start, range_start * m_model.get_block_size(), + range_length, range_length * m_model.get_block_size(), + range_length, range_length * m_model.get_block_size()) << dendl; } } -void HeaderedSeededRandomGenerator -::printDebugInformationDataBodyMismatchRange(uint64_t read_offset, - uint64_t start_block_offset, - uint64_t range_length_in_blocks, - const bufferlist& bufferlist) -{ - dout(0) << fmt::format("Data Mismatch detected in blocks from {} to {}. " - "Headers look as expected for range, " - "but generated data body does not match. " - "More information given for individual blocks below.", - start_block_offset, - start_block_offset + range_length_in_blocks - 1) +void HeaderedSeededRandomGenerator ::printDebugInformationDataBodyMismatchRange( + uint64_t read_offset, uint64_t start_block_offset, + uint64_t range_length_in_blocks, const bufferlist& bufferlist) { + dout(0) << fmt::format( + "Data Mismatch detected in blocks from {} to {}. " + "Headers look as expected for range, " + "but generated data body does not match. " + "More information given for individual blocks below.", + start_block_offset, + start_block_offset + range_length_in_blocks - 1) << dendl; for (uint64_t i = start_block_offset; - i < start_block_offset + range_length_in_blocks; i++) - { + i < start_block_offset + range_length_in_blocks; i++) { printDebugInformationForBlock(read_offset, i, bufferlist); } } -void HeaderedSeededRandomGenerator - ::printDebugInformationCorruptRange(uint64_t read_offset, - uint64_t start_block_offset, - uint64_t range_length_in_blocks, - const bufferlist& bufferlist) -{ - dout(0) << fmt::format("Data Mismatch detected in blocks from {} to {}. " - "Headers look as expected for range, " - "but generated data body does not match. " - "More information given for individual blocks below.", - start_block_offset, - start_block_offset + range_length_in_blocks - 1) +void HeaderedSeededRandomGenerator ::printDebugInformationCorruptRange( + uint64_t read_offset, uint64_t start_block_offset, + uint64_t range_length_in_blocks, const bufferlist& bufferlist) { + dout(0) << fmt::format( + "Data Mismatch detected in blocks from {} to {}. " + "Headers look as expected for range, " + "but generated data body does not match. " + "More information given for individual blocks below.", + start_block_offset, + start_block_offset + range_length_in_blocks - 1) << dendl; for (uint64_t i = start_block_offset; - i < start_block_offset + range_length_in_blocks; i++) - { + i < start_block_offset + range_length_in_blocks; i++) { printDebugInformationForBlock(read_offset, i, bufferlist); } } -void HeaderedSeededRandomGenerator - ::printDebugInformationDataNotFoundRange(uint64_t read_offset, - uint64_t start_block_offset, - uint64_t range_length_in_blocks, - const bufferlist& bufferlist) -{ - dout(0) << fmt::format("Data not found for blocks from {} to {}. " - "More information given for individual blocks below.", - start_block_offset, - start_block_offset + range_length_in_blocks - 1) +void HeaderedSeededRandomGenerator ::printDebugInformationDataNotFoundRange( + uint64_t read_offset, uint64_t start_block_offset, + uint64_t range_length_in_blocks, const bufferlist& bufferlist) { + dout(0) << fmt::format( + "Data not found for blocks from {} to {}. " + "More information given for individual blocks below.", + start_block_offset, + start_block_offset + range_length_in_blocks - 1) << dendl; - for (uint64_t i = start_block_offset; i < start_block_offset + range_length_in_blocks; i++) - { + for (uint64_t i = start_block_offset; + i < start_block_offset + range_length_in_blocks; i++) { printDebugInformationForBlock(read_offset, i, bufferlist); } } -void HeaderedSeededRandomGenerator - ::printDebugInformationForOffsets(uint64_t read_offset, - std::vector<uint64_t> offsets, - const bufferlist& bufferlist) -{ +void HeaderedSeededRandomGenerator ::printDebugInformationForOffsets( + uint64_t read_offset, std::vector<uint64_t> offsets, + const bufferlist& bufferlist) { uint64_t range_start = 0; uint64_t range_length = 0; ErrorType rangeError = ErrorType::UNKNOWN; - for (const uint64_t& block_offset : offsets) - { - ErrorType blockError = getErrorTypeForBlock(read_offset, block_offset, - bufferlist); + for (const uint64_t& block_offset : offsets) { + ErrorType blockError = + getErrorTypeForBlock(read_offset, block_offset, bufferlist); - if (range_start == 0 && range_length == 0) - { + if (range_start == 0 && range_length == 0) { range_start = block_offset; range_length = 1; rangeError = blockError; - } - else if (blockError == rangeError && - range_start + range_length == block_offset) -{ + } else if (blockError == rangeError && + range_start + range_length == block_offset) { range_length++; - } - else - { - if (range_length == 1) - { + } else { + if (range_length == 1) { printDebugInformationForBlock(read_offset, range_start, bufferlist); - } - else if (range_length > 1) - { + } else if (range_length > 1) { printDebugInformationForRange(read_offset, range_start, range_length, rangeError, bufferlist); } @@ -741,12 +644,9 @@ void HeaderedSeededRandomGenerator } } - if (range_length == 1) - { + if (range_length == 1) { printDebugInformationForBlock(read_offset, range_start, bufferlist); - } - else if (range_length > 1) - { + } else if (range_length > 1) { printDebugInformationForRange(read_offset, range_start, range_length, rangeError, bufferlist); } diff --git a/src/common/io_exerciser/DataGenerator.h b/src/common/io_exerciser/DataGenerator.h index 1e5784a54cc..c497c78ed61 100644 --- a/src/common/io_exerciser/DataGenerator.h +++ b/src/common/io_exerciser/DataGenerator.h @@ -3,8 +3,8 @@ #include <memory> #include <random> -#include "include/buffer.h" #include "ObjectModel.h" +#include "include/buffer.h" /* Overview * @@ -23,149 +23,139 @@ * * class HeaderedSeededRandomGenerator * Inherits from SeededDataGenerator. Generates entirely random patterns - * based on the seed retrieved by the model, however also appends a + * based on the seed retrieved by the model, however also appends a * header to the start of each block. This generator also provides * a range of verbose debug options to help disagnose a miscompare * whenever it detects unexpected data. */ namespace ceph { - namespace io_exerciser { - namespace data_generation { - enum class GenerationType { - SeededRandom, - HeaderedSeededRandom - // CompressedGenerator - // MixedGenerator - }; - - class DataGenerator { - public: - virtual ~DataGenerator() = default; - static std::unique_ptr<DataGenerator> - create_generator(GenerationType generatorType, - const ObjectModel& model); - virtual bufferlist generate_data(uint64_t length, uint64_t offset)=0; - virtual bool validate(bufferlist& bufferlist, uint64_t offset, - uint64_t length); - - // Used for testing debug outputs from data generation - virtual bufferlist generate_wrong_data(uint64_t offset, uint64_t length); - - protected: - const ObjectModel& m_model; - - DataGenerator(const ObjectModel& model) : m_model(model) {} - }; - - class SeededRandomGenerator : public DataGenerator - { - public: - SeededRandomGenerator(const ObjectModel& model) - : DataGenerator(model) {} - - virtual bufferptr generate_block(uint64_t offset); - virtual bufferlist generate_data(uint64_t length, uint64_t offset); - virtual bufferptr generate_wrong_block(uint64_t offset); - virtual bufferlist generate_wrong_data(uint64_t offset, uint64_t length) override; - }; - - class HeaderedSeededRandomGenerator : public SeededRandomGenerator - { - public: - HeaderedSeededRandomGenerator(const ObjectModel& model, - std::optional<uint64_t> unique_run_id = std::nullopt); - - bufferptr generate_block(uint64_t offset) override; - bufferptr generate_wrong_block(uint64_t offset) override; - bool validate(bufferlist& bufferlist, uint64_t offset, - uint64_t length) override; - - private: - using UniqueIdBytes = uint64_t; - using SeedBytes = int; - using TimeBytes = uint64_t; - - enum class ErrorType { - RUN_ID_MISMATCH, - SEED_MISMATCH, - DATA_MISMATCH, - DATA_NOT_FOUND, - UNKNOWN - }; - - constexpr uint8_t headerStart() const - { return 0; }; - constexpr uint8_t uniqueIdStart() const - { return headerStart(); }; - constexpr uint8_t uniqueIdLength() const - { return sizeof(UniqueIdBytes); }; - constexpr uint8_t seedStart() const - { return uniqueIdStart() + uniqueIdLength(); }; - constexpr uint8_t seedLength() const - { return sizeof(SeedBytes); }; - constexpr uint8_t timeStart() const - { return seedStart() + seedLength(); }; - constexpr uint8_t timeLength() const - { return sizeof(TimeBytes); }; - constexpr uint8_t timeEnd() const - { return timeStart() + timeLength(); }; - constexpr uint8_t headerLength() const - { return uniqueIdLength() + seedLength() + timeLength(); }; - constexpr uint8_t bodyStart() const - { return headerStart() + headerLength(); }; - - const UniqueIdBytes readUniqueRunId(uint64_t block_offset, - const bufferlist& bufferlist); - const SeedBytes readSeed(uint64_t block_offset, - const bufferlist& bufferlist); - const TimeBytes readDateTime(uint64_t block_offset, +namespace io_exerciser { +namespace data_generation { +enum class GenerationType { + SeededRandom, + HeaderedSeededRandom + // CompressedGenerator + // MixedGenerator +}; + +class DataGenerator { + public: + virtual ~DataGenerator() = default; + static std::unique_ptr<DataGenerator> create_generator( + GenerationType generatorType, const ObjectModel& model); + virtual bufferlist generate_data(uint64_t length, uint64_t offset) = 0; + virtual bool validate(bufferlist& bufferlist, uint64_t offset, + uint64_t length); + + // Used for testing debug outputs from data generation + virtual bufferlist generate_wrong_data(uint64_t offset, uint64_t length); + + protected: + const ObjectModel& m_model; + + DataGenerator(const ObjectModel& model) : m_model(model) {} +}; + +class SeededRandomGenerator : public DataGenerator { + public: + SeededRandomGenerator(const ObjectModel& model) : DataGenerator(model) {} + + virtual bufferptr generate_block(uint64_t offset); + bufferlist generate_data(uint64_t length, uint64_t offset) override; + virtual bufferptr generate_wrong_block(uint64_t offset); + bufferlist generate_wrong_data(uint64_t offset, + uint64_t length) override; +}; + +class HeaderedSeededRandomGenerator : public SeededRandomGenerator { + public: + HeaderedSeededRandomGenerator( + const ObjectModel& model, + std::optional<uint64_t> unique_run_id = std::nullopt); + + bufferptr generate_block(uint64_t offset) override; + bufferptr generate_wrong_block(uint64_t offset) override; + bool validate(bufferlist& bufferlist, uint64_t offset, + uint64_t length) override; + + private: + using UniqueIdBytes = uint64_t; + using SeedBytes = int; + using TimeBytes = uint64_t; + + enum class ErrorType { + RUN_ID_MISMATCH, + SEED_MISMATCH, + DATA_MISMATCH, + DATA_NOT_FOUND, + UNKNOWN + }; + + constexpr uint8_t headerStart() const { return 0; }; + constexpr uint8_t uniqueIdStart() const { return headerStart(); }; + constexpr uint8_t uniqueIdLength() const { return sizeof(UniqueIdBytes); }; + constexpr uint8_t seedStart() const { + return uniqueIdStart() + uniqueIdLength(); + }; + constexpr uint8_t seedLength() const { return sizeof(SeedBytes); }; + constexpr uint8_t timeStart() const { return seedStart() + seedLength(); }; + constexpr uint8_t timeLength() const { return sizeof(TimeBytes); }; + constexpr uint8_t timeEnd() const { return timeStart() + timeLength(); }; + constexpr uint8_t headerLength() const { + return uniqueIdLength() + seedLength() + timeLength(); + }; + constexpr uint8_t bodyStart() const { + return headerStart() + headerLength(); + }; + + const UniqueIdBytes readUniqueRunId(uint64_t block_offset, + const bufferlist& bufferlist); + const SeedBytes readSeed(uint64_t block_offset, const bufferlist& bufferlist); + const TimeBytes readDateTime(uint64_t block_offset, + const bufferlist& bufferlist); + + const UniqueIdBytes unique_run_id; + + uint64_t generate_unique_run_id(); + + bool validate_block(uint64_t block_offset, const char* buffer_start); + + const ErrorType getErrorTypeForBlock(uint64_t read_offset, + uint64_t block_offset, const bufferlist& bufferlist); - const UniqueIdBytes unique_run_id; - - uint64_t generate_unique_run_id(); - - bool validate_block(uint64_t block_offset, const char* buffer_start); - - const ErrorType getErrorTypeForBlock(uint64_t read_offset, - uint64_t block_offset, - const bufferlist& bufferlist); - - void printDebugInformationForBlock(uint64_t read_offset, - uint64_t block_offset, - const bufferlist& bufferlist); - void printDebugInformationForRange(uint64_t read_offset, - uint64_t start_block_offset, - uint64_t range_length_in_blocks, - ErrorType rangeError, - const bufferlist& bufferlist); - - void printDebugInformationForRunIdMismatchRange(uint64_t read_offset, - uint64_t start_block_offset, - uint64_t range_length_in_blocks, - const bufferlist& bufferlist); - void printDebugInformationForSeedMismatchRange(uint64_t read_offset, - uint64_t start_block_offset, - uint64_t range_length_in_blocks, - const bufferlist& bufferlist); - void printDebugInformationDataBodyMismatchRange(uint64_t read_offset, - uint64_t start_block_offset, - uint64_t range_length_in_blocks, - const bufferlist& bufferlist); - void printDebugInformationDataNotFoundRange(uint64_t ßread_offset, - uint64_t start_block_offset, - uint64_t range_length_in_blocks, - const bufferlist& bufferlist); - void printDebugInformationCorruptRange(uint64_t read_offset, - uint64_t start_block_offset, - uint64_t range_length_in_blocks, - const bufferlist& bufferlist); - - void printDebugInformationForOffsets(uint64_t read_offset, - std::vector<uint64_t> offsets, - const bufferlist& bufferlist); - }; - } - } -} + void printDebugInformationForBlock(uint64_t read_offset, + uint64_t block_offset, + const bufferlist& bufferlist); + void printDebugInformationForRange(uint64_t read_offset, + uint64_t start_block_offset, + uint64_t range_length_in_blocks, + ErrorType rangeError, + const bufferlist& bufferlist); + + void printDebugInformationForRunIdMismatchRange( + uint64_t read_offset, uint64_t start_block_offset, + uint64_t range_length_in_blocks, const bufferlist& bufferlist); + void printDebugInformationForSeedMismatchRange( + uint64_t read_offset, uint64_t start_block_offset, + uint64_t range_length_in_blocks, const bufferlist& bufferlist); + void printDebugInformationDataBodyMismatchRange( + uint64_t read_offset, uint64_t start_block_offset, + uint64_t range_length_in_blocks, const bufferlist& bufferlist); + void printDebugInformationDataNotFoundRange(uint64_t ßread_offset, + uint64_t start_block_offset, + uint64_t range_length_in_blocks, + const bufferlist& bufferlist); + void printDebugInformationCorruptRange(uint64_t read_offset, + uint64_t start_block_offset, + uint64_t range_length_in_blocks, + const bufferlist& bufferlist); + + void printDebugInformationForOffsets(uint64_t read_offset, + std::vector<uint64_t> offsets, + const bufferlist& bufferlist); +}; +} // namespace data_generation +} // namespace io_exerciser +} // namespace ceph diff --git a/src/common/io_exerciser/EcIoSequence.cc b/src/common/io_exerciser/EcIoSequence.cc new file mode 100644 index 00000000000..611920c96e0 --- /dev/null +++ b/src/common/io_exerciser/EcIoSequence.cc @@ -0,0 +1,267 @@ +#include "EcIoSequence.h" + +#include <memory> + +using IoOp = ceph::io_exerciser::IoOp; +using Sequence = ceph::io_exerciser::Sequence; +using IoSequence = ceph::io_exerciser::IoSequence; +using EcIoSequence = ceph::io_exerciser::EcIoSequence; +using ReadInjectSequence = ceph::io_exerciser::ReadInjectSequence; + +bool EcIoSequence::is_supported(Sequence sequence) const { return true; } + +std::unique_ptr<IoSequence> EcIoSequence::generate_sequence( + Sequence sequence, std::pair<int, int> obj_size_range, int k, int m, + int seed) { + switch (sequence) { + case Sequence::SEQUENCE_SEQ0: + [[fallthrough]]; + case Sequence::SEQUENCE_SEQ1: + [[fallthrough]]; + case Sequence::SEQUENCE_SEQ2: + [[fallthrough]]; + case Sequence::SEQUENCE_SEQ3: + [[fallthrough]]; + case Sequence::SEQUENCE_SEQ4: + [[fallthrough]]; + case Sequence::SEQUENCE_SEQ5: + [[fallthrough]]; + case Sequence::SEQUENCE_SEQ6: + [[fallthrough]]; + case Sequence::SEQUENCE_SEQ7: + [[fallthrough]]; + case Sequence::SEQUENCE_SEQ8: + [[fallthrough]]; + case Sequence::SEQUENCE_SEQ9: + return std::make_unique<ReadInjectSequence>(obj_size_range, seed, + sequence, k, m); + case Sequence::SEQUENCE_SEQ10: + return std::make_unique<Seq10>(obj_size_range, seed, k, m); + default: + ceph_abort_msg("Unrecognised sequence"); + } +} + +EcIoSequence::EcIoSequence(std::pair<int, int> obj_size_range, int seed) + : IoSequence(obj_size_range, seed), + setup_inject(false), + clear_inject(false), + shard_to_inject(std::nullopt) {} + +void EcIoSequence::select_random_data_shard_to_inject_read_error(int k, int m) { + shard_to_inject = rng(k - 1); + setup_inject = true; +} + +void EcIoSequence::select_random_data_shard_to_inject_write_error(int k, + int m) { + // Write errors do not support injecting to the primary OSD + shard_to_inject = rng(1, k - 1); + setup_inject = true; +} + +void EcIoSequence::select_random_shard_to_inject_read_error(int k, int m) { + shard_to_inject = rng(k + m - 1); + setup_inject = true; +} + +void EcIoSequence::select_random_shard_to_inject_write_error(int k, int m) { + // Write errors do not support injecting to the primary OSD + shard_to_inject = rng(1, k + m - 1); + setup_inject = true; +} + +void EcIoSequence::generate_random_read_inject_type() { + inject_op_type = static_cast<InjectOpType>( + rng(static_cast<int>(InjectOpType::ReadEIO), + static_cast<int>(InjectOpType::ReadMissingShard))); +} + +void EcIoSequence::generate_random_write_inject_type() { + inject_op_type = static_cast<InjectOpType>( + rng(static_cast<int>(InjectOpType::WriteFailAndRollback), + static_cast<int>(InjectOpType::WriteOSDAbort))); +} + +ceph::io_exerciser::ReadInjectSequence::ReadInjectSequence( + std::pair<int, int> obj_size_range, int seed, Sequence s, int k, int m) + : EcIoSequence(obj_size_range, seed) { + child_sequence = IoSequence::generate_sequence(s, obj_size_range, seed); + select_random_data_shard_to_inject_read_error(k, m); + generate_random_read_inject_type(); +} + +Sequence ceph::io_exerciser::ReadInjectSequence::get_id() const { + return child_sequence->get_id(); +} + +std::string ceph::io_exerciser::ReadInjectSequence::get_name() const { + return child_sequence->get_name() + + " running with read errors injected on shard " + + std::to_string(*shard_to_inject); +} + +std::unique_ptr<IoOp> ReadInjectSequence::next() { + step++; + + if (nextOp) { + std::unique_ptr<IoOp> retOp = nullptr; + nextOp.swap(retOp); + return retOp; + } + + std::unique_ptr<IoOp> childOp = child_sequence->next(); + + switch (childOp->getOpType()) { + case OpType::Remove: + nextOp.swap(childOp); + switch (inject_op_type) { + case InjectOpType::ReadEIO: + return ClearReadErrorInjectOp::generate(*shard_to_inject, 0); + case InjectOpType::ReadMissingShard: + return ClearReadErrorInjectOp::generate(*shard_to_inject, 1); + case InjectOpType::WriteFailAndRollback: + return ClearWriteErrorInjectOp::generate(*shard_to_inject, 0); + case InjectOpType::WriteOSDAbort: + return ClearWriteErrorInjectOp::generate(*shard_to_inject, 3); + case InjectOpType::None: + [[fallthrough]]; + default: + ceph_abort_msg("Unsupported operation"); + } + break; + case OpType::Create: + switch (inject_op_type) { + case InjectOpType::ReadEIO: + nextOp = InjectReadErrorOp::generate( + *shard_to_inject, 0, 0, std::numeric_limits<uint64_t>::max()); + break; + case InjectOpType::ReadMissingShard: + nextOp = InjectReadErrorOp::generate( + *shard_to_inject, 1, 0, std::numeric_limits<uint64_t>::max()); + break; + case InjectOpType::WriteFailAndRollback: + nextOp = InjectWriteErrorOp::generate( + *shard_to_inject, 0, 0, std::numeric_limits<uint64_t>::max()); + break; + case InjectOpType::WriteOSDAbort: + nextOp = InjectWriteErrorOp::generate( + *shard_to_inject, 3, 0, std::numeric_limits<uint64_t>::max()); + break; + case InjectOpType::None: + [[fallthrough]]; + default: + ceph_abort_msg("Unsupported operation"); + } + break; + default: + // Do nothing in default case + break; + } + + return childOp; +} + +std::unique_ptr<ceph::io_exerciser::IoOp> +ceph::io_exerciser::ReadInjectSequence::_next() { + ceph_abort_msg( + "Should not reach this point, " + "this sequence should only consume complete sequences"); + + return DoneOp::generate(); +} + +ceph::io_exerciser::Seq10::Seq10(std::pair<int, int> obj_size_range, int seed, + int k, int m) + : EcIoSequence(obj_size_range, seed), + offset(0), + length(1), + inject_error_done(false), + failed_write_done(false), + read_done(false), + successful_write_done(false), + test_all_lengths(false), // Only test length(1) due to time constraints + test_all_sizes( + false) // Only test obj_size(rand()) due to time constraints +{ + select_random_shard_to_inject_write_error(k, m); + // We will inject specifically as part of our sequence in this sequence + setup_inject = false; + if (!test_all_sizes) { + select_random_object_size(); + } +} + +Sequence ceph::io_exerciser::Seq10::get_id() const { + return Sequence::SEQUENCE_SEQ10; +} + +std::string ceph::io_exerciser::Seq10::get_name() const { + return "Sequential writes of length " + std::to_string(length) + + " with queue depth 1" + " first injecting a failed write and read it to ensure it rolls back, " + "then" + " successfully writing the data and reading the write the ensure it " + "is applied"; +} + +std::unique_ptr<ceph::io_exerciser::IoOp> ceph::io_exerciser::Seq10::_next() { + if (!inject_error_done) { + inject_error_done = true; + return InjectWriteErrorOp::generate(*shard_to_inject, 0, 0, + std::numeric_limits<uint64_t>::max()); + } else if (!failed_write_done) { + failed_write_done = true; + read_done = false; + barrier = true; + return SingleFailedWriteOp::generate(offset, length); + } else if (failed_write_done && !read_done) { + read_done = true; + barrier = true; + return SingleReadOp::generate(offset, length); + } else if (!clear_inject_done) { + clear_inject_done = true; + return ClearWriteErrorInjectOp::generate(*shard_to_inject, 0); + } else if (!successful_write_done) { + successful_write_done = true; + read_done = false; + barrier = true; + return SingleWriteOp::generate(offset, length); + } else if (successful_write_done && !read_done) { + read_done = true; + return SingleReadOp::generate(offset, length); + } else if (successful_write_done && read_done) { + offset++; + inject_error_done = false; + failed_write_done = false; + read_done = false; + clear_inject_done = false; + successful_write_done = false; + + if (offset + length >= obj_size) { + if (!test_all_lengths) { + remove = true; + done = true; + return BarrierOp::generate(); + } + + offset = 0; + length++; + if (length > obj_size) { + if (!test_all_sizes) { + remove = true; + done = true; + return BarrierOp::generate(); + } + + length = 1; + return increment_object_size(); + } + } + + return BarrierOp::generate(); + } else { + ceph_abort_msg("Sequence in undefined state. Aborting"); + return DoneOp::generate(); + } +}
\ No newline at end of file diff --git a/src/common/io_exerciser/EcIoSequence.h b/src/common/io_exerciser/EcIoSequence.h new file mode 100644 index 00000000000..37283b3906b --- /dev/null +++ b/src/common/io_exerciser/EcIoSequence.h @@ -0,0 +1,65 @@ +#include "IoSequence.h" + +namespace ceph { +namespace io_exerciser { +class EcIoSequence : public IoSequence { + public: + virtual bool is_supported(Sequence sequence) const override; + static std::unique_ptr<IoSequence> generate_sequence( + Sequence s, std::pair<int, int> obj_size_range, int k, int m, int seed); + + protected: + bool setup_inject; + bool clear_inject; + std::optional<uint64_t> shard_to_inject; + InjectOpType inject_op_type; + + EcIoSequence(std::pair<int, int> obj_size_range, int seed); + + // Writes cannot be sent to injected on shard zero, so selections seperated + // out + void select_random_data_shard_to_inject_read_error(int k, int m); + void select_random_data_shard_to_inject_write_error(int k, int m); + void select_random_shard_to_inject_read_error(int k, int m); + void select_random_shard_to_inject_write_error(int k, int m); + void generate_random_read_inject_type(); + void generate_random_write_inject_type(); +}; + +class ReadInjectSequence : public EcIoSequence { + public: + ReadInjectSequence(std::pair<int, int> obj_size_range, int seed, Sequence s, + int k, int m); + + Sequence get_id() const override; + std::string get_name() const override; + virtual std::unique_ptr<IoOp> next() override; + std::unique_ptr<IoOp> _next() override; + + private: + std::unique_ptr<IoSequence> child_sequence; + std::unique_ptr<IoOp> nextOp; +}; + +class Seq10 : public EcIoSequence { + public: + Seq10(std::pair<int, int> obj_size_range, int seed, int k, int m); + + Sequence get_id() const override; + std::string get_name() const override; + std::unique_ptr<IoOp> _next() override; + + private: + uint64_t offset; + uint64_t length; + + bool inject_error_done; + bool failed_write_done; + bool read_done; + bool clear_inject_done; + bool successful_write_done; + bool test_all_lengths; + bool test_all_sizes; +}; +} // namespace io_exerciser +} // namespace ceph
\ No newline at end of file diff --git a/src/common/io_exerciser/IoOp.cc b/src/common/io_exerciser/IoOp.cc index cd855ba6fff..493d1f435b4 100644 --- a/src/common/io_exerciser/IoOp.cc +++ b/src/common/io_exerciser/IoOp.cc @@ -1,188 +1,316 @@ #include "IoOp.h" -using IoOp = ceph::io_exerciser::IoOp; +#include "fmt/format.h" +#include "include/ceph_assert.h" -IoOp::IoOp( OpType op, - uint64_t offset1, uint64_t length1, - uint64_t offset2, uint64_t length2, - uint64_t offset3, uint64_t length3) : - op(op), - offset1(offset1), length1(length1), - offset2(offset2), length2(length2), - offset3(offset3), length3(length3) -{ +using IoOp = ceph::io_exerciser::IoOp; +using OpType = ceph::io_exerciser::OpType; -} +using DoneOp = ceph::io_exerciser::DoneOp; +using BarrierOp = ceph::io_exerciser::BarrierOp; +using CreateOp = ceph::io_exerciser::CreateOp; +using RemoveOp = ceph::io_exerciser::RemoveOp; +using SingleReadOp = ceph::io_exerciser::SingleReadOp; +using DoubleReadOp = ceph::io_exerciser::DoubleReadOp; +using TripleReadOp = ceph::io_exerciser::TripleReadOp; +using SingleWriteOp = ceph::io_exerciser::SingleWriteOp; +using DoubleWriteOp = ceph::io_exerciser::DoubleWriteOp; +using TripleWriteOp = ceph::io_exerciser::TripleWriteOp; +using SingleFailedWriteOp = ceph::io_exerciser::SingleFailedWriteOp; +using DoubleFailedWriteOp = ceph::io_exerciser::DoubleFailedWriteOp; +using TripleFailedWriteOp = ceph::io_exerciser::TripleFailedWriteOp; -std::string IoOp::value_to_string(uint64_t v) const -{ +namespace { +std::string value_to_string(uint64_t v) { if (v < 1024 || (v % 1024) != 0) { return std::to_string(v); - }else if (v < 1024*1024 || (v % (1024 * 1024)) != 0 ) { + } else if (v < 1024 * 1024 || (v % (1024 * 1024)) != 0) { return std::to_string(v / 1024) + "K"; - }else{ + } else { return std::to_string(v / 1024 / 1024) + "M"; } } +} // namespace -std::unique_ptr<IoOp> IoOp - ::generate_done() { +IoOp::IoOp() {} - return std::make_unique<IoOp>(OpType::Done); -} +template <OpType opType> +ceph::io_exerciser::TestOp<opType>::TestOp() : IoOp() {} + +DoneOp::DoneOp() : TestOp<OpType::Done>() {} -std::unique_ptr<IoOp> IoOp - ::generate_barrier() { +std::string DoneOp::to_string(uint64_t block_size) const { return "Done"; } - return std::make_unique<IoOp>(OpType::BARRIER); +std::unique_ptr<DoneOp> DoneOp::generate() { + return std::make_unique<DoneOp>(); } -std::unique_ptr<IoOp> IoOp - ::generate_create(uint64_t size) { +BarrierOp::BarrierOp() : TestOp<OpType::Barrier>() {} - return std::make_unique<IoOp>(OpType::CREATE,0,size); +std::unique_ptr<BarrierOp> BarrierOp::generate() { + return std::make_unique<BarrierOp>(); } -std::unique_ptr<IoOp> IoOp - ::generate_remove() { - - return std::make_unique<IoOp>(OpType::REMOVE); +std::string BarrierOp::to_string(uint64_t block_size) const { + return "Barrier"; } -std::unique_ptr<IoOp> IoOp - ::generate_read(uint64_t offset, uint64_t length) { +CreateOp::CreateOp(uint64_t size) : TestOp<OpType::Create>(), size(size) {} - return std::make_unique<IoOp>(OpType::READ, offset, length); +std::unique_ptr<CreateOp> CreateOp::generate(uint64_t size) { + return std::make_unique<CreateOp>(size); } -std::unique_ptr<IoOp> IoOp - ::generate_read2(uint64_t offset1, uint64_t length1, - uint64_t offset2, uint64_t length2) { +std::string CreateOp::to_string(uint64_t block_size) const { + return "Create (size=" + value_to_string(size * block_size) + ")"; +} - if (offset1 < offset2) { - ceph_assert( offset1 + length1 <= offset2 ); - } else { - ceph_assert( offset2 + length2 <= offset1 ); - } +RemoveOp::RemoveOp() : TestOp<OpType::Remove>() {} - return std::make_unique<IoOp>(OpType::READ2, - offset1, length1, - offset2, length2); +std::unique_ptr<RemoveOp> RemoveOp::generate() { + return std::make_unique<RemoveOp>(); } -std::unique_ptr<IoOp> IoOp - ::generate_read3(uint64_t offset1, uint64_t length1, - uint64_t offset2, uint64_t length2, - uint64_t offset3, uint64_t length3) { +std::string RemoveOp::to_string(uint64_t block_size) const { return "Remove"; } - if (offset1 < offset2) { - ceph_assert( offset1 + length1 <= offset2 ); - } else { - ceph_assert( offset2 + length2 <= offset1 ); +template <OpType opType, int numIOs> +ceph::io_exerciser::ReadWriteOp<opType, numIOs>::ReadWriteOp( + std::array<uint64_t, numIOs>&& offset, + std::array<uint64_t, numIOs>&& length) + : TestOp<opType>(), offset(offset), length(length) { + auto compare = [](uint64_t offset1, uint64_t length1, uint64_t offset2, + uint64_t length2) { + if (offset1 < offset2) { + ceph_assert(offset1 + length1 <= offset2); + } else { + ceph_assert(offset2 + length2 <= offset1); + } + }; + + if (numIOs > 1) { + for (int i = 0; i < numIOs - 1; i++) { + for (int j = i + 1; j < numIOs; j++) { + compare(offset[i], length[i], offset[j], length[j]); + } + } } - if (offset1 < offset3) { - ceph_assert( offset1 + length1 <= offset3 ); - } else { - ceph_assert( offset3 + length3 <= offset1 ); +} + +template <OpType opType, int numIOs> +std::string ceph::io_exerciser::ReadWriteOp<opType, numIOs>::to_string( + uint64_t block_size) const { + std::string offset_length_desc; + if (numIOs > 0) { + offset_length_desc += fmt::format( + "offset1={}", value_to_string(this->offset[0] * block_size)); + offset_length_desc += fmt::format( + ",length1={}", value_to_string(this->length[0] * block_size)); + for (int i = 1; i < numIOs; i++) { + offset_length_desc += fmt::format( + ",offset{}={}", i + 1, value_to_string(this->offset[i] * block_size)); + offset_length_desc += fmt::format( + ",length{}={}", i + 1, value_to_string(this->length[i] * block_size)); + } } - if (offset2 < offset3) { - ceph_assert( offset2 + length2 <= offset3 ); - } else { - ceph_assert( offset3 + length3 <= offset2 ); + switch (opType) { + case OpType::Read: + [[fallthrough]]; + case OpType::Read2: + [[fallthrough]]; + case OpType::Read3: + return fmt::format("Read{} ({})", numIOs, offset_length_desc); + case OpType::Write: + [[fallthrough]]; + case OpType::Write2: + [[fallthrough]]; + case OpType::Write3: + return fmt::format("Write{} ({})", numIOs, offset_length_desc); + case OpType::FailedWrite: + [[fallthrough]]; + case OpType::FailedWrite2: + [[fallthrough]]; + case OpType::FailedWrite3: + return fmt::format("FailedWrite{} ({})", numIOs, offset_length_desc); + default: + ceph_abort_msg( + fmt::format("Unsupported op type by ReadWriteOp ({})", opType)); } - return std::make_unique<IoOp>(OpType::READ3, - offset1, length1, - offset2, length2, - offset3, length3); } -std::unique_ptr<IoOp> IoOp::generate_write(uint64_t offset, uint64_t length) { - return std::make_unique<IoOp>(OpType::WRITE, offset, length); +SingleReadOp::SingleReadOp(uint64_t offset, uint64_t length) + : ReadWriteOp<OpType::Read, 1>({offset}, {length}) {} + +std::unique_ptr<SingleReadOp> SingleReadOp::generate(uint64_t offset, + uint64_t length) { + return std::make_unique<SingleReadOp>(offset, length); } -std::unique_ptr<IoOp> IoOp::generate_write2(uint64_t offset1, uint64_t length1, - uint64_t offset2, uint64_t length2) { - if (offset1 < offset2) { - ceph_assert( offset1 + length1 <= offset2 ); - } else { - ceph_assert( offset2 + length2 <= offset1 ); - } - return std::make_unique<IoOp>(OpType::WRITE2, - offset1, length1, - offset2, length2); +DoubleReadOp::DoubleReadOp(uint64_t offset1, uint64_t length1, uint64_t offset2, + uint64_t length2) + : ReadWriteOp<OpType::Read2, 2>({offset1, offset2}, {length1, length2}) {} + +std::unique_ptr<DoubleReadOp> DoubleReadOp::generate(uint64_t offset1, + uint64_t length1, + uint64_t offset2, + uint64_t length2) { + return std::make_unique<DoubleReadOp>(offset1, length1, offset2, length2); } -std::unique_ptr<IoOp> IoOp::generate_write3(uint64_t offset1, uint64_t length1, - uint64_t offset2, uint64_t length2, - uint64_t offset3, uint64_t length3) { - if (offset1 < offset2) { - ceph_assert( offset1 + length1 <= offset2 ); - } else { - ceph_assert( offset2 + length2 <= offset1 ); - } - if (offset1 < offset3) { - ceph_assert( offset1 + length1 <= offset3 ); - } else { - ceph_assert( offset3 + length3 <= offset1 ); - } - if (offset2 < offset3) { - ceph_assert( offset2 + length2 <= offset3 ); - } else { - ceph_assert( offset3 + length3 <= offset2 ); - } - return std::make_unique<IoOp>(OpType::WRITE3, - offset1, length1, - offset2, length2, - offset3, length3); -} - -bool IoOp::done() { - return (op == OpType::Done); -} - -std::string IoOp::to_string(uint64_t block_size) const -{ - switch (op) { - case OpType::Done: - return "Done"; - case OpType::BARRIER: - return "Barrier"; - case OpType::CREATE: - return "Create (size=" + value_to_string(length1 * block_size) + ")"; - case OpType::REMOVE: - return "Remove"; - case OpType::READ: - return "Read (offset=" + value_to_string(offset1 * block_size) + - ",length=" + value_to_string(length1 * block_size) + ")"; - case OpType::READ2: - return "Read2 (offset1=" + value_to_string(offset1 * block_size) + - ",length1=" + value_to_string(length1 * block_size) + - ",offset2=" + value_to_string(offset2 * block_size) + - ",length2=" + value_to_string(length2 * block_size) + ")"; - case OpType::READ3: - return "Read3 (offset1=" + value_to_string(offset1 * block_size) + - ",length1=" + value_to_string(length1 * block_size) + - ",offset2=" + value_to_string(offset2 * block_size) + - ",length2=" + value_to_string(length2 * block_size) + - ",offset3=" + value_to_string(offset3 * block_size) + - ",length3=" + value_to_string(length3 * block_size) + ")"; - case OpType::WRITE: - return "Write (offset=" + value_to_string(offset1 * block_size) + - ",length=" + value_to_string(length1 * block_size) + ")"; - case OpType::WRITE2: - return "Write2 (offset1=" + value_to_string(offset1 * block_size) + - ",length1=" + value_to_string(length1 * block_size) + - ",offset2=" + value_to_string(offset2 * block_size) + - ",length2=" + value_to_string(length2 * block_size) + ")"; - case OpType::WRITE3: - return "Write3 (offset1=" + value_to_string(offset1 * block_size) + - ",length1=" + value_to_string(length1 * block_size) + - ",offset2=" + value_to_string(offset2 * block_size) + - ",length2=" + value_to_string(length2 * block_size) + - ",offset3=" + value_to_string(offset3 * block_size) + - ",length3=" + value_to_string(length3 * block_size) + ")"; - default: - break; - } - return "Unknown"; +TripleReadOp::TripleReadOp(uint64_t offset1, uint64_t length1, uint64_t offset2, + uint64_t length2, uint64_t offset3, uint64_t length3) + : ReadWriteOp<OpType::Read3, 3>({offset1, offset2, offset3}, + {length1, length2, length3}) {} + +std::unique_ptr<TripleReadOp> TripleReadOp::generate( + uint64_t offset1, uint64_t length1, uint64_t offset2, uint64_t length2, + uint64_t offset3, uint64_t length3) { + return std::make_unique<TripleReadOp>(offset1, length1, offset2, length2, + offset3, length3); +} + +SingleWriteOp::SingleWriteOp(uint64_t offset, uint64_t length) + : ReadWriteOp<OpType::Write, 1>({offset}, {length}) {} + +std::unique_ptr<SingleWriteOp> SingleWriteOp::generate(uint64_t offset, + uint64_t length) { + return std::make_unique<SingleWriteOp>(offset, length); +} + +DoubleWriteOp::DoubleWriteOp(uint64_t offset1, uint64_t length1, + uint64_t offset2, uint64_t length2) + : ReadWriteOp<OpType::Write2, 2>({offset1, offset2}, {length1, length2}) {} + +std::unique_ptr<DoubleWriteOp> DoubleWriteOp::generate(uint64_t offset1, + uint64_t length1, + uint64_t offset2, + uint64_t length2) { + return std::make_unique<DoubleWriteOp>(offset1, length1, offset2, length2); +} + +TripleWriteOp::TripleWriteOp(uint64_t offset1, uint64_t length1, + uint64_t offset2, uint64_t length2, + uint64_t offset3, uint64_t length3) + : ReadWriteOp<OpType::Write3, 3>({offset1, offset2, offset3}, + {length1, length2, length3}) {} + +std::unique_ptr<TripleWriteOp> TripleWriteOp::generate( + uint64_t offset1, uint64_t length1, uint64_t offset2, uint64_t length2, + uint64_t offset3, uint64_t length3) { + return std::make_unique<TripleWriteOp>(offset1, length1, offset2, length2, + offset3, length3); +} + +SingleFailedWriteOp::SingleFailedWriteOp(uint64_t offset, uint64_t length) + : ReadWriteOp<OpType::FailedWrite, 1>({offset}, {length}) {} + +std::unique_ptr<SingleFailedWriteOp> SingleFailedWriteOp::generate( + uint64_t offset, uint64_t length) { + return std::make_unique<SingleFailedWriteOp>(offset, length); +} + +DoubleFailedWriteOp::DoubleFailedWriteOp(uint64_t offset1, uint64_t length1, + uint64_t offset2, uint64_t length2) + : ReadWriteOp<OpType::FailedWrite2, 2>({offset1, offset2}, + {length1, length2}) {} + +std::unique_ptr<DoubleFailedWriteOp> DoubleFailedWriteOp::generate( + uint64_t offset1, uint64_t length1, uint64_t offset2, uint64_t length2) { + return std::make_unique<DoubleFailedWriteOp>(offset1, length1, offset2, + length2); +} + +TripleFailedWriteOp::TripleFailedWriteOp(uint64_t offset1, uint64_t length1, + uint64_t offset2, uint64_t length2, + uint64_t offset3, uint64_t length3) + : ReadWriteOp<OpType::FailedWrite3, 3>({offset1, offset2, offset3}, + {length1, length2, length3}) {} + +std::unique_ptr<TripleFailedWriteOp> TripleFailedWriteOp::generate( + uint64_t offset1, uint64_t length1, uint64_t offset2, uint64_t length2, + uint64_t offset3, uint64_t length3) { + return std::make_unique<TripleFailedWriteOp>(offset1, length1, offset2, + length2, offset3, length3); +} + +template <ceph::io_exerciser::OpType opType> +ceph::io_exerciser::InjectErrorOp<opType>::InjectErrorOp( + int shard, const std::optional<uint64_t>& type, + const std::optional<uint64_t>& when, + const std::optional<uint64_t>& duration) + : TestOp<opType>(), + shard(shard), + type(type), + when(when), + duration(duration) {} + +template <ceph::io_exerciser::OpType opType> +std::string ceph::io_exerciser::InjectErrorOp<opType>::to_string( + uint64_t blocksize) const { + std::string_view inject_type = get_inject_type_string(); + return fmt::format( + "Inject {} error on shard {} of type {}" + " after {} successful inject(s) lasting {} inject(s)", + inject_type, shard, type.value_or(0), when.value_or(0), + duration.value_or(1)); +} + +ceph::io_exerciser::InjectReadErrorOp::InjectReadErrorOp( + int shard, const std::optional<uint64_t>& type, + const std::optional<uint64_t>& when, + const std::optional<uint64_t>& duration) + : InjectErrorOp<OpType::InjectReadError>(shard, type, when, duration) {} + +std::unique_ptr<ceph::io_exerciser::InjectReadErrorOp> +ceph::io_exerciser ::InjectReadErrorOp::generate( + int shard, const std::optional<uint64_t>& type, + const std::optional<uint64_t>& when, + const std::optional<uint64_t>& duration) { + return std::make_unique<InjectReadErrorOp>(shard, type, when, duration); +} + +ceph::io_exerciser::InjectWriteErrorOp::InjectWriteErrorOp( + int shard, const std::optional<uint64_t>& type, + const std::optional<uint64_t>& when, + const std::optional<uint64_t>& duration) + : InjectErrorOp<OpType::InjectWriteError>(shard, type, when, duration) {} + +std::unique_ptr<ceph::io_exerciser::InjectWriteErrorOp> +ceph::io_exerciser ::InjectWriteErrorOp::generate( + int shard, const std::optional<uint64_t>& type, + const std::optional<uint64_t>& when, + const std::optional<uint64_t>& duration) { + return std::make_unique<InjectWriteErrorOp>(shard, type, when, duration); +} + +template <ceph::io_exerciser::OpType opType> +ceph::io_exerciser::ClearErrorInjectOp<opType>::ClearErrorInjectOp( + int shard, const std::optional<uint64_t>& type) + : TestOp<opType>(), shard(shard), type(type) {} + +template <ceph::io_exerciser::OpType opType> +std::string ceph::io_exerciser::ClearErrorInjectOp<opType>::to_string( + uint64_t blocksize) const { + std::string_view inject_type = get_inject_type_string(); + return fmt::format("Clear {} injects on shard {} of type {}", inject_type, + shard, type.value_or(0)); +} + +ceph::io_exerciser::ClearReadErrorInjectOp::ClearReadErrorInjectOp( + int shard, const std::optional<uint64_t>& type) + : ClearErrorInjectOp<OpType::ClearReadErrorInject>(shard, type) {} + +std::unique_ptr<ceph::io_exerciser::ClearReadErrorInjectOp> +ceph::io_exerciser ::ClearReadErrorInjectOp::generate( + int shard, const std::optional<uint64_t>& type) { + return std::make_unique<ClearReadErrorInjectOp>(shard, type); +} + +ceph::io_exerciser::ClearWriteErrorInjectOp::ClearWriteErrorInjectOp( + int shard, const std::optional<uint64_t>& type) + : ClearErrorInjectOp<OpType::ClearWriteErrorInject>(shard, type) {} + +std::unique_ptr<ceph::io_exerciser::ClearWriteErrorInjectOp> +ceph::io_exerciser ::ClearWriteErrorInjectOp::generate( + int shard, const std::optional<uint64_t>& type) { + return std::make_unique<ClearWriteErrorInjectOp>(shard, type); }
\ No newline at end of file diff --git a/src/common/io_exerciser/IoOp.h b/src/common/io_exerciser/IoOp.h index 60c02a93d4e..1887eafcc1f 100644 --- a/src/common/io_exerciser/IoOp.h +++ b/src/common/io_exerciser/IoOp.h @@ -1,94 +1,248 @@ #pragma once -#include <string> +#include <array> #include <memory> -#include "include/ceph_assert.h" +#include <optional> +#include <string> + +#include "OpType.h" /* Overview * - * enum OpType - * Enumeration of different types of I/O operation - * * class IoOp * Stores details for an I/O operation. Generated by IoSequences * and applied by IoExerciser's */ namespace ceph { - namespace io_exerciser { - - enum class OpType { - Done, // End of I/O sequence - BARRIER, // Barrier - all prior I/Os must complete - CREATE, // Create object and pattern with data - REMOVE, // Remove object - READ, // Read - READ2, // 2 Reads in one op - READ3, // 3 Reads in one op - WRITE, // Write - WRITE2, // 2 Writes in one op - WRITE3 // 3 Writes in one op - }; - - class IoOp { - protected: - std::string value_to_string(uint64_t v) const; - - public: - OpType op; - uint64_t offset1; - uint64_t length1; - uint64_t offset2; - uint64_t length2; - uint64_t offset3; - uint64_t length3; - - IoOp( OpType op, - uint64_t offset1 = 0, uint64_t length1 = 0, - uint64_t offset2 = 0, uint64_t length2 = 0, - uint64_t offset3 = 0, uint64_t length3 = 0 ); - - static std::unique_ptr<IoOp> generate_done(); - - static std::unique_ptr<IoOp> generate_barrier(); - - static std::unique_ptr<IoOp> generate_create(uint64_t size); - - static std::unique_ptr<IoOp> generate_remove(); - - static std::unique_ptr<IoOp> generate_read(uint64_t offset, +namespace io_exerciser { + +class IoOp { + public: + IoOp(); + virtual ~IoOp() = default; + virtual std::string to_string(uint64_t block_size) const = 0; + virtual constexpr OpType getOpType() const = 0; +}; + +template <OpType opType> +class TestOp : public IoOp { + public: + TestOp(); + constexpr OpType getOpType() const override { return opType; } +}; + +class DoneOp : public TestOp<OpType::Done> { + public: + DoneOp(); + static std::unique_ptr<DoneOp> generate(); + std::string to_string(uint64_t block_size) const override; +}; + +class BarrierOp : public TestOp<OpType::Barrier> { + public: + BarrierOp(); + static std::unique_ptr<BarrierOp> generate(); + std::string to_string(uint64_t block_size) const override; +}; + +class CreateOp : public TestOp<OpType::Create> { + public: + CreateOp(uint64_t size); + static std::unique_ptr<CreateOp> generate(uint64_t size); + std::string to_string(uint64_t block_size) const override; + uint64_t size; +}; + +class RemoveOp : public TestOp<OpType::Remove> { + public: + RemoveOp(); + static std::unique_ptr<RemoveOp> generate(); + std::string to_string(uint64_t block_size) const override; +}; + +template <OpType opType, int numIOs> +class ReadWriteOp : public TestOp<opType> { + public: + std::array<uint64_t, numIOs> offset; + std::array<uint64_t, numIOs> length; + + protected: + ReadWriteOp(std::array<uint64_t, numIOs>&& offset, + std::array<uint64_t, numIOs>&& length); + std::string to_string(uint64_t block_size) const override; +}; + +class SingleReadOp : public ReadWriteOp<OpType::Read, 1> { + public: + SingleReadOp(uint64_t offset, uint64_t length); + static std::unique_ptr<SingleReadOp> generate(uint64_t offset, + uint64_t length); +}; + +class DoubleReadOp : public ReadWriteOp<OpType::Read2, 2> { + public: + DoubleReadOp(uint64_t offset1, uint64_t length1, uint64_t offset2, + uint64_t length2); + static std::unique_ptr<DoubleReadOp> generate(uint64_t offset1, + uint64_t length1, + uint64_t offset2, + uint64_t length2); +}; + +class TripleReadOp : public ReadWriteOp<OpType::Read3, 3> { + public: + TripleReadOp(uint64_t offset1, uint64_t length1, uint64_t offset2, + uint64_t length2, uint64_t offset3, uint64_t length3); + static std::unique_ptr<TripleReadOp> generate( + uint64_t offset1, uint64_t length1, uint64_t offset2, uint64_t length2, + uint64_t offset3, uint64_t length3); +}; + +class SingleWriteOp : public ReadWriteOp<OpType::Write, 1> { + public: + SingleWriteOp(uint64_t offset, uint64_t length); + static std::unique_ptr<SingleWriteOp> generate(uint64_t offset, uint64_t length); +}; + +class DoubleWriteOp : public ReadWriteOp<OpType::Write2, 2> { + public: + DoubleWriteOp(uint64_t offset1, uint64_t length1, uint64_t offset2, + uint64_t length2); + static std::unique_ptr<DoubleWriteOp> generate(uint64_t offset1, + uint64_t length1, + uint64_t offset2, + uint64_t length2); +}; + +class TripleWriteOp : public ReadWriteOp<OpType::Write3, 3> { + public: + TripleWriteOp(uint64_t offset1, uint64_t length1, uint64_t offset2, + uint64_t length2, uint64_t offset3, uint64_t length3); + static std::unique_ptr<TripleWriteOp> generate( + uint64_t offset1, uint64_t length1, uint64_t offset2, uint64_t length2, + uint64_t offset3, uint64_t length3); +}; + +class SingleFailedWriteOp : public ReadWriteOp<OpType::FailedWrite, 1> { + public: + SingleFailedWriteOp(uint64_t offset, uint64_t length); + static std::unique_ptr<SingleFailedWriteOp> generate(uint64_t offset, + uint64_t length); +}; + +class DoubleFailedWriteOp : public ReadWriteOp<OpType::FailedWrite2, 2> { + public: + DoubleFailedWriteOp(uint64_t offset1, uint64_t length1, uint64_t offset2, + uint64_t length2); + static std::unique_ptr<DoubleFailedWriteOp> generate(uint64_t offset1, + uint64_t length1, + uint64_t offset2, + uint64_t length2); +}; + +class TripleFailedWriteOp : public ReadWriteOp<OpType::FailedWrite3, 3> { + public: + TripleFailedWriteOp(uint64_t offset1, uint64_t length1, uint64_t offset2, + uint64_t length2, uint64_t offset3, uint64_t length3); + static std::unique_ptr<TripleFailedWriteOp> generate( + uint64_t offset1, uint64_t length1, uint64_t offset2, uint64_t length2, + uint64_t offset3, uint64_t length3); +}; + +template <ceph::io_exerciser::OpType opType> +class InjectErrorOp : public TestOp<opType> { + public: + InjectErrorOp(int shard, const std::optional<uint64_t>& type, + const std::optional<uint64_t>& when, + const std::optional<uint64_t>& duration); + + std::string to_string(uint64_t block_size) const override; + + int shard; + std::optional<uint64_t> type; + std::optional<uint64_t> when; + std::optional<uint64_t> duration; + + protected: + virtual inline constexpr std::string_view get_inject_type_string() const = 0; +}; + +class InjectReadErrorOp : public InjectErrorOp<OpType::InjectReadError> { + public: + InjectReadErrorOp(int shard, const std::optional<uint64_t>& type, + const std::optional<uint64_t>& when, + const std::optional<uint64_t>& duration); + + static std::unique_ptr<InjectReadErrorOp> generate( + int shard, const std::optional<uint64_t>& type, + const std::optional<uint64_t>& when, + const std::optional<uint64_t>& duration); + + protected: + inline constexpr std::string_view get_inject_type_string() const override { + return "read"; + } +}; + +class InjectWriteErrorOp : public InjectErrorOp<OpType::InjectWriteError> { + public: + InjectWriteErrorOp(int shard, const std::optional<uint64_t>& type, + const std::optional<uint64_t>& when, + const std::optional<uint64_t>& duration); + + static std::unique_ptr<InjectWriteErrorOp> generate( + int shard, const std::optional<uint64_t>& type, + const std::optional<uint64_t>& when, + const std::optional<uint64_t>& duration); + + protected: + inline constexpr std::string_view get_inject_type_string() const override { + return "write"; + } +}; + +template <ceph::io_exerciser::OpType opType> +class ClearErrorInjectOp : public TestOp<opType> { + public: + ClearErrorInjectOp(int shard, const std::optional<uint64_t>& type); + + std::string to_string(uint64_t block_size) const override; + + int shard; + std::optional<uint64_t> type; + + protected: + virtual inline constexpr std::string_view get_inject_type_string() const = 0; +}; + +class ClearReadErrorInjectOp + : public ClearErrorInjectOp<OpType::ClearReadErrorInject> { + public: + ClearReadErrorInjectOp(int shard, const std::optional<uint64_t>& type); + + static std::unique_ptr<ClearReadErrorInjectOp> generate( + int shard, const std::optional<uint64_t>& type); + + protected: + inline constexpr std::string_view get_inject_type_string() const override { + return "read"; + } +}; + +class ClearWriteErrorInjectOp + : public ClearErrorInjectOp<OpType::ClearWriteErrorInject> { + public: + ClearWriteErrorInjectOp(int shard, const std::optional<uint64_t>& type); + + static std::unique_ptr<ClearWriteErrorInjectOp> generate( + int shard, const std::optional<uint64_t>& type); - static std::unique_ptr<IoOp> generate_read2(uint64_t offset1, - uint64_t length1, - uint64_t offset2, - uint64_t length2); - - static std::unique_ptr<IoOp> generate_read3(uint64_t offset1, - uint64_t length1, - uint64_t offset2, - uint64_t length2, - uint64_t offset3, - uint64_t length3); - - static std::unique_ptr<IoOp> generate_write(uint64_t offset, - uint64_t length); - - static std::unique_ptr<IoOp> generate_write2(uint64_t offset1, - uint64_t length1, - uint64_t offset2, - uint64_t length2); - - static std::unique_ptr<IoOp> generate_write3(uint64_t offset1, - uint64_t length1, - uint64_t offset2, - uint64_t length2, - uint64_t offset3, - uint64_t length3); - - bool done(); - - std::string to_string(uint64_t block_size) const; - }; + protected: + inline constexpr std::string_view get_inject_type_string() const override { + return "write"; } -}
\ No newline at end of file +}; +} // namespace io_exerciser +} // namespace ceph
\ No newline at end of file diff --git a/src/common/io_exerciser/IoSequence.cc b/src/common/io_exerciser/IoSequence.cc index 4a7ca0593d1..83f1cc595a5 100644 --- a/src/common/io_exerciser/IoSequence.cc +++ b/src/common/io_exerciser/IoSequence.cc @@ -1,12 +1,12 @@ #include "IoSequence.h" +using IoOp = ceph::io_exerciser::IoOp; using Sequence = ceph::io_exerciser::Sequence; using IoSequence = ceph::io_exerciser::IoSequence; -std::ostream& ceph::io_exerciser::operator<<(std::ostream& os, const Sequence& seq) -{ - switch (seq) - { +std::ostream& ceph::io_exerciser::operator<<(std::ostream& os, + const Sequence& seq) { + switch (seq) { case Sequence::SEQUENCE_SEQ0: os << "SEQUENCE_SEQ0"; break; @@ -37,6 +37,9 @@ std::ostream& ceph::io_exerciser::operator<<(std::ostream& os, const Sequence& s case Sequence::SEQUENCE_SEQ9: os << "SEQUENCE_SEQ9"; break; + case Sequence::SEQUENCE_SEQ10: + os << "SEQUENCE_SEQ10"; + break; case Sequence::SEQUENCE_END: os << "SEQUENCE_END"; break; @@ -44,19 +47,12 @@ std::ostream& ceph::io_exerciser::operator<<(std::ostream& os, const Sequence& s return os; } -IoSequence::IoSequence(std::pair<int,int> obj_size_range, - int seed) : - min_obj_size(obj_size_range.first), max_obj_size(obj_size_range.second), - create(true), barrier(false), done(false), remove(false), - obj_size(min_obj_size), step(-1), seed(seed) -{ - rng.seed(seed); +bool IoSequence::is_supported(Sequence sequence) const { + return sequence != Sequence::SEQUENCE_SEQ10; } -std::unique_ptr<IoSequence> IoSequence::generate_sequence(Sequence s, - std::pair<int,int> obj_size_range, - int seed) -{ +std::unique_ptr<IoSequence> IoSequence::generate_sequence( + Sequence s, std::pair<int, int> obj_size_range, int seed) { switch (s) { case Sequence::SEQUENCE_SEQ0: return std::make_unique<Seq0>(obj_size_range, seed); @@ -78,24 +74,39 @@ std::unique_ptr<IoSequence> IoSequence::generate_sequence(Sequence s, return std::make_unique<Seq8>(obj_size_range, seed); case Sequence::SEQUENCE_SEQ9: return std::make_unique<Seq9>(obj_size_range, seed); + case Sequence::SEQUENCE_SEQ10: + ceph_abort_msg( + "Sequence 10 only supported for erasure coded pools " + "through the EcIoSequence interface"); + return nullptr; default: break; } return nullptr; } -int IoSequence::get_step() const -{ - return step; +IoSequence::IoSequence(std::pair<int, int> obj_size_range, int seed) + : min_obj_size(obj_size_range.first), + max_obj_size(obj_size_range.second), + create(true), + barrier(false), + done(false), + remove(false), + obj_size(min_obj_size), + step(-1), + seed(seed) { + rng.seed(seed); } -int IoSequence::get_seed() const -{ - return seed; +std::string ceph::io_exerciser::IoSequence::get_name_with_seqseed() const { + return get_name() + " (seqseed " + std::to_string(get_seed()) + ")"; } -void IoSequence::set_min_object_size(uint64_t size) -{ +int IoSequence::get_step() const { return step; } + +int IoSequence::get_seed() const { return seed; } + +void IoSequence::set_min_object_size(uint64_t size) { min_obj_size = size; if (obj_size < size) { obj_size = size; @@ -105,23 +116,20 @@ void IoSequence::set_min_object_size(uint64_t size) } } -void IoSequence::set_max_object_size(uint64_t size) -{ +void IoSequence::set_max_object_size(uint64_t size) { max_obj_size = size; if (obj_size > size) { done = true; } } -void IoSequence::select_random_object_size() -{ +void IoSequence::select_random_object_size() { if (max_obj_size != min_obj_size) { obj_size = min_obj_size + rng(max_obj_size - min_obj_size); } } -std::unique_ptr<ceph::io_exerciser::IoOp> IoSequence::increment_object_size() -{ +std::unique_ptr<IoOp> IoSequence::increment_object_size() { obj_size++; if (obj_size > max_obj_size) { done = true; @@ -129,106 +137,118 @@ std::unique_ptr<ceph::io_exerciser::IoOp> IoSequence::increment_object_size() create = true; barrier = true; remove = true; - return IoOp::generate_barrier(); + return BarrierOp::generate(); } -std::unique_ptr<ceph::io_exerciser::IoOp> IoSequence::next() -{ +Sequence IoSequence::getNextSupportedSequenceId() const { + Sequence sequence = get_id(); + ++sequence; + for (; sequence < Sequence::SEQUENCE_END; ++sequence) { + if (is_supported(sequence)) { + return sequence; + } + } + + return Sequence::SEQUENCE_END; +} + +std::unique_ptr<IoOp> IoSequence::next() { step++; if (remove) { remove = false; - return IoOp::generate_remove(); + return RemoveOp::generate(); } if (barrier) { barrier = false; - return IoOp::generate_barrier(); + return BarrierOp::generate(); } if (done) { - return IoOp::generate_done(); + return DoneOp::generate(); } if (create) { create = false; barrier = true; - return IoOp::generate_create(obj_size); + return CreateOp::generate(obj_size); } return _next(); } - - -ceph::io_exerciser::Seq0::Seq0(std::pair<int,int> obj_size_range, int seed) : - IoSequence(obj_size_range, seed), offset(0) -{ +ceph::io_exerciser::Seq0::Seq0(std::pair<int, int> obj_size_range, int seed) + : IoSequence(obj_size_range, seed), offset(0) { select_random_object_size(); length = 1 + rng(obj_size - 1); } -std::string ceph::io_exerciser::Seq0::get_name() const -{ +Sequence ceph::io_exerciser::Seq0::get_id() const { + return Sequence::SEQUENCE_SEQ0; +} + +std::string ceph::io_exerciser::Seq0::get_name() const { return "Sequential reads of length " + std::to_string(length) + - " with queue depth 1 (seqseed " + std::to_string(get_seed()) + ")"; + " with queue depth 1"; } -std::unique_ptr<ceph::io_exerciser::IoOp> ceph::io_exerciser::Seq0::_next() -{ +std::unique_ptr<ceph::io_exerciser::IoOp> ceph::io_exerciser::Seq0::_next() { std::unique_ptr<IoOp> r; if (offset >= obj_size) { done = true; barrier = true; remove = true; - return IoOp::generate_barrier(); + return BarrierOp::generate(); } if (offset + length > obj_size) { - r = IoOp::generate_read(offset, obj_size - offset); + r = SingleReadOp::generate(offset, obj_size - offset); } else { - r = IoOp::generate_read(offset, length); + r = SingleReadOp::generate(offset, length); } offset += length; return r; } - - -ceph::io_exerciser::Seq1::Seq1(std::pair<int,int> obj_size_range, int seed) : - IoSequence(obj_size_range, seed) -{ +ceph::io_exerciser::Seq1::Seq1(std::pair<int, int> obj_size_range, int seed) + : IoSequence(obj_size_range, seed) { select_random_object_size(); count = 3 * obj_size; } -std::string ceph::io_exerciser::Seq1::get_name() const -{ - return "Random offset, random length read/write I/O with queue depth 1 (seqseed " - + std::to_string(get_seed()) + ")"; +Sequence ceph::io_exerciser::Seq1::get_id() const { + return Sequence::SEQUENCE_SEQ1; } -std::unique_ptr<ceph::io_exerciser::IoOp> ceph::io_exerciser::Seq1::_next() -{ +std::string ceph::io_exerciser::Seq1::get_name() const { + return "Random offset, random length read/write I/O with queue depth 1"; +} + +std::unique_ptr<ceph::io_exerciser::IoOp> ceph::io_exerciser::Seq1::_next() { barrier = true; if (count-- == 0) { done = true; remove = true; - return IoOp::generate_barrier(); + return BarrierOp::generate(); } uint64_t offset = rng(obj_size - 1); uint64_t length = 1 + rng(obj_size - 1 - offset); - return (rng(2) != 0) ? IoOp::generate_write(offset, length) : - IoOp::generate_read(offset, length); -} + if (rng(2) != 0) { + return SingleWriteOp::generate(offset, length); + } else { + return SingleReadOp::generate(offset, length); + } +} +ceph::io_exerciser::Seq2::Seq2(std::pair<int, int> obj_size_range, int seed) + : IoSequence(obj_size_range, seed), offset(0), length(0) {} -ceph::io_exerciser::Seq2::Seq2(std::pair<int,int> obj_size_range, int seed) : - IoSequence(obj_size_range, seed), offset(0), length(0) {} +Sequence ceph::io_exerciser::Seq2::get_id() const { + return Sequence::SEQUENCE_SEQ2; +} -std::string ceph::io_exerciser::Seq2::get_name() const -{ +std::string ceph::io_exerciser::Seq2::get_name() const { return "Permutations of offset and length read I/O"; } -std::unique_ptr<ceph::io_exerciser::IoOp> ceph::io_exerciser::Seq2::_next() -{ +std::unique_ptr<ceph::io_exerciser::IoOp> ceph::io_exerciser::Seq2::_next() { length++; if (length > obj_size - offset) { length = 1; @@ -239,24 +259,23 @@ std::unique_ptr<ceph::io_exerciser::IoOp> ceph::io_exerciser::Seq2::_next() return increment_object_size(); } } - return IoOp::generate_read(offset, length); + return SingleReadOp::generate(offset, length); } - - -ceph::io_exerciser::Seq3::Seq3(std::pair<int,int> obj_size_range, int seed) : - IoSequence(obj_size_range, seed), offset1(0), offset2(0) -{ +ceph::io_exerciser::Seq3::Seq3(std::pair<int, int> obj_size_range, int seed) + : IoSequence(obj_size_range, seed), offset1(0), offset2(0) { set_min_object_size(2); } -std::string ceph::io_exerciser::Seq3::get_name() const -{ +Sequence ceph::io_exerciser::Seq3::get_id() const { + return Sequence::SEQUENCE_SEQ3; +} + +std::string ceph::io_exerciser::Seq3::get_name() const { return "Permutations of offset 2-region 1-block read I/O"; } -std::unique_ptr<ceph::io_exerciser::IoOp> ceph::io_exerciser::Seq3::_next() -{ +std::unique_ptr<ceph::io_exerciser::IoOp> ceph::io_exerciser::Seq3::_next() { offset2++; if (offset2 >= obj_size - offset1) { offset2 = 1; @@ -267,24 +286,23 @@ std::unique_ptr<ceph::io_exerciser::IoOp> ceph::io_exerciser::Seq3::_next() return increment_object_size(); } } - return IoOp::generate_read2(offset1, 1, offset1 + offset2, 1); + return DoubleReadOp::generate(offset1, 1, offset1 + offset2, 1); } - - -ceph::io_exerciser::Seq4::Seq4(std::pair<int,int> obj_size_range, int seed) : - IoSequence(obj_size_range, seed), offset1(0), offset2(1) -{ +ceph::io_exerciser::Seq4::Seq4(std::pair<int, int> obj_size_range, int seed) + : IoSequence(obj_size_range, seed), offset1(0), offset2(1) { set_min_object_size(3); } -std::string ceph::io_exerciser::Seq4::get_name() const -{ +Sequence ceph::io_exerciser::Seq4::get_id() const { + return Sequence::SEQUENCE_SEQ4; +} + +std::string ceph::io_exerciser::Seq4::get_name() const { return "Permutations of offset 3-region 1-block read I/O"; } -std::unique_ptr<ceph::io_exerciser::IoOp> ceph::io_exerciser::Seq4::_next() -{ +std::unique_ptr<ceph::io_exerciser::IoOp> ceph::io_exerciser::Seq4::_next() { offset2++; if (offset2 >= obj_size - offset1) { offset2 = 2; @@ -295,33 +313,35 @@ std::unique_ptr<ceph::io_exerciser::IoOp> ceph::io_exerciser::Seq4::_next() return increment_object_size(); } } - return IoOp::generate_read3(offset1, 1, - offset1 + offset2, 1, - (offset1 * 2 + offset2)/2, 1); + return TripleReadOp::generate(offset1, 1, (offset1 + offset2), 1, + (offset1 * 2 + offset2) / 2, 1); } +ceph::io_exerciser::Seq5::Seq5(std::pair<int, int> obj_size_range, int seed) + : IoSequence(obj_size_range, seed), + offset(0), + length(1), + doneread(false), + donebarrier(false) {} +Sequence ceph::io_exerciser::Seq5::get_id() const { + return Sequence::SEQUENCE_SEQ5; +} -ceph::io_exerciser::Seq5::Seq5(std::pair<int,int> obj_size_range, int seed) : - IoSequence(obj_size_range, seed), offset(0), length(1), - doneread(false), donebarrier(false) {} - -std::string ceph::io_exerciser::Seq5::get_name() const -{ +std::string ceph::io_exerciser::Seq5::get_name() const { return "Permutation of length sequential writes"; } -std::unique_ptr<ceph::io_exerciser::IoOp> ceph::io_exerciser::Seq5::_next() -{ +std::unique_ptr<ceph::io_exerciser::IoOp> ceph::io_exerciser::Seq5::_next() { if (offset >= obj_size) { if (!doneread) { if (!donebarrier) { donebarrier = true; - return IoOp::generate_barrier(); + return BarrierOp::generate(); } doneread = true; barrier = true; - return IoOp::generate_read(0, obj_size); + return SingleReadOp::generate(0, obj_size); } doneread = false; donebarrier = false; @@ -333,33 +353,36 @@ std::unique_ptr<ceph::io_exerciser::IoOp> ceph::io_exerciser::Seq5::_next() } } uint64_t io_len = (offset + length > obj_size) ? (obj_size - offset) : length; - std::unique_ptr<IoOp> r = IoOp::generate_write(offset, io_len); + std::unique_ptr<IoOp> r = SingleWriteOp::generate(offset, io_len); offset += io_len; return r; } +ceph::io_exerciser::Seq6::Seq6(std::pair<int, int> obj_size_range, int seed) + : IoSequence(obj_size_range, seed), + offset(0), + length(1), + doneread(false), + donebarrier(false) {} +Sequence ceph::io_exerciser::Seq6::get_id() const { + return Sequence::SEQUENCE_SEQ6; +} -ceph::io_exerciser::Seq6::Seq6(std::pair<int,int> obj_size_range, int seed) : - IoSequence(obj_size_range, seed), offset(0), length(1), - doneread(false), donebarrier(false) {} - -std::string ceph::io_exerciser::Seq6::get_name() const -{ +std::string ceph::io_exerciser::Seq6::get_name() const { return "Permutation of length sequential writes, different alignment"; } -std::unique_ptr<ceph::io_exerciser::IoOp> ceph::io_exerciser::Seq6::_next() -{ +std::unique_ptr<ceph::io_exerciser::IoOp> ceph::io_exerciser::Seq6::_next() { if (offset >= obj_size) { if (!doneread) { if (!donebarrier) { donebarrier = true; - return IoOp::generate_barrier(); + return BarrierOp::generate(); } doneread = true; barrier = true; - return IoOp::generate_read(0, obj_size); + return SingleReadOp::generate(0, obj_size); } doneread = false; donebarrier = false; @@ -374,74 +397,72 @@ std::unique_ptr<ceph::io_exerciser::IoOp> ceph::io_exerciser::Seq6::_next() if (io_len == 0) { io_len = length; } - std::unique_ptr<IoOp> r = IoOp::generate_write(offset, io_len); + std::unique_ptr<IoOp> r = SingleWriteOp::generate(offset, io_len); offset += io_len; return r; } - - -ceph::io_exerciser::Seq7::Seq7(std::pair<int,int> obj_size_range, int seed) : - IoSequence(obj_size_range, seed) -{ +ceph::io_exerciser::Seq7::Seq7(std::pair<int, int> obj_size_range, int seed) + : IoSequence(obj_size_range, seed) { set_min_object_size(2); offset = obj_size; } -std::string ceph::io_exerciser::Seq7::get_name() const -{ +Sequence ceph::io_exerciser::Seq7::get_id() const { + return Sequence::SEQUENCE_SEQ7; +} + +std::string ceph::io_exerciser::Seq7::get_name() const { return "Permutations of offset 2-region 1-block writes"; } -std::unique_ptr<ceph::io_exerciser::IoOp> ceph::io_exerciser::Seq7::_next() -{ +std::unique_ptr<ceph::io_exerciser::IoOp> ceph::io_exerciser::Seq7::_next() { if (!doneread) { if (!donebarrier) { donebarrier = true; - return IoOp::generate_barrier(); + return BarrierOp::generate(); } doneread = true; barrier = true; - return IoOp::generate_read(0, obj_size); + return SingleReadOp::generate(0, obj_size); } if (offset == 0) { doneread = false; donebarrier = false; - offset = obj_size+1; + offset = obj_size + 1; return increment_object_size(); } offset--; - if (offset == obj_size/2) { + if (offset == obj_size / 2) { return _next(); } doneread = false; donebarrier = false; - return IoOp::generate_write2(offset, 1, obj_size/2, 1); + return DoubleReadOp::generate(offset, 1, obj_size / 2, 1); } - - -ceph::io_exerciser::Seq8::Seq8(std::pair<int,int> obj_size_range, int seed) : - IoSequence(obj_size_range, seed), offset1(0), offset2(1) -{ +ceph::io_exerciser::Seq8::Seq8(std::pair<int, int> obj_size_range, int seed) + : IoSequence(obj_size_range, seed), offset1(0), offset2(1) { set_min_object_size(3); } -std::string ceph::io_exerciser::Seq8::get_name() const -{ +Sequence ceph::io_exerciser::Seq8::get_id() const { + return Sequence::SEQUENCE_SEQ8; +} + +std::string ceph::io_exerciser::Seq8::get_name() const { return "Permutations of offset 3-region 1-block write I/O"; } -std::unique_ptr<ceph::io_exerciser::IoOp> ceph::io_exerciser::Seq8::_next() -{ +std::unique_ptr<ceph::io_exerciser::IoOp> ceph::io_exerciser::Seq8::_next() { if (!doneread) { if (!donebarrier) { donebarrier = true; - return IoOp::generate_barrier(); + return BarrierOp::generate(); } doneread = true; barrier = true; - return IoOp::generate_read(0, obj_size); + return SingleReadOp::generate(0, obj_size); } offset2++; if (offset2 >= obj_size - offset1) { @@ -455,34 +476,30 @@ std::unique_ptr<ceph::io_exerciser::IoOp> ceph::io_exerciser::Seq8::_next() } doneread = false; donebarrier = false; - return IoOp::generate_write3(offset1, 1, - offset1 + offset2, 1, - (offset1 * 2 + offset2)/2, 1); + return TripleWriteOp::generate(offset1, 1, offset1 + offset2, 1, + (offset1 * 2 + offset2) / 2, 1); } +ceph::io_exerciser::Seq9::Seq9(std::pair<int, int> obj_size_range, int seed) + : IoSequence(obj_size_range, seed), offset(0), length(0) {} - -ceph::io_exerciser::Seq9::Seq9(std::pair<int,int> obj_size_range, int seed) : - IoSequence(obj_size_range, seed), offset(0), length(0) -{ - +Sequence ceph::io_exerciser::Seq9::get_id() const { + return Sequence::SEQUENCE_SEQ9; } -std::string ceph::io_exerciser::Seq9::get_name() const -{ +std::string ceph::io_exerciser::Seq9::get_name() const { return "Permutations of offset and length write I/O"; } -std::unique_ptr<ceph::io_exerciser::IoOp> ceph::io_exerciser::Seq9::_next() -{ +std::unique_ptr<ceph::io_exerciser::IoOp> ceph::io_exerciser::Seq9::_next() { if (!doneread) { if (!donebarrier) { donebarrier = true; - return IoOp::generate_barrier(); + return BarrierOp::generate(); } doneread = true; barrier = true; - return IoOp::generate_read(0, obj_size); + return SingleReadOp::generate(0, obj_size); } length++; if (length > obj_size - offset) { @@ -496,5 +513,5 @@ std::unique_ptr<ceph::io_exerciser::IoOp> ceph::io_exerciser::Seq9::_next() } doneread = false; donebarrier = false; - return IoOp::generate_write(offset, length); + return SingleWriteOp::generate(offset, length); }
\ No newline at end of file diff --git a/src/common/io_exerciser/IoSequence.h b/src/common/io_exerciser/IoSequence.h index 114ff76303f..b6c254cf096 100644 --- a/src/common/io_exerciser/IoSequence.h +++ b/src/common/io_exerciser/IoSequence.h @@ -3,7 +3,6 @@ #pragma once #include "IoOp.h" - #include "include/random.h" /* Overview @@ -29,195 +28,209 @@ */ namespace ceph { - namespace io_exerciser { - - enum class Sequence { - SEQUENCE_SEQ0, - SEQUENCE_SEQ1, - SEQUENCE_SEQ2, - SEQUENCE_SEQ3, - SEQUENCE_SEQ4, - SEQUENCE_SEQ5, - SEQUENCE_SEQ6, - SEQUENCE_SEQ7, - SEQUENCE_SEQ8, - SEQUENCE_SEQ9, - // - SEQUENCE_END, - SEQUENCE_BEGIN = SEQUENCE_SEQ0 - }; - - inline Sequence operator++( Sequence& s ) - { - return s = (Sequence)(((int)(s) + 1)); - } - - std::ostream& operator<<(std::ostream& os, const Sequence& seq); - - /* I/O Sequences */ - - class IoSequence { - public: - virtual ~IoSequence() = default; - - virtual std::string get_name() const = 0; - int get_step() const; - int get_seed() const; - - std::unique_ptr<IoOp> next(); - - static std::unique_ptr<IoSequence> - generate_sequence(Sequence s, std::pair<int,int> obj_size_range, int seed ); - - protected: - uint64_t min_obj_size; - uint64_t max_obj_size; - bool create; - bool barrier; - bool done; - bool remove; - uint64_t obj_size; - int step; - int seed; - ceph::util::random_number_generator<int> rng = - ceph::util::random_number_generator<int>(); - - IoSequence(std::pair<int,int> obj_size_range, int seed); - - virtual std::unique_ptr<IoOp> _next() = 0; - - void set_min_object_size(uint64_t size); - void set_max_object_size(uint64_t size); - void select_random_object_size(); - std::unique_ptr<IoOp> increment_object_size(); - - }; - - class Seq0: public IoSequence { - public: - Seq0(std::pair<int,int> obj_size_range, int seed); - - std::string get_name() const override; - std::unique_ptr<IoOp> _next() override; - - private: - uint64_t offset; - uint64_t length; - }; - - class Seq1: public IoSequence { - public: - Seq1(std::pair<int,int> obj_size_range, int seed); - - std::string get_name() const override; - std::unique_ptr<IoOp> _next(); - - private: - int count; - }; - - class Seq2: public IoSequence { - public: - Seq2(std::pair<int,int> obj_size_range, int seed); - - std::string get_name() const override; - std::unique_ptr<IoOp> _next() override; - - private: - uint64_t offset; - uint64_t length; - }; - - class Seq3: public IoSequence { - public: - Seq3(std::pair<int,int> obj_size_range, int seed); - - std::string get_name() const override; - std::unique_ptr<IoOp> _next() override; - private: - uint64_t offset1; - uint64_t offset2; - }; - - class Seq4: public IoSequence { - public: - Seq4(std::pair<int,int> obj_size_range, int seed); - - std::string get_name() const override; - std::unique_ptr<IoOp> _next() override; - - private: - uint64_t offset1; - uint64_t offset2; - }; - - class Seq5: public IoSequence { - public: - Seq5(std::pair<int,int> obj_size_range, int seed); - - std::string get_name() const override; - std::unique_ptr<IoOp> _next() override; - - private: - uint64_t offset; - uint64_t length; - bool doneread; - bool donebarrier; - }; - - class Seq6: public IoSequence { - public: - Seq6(std::pair<int,int> obj_size_range, int seed); - - std::string get_name() const override; - std::unique_ptr<IoOp> _next() override; - - private: - uint64_t offset; - uint64_t length; - bool doneread; - bool donebarrier; - }; - - class Seq7: public IoSequence { - public: - Seq7(std::pair<int,int> obj_size_range, int seed); - - std::string get_name() const override; - std::unique_ptr<IoOp> _next() override; - - private: - uint64_t offset; - bool doneread = true; - bool donebarrier = false; - }; - - class Seq8: public IoSequence { - public: - Seq8(std::pair<int,int> obj_size_range, int seed); - - std::string get_name() const override; - std::unique_ptr<IoOp> _next() override; - private: - uint64_t offset1; - uint64_t offset2; - bool doneread = true; - bool donebarrier = false; - }; - - class Seq9: public IoSequence { - private: - uint64_t offset; - uint64_t length; - bool doneread = true; - bool donebarrier = false; - - public: - Seq9(std::pair<int,int> obj_size_range, int seed); - - std::string get_name() const override; - - std::unique_ptr<IoOp> _next() override; - }; - } -}
\ No newline at end of file +namespace io_exerciser { + +enum class Sequence { + SEQUENCE_SEQ0, + SEQUENCE_SEQ1, + SEQUENCE_SEQ2, + SEQUENCE_SEQ3, + SEQUENCE_SEQ4, + SEQUENCE_SEQ5, + SEQUENCE_SEQ6, + SEQUENCE_SEQ7, + SEQUENCE_SEQ8, + SEQUENCE_SEQ9, + SEQUENCE_SEQ10, + + SEQUENCE_END, + SEQUENCE_BEGIN = SEQUENCE_SEQ0 +}; + +inline Sequence operator++(Sequence& s) { + return s = (Sequence)(((int)(s) + 1)); +} + +std::ostream& operator<<(std::ostream& os, const Sequence& seq); + +/* I/O Sequences */ + +class IoSequence { + public: + virtual ~IoSequence() = default; + + virtual Sequence get_id() const = 0; + virtual std::string get_name_with_seqseed() const; + virtual std::string get_name() const = 0; + int get_step() const; + int get_seed() const; + + virtual Sequence getNextSupportedSequenceId() const; + virtual std::unique_ptr<IoOp> next(); + + virtual bool is_supported(Sequence sequence) const; + static std::unique_ptr<IoSequence> generate_sequence( + Sequence s, std::pair<int, int> obj_size_range, int seed); + + protected: + uint64_t min_obj_size; + uint64_t max_obj_size; + bool create; + bool barrier; + bool done; + bool remove; + uint64_t obj_size; + int step; + int seed; + ceph::util::random_number_generator<int> rng = + ceph::util::random_number_generator<int>(); + + IoSequence(std::pair<int, int> obj_size_range, int seed); + + virtual std::unique_ptr<IoOp> _next() = 0; + + void set_min_object_size(uint64_t size); + void set_max_object_size(uint64_t size); + void select_random_object_size(); + std::unique_ptr<IoOp> increment_object_size(); +}; + +class Seq0 : public IoSequence { + public: + Seq0(std::pair<int, int> obj_size_range, int seed); + + Sequence get_id() const override; + std::string get_name() const override; + std::unique_ptr<IoOp> _next() override; + + private: + uint64_t offset; + uint64_t length; +}; + +class Seq1 : public IoSequence { + public: + Seq1(std::pair<int, int> obj_size_range, int seed); + + Sequence get_id() const override; + std::string get_name() const override; + std::unique_ptr<IoOp> _next() override; + + private: + int count; +}; + +class Seq2 : public IoSequence { + public: + Seq2(std::pair<int, int> obj_size_range, int seed); + + Sequence get_id() const override; + std::string get_name() const override; + std::unique_ptr<IoOp> _next() override; + + private: + uint64_t offset; + uint64_t length; +}; + +class Seq3 : public IoSequence { + public: + Seq3(std::pair<int, int> obj_size_range, int seed); + + Sequence get_id() const override; + std::string get_name() const override; + std::unique_ptr<IoOp> _next() override; + + private: + uint64_t offset1; + uint64_t offset2; +}; + +class Seq4 : public IoSequence { + public: + Seq4(std::pair<int, int> obj_size_range, int seed); + + Sequence get_id() const override; + std::string get_name() const override; + std::unique_ptr<IoOp> _next() override; + + private: + uint64_t offset1; + uint64_t offset2; +}; + +class Seq5 : public IoSequence { + public: + Seq5(std::pair<int, int> obj_size_range, int seed); + + Sequence get_id() const override; + std::string get_name() const override; + std::unique_ptr<IoOp> _next() override; + + private: + uint64_t offset; + uint64_t length; + bool doneread; + bool donebarrier; +}; + +class Seq6 : public IoSequence { + public: + Seq6(std::pair<int, int> obj_size_range, int seed); + + Sequence get_id() const override; + std::string get_name() const override; + std::unique_ptr<IoOp> _next() override; + + private: + uint64_t offset; + uint64_t length; + bool doneread; + bool donebarrier; +}; + +class Seq7 : public IoSequence { + public: + Seq7(std::pair<int, int> obj_size_range, int seed); + + Sequence get_id() const override; + std::string get_name() const override; + std::unique_ptr<IoOp> _next() override; + + private: + uint64_t offset; + bool doneread = true; + bool donebarrier = false; +}; + +class Seq8 : public IoSequence { + public: + Seq8(std::pair<int, int> obj_size_range, int seed); + + Sequence get_id() const override; + std::string get_name() const override; + std::unique_ptr<IoOp> _next() override; + + private: + uint64_t offset1; + uint64_t offset2; + bool doneread = true; + bool donebarrier = false; +}; + +class Seq9 : public IoSequence { + private: + uint64_t offset; + uint64_t length; + bool doneread = true; + bool donebarrier = false; + + public: + Seq9(std::pair<int, int> obj_size_range, int seed); + + Sequence get_id() const override; + std::string get_name() const override; + std::unique_ptr<IoOp> _next() override; +}; +} // namespace io_exerciser +} // namespace ceph
\ No newline at end of file diff --git a/src/common/io_exerciser/Model.cc b/src/common/io_exerciser/Model.cc index 50812ecbb15..6548e1eda7a 100644 --- a/src/common/io_exerciser/Model.cc +++ b/src/common/io_exerciser/Model.cc @@ -4,25 +4,11 @@ using Model = ceph::io_exerciser::Model; -Model::Model(const std::string& oid, uint64_t block_size) : -num_io(0), -oid(oid), -block_size(block_size) -{ +Model::Model(const std::string& oid, uint64_t block_size) + : num_io(0), oid(oid), block_size(block_size) {} -} +const uint64_t Model::get_block_size() const { return block_size; } -const uint64_t Model::get_block_size() const -{ - return block_size; -} +const std::string Model::get_oid() const { return oid; } -const std::string Model::get_oid() const -{ - return oid; -} - -int Model::get_num_io() const -{ - return num_io; -}
\ No newline at end of file +int Model::get_num_io() const { return num_io; }
\ No newline at end of file diff --git a/src/common/io_exerciser/Model.h b/src/common/io_exerciser/Model.h index 58d107409a6..9e421e79a78 100644 --- a/src/common/io_exerciser/Model.h +++ b/src/common/io_exerciser/Model.h @@ -1,15 +1,13 @@ #pragma once -#include "IoOp.h" - #include <boost/asio/io_context.hpp> -#include "librados/librados_asio.h" - -#include "include/interval_set.h" -#include "global/global_init.h" -#include "global/global_context.h" +#include "IoOp.h" #include "common/Thread.h" +#include "global/global_context.h" +#include "global/global_init.h" +#include "include/interval_set.h" +#include "librados/librados_asio.h" /* Overview * @@ -21,29 +19,27 @@ */ namespace ceph { - namespace io_exerciser { - - class Model - { - protected: - int num_io{0}; - std::string oid; - uint64_t block_size; - - public: - Model(const std::string& oid, uint64_t block_size); - virtual ~Model() = default; - - virtual bool readyForIoOp(IoOp& op) = 0; - virtual void applyIoOp(IoOp& op) = 0; - - const std::string get_oid() const; - const uint64_t get_block_size() const; - int get_num_io() const; - }; - - /* Simple RADOS I/O generator */ - - - } -}
\ No newline at end of file +namespace io_exerciser { + +class Model { + protected: + int num_io{0}; + std::string oid; + uint64_t block_size; + + public: + Model(const std::string& oid, uint64_t block_size); + virtual ~Model() = default; + + virtual bool readyForIoOp(IoOp& op) = 0; + virtual void applyIoOp(IoOp& op) = 0; + + const std::string get_oid() const; + const uint64_t get_block_size() const; + int get_num_io() const; +}; + +/* Simple RADOS I/O generator */ + +} // namespace io_exerciser +} // namespace ceph
\ No newline at end of file diff --git a/src/common/io_exerciser/ObjectModel.cc b/src/common/io_exerciser/ObjectModel.cc index 589f6434282..454d7254cf2 100644 --- a/src/common/io_exerciser/ObjectModel.cc +++ b/src/common/io_exerciser/ObjectModel.cc @@ -6,25 +6,20 @@ using ObjectModel = ceph::io_exerciser::ObjectModel; -ObjectModel::ObjectModel(const std::string& oid, uint64_t block_size, int seed) : - Model(oid, block_size), created(false) -{ +ObjectModel::ObjectModel(const std::string& oid, uint64_t block_size, int seed) + : Model(oid, block_size), created(false) { rng.seed(seed); } -int ObjectModel::get_seed(uint64_t offset) const -{ +int ObjectModel::get_seed(uint64_t offset) const { ceph_assert(offset < contents.size()); return contents[offset]; } -std::vector<int> ObjectModel::get_seed_offsets(int seed) const -{ +std::vector<int> ObjectModel::get_seed_offsets(int seed) const { std::vector<int> offsets; - for (size_t i = 0; i < contents.size(); i++) - { - if (contents[i] == seed) - { + for (size_t i = 0; i < contents.size(); i++) { + if (contents[i] == seed) { offsets.push_back(i); } } @@ -32,8 +27,7 @@ std::vector<int> ObjectModel::get_seed_offsets(int seed) const return offsets; } -std::string ObjectModel::to_string(int mask) const -{ +std::string ObjectModel::to_string(int mask) const { if (!created) { return "Object does not exist"; } @@ -48,107 +42,127 @@ std::string ObjectModel::to_string(int mask) const return result; } -bool ObjectModel::readyForIoOp(IoOp& op) -{ - return true; -} - -void ObjectModel::applyIoOp(IoOp& op) -{ - auto generate_random = [&rng = rng]() { - return rng(); - }; - - switch (op.op) { - case OpType::BARRIER: - reads.clear(); - writes.clear(); - break; - - case OpType::CREATE: - ceph_assert(!created); - ceph_assert(reads.empty()); - ceph_assert(writes.empty()); - created = true; - contents.resize(op.length1); - std::generate(std::execution::seq, contents.begin(), contents.end(), - generate_random); - break; - - case OpType::REMOVE: - ceph_assert(created); - ceph_assert(reads.empty()); - ceph_assert(writes.empty()); - created = false; - contents.resize(0); - break; - - case OpType::READ3: - ceph_assert(created); - ceph_assert(op.offset3 + op.length3 <= contents.size()); - // Not allowed: read overlapping with parallel write - ceph_assert(!writes.intersects(op.offset3, op.length3)); - reads.union_insert(op.offset3, op.length3); - [[fallthrough]]; - - case OpType::READ2: - ceph_assert(created); - ceph_assert(op.offset2 + op.length2 <= contents.size()); - // Not allowed: read overlapping with parallel write - ceph_assert(!writes.intersects(op.offset2, op.length2)); - reads.union_insert(op.offset2, op.length2); - [[fallthrough]]; - - case OpType::READ: - ceph_assert(created); - ceph_assert(op.offset1 + op.length1 <= contents.size()); - // Not allowed: read overlapping with parallel write - ceph_assert(!writes.intersects(op.offset1, op.length1)); - reads.union_insert(op.offset1, op.length1); - num_io++; - break; - - case OpType::WRITE3: - ceph_assert(created); - // Not allowed: write overlapping with parallel read or write - ceph_assert(!reads.intersects(op.offset3, op.length3)); - ceph_assert(!writes.intersects(op.offset3, op.length3)); - writes.union_insert(op.offset3, op.length3); - ceph_assert(op.offset3 + op.length3 <= contents.size()); - std::generate(std::execution::seq, - std::next(contents.begin(), op.offset3), - std::next(contents.begin(), op.offset3 + op.length3), - generate_random); - [[fallthrough]]; - - case OpType::WRITE2: - ceph_assert(created); - // Not allowed: write overlapping with parallel read or write - ceph_assert(!reads.intersects(op.offset2, op.length2)); - ceph_assert(!writes.intersects(op.offset2, op.length2)); - writes.union_insert(op.offset2, op.length2); - ceph_assert(op.offset2 + op.length2 <= contents.size()); - std::generate(std::execution::seq, - std::next(contents.begin(), op.offset2), - std::next(contents.begin(), op.offset2 + op.length2), - generate_random); - [[fallthrough]]; - - case OpType::WRITE: - ceph_assert(created); - // Not allowed: write overlapping with parallel read or write - ceph_assert(!reads.intersects(op.offset1, op.length1)); - ceph_assert(!writes.intersects(op.offset1, op.length1)); - writes.union_insert(op.offset1, op.length1); - ceph_assert(op.offset1 + op.length1 <= contents.size()); - std::generate(std::execution::seq, - std::next(contents.begin(), op.offset1), - std::next(contents.begin(), op.offset1 + op.length1), - generate_random); - num_io++; - break; - default: - break; +bool ObjectModel::readyForIoOp(IoOp& op) { return true; } + +void ObjectModel::applyIoOp(IoOp& op) { + auto generate_random = [&rng = rng]() { return rng(); }; + + auto verify_and_record_read_op = + [&contents = contents, &created = created, &num_io = num_io, + &reads = reads, + &writes = writes]<OpType opType, int N>(ReadWriteOp<opType, N>& readOp) { + ceph_assert(created); + for (int i = 0; i < N; i++) { + ceph_assert(readOp.offset[i] + readOp.length[i] <= contents.size()); + // Not allowed: read overlapping with parallel write + ceph_assert(!writes.intersects(readOp.offset[i], readOp.length[i])); + reads.union_insert(readOp.offset[i], readOp.length[i]); + } + num_io++; + }; + + auto verify_write_and_record_and_generate_seed = + [&generate_random, &contents = contents, &created = created, + &num_io = num_io, &reads = reads, + &writes = writes]<OpType opType, int N>(ReadWriteOp<opType, N> writeOp) { + ceph_assert(created); + for (int i = 0; i < N; i++) { + // Not allowed: write overlapping with parallel read or write + ceph_assert(!reads.intersects(writeOp.offset[i], writeOp.length[i])); + ceph_assert(!writes.intersects(writeOp.offset[i], writeOp.length[i])); + writes.union_insert(writeOp.offset[i], writeOp.length[i]); + ceph_assert(writeOp.offset[i] + writeOp.length[i] <= contents.size()); + std::generate(std::execution::seq, + std::next(contents.begin(), writeOp.offset[i]), + std::next(contents.begin(), + writeOp.offset[i] + writeOp.length[i]), + generate_random); + } + num_io++; + }; + + auto verify_failed_write_and_record = + [&contents = contents, &created = created, &num_io = num_io, + &reads = reads, + &writes = writes]<OpType opType, int N>(ReadWriteOp<opType, N> writeOp) { + // Ensure write should still be valid, even though we are expecting OSD + // failure + ceph_assert(created); + for (int i = 0; i < N; i++) { + // Not allowed: write overlapping with parallel read or write + ceph_assert(!reads.intersects(writeOp.offset[i], writeOp.length[i])); + ceph_assert(!writes.intersects(writeOp.offset[i], writeOp.length[i])); + writes.union_insert(writeOp.offset[i], writeOp.length[i]); + ceph_assert(writeOp.offset[i] + writeOp.length[i] <= contents.size()); + } + num_io++; + }; + + switch (op.getOpType()) { + case OpType::Barrier: + reads.clear(); + writes.clear(); + break; + + case OpType::Create: + ceph_assert(!created); + ceph_assert(reads.empty()); + ceph_assert(writes.empty()); + created = true; + contents.resize(static_cast<CreateOp&>(op).size); + std::generate(std::execution::seq, contents.begin(), contents.end(), + generate_random); + break; + + case OpType::Remove: + ceph_assert(created); + ceph_assert(reads.empty()); + ceph_assert(writes.empty()); + created = false; + contents.resize(0); + break; + + case OpType::Read: { + SingleReadOp& readOp = static_cast<SingleReadOp&>(op); + verify_and_record_read_op(readOp); + } break; + case OpType::Read2: { + DoubleReadOp& readOp = static_cast<DoubleReadOp&>(op); + verify_and_record_read_op(readOp); + } break; + case OpType::Read3: { + TripleReadOp& readOp = static_cast<TripleReadOp&>(op); + verify_and_record_read_op(readOp); + } break; + + case OpType::Write: { + ceph_assert(created); + SingleWriteOp& writeOp = static_cast<SingleWriteOp&>(op); + verify_write_and_record_and_generate_seed(writeOp); + } break; + case OpType::Write2: { + DoubleWriteOp& writeOp = static_cast<DoubleWriteOp&>(op); + verify_write_and_record_and_generate_seed(writeOp); + } break; + case OpType::Write3: { + TripleWriteOp& writeOp = static_cast<TripleWriteOp&>(op); + verify_write_and_record_and_generate_seed(writeOp); + } break; + case OpType::FailedWrite: { + ceph_assert(created); + SingleWriteOp& writeOp = static_cast<SingleWriteOp&>(op); + verify_failed_write_and_record(writeOp); + } break; + case OpType::FailedWrite2: { + DoubleWriteOp& writeOp = static_cast<DoubleWriteOp&>(op); + verify_failed_write_and_record(writeOp); + } break; + case OpType::FailedWrite3: { + TripleWriteOp& writeOp = static_cast<TripleWriteOp&>(op); + verify_failed_write_and_record(writeOp); + } break; + default: + break; } } diff --git a/src/common/io_exerciser/ObjectModel.h b/src/common/io_exerciser/ObjectModel.h index 93c70f41429..cad1307b84e 100644 --- a/src/common/io_exerciser/ObjectModel.h +++ b/src/common/io_exerciser/ObjectModel.h @@ -14,40 +14,41 @@ */ namespace ceph { - namespace io_exerciser { - /* Model of an object to track its data contents */ - - class ObjectModel : public Model { - private: - bool created; - std::vector<int> contents; - ceph::util::random_number_generator<int> rng = - ceph::util::random_number_generator<int>(); - - // Track read and write I/Os that can be submitted in - // parallel to detect violations: - // - // * Read may not overlap with a parallel write - // * Write may not overlap with a parallel read or write - // * Create / remove may not be in parallel with read or write - // - // Fix broken test cases by adding barrier ops to restrict - // I/O exercisers from issuing conflicting ops in parallel - interval_set<uint64_t> reads; - interval_set<uint64_t> writes; - public: - ObjectModel(const std::string& oid, uint64_t block_size, int seed); - - int get_seed(uint64_t offset) const; - std::vector<int> get_seed_offsets(int seed) const; - - std::string to_string(int mask = -1) const; - - bool readyForIoOp(IoOp& op); - void applyIoOp(IoOp& op); - - void encode(ceph::buffer::list& bl) const; - void decode(ceph::buffer::list::const_iterator& bl); - }; - } -}
\ No newline at end of file +namespace io_exerciser { +/* Model of an object to track its data contents */ + +class ObjectModel : public Model { + private: + bool created; + std::vector<int> contents; + ceph::util::random_number_generator<int> rng = + ceph::util::random_number_generator<int>(); + + // Track read and write I/Os that can be submitted in + // parallel to detect violations: + // + // * Read may not overlap with a parallel write + // * Write may not overlap with a parallel read or write + // * Create / remove may not be in parallel with read or write + // + // Fix broken test cases by adding barrier ops to restrict + // I/O exercisers from issuing conflicting ops in parallel + interval_set<uint64_t> reads; + interval_set<uint64_t> writes; + + public: + ObjectModel(const std::string& oid, uint64_t block_size, int seed); + + int get_seed(uint64_t offset) const; + std::vector<int> get_seed_offsets(int seed) const; + + std::string to_string(int mask = -1) const; + + bool readyForIoOp(IoOp& op); + void applyIoOp(IoOp& op); + + void encode(ceph::buffer::list& bl) const; + void decode(ceph::buffer::list::const_iterator& bl); +}; +} // namespace io_exerciser +} // namespace ceph
\ No newline at end of file diff --git a/src/common/io_exerciser/OpType.h b/src/common/io_exerciser/OpType.h new file mode 100644 index 00000000000..7cddb805e45 --- /dev/null +++ b/src/common/io_exerciser/OpType.h @@ -0,0 +1,91 @@ +#pragma once + +#include <fmt/format.h> +#include <include/ceph_assert.h> + +/* Overview + * + * enum OpType + * Enumeration of different types of I/O operation + * + */ + +namespace ceph { +namespace io_exerciser { +enum class OpType { + Done, // End of I/O sequence + Barrier, // Barrier - all prior I/Os must complete + Create, // Create object and pattern with data + Remove, // Remove object + Read, // Read + Read2, // Two reads in a single op + Read3, // Three reads in a single op + Write, // Write + Write2, // Two writes in a single op + Write3, // Three writes in a single op + FailedWrite, // A write which should fail + FailedWrite2, // Two writes in one op which should fail + FailedWrite3, // Three writes in one op which should fail + InjectReadError, // Op to tell OSD to inject read errors + InjectWriteError, // Op to tell OSD to inject write errors + ClearReadErrorInject, // Op to tell OSD to clear read error injects + ClearWriteErrorInject // Op to tell OSD to clear write error injects +}; + +enum class InjectOpType { + None, + ReadEIO, + ReadMissingShard, + WriteFailAndRollback, + WriteOSDAbort +}; +} // namespace io_exerciser +} // namespace ceph + +template <> +struct fmt::formatter<ceph::io_exerciser::OpType> { + constexpr auto parse(format_parse_context& ctx) { return ctx.begin(); } + + auto format(ceph::io_exerciser::OpType opType, + fmt::format_context& ctx) const -> fmt::format_context::iterator { + switch (opType) { + case ceph::io_exerciser::OpType::Done: + return fmt::format_to(ctx.out(), "Done"); + case ceph::io_exerciser::OpType::Barrier: + return fmt::format_to(ctx.out(), "Barrier"); + case ceph::io_exerciser::OpType::Create: + return fmt::format_to(ctx.out(), "Create"); + case ceph::io_exerciser::OpType::Remove: + return fmt::format_to(ctx.out(), "Remove"); + case ceph::io_exerciser::OpType::Read: + return fmt::format_to(ctx.out(), "Read"); + case ceph::io_exerciser::OpType::Read2: + return fmt::format_to(ctx.out(), "Read2"); + case ceph::io_exerciser::OpType::Read3: + return fmt::format_to(ctx.out(), "Read3"); + case ceph::io_exerciser::OpType::Write: + return fmt::format_to(ctx.out(), "Write"); + case ceph::io_exerciser::OpType::Write2: + return fmt::format_to(ctx.out(), "Write2"); + case ceph::io_exerciser::OpType::Write3: + return fmt::format_to(ctx.out(), "Write3"); + case ceph::io_exerciser::OpType::FailedWrite: + return fmt::format_to(ctx.out(), "FailedWrite"); + case ceph::io_exerciser::OpType::FailedWrite2: + return fmt::format_to(ctx.out(), "FailedWrite2"); + case ceph::io_exerciser::OpType::FailedWrite3: + return fmt::format_to(ctx.out(), "FailedWrite3"); + case ceph::io_exerciser::OpType::InjectReadError: + return fmt::format_to(ctx.out(), "InjectReadError"); + case ceph::io_exerciser::OpType::InjectWriteError: + return fmt::format_to(ctx.out(), "InjectWriteError"); + case ceph::io_exerciser::OpType::ClearReadErrorInject: + return fmt::format_to(ctx.out(), "ClearReadErrorInject"); + case ceph::io_exerciser::OpType::ClearWriteErrorInject: + return fmt::format_to(ctx.out(), "ClearWriteErrorInject"); + default: + ceph_abort_msg("Unknown OpType"); + return fmt::format_to(ctx.out(), "Unknown OpType"); + } + } +};
\ No newline at end of file diff --git a/src/common/io_exerciser/RadosIo.cc b/src/common/io_exerciser/RadosIo.cc index 44b82260263..a78c074228b 100644 --- a/src/common/io_exerciser/RadosIo.cc +++ b/src/common/io_exerciser/RadosIo.cc @@ -1,300 +1,453 @@ #include "RadosIo.h" +#include <fmt/format.h> +#include <json_spirit/json_spirit.h> + +#include <ranges> + #include "DataGenerator.h" +#include "common/ceph_json.h" +#include "common/json/OSDStructures.h" using RadosIo = ceph::io_exerciser::RadosIo; -RadosIo::RadosIo(librados::Rados& rados, - boost::asio::io_context& asio, - const std::string& pool, - const std::string& oid, - uint64_t block_size, - int seed, - int threads, - ceph::mutex& lock, - ceph::condition_variable& cond) : - Model(oid, block_size), - rados(rados), - asio(asio), - om(std::make_unique<ObjectModel>(oid, block_size, seed)), - db(data_generation::DataGenerator::create_generator( - data_generation::GenerationType::HeaderedSeededRandom, *om)), - pool(pool), - threads(threads), - lock(lock), - cond(cond), - outstanding_io(0) -{ +namespace { +template <typename S> +int send_osd_command(int osd, S& s, librados::Rados& rados, const char* name, + ceph::buffer::list& inbl, ceph::buffer::list* outbl, + Formatter* f) { + encode_json(name, s, f); + + std::ostringstream oss; + f->flush(oss); + int rc = rados.osd_command(osd, oss.str(), inbl, outbl, nullptr); + return rc; +} + +template <typename S> +int send_mon_command(S& s, librados::Rados& rados, const char* name, + ceph::buffer::list& inbl, ceph::buffer::list* outbl, + Formatter* f) { + encode_json(name, s, f); + + std::ostringstream oss; + f->flush(oss); + int rc = rados.mon_command(oss.str(), inbl, outbl, nullptr); + return rc; +} +} // namespace + +RadosIo::RadosIo(librados::Rados& rados, boost::asio::io_context& asio, + const std::string& pool, const std::string& oid, + const std::optional<std::vector<int>>& cached_shard_order, + uint64_t block_size, int seed, int threads, ceph::mutex& lock, + ceph::condition_variable& cond) + : Model(oid, block_size), + rados(rados), + asio(asio), + om(std::make_unique<ObjectModel>(oid, block_size, seed)), + db(data_generation::DataGenerator::create_generator( + data_generation::GenerationType::HeaderedSeededRandom, *om)), + pool(pool), + cached_shard_order(cached_shard_order), + threads(threads), + lock(lock), + cond(cond), + outstanding_io(0) { int rc; rc = rados.ioctx_create(pool.c_str(), io); ceph_assert(rc == 0); allow_ec_overwrites(true); } -RadosIo::~RadosIo() -{ -} +RadosIo::~RadosIo() {} -void RadosIo::start_io() -{ +void RadosIo::start_io() { std::lock_guard l(lock); outstanding_io++; } -void RadosIo::finish_io() -{ +void RadosIo::finish_io() { std::lock_guard l(lock); ceph_assert(outstanding_io > 0); outstanding_io--; cond.notify_all(); } -void RadosIo::wait_for_io(int count) -{ +void RadosIo::wait_for_io(int count) { std::unique_lock l(lock); while (outstanding_io > count) { cond.wait(l); } } -void RadosIo::allow_ec_overwrites(bool allow) -{ +void RadosIo::allow_ec_overwrites(bool allow) { int rc; bufferlist inbl, outbl; - std::string cmdstr = - "{\"prefix\": \"osd pool set\", \"pool\": \"" + pool + "\", \ + std::string cmdstr = "{\"prefix\": \"osd pool set\", \"pool\": \"" + pool + + "\", \ \"var\": \"allow_ec_overwrites\", \"val\": \"" + - (allow ? "true" : "false") + "\"}"; + (allow ? "true" : "false") + "\"}"; rc = rados.mon_command(cmdstr, inbl, &outbl, nullptr); ceph_assert(rc == 0); } -RadosIo::AsyncOpInfo::AsyncOpInfo(uint64_t offset1, uint64_t length1, - uint64_t offset2, uint64_t length2, - uint64_t offset3, uint64_t length3 ) : - offset1(offset1), length1(length1), - offset2(offset2), length2(length2), - offset3(offset3), length3(length3) -{ +template <int N> +RadosIo::AsyncOpInfo<N>::AsyncOpInfo(const std::array<uint64_t, N>& offset, + const std::array<uint64_t, N>& length) + : offset(offset), length(length) {} -} - -bool RadosIo::readyForIoOp(IoOp &op) -{ - ceph_assert(ceph_mutex_is_locked_by_me(lock)); //Must be called with lock held +bool RadosIo::readyForIoOp(IoOp& op) { + ceph_assert( + ceph_mutex_is_locked_by_me(lock)); // Must be called with lock held if (!om->readyForIoOp(op)) { return false; } - switch (op.op) { - case OpType::Done: - case OpType::BARRIER: - return outstanding_io == 0; - default: - return outstanding_io < threads; + + switch (op.getOpType()) { + case OpType::Done: + case OpType::Barrier: + return outstanding_io == 0; + default: + return outstanding_io < threads; } } -void RadosIo::applyIoOp(IoOp &op) -{ - std::shared_ptr<AsyncOpInfo> op_info; - +void RadosIo::applyIoOp(IoOp& op) { om->applyIoOp(op); // If there are thread concurrent I/Os in flight then wait for // at least one I/O to complete - wait_for_io(threads-1); - - switch (op.op) { - case OpType::Done: - [[ fallthrough ]]; - case OpType::BARRIER: - // Wait for all outstanding I/O to complete - wait_for_io(0); - break; - - case OpType::CREATE: - { + wait_for_io(threads - 1); + + switch (op.getOpType()) { + case OpType::Done: + [[fallthrough]]; + case OpType::Barrier: + // Wait for all outstanding I/O to complete + wait_for_io(0); + break; + + case OpType::Create: { start_io(); - op_info = std::make_shared<AsyncOpInfo>(0, op.length1); - op_info->bl1 = db->generate_data(0, op.length1); - op_info->wop.write_full(op_info->bl1); - auto create_cb = [this] (boost::system::error_code ec, - version_t ver) { + uint64_t opSize = static_cast<CreateOp&>(op).size; + std::shared_ptr<AsyncOpInfo<1>> op_info = + std::make_shared<AsyncOpInfo<1>>(std::array<uint64_t, 1>{0}, + std::array<uint64_t, 1>{opSize}); + op_info->bufferlist[0] = db->generate_data(0, opSize); + op_info->wop.write_full(op_info->bufferlist[0]); + auto create_cb = [this](boost::system::error_code ec, version_t ver) { ceph_assert(ec == boost::system::errc::success); finish_io(); }; - librados::async_operate(asio, io, oid, - &op_info->wop, 0, nullptr, create_cb); + librados::async_operate(asio, io, oid, &op_info->wop, 0, nullptr, + create_cb); + break; } - break; - case OpType::REMOVE: - { + case OpType::Remove: { start_io(); - op_info = std::make_shared<AsyncOpInfo>(); + auto op_info = std::make_shared<AsyncOpInfo<0>>(); op_info->wop.remove(); - auto remove_cb = [this] (boost::system::error_code ec, - version_t ver) { + auto remove_cb = [this](boost::system::error_code ec, version_t ver) { ceph_assert(ec == boost::system::errc::success); finish_io(); }; - librados::async_operate(asio, io, oid, - &op_info->wop, 0, nullptr, remove_cb); + librados::async_operate(asio, io, oid, &op_info->wop, 0, nullptr, + remove_cb); + break; } - break; + case OpType::Read: + [[fallthrough]]; + case OpType::Read2: + [[fallthrough]]; + case OpType::Read3: + [[fallthrough]]; + case OpType::Write: + [[fallthrough]]; + case OpType::Write2: + [[fallthrough]]; + case OpType::Write3: + [[fallthrough]]; + case OpType::FailedWrite: + [[fallthrough]]; + case OpType::FailedWrite2: + [[fallthrough]]; + case OpType::FailedWrite3: + applyReadWriteOp(op); + break; + case OpType::InjectReadError: + [[fallthrough]]; + case OpType::InjectWriteError: + [[fallthrough]]; + case OpType::ClearReadErrorInject: + [[fallthrough]]; + case OpType::ClearWriteErrorInject: + applyInjectOp(op); + break; + default: + ceph_abort_msg("Unrecognised Op"); + break; + } +} - case OpType::READ: - { - start_io(); - op_info = std::make_shared<AsyncOpInfo>(op.offset1, op.length1); - op_info->rop.read(op.offset1 * block_size, - op.length1 * block_size, - &op_info->bl1, nullptr); - auto read_cb = [this, op_info] (boost::system::error_code ec, - version_t ver, - bufferlist bl) { - ceph_assert(ec == boost::system::errc::success); - ceph_assert(db->validate(op_info->bl1, - op_info->offset1, - op_info->length1)); - finish_io(); - }; - librados::async_operate(asio, io, oid, - &op_info->rop, 0, nullptr, read_cb); - num_io++; +void RadosIo::applyReadWriteOp(IoOp& op) { + auto applyReadOp = [this]<OpType opType, int N>( + ReadWriteOp<opType, N> readOp) { + auto op_info = + std::make_shared<AsyncOpInfo<N>>(readOp.offset, readOp.length); + + for (int i = 0; i < N; i++) { + op_info->rop.read(readOp.offset[i] * block_size, + readOp.length[i] * block_size, &op_info->bufferlist[i], + nullptr); } - break; + auto read_cb = [this, op_info](boost::system::error_code ec, version_t ver, + bufferlist bl) { + ceph_assert(ec == boost::system::errc::success); + for (int i = 0; i < N; i++) { + ceph_assert(db->validate(op_info->bufferlist[i], op_info->offset[i], + op_info->length[i])); + } + finish_io(); + }; + librados::async_operate(asio, io, oid, &op_info->rop, 0, nullptr, read_cb); + num_io++; + }; - case OpType::READ2: - { - start_io(); - op_info = std::make_shared<AsyncOpInfo>(op.offset1, - op.length1, - op.offset2, - op.length2); - - op_info->rop.read(op.offset1 * block_size, - op.length1 * block_size, - &op_info->bl1, nullptr); - op_info->rop.read(op.offset2 * block_size, - op.length2 * block_size, - &op_info->bl2, nullptr); - auto read2_cb = [this, op_info] (boost::system::error_code ec, - version_t ver, - bufferlist bl) { - ceph_assert(ec == boost::system::errc::success); - ceph_assert(db->validate(op_info->bl1, - op_info->offset1, - op_info->length1)); - ceph_assert(db->validate(op_info->bl2, - op_info->offset2, - op_info->length2)); - finish_io(); - }; - librados::async_operate(asio, io, oid, - &op_info->rop, 0, nullptr, read2_cb); - num_io++; + auto applyWriteOp = [this]<OpType opType, int N>( + ReadWriteOp<opType, N> writeOp) { + auto op_info = + std::make_shared<AsyncOpInfo<N>>(writeOp.offset, writeOp.length); + for (int i = 0; i < N; i++) { + op_info->bufferlist[i] = + db->generate_data(writeOp.offset[i], writeOp.length[i]); + op_info->wop.write(writeOp.offset[i] * block_size, + op_info->bufferlist[i]); } - break; + auto write_cb = [this](boost::system::error_code ec, version_t ver) { + ceph_assert(ec == boost::system::errc::success); + finish_io(); + }; + librados::async_operate(asio, io, oid, &op_info->wop, 0, nullptr, write_cb); + num_io++; + }; - case OpType::READ3: - { - start_io(); - op_info = std::make_shared<AsyncOpInfo>(op.offset1, op.length1, - op.offset2, op.length2, - op.offset3, op.length3); - op_info->rop.read(op.offset1 * block_size, - op.length1 * block_size, - &op_info->bl1, nullptr); - op_info->rop.read(op.offset2 * block_size, - op.length2 * block_size, - &op_info->bl2, nullptr); - op_info->rop.read(op.offset3 * block_size, - op.length3 * block_size, - &op_info->bl3, nullptr); - auto read3_cb = [this, op_info] (boost::system::error_code ec, - version_t ver, - bufferlist bl) { - ceph_assert(ec == boost::system::errc::success); - ceph_assert(db->validate(op_info->bl1, - op_info->offset1, - op_info->length1)); - ceph_assert(db->validate(op_info->bl2, - op_info->offset2, - op_info->length2)); - ceph_assert(db->validate(op_info->bl3, - op_info->offset3, - op_info->length3)); - finish_io(); - }; - librados::async_operate(asio, io, oid, - &op_info->rop, 0, nullptr, read3_cb); - num_io++; + auto applyFailedWriteOp = [this]<OpType opType, int N>( + ReadWriteOp<opType, N> writeOp) { + auto op_info = + std::make_shared<AsyncOpInfo<N>>(writeOp.offset, writeOp.length); + for (int i = 0; i < N; i++) { + op_info->bufferlist[i] = + db->generate_data(writeOp.offset[i], writeOp.length[i]); + op_info->wop.write(writeOp.offset[i] * block_size, + op_info->bufferlist[i]); } - break; + auto write_cb = [this, writeOp](boost::system::error_code ec, + version_t ver) { + ceph_assert(ec != boost::system::errc::success); + finish_io(); + }; + librados::async_operate(asio, io, oid, &op_info->wop, 0, nullptr, write_cb); + num_io++; + }; - case OpType::WRITE: - { + switch (op.getOpType()) { + case OpType::Read: { start_io(); - op_info = std::make_shared<AsyncOpInfo>(op.offset1, op.length1); - op_info->bl1 = db->generate_data(op.offset1, op.length1); - - op_info->wop.write(op.offset1 * block_size, op_info->bl1); - auto write_cb = [this] (boost::system::error_code ec, - version_t ver) { - ceph_assert(ec == boost::system::errc::success); - finish_io(); - }; - librados::async_operate(asio, io, oid, - &op_info->wop, 0, nullptr, write_cb); - num_io++; + SingleReadOp& readOp = static_cast<SingleReadOp&>(op); + applyReadOp(readOp); + break; } - break; - - case OpType::WRITE2: - { + case OpType::Read2: { start_io(); - op_info = std::make_shared<AsyncOpInfo>(op.offset1, op.length1, - op.offset2, op.length2); - op_info->bl1 = db->generate_data(op.offset1, op.length1); - op_info->bl2 = db->generate_data(op.offset2, op.length2); - op_info->wop.write(op.offset1 * block_size, op_info->bl1); - op_info->wop.write(op.offset2 * block_size, op_info->bl2); - auto write2_cb = [this] (boost::system::error_code ec, - version_t ver) { - ceph_assert(ec == boost::system::errc::success); - finish_io(); - }; - librados::async_operate(asio, io, oid, - &op_info->wop, 0, nullptr, write2_cb); - num_io++; + DoubleReadOp& readOp = static_cast<DoubleReadOp&>(op); + applyReadOp(readOp); + break; + } + case OpType::Read3: { + start_io(); + TripleReadOp& readOp = static_cast<TripleReadOp&>(op); + applyReadOp(readOp); + break; + } + case OpType::Write: { + start_io(); + SingleWriteOp& writeOp = static_cast<SingleWriteOp&>(op); + applyWriteOp(writeOp); + break; + } + case OpType::Write2: { + start_io(); + DoubleWriteOp& writeOp = static_cast<DoubleWriteOp&>(op); + applyWriteOp(writeOp); + break; + } + case OpType::Write3: { + start_io(); + TripleWriteOp& writeOp = static_cast<TripleWriteOp&>(op); + applyWriteOp(writeOp); + break; } - break; - case OpType::WRITE3: - { + case OpType::FailedWrite: { start_io(); - op_info = std::make_shared<AsyncOpInfo>(op.offset1, op.length1, - op.offset2, op.length2, - op.offset3, op.length3); - op_info->bl1 = db->generate_data(op.offset1, op.length1); - op_info->bl2 = db->generate_data(op.offset2, op.length2); - op_info->bl3 = db->generate_data(op.offset3, op.length3); - op_info->wop.write(op.offset1 * block_size, op_info->bl1); - op_info->wop.write(op.offset2 * block_size, op_info->bl2); - op_info->wop.write(op.offset3 * block_size, op_info->bl3); - auto write3_cb = [this] (boost::system::error_code ec, - version_t ver) { - ceph_assert(ec == boost::system::errc::success); - finish_io(); - }; - librados::async_operate(asio, io, oid, - &op_info->wop, 0, nullptr, write3_cb); - num_io++; + SingleFailedWriteOp& writeOp = static_cast<SingleFailedWriteOp&>(op); + applyFailedWriteOp(writeOp); + break; + } + case OpType::FailedWrite2: { + start_io(); + DoubleFailedWriteOp& writeOp = static_cast<DoubleFailedWriteOp&>(op); + applyFailedWriteOp(writeOp); + break; + } + case OpType::FailedWrite3: { + start_io(); + TripleFailedWriteOp& writeOp = static_cast<TripleFailedWriteOp&>(op); + applyFailedWriteOp(writeOp); + break; } - break; - default: - break; + default: + ceph_abort_msg( + fmt::format("Unsupported Read/Write operation ({})", op.getOpType())); + break; } } + +void RadosIo::applyInjectOp(IoOp& op) { + bufferlist osdmap_inbl, inject_inbl, osdmap_outbl, inject_outbl; + auto formatter = std::make_unique<JSONFormatter>(false); + + int osd = -1; + std::vector<int> shard_order; + + ceph::messaging::osd::OSDMapRequest osdMapRequest{pool, get_oid(), ""}; + int rc = send_mon_command(osdMapRequest, rados, "OSDMapRequest", osdmap_inbl, + &osdmap_outbl, formatter.get()); + ceph_assert(rc == 0); + + JSONParser p; + bool success = p.parse(osdmap_outbl.c_str(), osdmap_outbl.length()); + ceph_assert(success); + + ceph::messaging::osd::OSDMapReply reply; + reply.decode_json(&p); + + osd = reply.acting_primary; + shard_order = reply.acting; + + switch (op.getOpType()) { + case OpType::InjectReadError: { + InjectReadErrorOp& errorOp = static_cast<InjectReadErrorOp&>(op); + + if (errorOp.type == 0) { + ceph::messaging::osd::InjectECErrorRequest<InjectOpType::ReadEIO> + injectErrorRequest{pool, oid, errorOp.shard, + errorOp.type, errorOp.when, errorOp.duration}; + int rc = send_osd_command(osd, injectErrorRequest, rados, + "InjectECErrorRequest", inject_inbl, + &inject_outbl, formatter.get()); + ceph_assert(rc == 0); + } else if (errorOp.type == 1) { + ceph::messaging::osd::InjectECErrorRequest< + InjectOpType::ReadMissingShard> + injectErrorRequest{pool, oid, errorOp.shard, + errorOp.type, errorOp.when, errorOp.duration}; + int rc = send_osd_command(osd, injectErrorRequest, rados, + "InjectECErrorRequest", inject_inbl, + &inject_outbl, formatter.get()); + ceph_assert(rc == 0); + } else { + ceph_abort_msg("Unsupported inject type"); + } + break; + } + case OpType::InjectWriteError: { + InjectWriteErrorOp& errorOp = static_cast<InjectWriteErrorOp&>(op); + + if (errorOp.type == 0) { + ceph::messaging::osd::InjectECErrorRequest< + InjectOpType::WriteFailAndRollback> + injectErrorRequest{pool, oid, errorOp.shard, + errorOp.type, errorOp.when, errorOp.duration}; + int rc = send_osd_command(osd, injectErrorRequest, rados, + "InjectECErrorRequest", inject_inbl, + &inject_outbl, formatter.get()); + ceph_assert(rc == 0); + } else if (errorOp.type == 3) { + ceph::messaging::osd::InjectECErrorRequest<InjectOpType::WriteOSDAbort> + injectErrorRequest{pool, oid, errorOp.shard, + errorOp.type, errorOp.when, errorOp.duration}; + int rc = send_osd_command(osd, injectErrorRequest, rados, + "InjectECErrorRequest", inject_inbl, + &inject_outbl, formatter.get()); + ceph_assert(rc == 0); + + // This inject is sent directly to the shard we want to inject the error + // on + osd = shard_order[errorOp.shard]; + } else { + ceph_abort("Unsupported inject type"); + } + + break; + } + case OpType::ClearReadErrorInject: { + ClearReadErrorInjectOp& errorOp = + static_cast<ClearReadErrorInjectOp&>(op); + + if (errorOp.type == 0) { + ceph::messaging::osd::InjectECClearErrorRequest<InjectOpType::ReadEIO> + clearErrorInject{pool, oid, errorOp.shard, errorOp.type}; + int rc = send_osd_command(osd, clearErrorInject, rados, + "InjectECClearErrorRequest", inject_inbl, + &inject_outbl, formatter.get()); + ceph_assert(rc == 0); + } else if (errorOp.type == 1) { + ceph::messaging::osd::InjectECClearErrorRequest< + InjectOpType::ReadMissingShard> + clearErrorInject{pool, oid, errorOp.shard, errorOp.type}; + int rc = send_osd_command(osd, clearErrorInject, rados, + "InjectECClearErrorRequest", inject_inbl, + &inject_outbl, formatter.get()); + ceph_assert(rc == 0); + } else { + ceph_abort("Unsupported inject type"); + } + + break; + } + case OpType::ClearWriteErrorInject: { + ClearReadErrorInjectOp& errorOp = + static_cast<ClearReadErrorInjectOp&>(op); + + if (errorOp.type == 0) { + ceph::messaging::osd::InjectECClearErrorRequest< + InjectOpType::WriteFailAndRollback> + clearErrorInject{pool, oid, errorOp.shard, errorOp.type}; + int rc = send_osd_command(osd, clearErrorInject, rados, + "InjectECClearErrorRequest", inject_inbl, + &inject_outbl, formatter.get()); + ceph_assert(rc == 0); + } else if (errorOp.type == 3) { + ceph::messaging::osd::InjectECClearErrorRequest< + InjectOpType::WriteOSDAbort> + clearErrorInject{pool, oid, errorOp.shard, errorOp.type}; + int rc = send_osd_command(osd, clearErrorInject, rados, + "InjectECClearErrorRequest", inject_inbl, + &inject_outbl, formatter.get()); + ceph_assert(rc == 0); + } else { + ceph_abort("Unsupported inject type"); + } + + break; + } + default: + ceph_abort_msg( + fmt::format("Unsupported inject operation ({})", op.getOpType())); + break; + } +}
\ No newline at end of file diff --git a/src/common/io_exerciser/RadosIo.h b/src/common/io_exerciser/RadosIo.h index 179c5bba3ae..a5c66ad4768 100644 --- a/src/common/io_exerciser/RadosIo.h +++ b/src/common/io_exerciser/RadosIo.h @@ -10,71 +10,65 @@ * in the object. Uses DataBuffer to create and validate * data buffers. When there are not barrier I/Os this may * issue multiple async I/Os in parallel. - * + * */ namespace ceph { - namespace io_exerciser { - namespace data_generation { - class DataGenerator; - } - - class RadosIo: public Model { - protected: - librados::Rados& rados; - boost::asio::io_context& asio; - std::unique_ptr<ObjectModel> om; - std::unique_ptr<ceph::io_exerciser::data_generation::DataGenerator> db; - std::string pool; - int threads; - ceph::mutex& lock; - ceph::condition_variable& cond; - librados::IoCtx io; - int outstanding_io; +namespace io_exerciser { +namespace data_generation { +class DataGenerator; +} + +class RadosIo : public Model { + protected: + librados::Rados& rados; + boost::asio::io_context& asio; + std::unique_ptr<ObjectModel> om; + std::unique_ptr<ceph::io_exerciser::data_generation::DataGenerator> db; + std::string pool; + std::optional<std::vector<int>> cached_shard_order; + int threads; + ceph::mutex& lock; + ceph::condition_variable& cond; + librados::IoCtx io; + int outstanding_io; + + void start_io(); + void finish_io(); + void wait_for_io(int count); + + public: + RadosIo(librados::Rados& rados, boost::asio::io_context& asio, + const std::string& pool, const std::string& oid, + const std::optional<std::vector<int>>& cached_shard_order, + uint64_t block_size, int seed, int threads, ceph::mutex& lock, + ceph::condition_variable& cond); - void start_io(); - void finish_io(); - void wait_for_io(int count); - - public: - RadosIo(librados::Rados& rados, - boost::asio::io_context& asio, - const std::string& pool, - const std::string& oid, - uint64_t block_size, - int seed, - int threads, - ceph::mutex& lock, - ceph::condition_variable& cond); + ~RadosIo(); - ~RadosIo(); + void allow_ec_overwrites(bool allow); - void allow_ec_overwrites(bool allow); + template <int N> + class AsyncOpInfo { + public: + librados::ObjectReadOperation rop; + librados::ObjectWriteOperation wop; + std::array<ceph::bufferlist, N> bufferlist; + std::array<uint64_t, N> offset; + std::array<uint64_t, N> length; - class AsyncOpInfo { - public: - librados::ObjectReadOperation rop; - librados::ObjectWriteOperation wop; - ceph::buffer::list bl1; - ceph::buffer::list bl2; - ceph::buffer::list bl3; - uint64_t offset1; - uint64_t length1; - uint64_t offset2; - uint64_t length2; - uint64_t offset3; - uint64_t length3; + AsyncOpInfo(const std::array<uint64_t, N>& offset = {}, + const std::array<uint64_t, N>& length = {}); + ~AsyncOpInfo() = default; + }; - AsyncOpInfo(uint64_t offset1 = 0, uint64_t length1 = 0, - uint64_t offset2 = 0, uint64_t length2 = 0, - uint64_t offset3 = 0, uint64_t length3 = 0 ); - ~AsyncOpInfo() = default; - }; + // Must be called with lock held + bool readyForIoOp(IoOp& op); + void applyIoOp(IoOp& op); - // Must be called with lock held - bool readyForIoOp(IoOp& op); - - void applyIoOp(IoOp& op); - }; - } -}
\ No newline at end of file + private: + void applyReadWriteOp(IoOp& op); + void applyInjectOp(IoOp& op); +}; +} // namespace io_exerciser +} // namespace ceph
\ No newline at end of file diff --git a/src/common/json/BalancerStructures.cc b/src/common/json/BalancerStructures.cc new file mode 100644 index 00000000000..48dfb843761 --- /dev/null +++ b/src/common/json/BalancerStructures.cc @@ -0,0 +1,38 @@ +#include "BalancerStructures.h" + +#include "common/ceph_json.h" + +using namespace ceph::messaging::balancer; + +void BalancerOffRequest::dump(Formatter* f) const { + encode_json("prefix", "balancer off", f); +} + +void BalancerOffRequest::decode_json(JSONObj* obj) {} + +void BalancerStatusRequest::dump(Formatter* f) const { + encode_json("prefix", "balancer status", f); +} + +void BalancerStatusRequest::decode_json(JSONObj* obj) {} + +void BalancerStatusReply::dump(Formatter* f) const { + encode_json("active", active, f); + encode_json("last_optimization_duration", last_optimization_duration, f); + encode_json("last_optimization_started", last_optimization_started, f); + encode_json("mode", mode, f); + encode_json("no_optimization_needed", no_optimization_needed, f); + encode_json("optimize_result", optimize_result, f); +} + +void BalancerStatusReply::decode_json(JSONObj* obj) { + JSONDecoder::decode_json("active", active, obj); + JSONDecoder::decode_json("last_optimization_duration", + last_optimization_duration, obj); + JSONDecoder::decode_json("last_optimization_started", + last_optimization_started, obj); + JSONDecoder::decode_json("mode", mode, obj); + JSONDecoder::decode_json("no_optimization_needed", no_optimization_needed, + obj); + JSONDecoder::decode_json("optimize_result", optimize_result, obj); +}
\ No newline at end of file diff --git a/src/common/json/BalancerStructures.h b/src/common/json/BalancerStructures.h new file mode 100644 index 00000000000..bbf5c748eb3 --- /dev/null +++ b/src/common/json/BalancerStructures.h @@ -0,0 +1,35 @@ +#pragma once + +#include <string> + +#include "include/types.h" + +class JSONObj; + +namespace ceph { +namespace messaging { +namespace balancer { +struct BalancerOffRequest { + void dump(Formatter* f) const; + void decode_json(JSONObj* obj); +}; + +struct BalancerStatusRequest { + void dump(Formatter* f) const; + void decode_json(JSONObj* obj); +}; + +struct BalancerStatusReply { + bool active; + std::string last_optimization_duration; + std::string last_optimization_started; + std::string mode; + bool no_optimization_needed; + std::string optimize_result; + + void dump(Formatter* f) const; + void decode_json(JSONObj* obj); +}; +} // namespace balancer +} // namespace messaging +} // namespace ceph
\ No newline at end of file diff --git a/src/common/json/CMakeLists.txt b/src/common/json/CMakeLists.txt new file mode 100644 index 00000000000..1497daf93db --- /dev/null +++ b/src/common/json/CMakeLists.txt @@ -0,0 +1,4 @@ +add_library(json_structures STATIC + BalancerStructures.cc ConfigStructures.cc OSDStructures.cc) + + target_link_libraries(json_structures global)
\ No newline at end of file diff --git a/src/common/json/ConfigStructures.cc b/src/common/json/ConfigStructures.cc new file mode 100644 index 00000000000..651278d002a --- /dev/null +++ b/src/common/json/ConfigStructures.cc @@ -0,0 +1,20 @@ +#include "ConfigStructures.h" + +#include "common/ceph_json.h" + +using namespace ceph::messaging::config; + +void ConfigSetRequest::dump(Formatter* f) const { + encode_json("prefix", "config set", f); + encode_json("who", who, f); + encode_json("name", name, f); + encode_json("value", value, f); + encode_json("force", force, f); +} + +void ConfigSetRequest::decode_json(JSONObj* obj) { + JSONDecoder::decode_json("who", who, obj); + JSONDecoder::decode_json("name", name, obj); + JSONDecoder::decode_json("value", value, obj); + JSONDecoder::decode_json("force", force, obj); +}
\ No newline at end of file diff --git a/src/common/json/ConfigStructures.h b/src/common/json/ConfigStructures.h new file mode 100644 index 00000000000..554229d75f4 --- /dev/null +++ b/src/common/json/ConfigStructures.h @@ -0,0 +1,24 @@ +#pragma once + +#include <optional> +#include <string> + +#include "include/types.h" + +class JSONObj; + +namespace ceph { +namespace messaging { +namespace config { +struct ConfigSetRequest { + std::string who; + std::string name; + std::string value; + std::optional<bool> force; + + void dump(Formatter* f) const; + void decode_json(JSONObj* obj); +}; +} // namespace config +} // namespace messaging +} // namespace ceph
\ No newline at end of file diff --git a/src/common/json/OSDStructures.cc b/src/common/json/OSDStructures.cc new file mode 100644 index 00000000000..aaac5f6e169 --- /dev/null +++ b/src/common/json/OSDStructures.cc @@ -0,0 +1,150 @@ +#include "OSDStructures.h" + +#include "common/ceph_json.h" +#include "common/io_exerciser/OpType.h" + +using namespace ceph::messaging::osd; + +void OSDMapRequest::dump(Formatter* f) const { + encode_json("prefix", "osd map", f); + encode_json("pool", pool, f); + encode_json("object", object, f); + encode_json("nspace", nspace, f); + encode_json("format", format, f); +} + +void OSDMapRequest::decode_json(JSONObj* obj) { + JSONDecoder::decode_json("pool", pool, obj); + JSONDecoder::decode_json("object", object, obj); + JSONDecoder::decode_json("nspace", nspace, obj); + JSONDecoder::decode_json("format", format, obj); +} + +void OSDMapReply::dump(Formatter* f) const { + encode_json("epoch", epoch, f); + encode_json("pool", pool, f); + encode_json("pool_id", pool_id, f); + encode_json("objname", objname, f); + encode_json("raw_pgid", raw_pgid, f); + encode_json("pgid", pgid, f); + encode_json("up", up, f); + encode_json("up_primary", up_primary, f); + encode_json("acting", acting, f); + encode_json("acting_primary", acting_primary, f); +} + +void OSDMapReply::decode_json(JSONObj* obj) { + JSONDecoder::decode_json("epoch", epoch, obj); + JSONDecoder::decode_json("pool", pool, obj); + JSONDecoder::decode_json("pool_id", pool_id, obj); + JSONDecoder::decode_json("objname", objname, obj); + JSONDecoder::decode_json("raw_pgid", raw_pgid, obj); + JSONDecoder::decode_json("pgid", pgid, obj); + JSONDecoder::decode_json("up", up, obj); + JSONDecoder::decode_json("up_primary", up_primary, obj); + JSONDecoder::decode_json("acting", acting, obj); + JSONDecoder::decode_json("acting_primary", acting_primary, obj); +} + +void OSDPoolGetRequest::dump(Formatter* f) const { + encode_json("prefix", "osd pool get", f); + encode_json("pool", pool, f); + encode_json("var", var, f); + encode_json("format", format, f); +} + +void OSDPoolGetRequest::decode_json(JSONObj* obj) { + JSONDecoder::decode_json("pool", pool, obj); + JSONDecoder::decode_json("var", var, obj); + JSONDecoder::decode_json("format", format, obj); +} + +void OSDPoolGetReply::dump(Formatter* f) const { + encode_json("erasure_code_profile", erasure_code_profile, f); +} + +void OSDPoolGetReply::decode_json(JSONObj* obj) { + JSONDecoder::decode_json("erasure_code_profile", erasure_code_profile, obj); +} + +void OSDECProfileGetRequest::dump(Formatter* f) const { + encode_json("prefix", "osd pool get", f); + encode_json("name", name, f); + encode_json("format", format, f); +} + +void OSDECProfileGetRequest::decode_json(JSONObj* obj) { + JSONDecoder::decode_json("name", name, obj); + JSONDecoder::decode_json("format", format, obj); +} + +void OSDECProfileGetReply::dump(Formatter* f) const { + encode_json("crush-device-class", crush_device_class, f); + encode_json("crush-failure-domain", crush_failure_domain, f); + encode_json("crush-num-failure-domains", crush_num_failure_domains, f); + encode_json("crush-osds-per-failure-domain", crush_osds_per_failure_domain, + f); + encode_json("crush-root", crush_root, f); + encode_json("jerasure-per-chunk-alignment", jerasure_per_chunk_alignment, f); + encode_json("k", k, f); + encode_json("m", m, f); + encode_json("plugin", plugin, f); + encode_json("technique", technique, f); + encode_json("w", w, f); +} + +void OSDECProfileGetReply::decode_json(JSONObj* obj) { + JSONDecoder::decode_json("crush-device-class", crush_device_class, obj); + JSONDecoder::decode_json("crush-failure-domain", crush_failure_domain, obj); + JSONDecoder::decode_json("crush-num-failure-domains", + crush_num_failure_domains, obj); + JSONDecoder::decode_json("crush-osds-per-failure-domain", + crush_osds_per_failure_domain, obj); + JSONDecoder::decode_json("crush-root", crush_root, obj); + JSONDecoder::decode_json("jerasure-per-chunk-alignment", + jerasure_per_chunk_alignment, obj); + JSONDecoder::decode_json("k", k, obj); + JSONDecoder::decode_json("m", m, obj); + JSONDecoder::decode_json("plugin", plugin, obj); + JSONDecoder::decode_json("technique", technique, obj); + JSONDecoder::decode_json("w", w, obj); +} + +void OSDECProfileSetRequest::dump(Formatter* f) const { + encode_json("prefix", "osd erasure-code-profile set", f); + encode_json("name", name, f); + encode_json("profile", profile, f); +} + +void OSDECProfileSetRequest::decode_json(JSONObj* obj) { + JSONDecoder::decode_json("name", name, obj); + JSONDecoder::decode_json("profile", profile, obj); +} + +void OSDECPoolCreateRequest::dump(Formatter* f) const { + encode_json("prefix", "osd pool create", f); + encode_json("pool", pool, f); + encode_json("pool_type", pool_type, f); + encode_json("pg_num", pg_num, f); + encode_json("pgp_num", pgp_num, f); + encode_json("erasure_code_profile", erasure_code_profile, f); +} + +void OSDECPoolCreateRequest::decode_json(JSONObj* obj) { + JSONDecoder::decode_json("pool", pool, obj); + JSONDecoder::decode_json("pool_type", pool_type, obj); + JSONDecoder::decode_json("pg_num", pg_num, obj); + JSONDecoder::decode_json("pgp_num", pgp_num, obj); + JSONDecoder::decode_json("erasure_code_profile", erasure_code_profile, obj); +} + +void OSDSetRequest::dump(Formatter* f) const { + encode_json("prefix", "osd set", f); + encode_json("key", key, f); + encode_json("yes_i_really_mean_it", yes_i_really_mean_it, f); +} + +void OSDSetRequest::decode_json(JSONObj* obj) { + JSONDecoder::decode_json("key", key, obj); + JSONDecoder::decode_json("yes_i_really_mean_it", yes_i_really_mean_it, obj); +}
\ No newline at end of file diff --git a/src/common/json/OSDStructures.h b/src/common/json/OSDStructures.h new file mode 100644 index 00000000000..3e4528a099f --- /dev/null +++ b/src/common/json/OSDStructures.h @@ -0,0 +1,189 @@ +#pragma once + +#include <memory> +#include <string> +#include <vector> + +#include "common/ceph_json.h" +#include "common/io_exerciser/OpType.h" +#include "include/types.h" + +class JSONObj; + +namespace ceph { +namespace messaging { +namespace osd { +struct OSDMapRequest { + std::string pool; + std::string object; + std::string nspace; + std::string format = "json"; + + void dump(Formatter* f) const; + void decode_json(JSONObj* obj); +}; + +struct OSDMapReply { + epoch_t epoch; + std::string pool; + uint64_t pool_id; + std::string objname; + std::string raw_pgid; + std::string pgid; + std::vector<int> up; + int up_primary; + std::vector<int> acting; + int acting_primary; + + void dump(Formatter* f) const; + void decode_json(JSONObj* obj); +}; + +struct OSDPoolGetRequest { + std::string pool; + std::string var = "erasure_code_profile"; + std::string format = "json"; + + void dump(Formatter* f) const; + void decode_json(JSONObj* obj); +}; + +struct OSDPoolGetReply { + std::string erasure_code_profile; + + void dump(Formatter* f) const; + void decode_json(JSONObj* obj); +}; + +struct OSDECProfileGetRequest { + std::string name; + std::string format = "json"; + + void dump(Formatter* f) const; + void decode_json(JSONObj* obj); +}; + +struct OSDECProfileGetReply { + std::string crush_device_class; + std::string crush_failure_domain; + int crush_num_failure_domains; + int crush_osds_per_failure_domain; + std::string crush_root; + bool jerasure_per_chunk_alignment; + int k; + int m; + std::string plugin; + std::string technique; + std::string w; + + void dump(Formatter* f) const; + void decode_json(JSONObj* obj); +}; + +struct OSDECProfileSetRequest { + std::string name; + std::vector<std::string> profile; + + void dump(Formatter* f) const; + void decode_json(JSONObj* obj); +}; + +struct OSDECPoolCreateRequest { + std::string pool; + std::string pool_type; + int pg_num; + int pgp_num; + std::string erasure_code_profile; + + void dump(Formatter* f) const; + void decode_json(JSONObj* obj); +}; + +struct OSDSetRequest { + std::string key; + std::optional<bool> yes_i_really_mean_it = std::nullopt; + + void dump(Formatter* f) const; + void decode_json(JSONObj* obj); +}; + +// These structures are sent directly to the relevant OSD +// rather than the monitor +template <io_exerciser::InjectOpType op_type> +struct InjectECErrorRequest { + std::string pool; + std::string objname; + int shardid; + std::optional<uint64_t> type; + std::optional<uint64_t> when; + std::optional<uint64_t> duration; + + void dump(Formatter* f) const { + switch (op_type) { + case io_exerciser::InjectOpType::ReadEIO: + [[fallthrough]]; + case io_exerciser::InjectOpType::ReadMissingShard: + ::encode_json("prefix", "injectecreaderr", f); + break; + case io_exerciser::InjectOpType::WriteFailAndRollback: + [[fallthrough]]; + case io_exerciser::InjectOpType::WriteOSDAbort: + ::encode_json("prefix", "injectecwriteerr", f); + break; + default: + ceph_abort_msg("Unsupported Inject Type"); + } + ::encode_json("pool", pool, f); + ::encode_json("objname", objname, f); + ::encode_json("shardid", shardid, f); + ::encode_json("type", type, f); + ::encode_json("when", when, f); + ::encode_json("duration", duration, f); + } + void decode_json(JSONObj* obj) { + JSONDecoder::decode_json("pool", pool, obj); + JSONDecoder::decode_json("objname", objname, obj); + JSONDecoder::decode_json("shardid", shardid, obj); + JSONDecoder::decode_json("type", type, obj); + JSONDecoder::decode_json("when", when, obj); + JSONDecoder::decode_json("duration", duration, obj); + } +}; + +template <io_exerciser::InjectOpType op_type> +struct InjectECClearErrorRequest { + std::string pool; + std::string objname; + int shardid; + std::optional<uint64_t> type; + + void dump(Formatter* f) const { + switch (op_type) { + case io_exerciser::InjectOpType::ReadEIO: + [[fallthrough]]; + case io_exerciser::InjectOpType::ReadMissingShard: + ::encode_json("prefix", "injectecclearreaderr", f); + break; + case io_exerciser::InjectOpType::WriteFailAndRollback: + [[fallthrough]]; + case io_exerciser::InjectOpType::WriteOSDAbort: + ::encode_json("prefix", "injectecclearwriteerr", f); + break; + default: + ceph_abort_msg("Unsupported Inject Type"); + } + ::encode_json("pool", pool, f); + ::encode_json("objname", objname, f); + ::encode_json("shardid", shardid, f); + ::encode_json("type", type, f); + } + void decode_json(JSONObj* obj) { + JSONDecoder::decode_json("pool", pool, obj); + JSONDecoder::decode_json("objname", objname, obj); + JSONDecoder::decode_json("shardid", shardid, obj); + JSONDecoder::decode_json("type", type, obj); + } +}; +} // namespace osd +} // namespace messaging +} // namespace ceph
\ No newline at end of file diff --git a/src/common/pick_address.cc b/src/common/pick_address.cc index d125d7171e0..a0629a15686 100644 --- a/src/common/pick_address.cc +++ b/src/common/pick_address.cc @@ -642,17 +642,24 @@ int get_iface_numa_node( bool is_addr_in_subnet( CephContext *cct, const std::string &networks, - const std::string &addr) + const entity_addr_t &addr) { const auto nets = get_str_list(networks); ceph_assert(!nets.empty()); - unsigned ipv = CEPH_PICK_ADDRESS_IPV4; - struct sockaddr_in public_addr; - public_addr.sin_family = AF_INET; - - if(inet_pton(AF_INET, addr.c_str(), &public_addr.sin_addr) != 1) { - lderr(cct) << "unable to convert chosen address to string: " << addr << dendl; + struct sockaddr_in6 public_addr6; + struct sockaddr_in public_addr4; + + if (addr.is_ipv4() && + inet_pton(AF_INET, addr.ip_only_to_str().c_str(), &public_addr4.sin_addr) == 1) { + public_addr4.sin_family = AF_INET; + } else if (addr.is_ipv6() && + inet_pton(AF_INET6, addr.ip_only_to_str().c_str(), &public_addr6.sin6_addr) == 1) { + public_addr6.sin6_family = AF_INET6; + ipv = CEPH_PICK_ADDRESS_IPV6; + } else { + std::string_view addr_type = addr.is_ipv4() ? "IPv4" : "IPv6"; + lderr(cct) << "IP address " << addr << " is not parseable as " << addr_type << dendl; return false; } @@ -660,10 +667,16 @@ bool is_addr_in_subnet( struct ifaddrs ifa; memset(&ifa, 0, sizeof(ifa)); ifa.ifa_next = nullptr; - ifa.ifa_addr = (struct sockaddr*)&public_addr; + if (addr.is_ipv4()) { + ifa.ifa_addr = (struct sockaddr*)&public_addr4; + } else if (addr.is_ipv6()) { + ifa.ifa_addr = (struct sockaddr*)&public_addr6; + } + if(matches_with_net(cct, ifa, net, ipv)) { return true; } } + lderr(cct) << "address " << addr << " is not in networks '" << networks << "'" << dendl; return false; } diff --git a/src/common/pick_address.h b/src/common/pick_address.h index 40575d7d155..c28a6037ded 100644 --- a/src/common/pick_address.h +++ b/src/common/pick_address.h @@ -98,6 +98,6 @@ int get_iface_numa_node( bool is_addr_in_subnet( CephContext *cct, const std::string &networks, - const std::string &addr); + const entity_addr_t &addr); #endif diff --git a/src/crimson/os/alienstore/alien_store.cc b/src/crimson/os/alienstore/alien_store.cc index a9c69f4660e..db6decd84f9 100644 --- a/src/crimson/os/alienstore/alien_store.cc +++ b/src/crimson/os/alienstore/alien_store.cc @@ -435,8 +435,21 @@ auto AlienStore::omap_get_values(CollectionRef ch, return do_with_op_gate(omap_values_t{}, [=, this] (auto &values) { return tp->submit(ch->get_cid().hash_to_shard(tp->size()), [=, this, &values] { auto c = static_cast<AlienCollection*>(ch.get()); - return store->omap_get_values(c->collection, oid, start, - reinterpret_cast<map<string, bufferlist>*>(&values)); + return store->omap_iterate( + c->collection, oid, + ObjectStore::omap_iter_seek_t{ + .seek_position = start.value_or(std::string{}), + // FIXME: classical OSDs begins iteration from LOWER_BOUND + // (or UPPER_BOUND if filter_prefix > start). However, these + // bits are not implemented yet + .seek_type = ObjectStore::omap_iter_seek_t::UPPER_BOUND + }, + [&values] + (std::string_view key, std::string_view value) mutable { + values[std::string{key}].append(value); + // FIXME: there is limit on number of entries yet + return ObjectStore::omap_iter_ret_t::NEXT; + }); }).then([&values] (int r) -> read_errorator::future<std::tuple<bool, omap_values_t>> { if (r == -ENOENT) { diff --git a/src/crimson/os/seastore/CMakeLists.txt b/src/crimson/os/seastore/CMakeLists.txt index e5b8960c38c..3da5e65ceec 100644 --- a/src/crimson/os/seastore/CMakeLists.txt +++ b/src/crimson/os/seastore/CMakeLists.txt @@ -1,5 +1,6 @@ set(crimson_seastore_srcs cached_extent.cc + lba_mapping.cc seastore_types.cc segment_manager.cc segment_manager/ephemeral.cc @@ -19,7 +20,6 @@ set(crimson_seastore_srcs omap_manager.cc omap_manager/btree/btree_omap_manager.cc omap_manager/btree/omap_btree_node_impl.cc - btree/btree_range_pin.cc btree/fixed_kv_node.cc onode.cc onode_manager/staged-fltree/node.cc diff --git a/src/crimson/os/seastore/async_cleaner.h b/src/crimson/os/seastore/async_cleaner.h index 01ab44c4c7c..1cef771aeb8 100644 --- a/src/crimson/os/seastore/async_cleaner.h +++ b/src/crimson/os/seastore/async_cleaner.h @@ -17,6 +17,7 @@ #include "crimson/os/seastore/randomblock_manager_group.h" #include "crimson/os/seastore/transaction.h" #include "crimson/os/seastore/segment_seq_allocator.h" +#include "crimson/os/seastore/backref_mapping.h" namespace crimson::os::seastore { diff --git a/src/crimson/os/seastore/backref/btree_backref_manager.h b/src/crimson/os/seastore/backref/btree_backref_manager.h index 38084bb00e6..24897dd55da 100644 --- a/src/crimson/os/seastore/backref/btree_backref_manager.h +++ b/src/crimson/os/seastore/backref/btree_backref_manager.h @@ -9,44 +9,28 @@ namespace crimson::os::seastore::backref { -constexpr size_t BACKREF_BLOCK_SIZE = 4096; - -class BtreeBackrefMapping : public BtreeNodeMapping<paddr_t, laddr_t> { - extent_types_t type; +class BtreeBackrefMapping : public BackrefMapping { public: BtreeBackrefMapping(op_context_t<paddr_t> ctx) - : BtreeNodeMapping(ctx) {} + : BackrefMapping(ctx) {} BtreeBackrefMapping( op_context_t<paddr_t> ctx, CachedExtentRef parent, uint16_t pos, backref_map_val_t &val, backref_node_meta_t &&meta) - : BtreeNodeMapping( + : BackrefMapping( + val.type, ctx, parent, pos, val.laddr, val.len, - std::forward<backref_node_meta_t>(meta)), - type(val.type) - {} - extent_types_t get_type() const final { - return type; - } - - bool is_clone() const final { - return false; - } - -protected: - std::unique_ptr<BtreeNodeMapping<paddr_t, laddr_t>> _duplicate( - op_context_t<paddr_t> ctx) const final { - return std::unique_ptr<BtreeNodeMapping<paddr_t, laddr_t>>( - new BtreeBackrefMapping(ctx)); - } + std::forward<backref_node_meta_t>(meta)) {} }; +constexpr size_t BACKREF_BLOCK_SIZE = 4096; + using BackrefBtree = FixedKVBtree< paddr_t, backref_map_val_t, BackrefInternalNode, BackrefLeafNode, BtreeBackrefMapping, BACKREF_BLOCK_SIZE, false>; diff --git a/src/crimson/os/seastore/backref_manager.h b/src/crimson/os/seastore/backref_manager.h index 3feedb997b4..8c746b571b2 100644 --- a/src/crimson/os/seastore/backref_manager.h +++ b/src/crimson/os/seastore/backref_manager.h @@ -6,6 +6,7 @@ #include "crimson/os/seastore/cache.h" #include "crimson/os/seastore/cached_extent.h" #include "crimson/os/seastore/transaction.h" +#include "crimson/os/seastore/backref_mapping.h" namespace crimson::os::seastore { diff --git a/src/crimson/os/seastore/backref_mapping.h b/src/crimson/os/seastore/backref_mapping.h new file mode 100644 index 00000000000..d0a6a0ea6ff --- /dev/null +++ b/src/crimson/os/seastore/backref_mapping.h @@ -0,0 +1,27 @@ +// -*- mode:C++; tab-width:8; c-basic-offset:2; indent-tabs-mode:t -*- +// vim: ts=8 sw=2 smarttab + +#pragma once + +#include "crimson/os/seastore/btree/btree_range_pin.h" + +namespace crimson::os::seastore { + +class BackrefMapping : public BtreeNodeMapping<paddr_t, laddr_t> { + extent_types_t type; +public: + BackrefMapping(op_context_t<paddr_t> ctx) + : BtreeNodeMapping(ctx) {} + template <typename... T> + BackrefMapping(extent_types_t type, T&&... t) + : BtreeNodeMapping(std::forward<T>(t)...), + type(type) {} + extent_types_t get_type() const { + return type; + } +}; + +using BackrefMappingRef = std::unique_ptr<BackrefMapping>; +using backref_pin_list_t = std::list<BackrefMappingRef>; + +} // namespace crimson::os::seastore diff --git a/src/crimson/os/seastore/btree/btree_range_pin.cc b/src/crimson/os/seastore/btree/btree_range_pin.cc deleted file mode 100644 index f0d507a24c4..00000000000 --- a/src/crimson/os/seastore/btree/btree_range_pin.cc +++ /dev/null @@ -1,54 +0,0 @@ -// -*- mode:C++; tab-width:8; c-basic-offset:2; indent-tabs-mode:t -*- -// vim: ts=8 sw=2 smarttab - -#include "crimson/os/seastore/btree/btree_range_pin.h" -#include "crimson/os/seastore/btree/fixed_kv_node.h" - -namespace crimson::os::seastore { - -template <typename key_t, typename val_t> -get_child_ret_t<LogicalCachedExtent> -BtreeNodeMapping<key_t, val_t>::get_logical_extent( - Transaction &t) -{ - ceph_assert(is_parent_viewable()); - assert(pos != std::numeric_limits<uint16_t>::max()); - ceph_assert(t.get_trans_id() == ctx.trans.get_trans_id()); - auto &p = (FixedKVNode<key_t>&)*parent; - auto k = this->is_indirect() - ? this->get_intermediate_base() - : get_key(); - auto v = p.template get_child<LogicalCachedExtent>(ctx, pos, k); - if (!v.has_child()) { - this->child_pos = v.get_child_pos(); - } - return v; -} - -template <typename key_t, typename val_t> -bool BtreeNodeMapping<key_t, val_t>::is_stable() const -{ - assert(!this->parent_modified()); - assert(pos != std::numeric_limits<uint16_t>::max()); - auto &p = (FixedKVNode<key_t>&)*parent; - auto k = this->is_indirect() - ? this->get_intermediate_base() - : get_key(); - return p.is_child_stable(ctx, pos, k); -} - -template <typename key_t, typename val_t> -bool BtreeNodeMapping<key_t, val_t>::is_data_stable() const -{ - assert(!this->parent_modified()); - assert(pos != std::numeric_limits<uint16_t>::max()); - auto &p = (FixedKVNode<key_t>&)*parent; - auto k = this->is_indirect() - ? this->get_intermediate_base() - : get_key(); - return p.is_child_data_stable(ctx, pos, k); -} - -template class BtreeNodeMapping<laddr_t, paddr_t>; -template class BtreeNodeMapping<paddr_t, laddr_t>; -} // namespace crimson::os::seastore diff --git a/src/crimson/os/seastore/btree/btree_range_pin.h b/src/crimson/os/seastore/btree/btree_range_pin.h index 91751801e5d..bfd350a8bed 100644 --- a/src/crimson/os/seastore/btree/btree_range_pin.h +++ b/src/crimson/os/seastore/btree/btree_range_pin.h @@ -7,11 +7,12 @@ #include "crimson/common/log.h" -#include "crimson/os/seastore/cache.h" #include "crimson/os/seastore/cached_extent.h" #include "crimson/os/seastore/seastore_types.h" +#include "crimson/os/seastore/transaction.h" namespace crimson::os::seastore { +class Cache; template <typename node_key_t> struct op_context_t { @@ -116,8 +117,6 @@ protected: extent_len_t len = 0; fixed_kv_node_meta_t<key_t> range; uint16_t pos = std::numeric_limits<uint16_t>::max(); - - virtual std::unique_ptr<BtreeNodeMapping> _duplicate(op_context_t<key_t>) const = 0; fixed_kv_node_meta_t<key_t> _get_pin_range() const { return range; } @@ -139,11 +138,7 @@ public: len(len), range(meta), pos(pos) - { - if (!parent->is_pending()) { - this->child_pos = {parent, pos}; - } - } + {} CachedExtentRef get_parent() const final { return parent; @@ -162,11 +157,6 @@ public: return len; } - extent_types_t get_type() const override { - ceph_abort("should never happen"); - return extent_types_t::ROOT; - } - val_t get_val() const final { if constexpr (std::is_same_v<val_t, paddr_t>) { return value.get_paddr(); @@ -180,16 +170,6 @@ public: return range.begin; } - PhysicalNodeMappingRef<key_t, val_t> duplicate() const final { - auto ret = _duplicate(ctx); - ret->range = range; - ret->value = value; - ret->parent = parent; - ret->len = len; - ret->pos = pos; - return ret; - } - bool has_been_invalidated() const final { return parent->has_been_invalidated(); } @@ -215,9 +195,6 @@ public: return unviewable; } - get_child_ret_t<LogicalCachedExtent> get_logical_extent(Transaction&) final; - bool is_stable() const final; - bool is_data_stable() const final; bool is_parent_viewable() const final { ceph_assert(parent); if (!parent->is_valid()) { diff --git a/src/crimson/os/seastore/cached_extent.cc b/src/crimson/os/seastore/cached_extent.cc index ab2492f5bb6..49fede1d9a8 100644 --- a/src/crimson/os/seastore/cached_extent.cc +++ b/src/crimson/os/seastore/cached_extent.cc @@ -7,6 +7,7 @@ #include "crimson/common/log.h" #include "crimson/os/seastore/btree/fixed_kv_node.h" +#include "crimson/os/seastore/lba_mapping.h" namespace { [[maybe_unused]] seastar::logger& logger() { @@ -142,6 +143,12 @@ void LogicalCachedExtent::on_replace_prior() { parent->children[off] = this; } +void LogicalCachedExtent::maybe_set_intermediate_laddr(LBAMapping &mapping) { + laddr = mapping.is_indirect() + ? mapping.get_intermediate_base() + : mapping.get_key(); +} + parent_tracker_t::~parent_tracker_t() { // this is parent's tracker, reset it auto &p = (FixedKVNode<laddr_t>&)*parent; @@ -150,32 +157,6 @@ parent_tracker_t::~parent_tracker_t() { } } -std::ostream &operator<<(std::ostream &out, const LBAMapping &rhs) -{ - out << "LBAMapping(" << rhs.get_key() - << "~0x" << std::hex << rhs.get_length() << std::dec - << "->" << rhs.get_val(); - if (rhs.is_indirect()) { - out << ",indirect(" << rhs.get_intermediate_base() - << "~0x" << std::hex << rhs.get_intermediate_length() - << "@0x" << rhs.get_intermediate_offset() << std::dec - << ")"; - } - out << ")"; - return out; -} - -std::ostream &operator<<(std::ostream &out, const lba_pin_list_t &rhs) -{ - bool first = true; - out << '['; - for (const auto &i: rhs) { - out << (first ? "" : ",") << *i; - first = false; - } - return out << ']'; -} - bool BufferSpace::is_range_loaded(extent_len_t offset, extent_len_t length) const { assert(length > 0); diff --git a/src/crimson/os/seastore/cached_extent.h b/src/crimson/os/seastore/cached_extent.h index f9356f40b83..9dc60d719eb 100644 --- a/src/crimson/os/seastore/cached_extent.h +++ b/src/crimson/os/seastore/cached_extent.h @@ -1279,7 +1279,6 @@ private: }; class ChildableCachedExtent; -class LogicalCachedExtent; class child_pos_t { public: @@ -1337,48 +1336,18 @@ using PhysicalNodeMappingRef = std::unique_ptr<PhysicalNodeMapping<key_t, val_t> template <typename key_t, typename val_t> class PhysicalNodeMapping { public: + PhysicalNodeMapping() = default; + PhysicalNodeMapping(const PhysicalNodeMapping&) = delete; virtual extent_len_t get_length() const = 0; - virtual extent_types_t get_type() const = 0; virtual val_t get_val() const = 0; virtual key_t get_key() const = 0; - virtual PhysicalNodeMappingRef<key_t, val_t> duplicate() const = 0; - virtual PhysicalNodeMappingRef<key_t, val_t> refresh_with_pending_parent() { - ceph_abort("impossible"); - return {}; - } virtual bool has_been_invalidated() const = 0; virtual CachedExtentRef get_parent() const = 0; virtual uint16_t get_pos() const = 0; - // An lba pin may be indirect, see comments in lba_manager/btree/btree_lba_manager.h - virtual bool is_indirect() const { return false; } - virtual key_t get_intermediate_key() const { return min_max_t<key_t>::null; } - virtual key_t get_intermediate_base() const { return min_max_t<key_t>::null; } - virtual extent_len_t get_intermediate_length() const { return 0; } virtual uint32_t get_checksum() const { ceph_abort("impossible"); return 0; } - // The start offset of the pin, must be 0 if the pin is not indirect - virtual extent_len_t get_intermediate_offset() const { - return std::numeric_limits<extent_len_t>::max(); - } - - virtual get_child_ret_t<LogicalCachedExtent> - get_logical_extent(Transaction &t) = 0; - - void link_child(ChildableCachedExtent *c) { - ceph_assert(child_pos); - child_pos->link_child(c); - } - - // For reserved mappings, the return values are - // undefined although it won't crash - virtual bool is_stable() const = 0; - virtual bool is_data_stable() const = 0; - virtual bool is_clone() const = 0; - bool is_zero_reserved() const { - return !get_val().is_real(); - } virtual bool is_parent_viewable() const = 0; virtual bool is_parent_valid() const = 0; virtual bool parent_modified() const { @@ -1391,24 +1360,8 @@ public: } virtual ~PhysicalNodeMapping() {} -protected: - std::optional<child_pos_t> child_pos = std::nullopt; }; -using LBAMapping = PhysicalNodeMapping<laddr_t, paddr_t>; -using LBAMappingRef = PhysicalNodeMappingRef<laddr_t, paddr_t>; - -std::ostream &operator<<(std::ostream &out, const LBAMapping &rhs); - -using lba_pin_list_t = std::list<LBAMappingRef>; - -std::ostream &operator<<(std::ostream &out, const lba_pin_list_t &rhs); - -using BackrefMapping = PhysicalNodeMapping<paddr_t, laddr_t>; -using BackrefMappingRef = PhysicalNodeMappingRef<paddr_t, laddr_t>; - -using backref_pin_list_t = std::list<BackrefMappingRef>; - /** * RetiredExtentPlaceholder * @@ -1522,6 +1475,8 @@ private: return out; } }; + +class LBAMapping; /** * LogicalCachedExtent * @@ -1556,11 +1511,7 @@ public: laddr = nladdr; } - void maybe_set_intermediate_laddr(LBAMapping &mapping) { - laddr = mapping.is_indirect() - ? mapping.get_intermediate_base() - : mapping.get_key(); - } + void maybe_set_intermediate_laddr(LBAMapping &mapping); void apply_delta_and_adjust_crc( paddr_t base, const ceph::bufferlist &bl) final { @@ -1660,8 +1611,6 @@ using lextent_list_t = addr_extent_list_base_t< } #if FMT_VERSION >= 90000 -template <> struct fmt::formatter<crimson::os::seastore::lba_pin_list_t> : fmt::ostream_formatter {}; template <> struct fmt::formatter<crimson::os::seastore::CachedExtent> : fmt::ostream_formatter {}; template <> struct fmt::formatter<crimson::os::seastore::LogicalCachedExtent> : fmt::ostream_formatter {}; -template <> struct fmt::formatter<crimson::os::seastore::LBAMapping> : fmt::ostream_formatter {}; #endif diff --git a/src/crimson/os/seastore/lba_manager.h b/src/crimson/os/seastore/lba_manager.h index a050b2cdf47..9a34bf56157 100644 --- a/src/crimson/os/seastore/lba_manager.h +++ b/src/crimson/os/seastore/lba_manager.h @@ -19,6 +19,7 @@ #include "crimson/os/seastore/cache.h" #include "crimson/os/seastore/seastore_types.h" +#include "crimson/os/seastore/lba_mapping.h" namespace crimson::os::seastore { diff --git a/src/crimson/os/seastore/lba_manager/btree/btree_lba_manager.cc b/src/crimson/os/seastore/lba_manager/btree/btree_lba_manager.cc index 007737ff450..888d3c359ac 100644 --- a/src/crimson/os/seastore/lba_manager/btree/btree_lba_manager.cc +++ b/src/crimson/os/seastore/lba_manager/btree/btree_lba_manager.cc @@ -94,6 +94,45 @@ void unlink_phy_tree_root_node<laddr_t>(RootBlockRef &root_block) { namespace crimson::os::seastore::lba_manager::btree { +get_child_ret_t<LogicalCachedExtent> +BtreeLBAMapping::get_logical_extent(Transaction &t) +{ + ceph_assert(is_parent_viewable()); + assert(pos != std::numeric_limits<uint16_t>::max()); + ceph_assert(t.get_trans_id() == ctx.trans.get_trans_id()); + auto &p = static_cast<LBALeafNode&>(*parent); + auto k = this->is_indirect() + ? this->get_intermediate_base() + : get_key(); + auto v = p.template get_child<LogicalCachedExtent>(ctx, pos, k); + if (!v.has_child()) { + this->child_pos = v.get_child_pos(); + } + return v; +} + +bool BtreeLBAMapping::is_stable() const +{ + assert(!this->parent_modified()); + assert(pos != std::numeric_limits<uint16_t>::max()); + auto &p = static_cast<LBALeafNode&>(*parent); + auto k = this->is_indirect() + ? this->get_intermediate_base() + : get_key(); + return p.is_child_stable(ctx, pos, k); +} + +bool BtreeLBAMapping::is_data_stable() const +{ + assert(!this->parent_modified()); + assert(pos != std::numeric_limits<uint16_t>::max()); + auto &p = static_cast<LBALeafNode&>(*parent); + auto k = this->is_indirect() + ? this->get_intermediate_base() + : get_key(); + return p.is_child_data_stable(ctx, pos, k); +} + BtreeLBAManager::mkfs_ret BtreeLBAManager::mkfs( Transaction &t) diff --git a/src/crimson/os/seastore/lba_manager/btree/btree_lba_manager.h b/src/crimson/os/seastore/lba_manager/btree/btree_lba_manager.h index ef10ff9623b..e0902053d0e 100644 --- a/src/crimson/os/seastore/lba_manager/btree/btree_lba_manager.h +++ b/src/crimson/os/seastore/lba_manager/btree/btree_lba_manager.h @@ -23,11 +23,15 @@ #include "crimson/os/seastore/lba_manager/btree/lba_btree_node.h" #include "crimson/os/seastore/btree/btree_range_pin.h" +namespace crimson::os::seastore { +class LogicalCachedExtent; +} + namespace crimson::os::seastore::lba_manager::btree { struct LBALeafNode; -class BtreeLBAMapping : public BtreeNodeMapping<laddr_t, paddr_t> { +class BtreeLBAMapping : public LBAMapping { // To support cloning, there are two kinds of lba mappings: // 1. physical lba mapping: the pladdr in the value of which is the paddr of // the corresponding extent; @@ -61,14 +65,14 @@ class BtreeLBAMapping : public BtreeNodeMapping<laddr_t, paddr_t> { // their keys. public: BtreeLBAMapping(op_context_t<laddr_t> ctx) - : BtreeNodeMapping(ctx) {} + : LBAMapping(ctx) {} BtreeLBAMapping( op_context_t<laddr_t> c, LBALeafNodeRef parent, uint16_t pos, lba_map_val_t &val, lba_node_meta_t meta) - : BtreeNodeMapping( + : LBAMapping( c, parent, pos, @@ -190,8 +194,12 @@ public: SUBDEBUGT(seastore_lba, "new pin {}", ctx.trans, static_cast<LBAMapping&>(*new_pin)); return new_pin; } + bool is_stable() const final; + bool is_data_stable() const final; + get_child_ret_t<LogicalCachedExtent> get_logical_extent(Transaction &t); + protected: - std::unique_ptr<BtreeNodeMapping<laddr_t, paddr_t>> _duplicate( + LBAMappingRef _duplicate( op_context_t<laddr_t> ctx) const final { auto pin = std::unique_ptr<BtreeLBAMapping>(new BtreeLBAMapping(ctx)); pin->key = key; diff --git a/src/crimson/os/seastore/lba_mapping.cc b/src/crimson/os/seastore/lba_mapping.cc new file mode 100644 index 00000000000..90fae09ce21 --- /dev/null +++ b/src/crimson/os/seastore/lba_mapping.cc @@ -0,0 +1,44 @@ +// -*- mode:C++; tab-width:8; c-basic-offset:2; indent-tabs-mode:t -*- +// vim: ts=8 sw=2 smarttab + +#include "lba_mapping.h" + +namespace crimson::os::seastore { + +std::ostream &operator<<(std::ostream &out, const LBAMapping &rhs) +{ + out << "LBAMapping(" << rhs.get_key() + << "~0x" << std::hex << rhs.get_length() << std::dec + << "->" << rhs.get_val(); + if (rhs.is_indirect()) { + out << ",indirect(" << rhs.get_intermediate_base() + << "~0x" << std::hex << rhs.get_intermediate_length() + << "@0x" << rhs.get_intermediate_offset() << std::dec + << ")"; + } + out << ")"; + return out; +} + +std::ostream &operator<<(std::ostream &out, const lba_pin_list_t &rhs) +{ + bool first = true; + out << '['; + for (const auto &i: rhs) { + out << (first ? "" : ",") << *i; + first = false; + } + return out << ']'; +} + +LBAMappingRef LBAMapping::duplicate() const { + auto ret = _duplicate(ctx); + ret->range = range; + ret->value = value; + ret->parent = parent; + ret->len = len; + ret->pos = pos; + return ret; +} + +} // namespace crimson::os::seastore diff --git a/src/crimson/os/seastore/lba_mapping.h b/src/crimson/os/seastore/lba_mapping.h new file mode 100644 index 00000000000..338d4d53f55 --- /dev/null +++ b/src/crimson/os/seastore/lba_mapping.h @@ -0,0 +1,73 @@ +// -*- mode:C++; tab-width:8; c-basic-offset:2; indent-tabs-mode:t -*- +// vim: ts=8 sw=2 smarttab + +#pragma once + +#include "crimson/os/seastore/cached_extent.h" +#include "crimson/os/seastore/btree/btree_range_pin.h" + +namespace crimson::os::seastore { + +class LBAMapping; +using LBAMappingRef = std::unique_ptr<LBAMapping>; + +class LogicalCachedExtent; + +class LBAMapping : public BtreeNodeMapping<laddr_t, paddr_t> { +public: + LBAMapping(op_context_t<laddr_t> ctx) + : BtreeNodeMapping<laddr_t, paddr_t>(ctx) {} + template <typename... T> + LBAMapping(T&&... t) + : BtreeNodeMapping<laddr_t, paddr_t>(std::forward<T>(t)...) + { + if (!parent->is_pending()) { + this->child_pos = {parent, pos}; + } + } + + // An lba pin may be indirect, see comments in lba_manager/btree/btree_lba_manager.h + virtual bool is_indirect() const = 0; + virtual laddr_t get_intermediate_key() const = 0; + virtual laddr_t get_intermediate_base() const = 0; + virtual extent_len_t get_intermediate_length() const = 0; + // The start offset of the pin, must be 0 if the pin is not indirect + virtual extent_len_t get_intermediate_offset() const = 0; + + virtual get_child_ret_t<LogicalCachedExtent> + get_logical_extent(Transaction &t) = 0; + + void link_child(ChildableCachedExtent *c) { + ceph_assert(child_pos); + child_pos->link_child(c); + } + virtual LBAMappingRef refresh_with_pending_parent() = 0; + + // For reserved mappings, the return values are + // undefined although it won't crash + virtual bool is_stable() const = 0; + virtual bool is_data_stable() const = 0; + virtual bool is_clone() const = 0; + bool is_zero_reserved() const { + return !get_val().is_real(); + } + + LBAMappingRef duplicate() const; + + virtual ~LBAMapping() {} +protected: + virtual LBAMappingRef _duplicate(op_context_t<laddr_t>) const = 0; + std::optional<child_pos_t> child_pos = std::nullopt; +}; + +std::ostream &operator<<(std::ostream &out, const LBAMapping &rhs); +using lba_pin_list_t = std::list<LBAMappingRef>; + +std::ostream &operator<<(std::ostream &out, const lba_pin_list_t &rhs); + +} // namespace crimson::os::seastore + +#if FMT_VERSION >= 90000 +template <> struct fmt::formatter<crimson::os::seastore::LBAMapping> : fmt::ostream_formatter {}; +template <> struct fmt::formatter<crimson::os::seastore::lba_pin_list_t> : fmt::ostream_formatter {}; +#endif diff --git a/src/crimson/osd/backfill_state.cc b/src/crimson/osd/backfill_state.cc index 1392ee330ac..f957f072c93 100644 --- a/src/crimson/osd/backfill_state.cc +++ b/src/crimson/osd/backfill_state.cc @@ -342,6 +342,7 @@ BackfillState::Enqueuing::Enqueuing(my_context ctx) do { if (!backfill_listener().budget_available()) { + DEBUGDPP("throttle failed, turning to Waiting", pg()); post_event(RequestWaiting{}); return; } else if (should_rescan_replicas(backfill_state().peer_backfill_info, @@ -380,16 +381,25 @@ BackfillState::Enqueuing::Enqueuing(my_context ctx) } } while (!all_emptied(primary_bi, backfill_state().peer_backfill_info)); - if (backfill_state().progress_tracker->tracked_objects_completed() - && Enqueuing::all_enqueued(peering_state(), - backfill_state().backfill_info, - backfill_state().peer_backfill_info)) { - backfill_state().last_backfill_started = hobject_t::get_max(); - backfill_listener().update_peers_last_backfill(hobject_t::get_max()); + if (should_rescan_primary(backfill_state().peer_backfill_info, + primary_bi)) { + // need to grab one another chunk of the object namespace and restart + // the queueing. + DEBUGDPP("reached end for current local chunk", pg()); + post_event(RequestPrimaryScanning{}); + return; + } else { + if (backfill_state().progress_tracker->tracked_objects_completed() + && Enqueuing::all_enqueued(peering_state(), + backfill_state().backfill_info, + backfill_state().peer_backfill_info)) { + backfill_state().last_backfill_started = hobject_t::get_max(); + backfill_listener().update_peers_last_backfill(hobject_t::get_max()); + } + DEBUGDPP("reached end for both local and all peers " + "but still has in-flight operations", pg()); + post_event(RequestWaiting{}); } - DEBUGDPP("reached end for both local and all peers " - "but still has in-flight operations", pg()); - post_event(RequestWaiting{}); } // -- PrimaryScanning @@ -676,6 +686,17 @@ void BackfillState::enqueue_standalone_push( backfill_machine.backfill_listener.enqueue_push(obj, v, peers); } +void BackfillState::enqueue_standalone_delete( + const hobject_t &obj, + const eversion_t &v, + const std::vector<pg_shard_t> &peers) +{ + progress_tracker->enqueue_drop(obj); + for (auto bt : peers) { + backfill_machine.backfill_listener.enqueue_drop(bt, obj, v); + } +} + std::ostream &operator<<(std::ostream &out, const BackfillState::PGFacade &pg) { return pg.print(out); } diff --git a/src/crimson/osd/backfill_state.h b/src/crimson/osd/backfill_state.h index 463be4a7a2e..517a02ea4df 100644 --- a/src/crimson/osd/backfill_state.h +++ b/src/crimson/osd/backfill_state.h @@ -62,6 +62,8 @@ struct BackfillState { struct CancelBackfill : sc::event<CancelBackfill> { }; + struct ThrottleAcquired : sc::event<ThrottleAcquired> { + }; private: // internal events struct RequestPrimaryScanning : sc::event<RequestPrimaryScanning> { @@ -257,6 +259,7 @@ public: sc::transition<RequestDone, Done>, sc::custom_reaction<CancelBackfill>, sc::custom_reaction<Triggered>, + sc::transition<ThrottleAcquired, Enqueuing>, sc::transition<sc::event_base, Crashed>>; explicit Waiting(my_context); sc::result react(ObjectPushed); @@ -289,6 +292,11 @@ public: const hobject_t &obj, const eversion_t &v, const std::vector<pg_shard_t> &peers); + void enqueue_standalone_delete( + const hobject_t &obj, + const eversion_t &v, + const std::vector<pg_shard_t> &peers); + bool is_triggered() const { return backfill_machine.triggering_event() != nullptr; diff --git a/src/crimson/osd/osd_operation.h b/src/crimson/osd/osd_operation.h index 6376dabd04d..394375c1129 100644 --- a/src/crimson/osd/osd_operation.h +++ b/src/crimson/osd/osd_operation.h @@ -341,6 +341,18 @@ public: with_throttle_while(std::forward<Args>(args)...), *this); } + // Returns std::nullopt if the throttle is acquired immediately, + // returns the future for the acquiring otherwise + std::optional<seastar::future<>> + try_acquire_throttle_now(crimson::osd::scheduler::params_t params) { + if (!max_in_progress || in_progress < max_in_progress) { + ++in_progress; + --pending; + return std::nullopt; + } + return acquire_throttle(params); + } + private: void dump_detail(Formatter *f) const final; diff --git a/src/crimson/osd/pg.cc b/src/crimson/osd/pg.cc index bf521498abf..2746e730f2b 100644 --- a/src/crimson/osd/pg.cc +++ b/src/crimson/osd/pg.cc @@ -879,6 +879,17 @@ void PG::enqueue_push_for_backfill( backfill_state->enqueue_standalone_push(obj, v, peers); } +void PG::enqueue_delete_for_backfill( + const hobject_t &obj, + const eversion_t &v, + const std::vector<pg_shard_t> &peers) +{ + assert(recovery_handler); + assert(recovery_handler->backfill_state); + auto backfill_state = recovery_handler->backfill_state.get(); + backfill_state->enqueue_standalone_delete(obj, v, peers); +} + PG::interruptible_future< std::tuple<PG::interruptible_future<>, PG::interruptible_future<>>> diff --git a/src/crimson/osd/pg.h b/src/crimson/osd/pg.h index 6db73ee835b..06038c0aa00 100644 --- a/src/crimson/osd/pg.h +++ b/src/crimson/osd/pg.h @@ -904,6 +904,11 @@ private: const hobject_t &obj, const eversion_t &v, const std::vector<pg_shard_t> &peers); + void enqueue_delete_for_backfill( + const hobject_t &obj, + const eversion_t &v, + const std::vector<pg_shard_t> &peers); + bool can_discard_replica_op(const Message& m, epoch_t m_map_epoch) const; bool can_discard_op(const MOSDOp& m) const; void context_registry_on_change(); diff --git a/src/crimson/osd/pg_recovery.cc b/src/crimson/osd/pg_recovery.cc index ec3af0d2b00..5eef584c776 100644 --- a/src/crimson/osd/pg_recovery.cc +++ b/src/crimson/osd/pg_recovery.cc @@ -67,8 +67,6 @@ PGRecovery::start_recovery_ops( if (max_to_start > 0) { max_to_start -= start_replica_recovery_ops(trigger, max_to_start, &started); } - using interruptor = - crimson::interruptible::interruptor<crimson::osd::IOInterruptCondition>; return interruptor::parallel_for_each(started, [] (auto&& ifut) { return std::move(ifut); @@ -609,8 +607,21 @@ void PGRecovery::update_peers_last_backfill( bool PGRecovery::budget_available() const { - // TODO: the limits! - return true; + crimson::osd::scheduler::params_t params = + {1, 0, crimson::osd::scheduler::scheduler_class_t::background_best_effort}; + auto &ss = pg->get_shard_services(); + auto futopt = ss.try_acquire_throttle_now(std::move(params)); + if (!futopt) { + return true; + } + std::ignore = interruptor::make_interruptible(std::move(*futopt) + ).then_interruptible([this] { + assert(!backfill_state->is_triggered()); + using BackfillState = crimson::osd::BackfillState; + backfill_state->process_event( + BackfillState::ThrottleAcquired{}.intrusive_from_this()); + }); + return false; } void PGRecovery::on_pg_clean() diff --git a/src/crimson/osd/pg_recovery.h b/src/crimson/osd/pg_recovery.h index 657e6d3e888..5c7b5c5ef2b 100644 --- a/src/crimson/osd/pg_recovery.h +++ b/src/crimson/osd/pg_recovery.h @@ -25,6 +25,8 @@ class PGBackend; class PGRecovery : public crimson::osd::BackfillState::BackfillListener { public: + using interruptor = + crimson::interruptible::interruptor<crimson::osd::IOInterruptCondition>; template <typename T = void> using interruptible_future = RecoveryBackend::interruptible_future<T>; PGRecovery(PGRecoveryListener* pg) : pg(pg) {} diff --git a/src/crimson/osd/replicated_backend.cc b/src/crimson/osd/replicated_backend.cc index f09cd147ea9..6c8abecffaf 100644 --- a/src/crimson/osd/replicated_backend.cc +++ b/src/crimson/osd/replicated_backend.cc @@ -96,11 +96,18 @@ ReplicatedBackend::submit_transaction( bufferlist encoded_txn; encode(txn, encoded_txn); + bool is_delete = false; for (auto &le : log_entries) { le.mark_unrollbackable(); + if (le.is_delete()) { + is_delete = true; + } } + co_await pg.update_snap_map(log_entries, txn); + std::vector<pg_shard_t> to_push_clone; + std::vector<pg_shard_t> to_push_delete; auto sends = std::make_unique<std::vector<seastar::future<>>>(); for (auto &pg_shard : pg_shards) { if (pg_shard == whoami) { @@ -115,12 +122,17 @@ ReplicatedBackend::submit_transaction( m = new_repop_msg( pg_shard, hoid, encoded_txn, osd_op_p, min_epoch, map_epoch, log_entries, false, tid); - if (_new_clone && pg.is_missing_on_peer(pg_shard, hoid)) { - // The head is in the push queue but hasn't been pushed yet. - // We need to ensure that the newly created clone will be - // pushed as well, otherwise we might skip it. - // See: https://tracker.ceph.com/issues/68808 - to_push_clone.push_back(pg_shard); + if (pg.is_missing_on_peer(pg_shard, hoid)) { + if (_new_clone) { + // The head is in the push queue but hasn't been pushed yet. + // We need to ensure that the newly created clone will be + // pushed as well, otherwise we might skip it. + // See: https://tracker.ceph.com/issues/68808 + to_push_clone.push_back(pg_shard); + } + if (is_delete) { + to_push_delete.push_back(pg_shard); + } } } pending_txn->second.acked_peers.push_back({pg_shard, eversion_t{}}); @@ -130,8 +142,6 @@ ReplicatedBackend::submit_transaction( pg_shard.osd, std::move(m), map_epoch)); } - co_await pg.update_snap_map(log_entries, txn); - pg.log_operation( std::move(log_entries), osd_op_p.pg_trim_to, @@ -157,7 +167,8 @@ ReplicatedBackend::submit_transaction( return seastar::now(); } return peers->all_committed.get_shared_future(); - }).then_interruptible([pending_txn, this, _new_clone, + }).then_interruptible([pending_txn, this, _new_clone, &hoid, + to_push_delete=std::move(to_push_delete), to_push_clone=std::move(to_push_clone)] { auto acked_peers = std::move(pending_txn->second.acked_peers); pending_trans.erase(pending_txn); @@ -167,6 +178,9 @@ ReplicatedBackend::submit_transaction( _new_clone->obs.oi.version, to_push_clone); } + if (!to_push_delete.empty()) { + pg.enqueue_delete_for_backfill(hoid, {}, to_push_delete); + } return seastar::make_ready_future< crimson::osd::acked_peers_t>(std::move(acked_peers)); }); diff --git a/src/crimson/osd/replicated_recovery_backend.cc b/src/crimson/osd/replicated_recovery_backend.cc index 30e7a8a333d..0d6c9d38236 100644 --- a/src/crimson/osd/replicated_recovery_backend.cc +++ b/src/crimson/osd/replicated_recovery_backend.cc @@ -35,6 +35,15 @@ ReplicatedRecoveryBackend::recover_object( logger().debug("recover_object: loading obc: {}", soid); return pg.obc_loader.with_obc<RWState::RWREAD>(soid, [this, soid, need](auto head, auto obc) { + if (!obc->obs.exists) { + // XXX: this recovery must be triggered by backfills and the corresponding + // object must have been deleted by some client request after the object + // is enqueued for push but before the lock is acquired by the recovery. + // + // Abort the recovery in this case, a "recover_delete" must have been + // added for this object by the client request that deleted it. + return interruptor::now(); + } logger().debug("recover_object: loaded obc: {}", obc->obs.oi.soid); auto& recovery_waiter = get_recovering(soid); recovery_waiter.obc = obc; diff --git a/src/crimson/osd/shard_services.h b/src/crimson/osd/shard_services.h index f4d4b4c2eb4..f1ed9b8d911 100644 --- a/src/crimson/osd/shard_services.h +++ b/src/crimson/osd/shard_services.h @@ -591,6 +591,7 @@ public: FORWARD_TO_OSD_SINGLETON(get_pool_info) FORWARD(with_throttle_while, with_throttle_while, local_state.throttler) + FORWARD(try_acquire_throttle_now, try_acquire_throttle_now, local_state.throttler) FORWARD_TO_OSD_SINGLETON(build_incremental_map_msg) FORWARD_TO_OSD_SINGLETON(send_incremental_map) diff --git a/src/exporter/ceph_exporter.cc b/src/exporter/ceph_exporter.cc index 44b67c7e615..2232851c094 100644 --- a/src/exporter/ceph_exporter.cc +++ b/src/exporter/ceph_exporter.cc @@ -30,13 +30,13 @@ static void handle_signal(int signum) static void usage() { std::cout << "usage: ceph-exporter [options]\n" << "options:\n" - " --sock-dir: The path to ceph daemons socket files dir\n" - " --addrs: Host ip address where exporter is deployed\n" - " --port: Port to deploy exporter on. Default is 9926\n" - " --cert-file: Path to the certificate file to use https\n" - " --key-file: Path to the certificate key file to use https\n" + " --sock-dir: The path to Ceph daemon sockets (*.asok)\n" + " --addrs: Host IP address on which the exporter is to listen\n" + " --port: TCP Port on which the exporter is to listen. Default is 9926\n" + " --cert-file: Path to the certificate file when using HTTPS\n" + " --key-file: Path to the certificate key file when using HTTPS\n" " --prio-limit: Only perf counters greater than or equal to prio-limit are fetched. Default: 5\n" - " --stats-period: Time to wait before sending requests again to exporter server (seconds). Default: 5s" + " --stats-period: Interval between daemon scrapes (seconds). Default: 5s" << std::endl; generic_server_usage(); } diff --git a/src/include/random.h b/src/include/random.h index f2e3e37bcd7..6b7c9405efd 100644 --- a/src/include/random.h +++ b/src/include/random.h @@ -16,9 +16,9 @@ #define CEPH_RANDOM_H 1 #include <mutex> +#include <optional> #include <random> #include <type_traits> -#include <boost/optional.hpp> // Workaround for https://gcc.gnu.org/bugzilla/show_bug.cgi?id=85494 #ifdef __MINGW32__ @@ -123,7 +123,7 @@ void randomize_rng() template <typename EngineT> EngineT& engine() { - thread_local boost::optional<EngineT> rng_engine; + thread_local std::optional<EngineT> rng_engine; if (!rng_engine) { rng_engine.emplace(EngineT()); diff --git a/src/kv/KeyValueDB.h b/src/kv/KeyValueDB.h index 858742d511e..d926840180e 100644 --- a/src/kv/KeyValueDB.h +++ b/src/kv/KeyValueDB.h @@ -9,6 +9,7 @@ #include <map> #include <optional> #include <string> +#include <string_view> #include <boost/scoped_ptr.hpp> #include "include/encoding.h" #include "common/Formatter.h" @@ -211,6 +212,10 @@ public: return ""; } virtual ceph::buffer::list value() = 0; + // When valid() returns true, value returned as string-view + // is guaranteed to be valid until iterator is moved to another + // position; that is until call to next() / seek_to_first() / etc. + virtual std::string_view value_as_sv() = 0; virtual int status() = 0; virtual ~SimplestIteratorImpl() {} }; @@ -220,7 +225,12 @@ public: virtual ~IteratorImpl() {} virtual int seek_to_last() = 0; virtual int prev() = 0; + // When valid() returns true, key returned as string-view + // is guaranteed to be valid until iterator is moved to another + // position; that is until call to next() / seek_to_first() / etc. + virtual std::string_view key_as_sv() = 0; virtual std::pair<std::string, std::string> raw_key() = 0; + virtual std::pair<std::string_view, std::string_view> raw_key_as_sv() = 0; virtual ceph::buffer::ptr value_as_ptr() { ceph::buffer::list bl = value(); if (bl.length() == 1) { @@ -247,7 +257,9 @@ public: virtual int next() = 0; virtual int prev() = 0; virtual std::string key() = 0; + virtual std::string_view key_as_sv() = 0; virtual std::pair<std::string,std::string> raw_key() = 0; + virtual std::pair<std::string_view, std::string_view> raw_key_as_sv() = 0; virtual bool raw_key_is_prefixed(const std::string &prefix) = 0; virtual ceph::buffer::list value() = 0; virtual ceph::buffer::ptr value_as_ptr() { @@ -258,6 +270,7 @@ public: return ceph::buffer::ptr(); } } + virtual std::string_view value_as_sv() = 0; virtual int status() = 0; virtual size_t key_size() { return 0; @@ -315,15 +328,24 @@ private: std::string key() override { return generic_iter->key(); } + std::string_view key_as_sv() override { + return generic_iter->key_as_sv(); + } std::pair<std::string, std::string> raw_key() override { return generic_iter->raw_key(); } + std::pair<std::string_view, std::string_view> raw_key_as_sv() override { + return generic_iter->raw_key_as_sv(); + } ceph::buffer::list value() override { return generic_iter->value(); } ceph::buffer::ptr value_as_ptr() override { return generic_iter->value_as_ptr(); } + std::string_view value_as_sv() override { + return generic_iter->value_as_sv(); + } int status() override { return generic_iter->status(); } diff --git a/src/kv/RocksDBStore.cc b/src/kv/RocksDBStore.cc index ca63ea06484..51d224b67c0 100644 --- a/src/kv/RocksDBStore.cc +++ b/src/kv/RocksDBStore.cc @@ -6,6 +6,7 @@ #include <memory> #include <set> #include <string> +#include <string_view> #include <errno.h> #include <unistd.h> #include <sys/types.h> @@ -47,6 +48,7 @@ using std::ostream; using std::pair; using std::set; using std::string; +using std::string_view; using std::unique_ptr; using std::vector; @@ -1992,7 +1994,7 @@ int RocksDBStore::split_key(rocksdb::Slice in, string *prefix, string *key) // Find separator inside Slice char* separator = (char*) memchr(in.data(), 0, in.size()); - if (separator == NULL) + if (separator == nullptr) return -EINVAL; prefix_len = size_t(separator - in.data()); if (prefix_len >= in.size()) @@ -2006,6 +2008,27 @@ int RocksDBStore::split_key(rocksdb::Slice in, string *prefix, string *key) return 0; } +// TODO: deduplicate the code, preferrably by removing the string variant +int RocksDBStore::split_key(rocksdb::Slice in, string_view *prefix, string_view *key) +{ + size_t prefix_len = 0; + + // Find separator inside Slice + char* separator = (char*) memchr(in.data(), 0, in.size()); + if (separator == nullptr) + return -EINVAL; + prefix_len = size_t(separator - in.data()); + if (prefix_len >= in.size()) + return -EINVAL; + + // Fetch prefix and/or key directly from Slice + if (prefix) + *prefix = string_view(in.data(), prefix_len); + if (key) + *key = string_view(separator + 1, in.size() - prefix_len - 1); + return 0; +} + void RocksDBStore::compact() { dout(2) << __func__ << " starting" << dendl; @@ -2226,7 +2249,13 @@ int RocksDBStore::RocksDBWholeSpaceIteratorImpl::prev() string RocksDBStore::RocksDBWholeSpaceIteratorImpl::key() { string out_key; - split_key(dbiter->key(), 0, &out_key); + split_key(dbiter->key(), nullptr, &out_key); + return out_key; +} +string_view RocksDBStore::RocksDBWholeSpaceIteratorImpl::key_as_sv() +{ + string_view out_key; + split_key(dbiter->key(), nullptr, &out_key); return out_key; } pair<string,string> RocksDBStore::RocksDBWholeSpaceIteratorImpl::raw_key() @@ -2235,6 +2264,12 @@ pair<string,string> RocksDBStore::RocksDBWholeSpaceIteratorImpl::raw_key() split_key(dbiter->key(), &prefix, &key); return make_pair(prefix, key); } +pair<string_view,string_view> RocksDBStore::RocksDBWholeSpaceIteratorImpl::raw_key_as_sv() +{ + string_view prefix, key; + split_key(dbiter->key(), &prefix, &key); + return make_pair(prefix, key); +} bool RocksDBStore::RocksDBWholeSpaceIteratorImpl::raw_key_is_prefixed(const string &prefix) { // Look for "prefix\0" right in rocksb::Slice @@ -2267,6 +2302,12 @@ bufferptr RocksDBStore::RocksDBWholeSpaceIteratorImpl::value_as_ptr() return bufferptr(val.data(), val.size()); } +std::string_view RocksDBStore::RocksDBWholeSpaceIteratorImpl::value_as_sv() +{ + rocksdb::Slice val = dbiter->value(); + return std::string_view{val.data(), val.size()}; +} + int RocksDBStore::RocksDBWholeSpaceIteratorImpl::status() { return dbiter->status().ok() ? 0 : -1; @@ -2348,9 +2389,15 @@ public: string key() override { return dbiter->key().ToString(); } + string_view key_as_sv() override { + return dbiter->key().ToStringView(); + } std::pair<std::string, std::string> raw_key() override { return make_pair(prefix, key()); } + std::pair<std::string_view, std::string_view> raw_key_as_sv() override { + return make_pair(prefix, dbiter->key().ToStringView()); + } bufferlist value() override { return to_bufferlist(dbiter->value()); } @@ -2358,6 +2405,10 @@ public: rocksdb::Slice val = dbiter->value(); return bufferptr(val.data(), val.size()); } + std::string_view value_as_sv() override { + rocksdb::Slice val = dbiter->value(); + return std::string_view{val.data(), val.size()}; + } int status() override { return dbiter->status().ok() ? 0 : -1; } @@ -2668,6 +2719,15 @@ public: } } + std::string_view key_as_sv() override + { + if (smaller == on_main) { + return main->key_as_sv(); + } else { + return current_shard->second->key_as_sv(); + } + } + std::pair<std::string,std::string> raw_key() override { if (smaller == on_main) { @@ -2677,6 +2737,15 @@ public: } } + std::pair<std::string_view,std::string_view> raw_key_as_sv() override + { + if (smaller == on_main) { + return main->raw_key_as_sv(); + } else { + return { current_shard->first, current_shard->second->key_as_sv() }; + } + } + bool raw_key_is_prefixed(const std::string &prefix) override { if (smaller == on_main) { @@ -2695,6 +2764,15 @@ public: } } + std::string_view value_as_sv() override + { + if (smaller == on_main) { + return main->value_as_sv(); + } else { + return current_shard->second->value_as_sv(); + } + } + int status() override { //because we already had to inspect key, it must be ok @@ -3017,9 +3095,15 @@ public: string key() override { return iters[0]->key().ToString(); } + string_view key_as_sv() override { + return iters[0]->key().ToStringView(); + } std::pair<std::string, std::string> raw_key() override { return make_pair(prefix, key()); } + std::pair<std::string_view, std::string_view> raw_key_as_sv() override { + return make_pair(prefix, iters[0]->key().ToStringView()); + } bufferlist value() override { return to_bufferlist(iters[0]->value()); } @@ -3027,6 +3111,10 @@ public: rocksdb::Slice val = iters[0]->value(); return bufferptr(val.data(), val.size()); } + std::string_view value_as_sv() override { + rocksdb::Slice val = iters[0]->value(); + return std::string_view{val.data(), val.size()}; + } int status() override { return iters[0]->status().ok() ? 0 : -1; } diff --git a/src/kv/RocksDBStore.h b/src/kv/RocksDBStore.h index 477b209854c..50b91be2bf6 100644 --- a/src/kv/RocksDBStore.h +++ b/src/kv/RocksDBStore.h @@ -386,10 +386,13 @@ public: int next() override; int prev() override; std::string key() override; + std::string_view key_as_sv() override; std::pair<std::string,std::string> raw_key() override; + std::pair<std::string_view,std::string_view> raw_key_as_sv() override; bool raw_key_is_prefixed(const std::string &prefix) override; ceph::bufferlist value() override; ceph::bufferptr value_as_ptr() override; + std::string_view value_as_sv() override; int status() override; size_t key_size() override; size_t value_size() override; @@ -419,6 +422,7 @@ public: } static int split_key(rocksdb::Slice in, std::string *prefix, std::string *key); + static int split_key(rocksdb::Slice in, std::string_view *prefix, std::string_view *key); static std::string past_prefix(const std::string &prefix); diff --git a/src/librbd/migration/HttpClient.cc b/src/librbd/migration/HttpClient.cc index 09fe91da02a..d212981a917 100644 --- a/src/librbd/migration/HttpClient.cc +++ b/src/librbd/migration/HttpClient.cc @@ -193,7 +193,7 @@ protected: ldout(cct, 15) << dendl; boost::system::error_code ec; - boost::beast::get_lowest_layer(derived().stream()).socket().close(ec); + derived().stream().lowest_layer().close(ec); } private: @@ -357,8 +357,7 @@ private: } int shutdown_socket() { - if (!boost::beast::get_lowest_layer( - derived().stream()).socket().is_open()) { + if (!derived().stream().lowest_layer().is_open()) { return 0; } @@ -366,7 +365,7 @@ private: ldout(cct, 15) << dendl; boost::system::error_code ec; - boost::beast::get_lowest_layer(derived().stream()).socket().shutdown( + derived().stream().lowest_layer().shutdown( boost::asio::ip::tcp::socket::shutdown_both, ec); if (ec && ec != boost::beast::errc::not_connected) { @@ -595,7 +594,7 @@ public: this->close_socket(); } - inline boost::beast::tcp_stream& + inline boost::asio::ip::tcp::socket& stream() { return m_stream; } @@ -607,12 +606,13 @@ protected: auto cct = http_client->m_cct; ldout(cct, 15) << dendl; - ceph_assert(!m_stream.socket().is_open()); - m_stream.async_connect( - results, - [on_finish](boost::system::error_code ec, const auto& endpoint) { - on_finish->complete(-ec.value()); - }); + ceph_assert(!m_stream.is_open()); + boost::asio::async_connect(m_stream, + results, + [on_finish](boost::system::error_code ec, + const auto& endpoint) { + on_finish->complete(-ec.value()); + }); } void disconnect(Context* on_finish) override { @@ -624,7 +624,7 @@ protected: } private: - boost::beast::tcp_stream m_stream; + boost::asio::ip::tcp::socket m_stream; }; #undef dout_prefix @@ -643,7 +643,7 @@ public: this->close_socket(); } - inline boost::beast::ssl_stream<boost::beast::tcp_stream>& + inline boost::asio::ssl::stream<boost::asio::ip::tcp::socket>& stream() { return m_stream; } @@ -655,8 +655,9 @@ protected: auto cct = http_client->m_cct; ldout(cct, 15) << dendl; - ceph_assert(!boost::beast::get_lowest_layer(m_stream).socket().is_open()); - boost::beast::get_lowest_layer(m_stream).async_connect( + ceph_assert(!m_stream.lowest_layer().is_open()); + async_connect( + m_stream.lowest_layer(), results, [this, on_finish](boost::system::error_code ec, const auto& endpoint) { handle_connect(-ec.value(), on_finish); @@ -681,12 +682,12 @@ protected: // ssl_stream object can't be reused after shut down -- move-in // a freshly constructed instance - m_stream = boost::beast::ssl_stream<boost::beast::tcp_stream>( + m_stream = boost::asio::ssl::stream<boost::asio::ip::tcp::socket>( http_client->m_strand, http_client->m_ssl_context); } private: - boost::beast::ssl_stream<boost::beast::tcp_stream> m_stream; + boost::asio::ssl::stream<boost::asio::ip::tcp::socket> m_stream; void handle_connect(int r, Context* on_finish) { auto http_client = this->m_http_client; diff --git a/src/librbd/migration/HttpClient.h b/src/librbd/migration/HttpClient.h index 3997e6159e7..5844f918693 100644 --- a/src/librbd/migration/HttpClient.h +++ b/src/librbd/migration/HttpClient.h @@ -13,13 +13,12 @@ #include <boost/asio/strand.hpp> #include <boost/asio/ip/tcp.hpp> #include <boost/asio/ssl/context.hpp> +#include <boost/asio/ssl/stream.hpp> #include <boost/beast/version.hpp> -#include <boost/beast/core/tcp_stream.hpp> #include <boost/beast/http/empty_body.hpp> #include <boost/beast/http/message.hpp> #include <boost/beast/http/string_body.hpp> #include <boost/beast/http/write.hpp> -#include <boost/beast/ssl/ssl_stream.hpp> #include <functional> #include <memory> #include <string> @@ -97,7 +96,7 @@ public: completion(r, std::move(response)); } - void operator()(boost::beast::tcp_stream& stream) override { + void operator()(boost::asio::ip::tcp::socket& stream) override { preprocess_request(); boost::beast::http::async_write( @@ -110,7 +109,7 @@ public: } void operator()( - boost::beast::ssl_stream<boost::beast::tcp_stream>& stream) override { + boost::asio::ssl::stream<boost::asio::ip::tcp::socket>& stream) override { preprocess_request(); boost::beast::http::async_write( @@ -152,9 +151,9 @@ private: virtual bool need_eof() const = 0; virtual bool header_only() const = 0; virtual void complete(int r, Response&&) = 0; - virtual void operator()(boost::beast::tcp_stream& stream) = 0; + virtual void operator()(boost::asio::ip::tcp::socket& stream) = 0; virtual void operator()( - boost::beast::ssl_stream<boost::beast::tcp_stream>& stream) = 0; + boost::asio::ssl::stream<boost::asio::ip::tcp::socket>& stream) = 0; }; template <typename D> struct HttpSession; diff --git a/src/mds/Server.cc b/src/mds/Server.cc index 5874a3dce56..e66b5aa08c7 100644 --- a/src/mds/Server.cc +++ b/src/mds/Server.cc @@ -4167,7 +4167,7 @@ void Server::handle_client_getattr(const MDRequestRef& mdr, bool is_lookup) if (r < 0) { // fall-thru. let rdlock_path_pin_ref() check again. - } else if (is_lookup) { + } else if (is_lookup && mdr->dn[0].size()) { CDentry* dn = mdr->dn[0].back(); mdr->pin(dn); auto em = dn->batch_ops.emplace(std::piecewise_construct, std::forward_as_tuple(mask), std::forward_as_tuple()); @@ -4274,7 +4274,7 @@ void Server::handle_client_getattr(const MDRequestRef& mdr, bool is_lookup) // reply dout(10) << "reply to stat on " << *req << dendl; mdr->tracei = ref; - if (is_lookup) + if (is_lookup && mdr->dn[0].size()) mdr->tracedn = mdr->dn[0].back(); respond_to_request(mdr, 0); } diff --git a/src/mgr/PyModule.cc b/src/mgr/PyModule.cc index cff63ef4a6b..4f996489ba0 100644 --- a/src/mgr/PyModule.cc +++ b/src/mgr/PyModule.cc @@ -38,6 +38,18 @@ std::string PyModule::mgr_store_prefix = "mgr/"; #define BOOST_BIND_GLOBAL_PLACEHOLDERS // Boost apparently can't be bothered to fix its own usage of its own // deprecated features. + +// Fix instances of "'BOOST_PP_ITERATION_02' was not declared in this scope; did +// you mean 'BOOST_PP_ITERATION_05'" and related macro error bullshit that spans +// 300 lines of errors +// +// Apparently you can't include boost/python stuff _and_ have this header +// defined +// +// Thanks to the ceph-aur folks for the fix at: +// https://github.com/bazaah/aur-ceph/commit/8c5cc7d8deec002f7596b6d0860859a0a718f12b +#undef BOOST_MPL_CFG_NO_PREPROCESSED_HEADERS + #include <boost/python/extract.hpp> #include <boost/python/import.hpp> #include <boost/python/object.hpp> diff --git a/src/mgr/PyModule.h b/src/mgr/PyModule.h index 177447c2cb3..a47db3a47ef 100644 --- a/src/mgr/PyModule.h +++ b/src/mgr/PyModule.h @@ -161,9 +161,9 @@ public: } const std::string &get_name() const { - std::lock_guard l(lock) ; return module_name; + return module_name; } - const std::string &get_error_string() const { + std::string get_error_string() const { std::lock_guard l(lock) ; return error_string; } bool get_can_run() const { diff --git a/src/mon/Monitor.cc b/src/mon/Monitor.cc index 7332ec3edb1..833bdddc71b 100644 --- a/src/mon/Monitor.cc +++ b/src/mon/Monitor.cc @@ -4024,7 +4024,7 @@ void Monitor::handle_command(MonOpRequestRef op) for (auto& p : mgrstatmon()->get_service_map().services) { auto &service = p.first; - if (ServiceMap::is_normal_ceph_entity(service)) { + if (ServiceMap::is_normal_ceph_entity(service) || service == "nvmeof") { continue; } f->open_object_section(service.c_str()); diff --git a/src/msg/async/AsyncMessenger.cc b/src/msg/async/AsyncMessenger.cc index 2e38bd434a8..6b3a8c3f6dc 100644 --- a/src/msg/async/AsyncMessenger.cc +++ b/src/msg/async/AsyncMessenger.cc @@ -207,22 +207,22 @@ void Processor::accept() } else if (r == -EAGAIN) { break; } else if (r == -EMFILE || r == -ENFILE) { - lderr(msgr->cct) << __func__ << " open file descriptions limit reached sd = " << listen_socket.fd() + lderr(msgr->cct) << __func__ << " open file descriptors limit reached fd = " << listen_socket.fd() << " errno " << r << " " << cpp_strerror(r) << dendl; if (++accept_error_num > msgr->cct->_conf->ms_max_accept_failures) { - lderr(msgr->cct) << "Proccessor accept has encountered enough error numbers, just do ceph_abort()." << dendl; + lderr(msgr->cct) << "Proccessor accept has encountered too many errors, just do ceph_abort()." << dendl; ceph_abort(); } continue; } else if (r == -ECONNABORTED) { - ldout(msgr->cct, 0) << __func__ << " it was closed because of rst arrived sd = " << listen_socket.fd() + ldout(msgr->cct, 0) << __func__ << " closed because of rst arrival fd = " << listen_socket.fd() << " errno " << r << " " << cpp_strerror(r) << dendl; continue; } else { lderr(msgr->cct) << __func__ << " no incoming connection?" << " errno " << r << " " << cpp_strerror(r) << dendl; if (++accept_error_num > msgr->cct->_conf->ms_max_accept_failures) { - lderr(msgr->cct) << "Proccessor accept has encountered enough error numbers, just do ceph_abort()." << dendl; + lderr(msgr->cct) << "Proccessor accept has encountered too many errors, just do ceph_abort()." << dendl; ceph_abort(); } continue; diff --git a/src/msg/async/EventEpoll.cc b/src/msg/async/EventEpoll.cc index 7ed5321dcda..eb04e3b8e98 100644 --- a/src/msg/async/EventEpoll.cc +++ b/src/msg/async/EventEpoll.cc @@ -17,6 +17,7 @@ #include "common/errno.h" #include <fcntl.h> #include "EventEpoll.h" +#include "Timeout.h" #define dout_subsys ceph_subsys_ms @@ -120,8 +121,7 @@ int EpollDriver::event_wait(std::vector<FiredFileEvent> &fired_events, struct ti { int retval, numevents = 0; - retval = epoll_wait(epfd, events, nevent, - tvp ? (tvp->tv_sec*1000 + tvp->tv_usec/1000) : -1); + retval = epoll_wait(epfd, events, nevent, timeout_to_milliseconds(tvp)); if (retval > 0) { numevents = retval; fired_events.resize(numevents); diff --git a/src/msg/async/EventPoll.cc b/src/msg/async/EventPoll.cc index 4c09dbb4db4..f46528715e3 100644 --- a/src/msg/async/EventPoll.cc +++ b/src/msg/async/EventPoll.cc @@ -15,6 +15,7 @@ #include "common/errno.h" #include "EventPoll.h" +#include "Timeout.h" #include <unistd.h> #define dout_subsys ceph_subsys_ms @@ -161,11 +162,9 @@ int PollDriver::event_wait(std::vector<FiredFileEvent> &fired_events, struct timeval *tvp) { int retval, numevents = 0; #ifdef _WIN32 - retval = WSAPoll(pfds, max_pfds, - tvp ? (tvp->tv_sec*1000 + tvp->tv_usec/1000) : -1); + retval = WSAPoll(pfds, max_pfds, timeout_to_milliseconds(tvp)); #else - retval = poll(pfds, max_pfds, - tvp ? (tvp->tv_sec*1000 + tvp->tv_usec/1000) : -1); + retval = poll(pfds, max_pfds, timeout_to_milliseconds(tvp)); #endif if (retval > 0) { for (int j = 0; j < max_pfds; j++) { diff --git a/src/msg/async/Timeout.h b/src/msg/async/Timeout.h new file mode 100644 index 00000000000..b8df1b40761 --- /dev/null +++ b/src/msg/async/Timeout.h @@ -0,0 +1,47 @@ +// -*- mode:C++; tab-width:8; c-basic-offset:2; indent-tabs-mode:t -*- +// vim: ts=8 sw=2 smarttab +/* + * Ceph - scalable distributed file system + * + * Copyright (C) 2024 IONOS SE + * + * Author: Max Kellermann <max.kellermann@ionos.com> + * + * This is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License version 2.1, as published by the Free Software + * Foundation. See file COPYING. + * + */ + +#ifndef CEPH_MSG_TIMEOUT_H +#define CEPH_MSG_TIMEOUT_H + +#include "include/intarith.h" // for div_round_up() + +#include <time.h> // for struct timeval + +/** + * Convert the given `struct timeval` to milliseconds. + * + * This is supposed to be used as timeout parameter to system calls + * such as poll() and epoll_wait(). + */ +constexpr int +timeout_to_milliseconds(const struct timeval &tv) noexcept +{ + /* round up to the next millisecond so we don't wake up too early */ + return tv.tv_sec * 1000 + div_round_up(tv.tv_usec, 1000); +} + +/** + * This overload makes the timeout optional; on nullptr, it returns + * -1. + */ +constexpr int +timeout_to_milliseconds(const struct timeval *tv) noexcept +{ + return tv != nullptr ? timeout_to_milliseconds(*tv) : -1; +} + +#endif diff --git a/src/os/DBObjectMap.cc b/src/os/DBObjectMap.cc index 7da9a67be62..65627b5f818 100644 --- a/src/os/DBObjectMap.cc +++ b/src/os/DBObjectMap.cc @@ -519,6 +519,11 @@ bufferlist DBObjectMap::DBObjectMapIteratorImpl::value() return cur_iter->value(); } +std::string_view DBObjectMap::DBObjectMapIteratorImpl::value_as_sv() +{ + return cur_iter->value_as_sv(); +} + int DBObjectMap::DBObjectMapIteratorImpl::status() { return r; diff --git a/src/os/DBObjectMap.h b/src/os/DBObjectMap.h index 444f21eb815..1e1452010e7 100644 --- a/src/os/DBObjectMap.h +++ b/src/os/DBObjectMap.h @@ -393,6 +393,7 @@ private: int next() override { ceph_abort(); return 0; } std::string key() override { ceph_abort(); return ""; } ceph::buffer::list value() override { ceph_abort(); return ceph::buffer::list(); } + std::string_view value_as_sv() override { ceph_abort(); return std::string_view(); } int status() override { return 0; } }; @@ -431,6 +432,7 @@ private: int next() override; std::string key() override; ceph::buffer::list value() override; + std::string_view value_as_sv() override; int status() override; bool on_parent() { diff --git a/src/os/ObjectStore.h b/src/os/ObjectStore.h index 521435b6c31..df3ae920a2f 100644 --- a/src/os/ObjectStore.h +++ b/src/os/ObjectStore.h @@ -29,6 +29,7 @@ #include <errno.h> #include <sys/stat.h> +#include <functional> #include <map> #include <memory> #include <vector> @@ -735,15 +736,6 @@ public: std::map<std::string, ceph::buffer::list> *out ///< [out] Returned keys and values ) = 0; -#ifdef WITH_SEASTAR - virtual int omap_get_values( - CollectionHandle &c, ///< [in] Collection containing oid - const ghobject_t &oid, ///< [in] Object containing omap - const std::optional<std::string> &start_after, ///< [in] Keys to get - std::map<std::string, ceph::buffer::list> *out ///< [out] Returned keys and values - ) = 0; -#endif - /// Filters keys into out which are defined on oid virtual int omap_check_keys( CollectionHandle &c, ///< [in] Collection containing oid @@ -766,6 +758,48 @@ public: const ghobject_t &oid ///< [in] object ) = 0; + struct omap_iter_seek_t { + std::string seek_position; + enum { + // start with provided key (seek_position), if it exists + LOWER_BOUND, + // skip provided key (seek_position) even if it exists + UPPER_BOUND + } seek_type = LOWER_BOUND; + static omap_iter_seek_t min_lower_bound() { return {}; } + }; + enum class omap_iter_ret_t { + STOP, + NEXT + }; + /** + * Iterate over object map with user-provided callable + * + * Warning! The callable is executed under lock on bluestore + * operations in c. Do not use bluestore methods on c while + * iterating. (Filling in a transaction is no problem). + * + * @param c collection + * @param oid object + * @param start_from where the iterator should point to at + * the beginning + * @param visitor callable that takes OMAP key and corresponding + * value as string_views and controls iteration + * by the return. It is executed for every object's + * OMAP entry from `start_from` till end of the + * object's OMAP or till the iteration is stopped + * by `STOP`. Please note that if there is no such + * entry, `visitor` will be called 0 times. + * @return error code, zero on success + */ + virtual int omap_iterate( + CollectionHandle &c, + const ghobject_t &oid, + omap_iter_seek_t start_from, + std::function<omap_iter_ret_t(std::string_view, + std::string_view)> visitor + ) = 0; + virtual int flush_journal() { return -EOPNOTSUPP; } virtual int dump_journal(std::ostream& out) { return -EOPNOTSUPP; } diff --git a/src/os/bluestore/BlueFS.cc b/src/os/bluestore/BlueFS.cc index e123a0a200a..50f293d45fd 100644 --- a/src/os/bluestore/BlueFS.cc +++ b/src/os/bluestore/BlueFS.cc @@ -1706,7 +1706,8 @@ int BlueFS::_replay(bool noop, bool to_stdout) << " fnode=" << fnode << " delta=" << delta << dendl; - ceph_assert(delta.offset == fnode.allocated); + // be leanient, if there is no extents just produce error message + ceph_assert(delta.offset == fnode.allocated || delta.extents.empty()); } if (cct->_conf->bluefs_log_replay_check_allocations) { int r = _check_allocations(fnode, @@ -3793,7 +3794,7 @@ int BlueFS::truncate(FileWriter *h, uint64_t offset)/*_WF_L*/ if (offset > fnode.size) { ceph_abort_msg("truncate up not supported"); } - ceph_assert(offset <= fnode.size); + _flush_bdev(h); { std::lock_guard ll(log.lock); @@ -3802,43 +3803,42 @@ int BlueFS::truncate(FileWriter *h, uint64_t offset)/*_WF_L*/ vselector->sub_usage(h->file->vselector_hint, fnode); uint64_t x_off = 0; auto p = fnode.seek(offset, &x_off); - uint64_t cut_off = - (p == fnode.extents.end()) ? 0 : p2roundup(x_off, alloc_size[p->bdev]); - uint64_t new_allocated; - if (0 == cut_off) { - // whole pextent to remove - changed_extents = true; - new_allocated = offset; - } else if (cut_off < p->length) { - dirty.pending_release[p->bdev].insert(p->offset + cut_off, p->length - cut_off); - new_allocated = (offset - x_off) + cut_off; - p->length = cut_off; - changed_extents = true; - ++p; - } else { - ceph_assert(cut_off >= p->length); - new_allocated = (offset - x_off) + p->length; - // just leave it here - ++p; - } - while (p != fnode.extents.end()) { - dirty.pending_release[p->bdev].insert(p->offset, p->length); - p = fnode.extents.erase(p); - changed_extents = true; + if (p != fnode.extents.end()) { + uint64_t cut_off = p2roundup(x_off, alloc_size[p->bdev]); + if (0 == cut_off) { + // whole pextent to remove + fnode.allocated = offset; + changed_extents = true; + } else if (cut_off < p->length) { + dirty.pending_release[p->bdev].insert(p->offset + cut_off, + p->length - cut_off); + fnode.allocated = (offset - x_off) + cut_off; + p->length = cut_off; + changed_extents = true; + ++p; + } else { + // cut_off > p->length means that we misaligned the extent + ceph_assert(cut_off == p->length); + fnode.allocated = (offset - x_off) + p->length; + ++p; // leave extent untouched + } + while (p != fnode.extents.end()) { + dirty.pending_release[p->bdev].insert(p->offset, p->length); + p = fnode.extents.erase(p); + changed_extents = true; + } } if (changed_extents) { fnode.size = offset; - fnode.allocated = new_allocated; fnode.reset_delta(); + fnode.recalc_allocated(); log.t.op_file_update(fnode); // sad, but is_dirty must be set to signal flushing of the log h->file->is_dirty = true; - } else { - if (offset != fnode.size) { - fnode.size = offset; - //skipping log.t.op_file_update_inc, it will be done by flush() - h->file->is_dirty = true; - } + } else if (offset != fnode.size) { + fnode.size = offset; + // skipping log.t.op_file_update_inc, it will be done by flush() + h->file->is_dirty = true; } vselector->add_usage(h->file->vselector_hint, fnode); } diff --git a/src/os/bluestore/BlueStore.cc b/src/os/bluestore/BlueStore.cc index a024a0c2105..8f1d995fa8d 100644 --- a/src/os/bluestore/BlueStore.cc +++ b/src/os/bluestore/BlueStore.cc @@ -4830,7 +4830,7 @@ void BlueStore::Onode::rewrite_omap_key(const string& old, string *out) out->append(old.c_str() + out->length(), old.size() - out->length()); } -void BlueStore::Onode::decode_omap_key(const string& key, string *user_key) +size_t BlueStore::Onode::calc_userkey_offset_in_omap_key() const { size_t pos = sizeof(uint64_t) + 1; if (!onode.is_pgmeta_omap()) { @@ -4840,9 +4840,15 @@ void BlueStore::Onode::decode_omap_key(const string& key, string *user_key) pos += sizeof(uint64_t); } } - *user_key = key.substr(pos); + return pos; } +void BlueStore::Onode::decode_omap_key(const string& key, string *user_key) +{ + *user_key = key.substr(calc_userkey_offset_in_omap_key()); +} + + void BlueStore::Onode::finish_write(TransContext* txc, uint32_t offset, uint32_t length) { while (true) { @@ -5519,7 +5525,13 @@ BlueStore::OmapIteratorImpl::OmapIteratorImpl( if (o->onode.has_omap()) { o->get_omap_key(string(), &head); o->get_omap_tail(&tail); + auto start1 = mono_clock::now(); it->lower_bound(head); + c->store->log_latency( + __func__, + l_bluestore_omap_seek_to_first_lat, + mono_clock::now() - start1, + c->store->cct->_conf->bluestore_log_omap_iterator_age); } } BlueStore::OmapIteratorImpl::~OmapIteratorImpl() @@ -5654,6 +5666,13 @@ bufferlist BlueStore::OmapIteratorImpl::value() return it->value(); } +std::string_view BlueStore::OmapIteratorImpl::value_as_sv() +{ + std::shared_lock l(c->lock); + ceph_assert(it->valid()); + return it->value_as_sv(); +} + // ===================================== @@ -6911,8 +6930,19 @@ int BlueStore::_check_main_bdev_label() return -EIO; } if (bluestore_bdev_label_require_all && r != 0) { - derr << __func__ << " not all labels read properly" << dendl; - return -EIO; + // We are about to complain that some labels failed. + // But in case if we expanded block device some labels will not be good. + uint64_t lsize = std::max(BDEV_LABEL_BLOCK_SIZE, min_alloc_size); + uint32_t valid_locations = 0; + for (uint64_t loc : bdev_label_positions) { + if (loc + lsize <= bdev_label.size) { + ++valid_locations; + } + } + if (valid_locations != bdev_label_valid_locations.size()) { + derr << __func__ << " not all labels read properly" << dendl; + return -EIO; + } } return 0; } @@ -8948,11 +8978,25 @@ int BlueStore::expand_devices(ostream& out) _close_db_and_around(); // mount in read/write to sync expansion changes + if (bdev_label_multi) { + // We need not do fsck, because we can be broken - size is increased, + // but we might not have labels set. + cct->_conf.set_val_or_die("bluestore_fsck_on_mount", "false"); + } r = _mount(); ceph_assert(r == 0); if (fm && fm->is_null_manager()) { // we grow the allocation range, must reflect it in the allocation file alloc->init_add_free(size0, size - size0); + if (bdev_label_multi) { + uint64_t lsize = std::max(BDEV_LABEL_BLOCK_SIZE, min_alloc_size); + for (uint64_t loc : bdev_label_positions) { + if ((loc >= size0) && (loc + lsize <= size)) { + bdev_label_valid_locations.push_back(loc); + } + } + _write_bdev_label(cct, bdev, path + "/block", bdev_label, bdev_label_valid_locations); + } need_to_destage_allocation_file = true; } umount(); @@ -13601,52 +13645,6 @@ int BlueStore::omap_get_values( return r; } -#ifdef WITH_SEASTAR -int BlueStore::omap_get_values( - CollectionHandle &c_, ///< [in] Collection containing oid - const ghobject_t &oid, ///< [in] Object containing omap - const std::optional<string> &start_after, ///< [in] Keys to get - map<string, bufferlist> *output ///< [out] Returned keys and values - ) -{ - Collection *c = static_cast<Collection *>(c_.get()); - dout(15) << __func__ << " " << c->get_cid() << " oid " << oid << dendl; - if (!c->exists) - return -ENOENT; - std::shared_lock l(c->lock); - int r = 0; - OnodeRef o = c->get_onode(oid, false); - if (!o || !o->exists) { - r = -ENOENT; - goto out; - } - if (!o->onode.has_omap()) { - goto out; - } - o->flush(); - { - ObjectMap::ObjectMapIterator iter = get_omap_iterator(c_, oid); - if (!iter) { - r = -ENOENT; - goto out; - } - if (start_after) { - iter->upper_bound(*start_after); - } else { - iter->seek_to_first(); - } - for (; iter->valid(); iter->next()) { - output->insert(make_pair(iter->key(), iter->value())); - } - } - -out: - dout(10) << __func__ << " " << c->get_cid() << " oid " << oid << " = " << r - << dendl; - return r; -} -#endif - int BlueStore::omap_check_keys( CollectionHandle &c_, ///< [in] Collection containing oid const ghobject_t &oid, ///< [in] Object containing omap @@ -13724,6 +13722,94 @@ ObjectMap::ObjectMapIterator BlueStore::get_omap_iterator( return ObjectMap::ObjectMapIterator(new OmapIteratorImpl(logger,c, o, it)); } +int BlueStore::omap_iterate( + CollectionHandle &c_, ///< [in] collection + const ghobject_t &oid, ///< [in] object + ObjectStore::omap_iter_seek_t start_from, ///< [in] where the iterator should point to at the beginning + std::function<omap_iter_ret_t(std::string_view, std::string_view)> f + ) +{ + Collection *c = static_cast<Collection *>(c_.get()); + dout(10) << __func__ << " " << c->get_cid() << " " << oid << dendl; + if (!c->exists) { + return -ENOENT; + } + std::shared_lock l(c->lock); + OnodeRef o = c->get_onode(oid, false); + if (!o || !o->exists) { + dout(10) << __func__ << " " << oid << "doesn't exist" <<dendl; + return -ENOENT; + } + o->flush(); + dout(10) << __func__ << " has_omap = " << (int)o->onode.has_omap() <<dendl; + if (!o->onode.has_omap()) { + // nothing to do + return 0; + } + + KeyValueDB::Iterator it; + { + auto bounds = KeyValueDB::IteratorBounds(); + std::string lower_bound, upper_bound; + o->get_omap_key(string(), &lower_bound); + o->get_omap_tail(&upper_bound); + bounds.lower_bound = std::move(lower_bound); + bounds.upper_bound = std::move(upper_bound); + it = db->get_iterator(o->get_omap_prefix(), 0, std::move(bounds)); + } + + // seek the iterator + { + std::string key; + o->get_omap_key(start_from.seek_position, &key); + auto start = ceph::mono_clock::now(); + if (start_from.seek_type == omap_iter_seek_t::LOWER_BOUND) { + it->lower_bound(key); + c->store->log_latency( + __func__, + l_bluestore_omap_lower_bound_lat, + ceph::mono_clock::now() - start, + c->store->cct->_conf->bluestore_log_omap_iterator_age); + } else { + it->upper_bound(key); + c->store->log_latency( + __func__, + l_bluestore_omap_upper_bound_lat, + ceph::mono_clock::now() - start, + c->store->cct->_conf->bluestore_log_omap_iterator_age); + } + } + + // iterate! + std::string tail; + o->get_omap_tail(&tail); + const std::string_view::size_type userkey_offset_in_dbkey = + o->calc_userkey_offset_in_omap_key(); + ceph::timespan next_lat_acc{0}; + while (it->valid()) { + const auto& db_key = it->raw_key_as_sv().second; + if (db_key >= tail) { + break; + } + std::string_view user_key = db_key.substr(userkey_offset_in_dbkey); + omap_iter_ret_t ret = f(user_key, it->value_as_sv()); + if (ret == omap_iter_ret_t::STOP) { + break; + } else if (ret == omap_iter_ret_t::NEXT) { + ceph::time_guard<ceph::mono_clock>{next_lat_acc}; + it->next(); + } else { + ceph_abort(); + } + } + c->store->log_latency( + __func__, + l_bluestore_omap_next_lat, + next_lat_acc, + c->store->cct->_conf->bluestore_log_omap_iterator_age); + return 0; +} + // ----------------- // write helpers diff --git a/src/os/bluestore/BlueStore.h b/src/os/bluestore/BlueStore.h index 99f8d057cf0..5549f97ffea 100644 --- a/src/os/bluestore/BlueStore.h +++ b/src/os/bluestore/BlueStore.h @@ -1457,6 +1457,7 @@ public: } void rewrite_omap_key(const std::string& old, std::string *out); + size_t calc_userkey_offset_in_omap_key() const; void decode_omap_key(const std::string& key, std::string *user_key); void finish_write(TransContext* txc, uint32_t offset, uint32_t length); @@ -1753,6 +1754,7 @@ public: int next() override; std::string key() override; ceph::buffer::list value() override; + std::string_view value_as_sv() override; std::string tail_key() override { return tail; } @@ -3416,15 +3418,6 @@ public: std::map<std::string, ceph::buffer::list> *out ///< [out] Returned keys and values ) override; -#ifdef WITH_SEASTAR - int omap_get_values( - CollectionHandle &c, ///< [in] Collection containing oid - const ghobject_t &oid, ///< [in] Object containing omap - const std::optional<std::string> &start_after, ///< [in] Keys to get - std::map<std::string, ceph::buffer::list> *out ///< [out] Returned keys and values - ) override; -#endif - /// Filters keys into out which are defined on oid int omap_check_keys( CollectionHandle &c, ///< [in] Collection containing oid @@ -3438,6 +3431,13 @@ public: const ghobject_t &oid ///< [in] object ) override; + int omap_iterate( + CollectionHandle &c, ///< [in] collection + const ghobject_t &oid, ///< [in] object + omap_iter_seek_t start_from, ///< [in] where the iterator should point to at the beginning + std::function<omap_iter_ret_t(std::string_view, std::string_view)> f + ) override; + void set_fsid(uuid_d u) override { fsid = u; } diff --git a/src/os/bluestore/bluefs_types.cc b/src/os/bluestore/bluefs_types.cc index e18dd490140..fe77f7f74d8 100644 --- a/src/os/bluestore/bluefs_types.cc +++ b/src/os/bluestore/bluefs_types.cc @@ -154,7 +154,9 @@ mempool::bluefs::vector<bluefs_extent_t>::iterator bluefs_fnode_t::seek( assert(it != extents_index.begin()); --it; assert(offset >= *it); - p += it - extents_index.begin(); + uint32_t skip = it - extents_index.begin(); + ceph_assert(skip <= extents.size()); + p += skip; offset -= *it; } diff --git a/src/os/bluestore/bluefs_types.h b/src/os/bluestore/bluefs_types.h index 627118c12f8..08b3ca0cf41 100644 --- a/src/os/bluestore/bluefs_types.h +++ b/src/os/bluestore/bluefs_types.h @@ -89,6 +89,7 @@ struct bluefs_fnode_t { void recalc_allocated() { allocated = 0; extents_index.reserve(extents.size()); + extents_index.clear(); for (auto& p : extents) { extents_index.emplace_back(allocated); allocated += p.length; diff --git a/src/os/kstore/KStore.cc b/src/os/kstore/KStore.cc index 7158486ca38..a069d429155 100644 --- a/src/os/kstore/KStore.cc +++ b/src/os/kstore/KStore.cc @@ -1651,6 +1651,13 @@ bufferlist KStore::OmapIteratorImpl::value() return it->value(); } +std::string_view KStore::OmapIteratorImpl::value_as_sv() +{ + std::shared_lock l{c->lock}; + ceph_assert(it->valid()); + return it->value_as_sv(); +} + int KStore::omap_get( CollectionHandle& ch, ///< [in] Collection containing oid const ghobject_t &oid, ///< [in] Object containing omap @@ -1866,6 +1873,71 @@ ObjectMap::ObjectMapIterator KStore::get_omap_iterator( return ObjectMap::ObjectMapIterator(new OmapIteratorImpl(c, o, it)); } +int KStore::omap_iterate( + CollectionHandle &ch, ///< [in] collection + const ghobject_t &oid, ///< [in] object + ObjectStore::omap_iter_seek_t start_from, ///< [in] where the iterator should point to at the beginning + std::function<omap_iter_ret_t(std::string_view, std::string_view)> f) +{ + dout(10) << __func__ << " " << ch->cid << " " << oid << dendl; + Collection *c = static_cast<Collection*>(ch.get()); + { + std::shared_lock l{c->lock}; + + OnodeRef o = c->get_onode(oid, false); + if (!o || !o->exists) { + dout(10) << __func__ << " " << oid << "doesn't exist" <<dendl; + return -ENOENT; + } + o->flush(); + dout(10) << __func__ << " header = " << o->onode.omap_head <<dendl; + + KeyValueDB::Iterator it = db->get_iterator(PREFIX_OMAP); + std::string tail; + std::string seek_key; + if (o->onode.omap_head) { + return 0; // nothing to do + } + + // acquire data depedencies for seek & iterate + get_omap_key(o->onode.omap_head, start_from.seek_position, &seek_key); + get_omap_tail(o->onode.omap_head, &tail); + + // acquire the iterator + { + it = db->get_iterator(PREFIX_OMAP); + } + + // seek the iterator + { + if (start_from.seek_type == omap_iter_seek_t::LOWER_BOUND) { + it->lower_bound(seek_key); + } else { + it->upper_bound(seek_key); + } + } + + // iterate! + while (it->valid()) { + std::string user_key; + if (const auto& db_key = it->raw_key().second; db_key >= tail) { + break; + } else { + decode_omap_key(db_key, &user_key); + } + omap_iter_ret_t ret = f(user_key, it->value_as_sv()); + if (ret == omap_iter_ret_t::STOP) { + break; + } else if (ret == omap_iter_ret_t::NEXT) { + it->next(); + } else { + ceph_abort(); + } + } + } + return 0; +} + // ----------------- // write helpers diff --git a/src/os/kstore/KStore.h b/src/os/kstore/KStore.h index 9a9d413c66a..06115d3cab7 100644 --- a/src/os/kstore/KStore.h +++ b/src/os/kstore/KStore.h @@ -180,6 +180,7 @@ public: int next() override; std::string key() override; ceph::buffer::list value() override; + std::string_view value_as_sv() override; int status() override { return 0; } @@ -553,6 +554,13 @@ public: const ghobject_t &oid ///< [in] object ) override; + int omap_iterate( + CollectionHandle &c, ///< [in] collection + const ghobject_t &oid, ///< [in] object + omap_iter_seek_t start_from, ///< [in] where the iterator should point to at the beginning + std::function<omap_iter_ret_t(std::string_view, std::string_view)> f + ) override; + void set_fsid(uuid_d u) override { fsid = u; } diff --git a/src/os/memstore/MemStore.cc b/src/os/memstore/MemStore.cc index 89cb09361cf..f9d3bf0d8a2 100644 --- a/src/os/memstore/MemStore.cc +++ b/src/os/memstore/MemStore.cc @@ -537,30 +537,6 @@ int MemStore::omap_get_values( return 0; } -#ifdef WITH_SEASTAR -int MemStore::omap_get_values( - CollectionHandle& ch, ///< [in] Collection containing oid - const ghobject_t &oid, ///< [in] Object containing omap - const std::optional<std::string> &start_after, ///< [in] Keys to get - std::map<std::string, ceph::buffer::list> *out ///< [out] Returned keys and values - ) -{ - dout(10) << __func__ << " " << ch->cid << " " << oid << dendl; - Collection *c = static_cast<Collection*>(ch.get()); - ObjectRef o = c->get_object(oid); - if (!o) - return -ENOENT; - assert(start_after); - std::lock_guard lock{o->omap_mutex}; - for (auto it = o->omap.upper_bound(*start_after); - it != std::end(o->omap); - ++it) { - out->insert(*it); - } - return 0; -} -#endif - int MemStore::omap_check_keys( CollectionHandle& ch, ///< [in] Collection containing oid const ghobject_t &oid, ///< [in] Object containing omap @@ -622,6 +598,10 @@ public: std::lock_guard lock{o->omap_mutex}; return it->second; } + std::string_view value_as_sv() override { + std::lock_guard lock{o->omap_mutex}; + return std::string_view{it->second.c_str(), it->second.length()}; + } int status() override { return 0; } @@ -639,6 +619,48 @@ ObjectMap::ObjectMapIterator MemStore::get_omap_iterator( return ObjectMap::ObjectMapIterator(new OmapIteratorImpl(c, o)); } +int MemStore::omap_iterate( + CollectionHandle &ch, ///< [in] collection + const ghobject_t &oid, ///< [in] object + ObjectStore::omap_iter_seek_t start_from, ///< [in] where the iterator should point to at the beginning + std::function<omap_iter_ret_t(std::string_view, std::string_view)> f) +{ + Collection *c = static_cast<Collection*>(ch.get()); + ObjectRef o = c->get_object(oid); + if (!o) { + return -ENOENT; + } + + { + std::lock_guard lock{o->omap_mutex}; + + // obtain seek the iterator + decltype(o->omap)::iterator it; + { + if (start_from.seek_type == omap_iter_seek_t::LOWER_BOUND) { + it = o->omap.lower_bound(start_from.seek_position); + } else { + it = o->omap.upper_bound(start_from.seek_position); + } + } + + // iterate! + while (it != o->omap.end()) { + // potentially rectifying memcpy but who cares for memstore? + omap_iter_ret_t ret = + f(it->first, std::string_view{it->second.c_str(), it->second.length()}); + if (ret == omap_iter_ret_t::STOP) { + break; + } else if (ret == omap_iter_ret_t::NEXT) { + ++it; + } else { + ceph_abort(); + } + } + } + return 0; +} + // --------------- // write operations diff --git a/src/os/memstore/MemStore.h b/src/os/memstore/MemStore.h index 2abe552891f..9621773598f 100644 --- a/src/os/memstore/MemStore.h +++ b/src/os/memstore/MemStore.h @@ -363,14 +363,6 @@ public: const std::set<std::string> &keys, ///< [in] Keys to get std::map<std::string, ceph::buffer::list> *out ///< [out] Returned keys and values ) override; -#ifdef WITH_SEASTAR - int omap_get_values( - CollectionHandle &c, ///< [in] Collection containing oid - const ghobject_t &oid, ///< [in] Object containing omap - const std::optional<std::string> &start_after, ///< [in] Keys to get - std::map<std::string, ceph::buffer::list> *out ///< [out] Returned keys and values - ) override; -#endif using ObjectStore::omap_check_keys; /// Filters keys into out which are defined on oid @@ -387,6 +379,13 @@ public: const ghobject_t &oid ///< [in] object ) override; + int omap_iterate( + CollectionHandle &c, ///< [in] collection + const ghobject_t &oid, ///< [in] object + omap_iter_seek_t start_from, ///< [in] where the iterator should point to at the beginning + std::function<omap_iter_ret_t(std::string_view, std::string_view)> f + ) override; + void set_fsid(uuid_d u) override; uuid_d get_fsid() override; diff --git a/src/osd/ECBackend.cc b/src/osd/ECBackend.cc index fa2570aba42..8630b038812 100644 --- a/src/osd/ECBackend.cc +++ b/src/osd/ECBackend.cc @@ -945,6 +945,10 @@ void ECBackend::handle_sub_write( } trace.event("handle_sub_write"); + if (cct->_conf->bluestore_debug_inject_read_err && + ec_inject_test_write_error3(op.soid)) { + ceph_abort_msg("Error inject - OSD down"); + } if (!get_parent()->pgb_is_primary()) get_parent()->update_stats(op.stats); ObjectStore::Transaction localt; @@ -1191,6 +1195,15 @@ void ECBackend::handle_sub_write_reply( i->second->on_all_commit = 0; i->second->trace.event("ec write all committed"); } + if (cct->_conf->bluestore_debug_inject_read_err && + (i->second->pending_commit.size() == 1) && + ec_inject_test_write_error2(i->second->hoid)) { + std::string cmd = + "{ \"prefix\": \"osd down\", \"ids\": [\"" + std::to_string( get_parent()->whoami() ) + "\"] }"; + vector<std::string> vcmd{cmd}; + dout(0) << __func__ << " Error inject - marking OSD down" << dendl; + get_parent()->start_mon_command(vcmd, {}, nullptr, nullptr, nullptr); + } rmw_pipeline.check_ops(); } @@ -1208,6 +1221,19 @@ void ECBackend::handle_sub_read_reply( return; } ReadOp &rop = iter->second; + if (cct->_conf->bluestore_debug_inject_read_err) { + for (auto i = op.buffers_read.begin(); + i != op.buffers_read.end(); + ++i) { + if (ec_inject_test_read_error0(ghobject_t(i->first, ghobject_t::NO_GEN, op.from.shard))) { + dout(0) << __func__ << " Error inject - EIO error for shard " << op.from.shard << dendl; + op.buffers_read.erase(i->first); + op.attrs_read.erase(i->first); + op.errors[i->first] = -EIO; + } + + } + } for (auto i = op.buffers_read.begin(); i != op.buffers_read.end(); ++i) { diff --git a/src/osd/ECCommon.cc b/src/osd/ECCommon.cc index 609ac3141ae..59077547fcb 100644 --- a/src/osd/ECCommon.cc +++ b/src/osd/ECCommon.cc @@ -226,8 +226,14 @@ void ECCommon::ReadPipeline::get_all_avail_shards( ++i) { dout(10) << __func__ << ": checking acting " << *i << dendl; const pg_missing_t &missing = get_parent()->get_shard_missing(*i); - if (error_shards.find(*i) != error_shards.end()) + if (error_shards.contains(*i)) { continue; + } + if (cct->_conf->bluestore_debug_inject_read_err && + ec_inject_test_read_error1(ghobject_t(hoid, ghobject_t::NO_GEN, i->shard))) { + dout(0) << __func__ << " Error inject - Missing shard " << i->shard << dendl; + continue; + } if (!missing.is_missing(hoid)) { ceph_assert(!have.count(i->shard)); have.insert(i->shard); @@ -912,6 +918,11 @@ bool ECCommon::RMWPipeline::try_reads_to_commit() if (*i == get_parent()->whoami_shard()) { should_write_local = true; local_write_op.claim(sop); + } else if (cct->_conf->bluestore_debug_inject_read_err && + ec_inject_test_write_error1(ghobject_t(op->hoid, + ghobject_t::NO_GEN, i->shard))) { + dout(0) << " Error inject - Dropping write message to shard " << + i->shard << dendl; } else { MOSDECSubOpWrite *r = new MOSDECSubOpWrite(sop); r->pgid = spg_t(get_parent()->primary_spg_t().pgid, i->shard); @@ -1090,3 +1101,305 @@ ECUtil::HashInfoRef ECCommon::UnstableHashInfoRegistry::get_hash_info( } return ref; } + +// Error inject interfaces +static ceph::recursive_mutex ec_inject_lock = + ceph::make_recursive_mutex("ECCommon::ec_inject_lock"); +static std::map<ghobject_t,std::pair<int64_t,int64_t>> ec_inject_read_failures0; +static std::map<ghobject_t,std::pair<int64_t,int64_t>> ec_inject_read_failures1; +static std::map<ghobject_t,std::pair<int64_t,int64_t>> ec_inject_write_failures0; +static std::map<ghobject_t,std::pair<int64_t,int64_t>> ec_inject_write_failures1; +static std::map<ghobject_t,std::pair<int64_t,int64_t>> ec_inject_write_failures2; +static std::map<ghobject_t,std::pair<int64_t,int64_t>> ec_inject_write_failures3; +static std::map<ghobject_t,shard_id_t> ec_inject_write_failures0_shard; +static std::set<osd_reqid_t> ec_inject_write_failures0_reqid; + +/** + * Configure a read error inject that typically forces additional reads of + * shards in an EC pool to recover data using the redundancy. With multiple + * errors it is possible to force client reads to fail. + * + * Type 0 - Simulate a medium error. Fail a read with -EIO to force + * additional reads and a decode + * + * Type 1 - Simulate a missing OSD. Dont even try to read a shard + * + * @brief Set up a read error inject for an object in an EC pool. + * @param o Target object for the error inject. + * @param when Error inject starts after this many object store reads. + * @param duration Error inject affects this many object store reads. + * @param type Type of error inject 0 = EIO, 1 = missing shard. + * @return string Result of configuring the error inject. + */ +std::string ec_inject_read_error(const ghobject_t& o, + const int64_t type, + const int64_t when, + const int64_t duration) { + std::lock_guard<ceph::recursive_mutex> l(ec_inject_lock); + ghobject_t os = o; + if (os.hobj.oid.name == "*") { + os.hobj.set_hash(0); + } + switch (type) { + case 0: + ec_inject_read_failures0[os] = std::pair(when, duration); + return "ok - read returns EIO"; + case 1: + ec_inject_read_failures1[os] = std::pair(when, duration); + return "ok - read pretends shard is missing"; + default: + break; + } + return "unrecognized error inject type"; +} + +/** + * Configure a write error inject that either fails an OSD or causes a + * client write operation to be rolled back. + * + * Type 0 - Tests rollback. Drop a write I/O to a shard, then simulate an OSD + * down to force rollback to occur, lastly fail the retried write from the + * client so the results of the rollback can be inspected. + * + * Type 1 - Drop a write I/O to a shard. Used on its own this will hang a + * write I/O. + * + * Type 2 - Simulate an OSD down (ceph osd down) to force a new epoch. Usually + * used together with type 1 to force a rollback + * + * Type 3 - Abort when an OSD processes a write I/O to a shard. Typically the + * client write will be commited while the OSD is absent which will result in + * recovery or backfill later when the OSD returns. + * + * @brief Set up a write error inject for an object in an EC pool. + * @param o Target object for the error inject. + * @param when Error inject starts after this many object store reads. + * @param duration Error inject affects this many object store reads. + * @param type Type of error inject 0 = EIO, 1 = missing shard. + * @return string Result of configuring the error inect. + */ +std::string ec_inject_write_error(const ghobject_t& o, + const int64_t type, + const int64_t when, + const int64_t duration) { + std::lock_guard<ceph::recursive_mutex> l(ec_inject_lock); + std::map<ghobject_t,std::pair<int64_t,int64_t>> *failures; + ghobject_t os = o; + bool no_shard = true; + std::string result; + switch (type) { + case 0: + failures = &ec_inject_write_failures0; + result = "ok - drop write, sim OSD down and fail client retry with EINVAL"; + break; + case 1: + failures = &ec_inject_write_failures1; + no_shard = false; + result = "ok - drop write to shard"; + break; + case 2: + failures = &ec_inject_write_failures2; + result = "ok - inject OSD down"; + break; + case 3: + if (duration != 1) { + return "duration must be 1"; + } + failures = &ec_inject_write_failures3; + result = "ok - write abort OSDs"; + break; + default: + return "unrecognized error inject type"; + } + if (no_shard) { + os.set_shard(shard_id_t::NO_SHARD); + } + if (os.hobj.oid.name == "*") { + os.hobj.set_hash(0); + } + (*failures)[os] = std::pair(when, duration); + if (type == 0) { + ec_inject_write_failures0_shard[os] = o.shard_id; + } + return result; +} + +/** + * @brief Clear a previously configured read error inject. + * @param o Target object for the error inject. + * @param type Type of error inject 0 = EIO, 1 = missing shard. + * @return string Indication of how many errors were cleared. + */ +std::string ec_inject_clear_read_error(const ghobject_t& o, + const int64_t type) { + std::lock_guard<ceph::recursive_mutex> l(ec_inject_lock); + std::map<ghobject_t,std::pair<int64_t,int64_t>> *failures; + ghobject_t os = o; + int64_t remaining = 0; + switch (type) { + case 0: + failures = &ec_inject_read_failures0; + break; + case 1: + failures = &ec_inject_read_failures1; + break; + default: + return "unrecognized error inject type"; + } + if (os.hobj.oid.name == "*") { + os.hobj.set_hash(0); + } + auto it = failures->find(os); + if (it != failures->end()) { + remaining = it->second.second; + failures->erase(it); + } + if (remaining == 0) { + return "no outstanding error injects"; + } else if (remaining == 1) { + return "ok - 1 inject cleared"; + } + return "ok - " + std::to_string(remaining) + " injects cleared"; +} + +/** + * @brief Clear a previously configured write error inject. + * @param o Target object for the error inject. + * @param type Type of error inject 0 = EIO, 1 = missing shard. + * @return string Indication of how many errors were cleared. + */ +std::string ec_inject_clear_write_error(const ghobject_t& o, + const int64_t type) { + std::lock_guard<ceph::recursive_mutex> l(ec_inject_lock); + std::map<ghobject_t,std::pair<int64_t,int64_t>> *failures; + ghobject_t os = o; + bool no_shard = true; + int64_t remaining = 0; + switch (type) { + case 0: + failures = &ec_inject_write_failures0; + break; + case 1: + failures = &ec_inject_write_failures1; + no_shard = false; + break; + case 2: + failures = &ec_inject_write_failures2; + break; + case 3: + failures = &ec_inject_write_failures3; + break; + default: + return "unrecognized error inject type"; + } + if (no_shard) { + os.set_shard(shard_id_t::NO_SHARD); + } + if (os.hobj.oid.name == "*") { + os.hobj.set_hash(0); + } + auto it = failures->find(os); + if (it != failures->end()) { + remaining = it->second.second; + failures->erase(it); + if (type == 0) { + ec_inject_write_failures0_shard.erase(os); + } + } + if (remaining == 0) { + return "no outstanding error injects"; + } else if (remaining == 1) { + return "ok - 1 inject cleared"; + } + return "ok - " + std::to_string(remaining) + " injects cleared"; +} + +static bool ec_inject_test_error(const ghobject_t& o, + std::map<ghobject_t,std::pair<int64_t,int64_t>> *failures) +{ + std::lock_guard<ceph::recursive_mutex> l(ec_inject_lock); + auto it = failures->find(o); + if (it == failures->end()) { + ghobject_t os = o; + os.hobj.oid.name = "*"; + os.hobj.set_hash(0); + it = failures->find(os); + } + if (it != failures->end()) { + auto && [when,duration] = it->second; + if (when > 0) { + when--; + return false; + } + if (--duration <= 0) { + failures->erase(it); + } + return true; + } + return false; +} + +bool ec_inject_test_read_error0(const ghobject_t& o) +{ + return ec_inject_test_error(o, &ec_inject_read_failures0); +} + +bool ec_inject_test_read_error1(const ghobject_t& o) +{ + return ec_inject_test_error(o, &ec_inject_read_failures1); +} + +bool ec_inject_test_write_error0(const hobject_t& o, + const osd_reqid_t& reqid) { + std::lock_guard<ceph::recursive_mutex> l(ec_inject_lock); + ghobject_t os = ghobject_t(o, ghobject_t::NO_GEN, shard_id_t::NO_SHARD); + if (ec_inject_write_failures0_reqid.count(reqid)) { + // Matched reqid of retried write - flag for failure + ec_inject_write_failures0_reqid.erase(reqid); + return true; + } + auto it = ec_inject_write_failures0.find(os); + if (it == ec_inject_write_failures0.end()) { + os.hobj.oid.name = "*"; + os.hobj.set_hash(0); + it = ec_inject_write_failures0.find(os); + } + if (it != ec_inject_write_failures0.end()) { + auto && [when, duration] = it->second; + auto shard = ec_inject_write_failures0_shard.find(os)->second; + if (when > 0) { + when--; + } else { + if (--duration <= 0) { + ec_inject_write_failures0.erase(it); + ec_inject_write_failures0_shard.erase(os); + } + // Error inject triggered - save reqid + ec_inject_write_failures0_reqid.insert(reqid); + // Set up error inject to drop message to primary + ec_inject_write_error(ghobject_t(o, ghobject_t::NO_GEN, shard), 1, 0, 1); + } + } + return false; +} + +bool ec_inject_test_write_error1(const ghobject_t& o) { + bool rc = ec_inject_test_error(o, &ec_inject_write_failures1); + if (rc) { + // Set up error inject to generate OSD down + ec_inject_write_error(o, 2, 0, 1); + } + return rc; +} + +bool ec_inject_test_write_error2(const hobject_t& o) { + return ec_inject_test_error( + ghobject_t(o, ghobject_t::NO_GEN, shard_id_t::NO_SHARD), + &ec_inject_write_failures2); +} + +bool ec_inject_test_write_error3(const hobject_t& o) { + return ec_inject_test_error( + ghobject_t(o, ghobject_t::NO_GEN, shard_id_t::NO_SHARD), + &ec_inject_write_failures3); +} diff --git a/src/osd/ECCommon.h b/src/osd/ECCommon.h index 7ff9cae7646..de4c11ad50f 100644 --- a/src/osd/ECCommon.h +++ b/src/osd/ECCommon.h @@ -493,6 +493,7 @@ struct ECCommon { ); ///< @return error code, 0 on success void schedule_recovery_work(); + }; /** @@ -843,3 +844,15 @@ void ECCommon::ReadPipeline::filter_read_op( on_schedule_recovery(op); } } + +// Error inject interfaces +std::string ec_inject_read_error(const ghobject_t& o, const int64_t type, const int64_t when, const int64_t duration); +std::string ec_inject_write_error(const ghobject_t& o, const int64_t type, const int64_t when, const int64_t duration); +std::string ec_inject_clear_read_error(const ghobject_t& o, const int64_t type); +std::string ec_inject_clear_write_error(const ghobject_t& o, const int64_t type); +bool ec_inject_test_read_error0(const ghobject_t& o); +bool ec_inject_test_read_error1(const ghobject_t& o); +bool ec_inject_test_write_error0(const hobject_t& o,const osd_reqid_t& reqid); +bool ec_inject_test_write_error1(const ghobject_t& o); +bool ec_inject_test_write_error2(const hobject_t& o); +bool ec_inject_test_write_error3(const hobject_t& o); diff --git a/src/osd/ExtentCache.h b/src/osd/ExtentCache.h index 972228cd077..7dc1d4f7263 100644 --- a/src/osd/ExtentCache.h +++ b/src/osd/ExtentCache.h @@ -363,7 +363,7 @@ private: extent, boost::intrusive::list_member_hook<>, &extent::pin_list_member>; - using list = boost::intrusive::list<extent, list_member_options>; + using list = boost::intrusive::list<extent, boost::intrusive::constant_time_size<false>, list_member_options>; list pin_list; ~pin_state() { ceph_assert(pin_list.empty()); diff --git a/src/osd/OSD.cc b/src/osd/OSD.cc index 5223eb283e9..9c9e540cf61 100644 --- a/src/osd/OSD.cc +++ b/src/osd/OSD.cc @@ -37,6 +37,7 @@ #include "osd/PG.h" #include "osd/scrubber/scrub_machine.h" #include "osd/scrubber/pg_scrubber.h" +#include "osd/ECCommon.h" #include "include/types.h" #include "include/compat.h" @@ -4348,6 +4349,46 @@ void OSD::final_init() "inject metadata error to an object"); ceph_assert(r == 0); r = admin_socket->register_command( + "injectecreaderr " \ + "name=pool,type=CephString " \ + "name=objname,type=CephObjectname " \ + "name=shardid,type=CephInt,req=true,range=0|255 " \ + "name=type,type=CephInt,req=false " \ + "name=when,type=CephInt,req=false " \ + "name=duration,type=CephInt,req=false", + test_ops_hook, + "inject error for read of object in an EC pool"); + ceph_assert(r == 0); + r = admin_socket->register_command( + "injectecclearreaderr " \ + "name=pool,type=CephString " \ + "name=objname,type=CephObjectname " \ + "name=shardid,type=CephInt,req=true,range=0|255 " \ + "name=type,type=CephInt,req=false", + test_ops_hook, + "clear read error injects for object in an EC pool"); + ceph_assert(r == 0); + r = admin_socket->register_command( + "injectecwriteerr " \ + "name=pool,type=CephString " \ + "name=objname,type=CephObjectname " \ + "name=shardid,type=CephInt,req=true,range=0|255 " \ + "name=type,type=CephInt,req=false " \ + "name=when,type=CephInt,req=false " \ + "name=duration,type=CephInt,req=false", + test_ops_hook, + "inject error for write of object in an EC pool"); + ceph_assert(r == 0); + r = admin_socket->register_command( + "injectecclearwriteerr " \ + "name=pool,type=CephString " \ + "name=objname,type=CephObjectname " \ + "name=shardid,type=CephInt,req=true,range=0|255 " \ + "name=type,type=CephInt,req=false", + test_ops_hook, + "clear write error inject for object in an EC pool"); + ceph_assert(r == 0); + r = admin_socket->register_command( "set_recovery_delay " \ "name=utime,type=CephInt,req=false", test_ops_hook, @@ -6487,8 +6528,10 @@ void TestOpsSocketHook::test_ops(OSDService *service, ObjectStore *store, //directly request the osd make a change. if (command == "setomapval" || command == "rmomapkey" || command == "setomapheader" || command == "getomap" || - command == "truncobj" || command == "injectmdataerr" || - command == "injectdataerr" + command == "truncobj" || + command == "injectmdataerr" || command == "injectdataerr" || + command == "injectecreaderr" || command == "injectecclearreaderr" || + command == "injectecwriteerr" || command == "injectecclearwriteerr" ) { pg_t rawpg; int64_t pool; @@ -6527,8 +6570,21 @@ void TestOpsSocketHook::test_ops(OSDService *service, ObjectStore *store, ghobject_t gobj(obj, ghobject_t::NO_GEN, shard_id_t(uint8_t(shardid))); spg_t pgid(curmap->raw_pg_to_pg(rawpg), shard_id_t(shardid)); if (curmap->pg_is_ec(rawpg)) { - if ((command != "injectdataerr") && (command != "injectmdataerr")) { - ss << "Must not call on ec pool, except injectdataerr or injectmdataerr"; + if ((command != "injectdataerr") && + (command != "injectmdataerr") && + (command != "injectecreaderr") && + (command != "injectecclearreaderr") && + (command != "injectecwriteerr") && + (command != "injectecclearwriteerr")) { + ss << "Must not call on ec pool"; + return; + } + } else { + if ((command == "injectecreaderr") || + (command == "injecteclearreaderr") || + (command == "injectecwriteerr") || + (command == "injecteclearwriteerr")) { + ss << "Only supported on ec pool"; return; } } @@ -6607,6 +6663,38 @@ void TestOpsSocketHook::test_ops(OSDService *service, ObjectStore *store, } else if (command == "injectmdataerr") { store->inject_mdata_error(gobj); ss << "ok"; + } else if (command == "injectecreaderr") { + if (service->cct->_conf->bluestore_debug_inject_read_err) { + int64_t type = cmd_getval_or<int64_t>(cmdmap, "type", 0); + int64_t when = cmd_getval_or<int64_t>(cmdmap, "when", 0); + int64_t duration = cmd_getval_or<int64_t>(cmdmap, "duration", 1); + ss << ec_inject_read_error(gobj, type, when, duration); + } else { + ss << "bluestore_debug_inject_read_err not enabled"; + } + } else if (command == "injectecclearreaderr") { + if (service->cct->_conf->bluestore_debug_inject_read_err) { + int64_t type = cmd_getval_or<int64_t>(cmdmap, "type", 0); + ss << ec_inject_clear_read_error(gobj, type); + } else { + ss << "bluestore_debug_inject_read_err not enabled"; + } + } else if (command == "injectecwriteerr") { + if (service->cct->_conf->bluestore_debug_inject_read_err) { + int64_t type = cmd_getval_or<int64_t>(cmdmap, "type", 0); + int64_t when = cmd_getval_or<int64_t>(cmdmap, "when", 0); + int64_t duration = cmd_getval_or<int64_t>(cmdmap, "duration", 1); + ss << ec_inject_write_error(gobj, type, when, duration); + } else { + ss << "bluestore_debug_inject_read_err not enabled"; + } + } else if (command == "injectecclearwriteerr") { + if (service->cct->_conf->bluestore_debug_inject_read_err) { + int64_t type = cmd_getval_or<int64_t>(cmdmap, "type", 0); + ss << ec_inject_clear_write_error(gobj, type); + } else { + ss << "bluestore_debug_inject_read_err not enabled"; + } } return; } diff --git a/src/osd/OSDMap.cc b/src/osd/OSDMap.cc index b87484c1a9d..9b3593d54e5 100644 --- a/src/osd/OSDMap.cc +++ b/src/osd/OSDMap.cc @@ -1642,12 +1642,10 @@ void OSDMap::get_out_of_subnet_osd_counts(CephContext *cct, for (int i = 0; i < max_osd; i++) { if (exists(i) && is_up(i)) { if (const auto& addrs = get_addrs(i).v; addrs.size() >= 2) { - auto v1_addr = addrs[0].ip_only_to_str(); - if (!is_addr_in_subnet(cct, public_network, v1_addr)) { + if (!is_addr_in_subnet(cct, public_network, addrs[0])) { unreachable->emplace(i); } - auto v2_addr = addrs[1].ip_only_to_str(); - if (!is_addr_in_subnet(cct, public_network, v2_addr)) { + if (!is_addr_in_subnet(cct, public_network, addrs[1])) { unreachable->emplace(i); } } diff --git a/src/osd/PGBackend.h b/src/osd/PGBackend.h index b87aa1da677..f5eb9ea951e 100644 --- a/src/osd/PGBackend.h +++ b/src/osd/PGBackend.h @@ -290,6 +290,10 @@ typedef std::shared_ptr<const OSDMap> OSDMapRef; MessageRef, Connection *con) = 0; virtual void send_message_osd_cluster( Message *m, const ConnectionRef& con) = 0; + virtual void start_mon_command( + const std::vector<std::string>& cmd, const bufferlist& inbl, + bufferlist *outbl, std::string *outs, + Context *onfinish) = 0; virtual ConnectionRef get_con_osd_cluster(int peer, epoch_t from_epoch) = 0; virtual entity_name_t get_cluster_msgr_name() = 0; diff --git a/src/osd/PrimaryLogPG.cc b/src/osd/PrimaryLogPG.cc index 44f8e85b5ef..3324ba9dc91 100644 --- a/src/osd/PrimaryLogPG.cc +++ b/src/osd/PrimaryLogPG.cc @@ -2286,6 +2286,16 @@ void PrimaryLogPG::do_op(OpRequestRef& op) } } + if (cct->_conf->bluestore_debug_inject_read_err && + op->may_write() && + pool.info.is_erasure() && + ec_inject_test_write_error0(m->get_hobj(), m->get_reqid())) { + // Fail retried write with error + dout(0) << __func__ << " Error inject - Fail retried write with EINVAL" << dendl; + osd->reply_op_error(op, -EINVAL); + return; + } + ObjectContextRef obc; bool can_create = op->may_write(); hobject_t missing_oid; @@ -5798,10 +5808,19 @@ int PrimaryLogPG::do_extent_cmp(OpContext *ctx, OSDOp& osd_op) int PrimaryLogPG::finish_extent_cmp(OSDOp& osd_op, const bufferlist &read_bl) { - for (uint64_t idx = 0; idx < osd_op.indata.length(); ++idx) { - char read_byte = (idx < read_bl.length() ? read_bl[idx] : 0); - if (osd_op.indata[idx] != read_byte) { - return (-MAX_ERRNO - idx); + auto input_iter = osd_op.indata.begin(); + auto read_iter = read_bl.begin(); + uint64_t idx = 0; + + while (input_iter != osd_op.indata.end()) { + char read_byte = (read_iter != read_bl.end() ? *read_iter : 0); + if (*input_iter != read_byte) { + return (-MAX_ERRNO - idx); + } + ++idx; + ++input_iter; + if (read_iter != read_bl.end()) { + ++read_iter; } } @@ -7767,27 +7786,34 @@ int PrimaryLogPG::do_osd_ops(OpContext *ctx, vector<OSDOp>& ops) bool truncated = false; bufferlist bl; if (oi.is_omap()) { - ObjectMap::ObjectMapIterator iter = osd->store->get_omap_iterator( - ch, ghobject_t(soid) - ); - if (!iter) { - result = -ENOENT; - goto fail; - } - iter->upper_bound(start_after); - if (filter_prefix > start_after) iter->lower_bound(filter_prefix); - for (num = 0; - iter->valid() && - iter->key().substr(0, filter_prefix.size()) == filter_prefix; - ++num, iter->next()) { - dout(20) << "Found key " << iter->key() << dendl; - if (num >= max_return || - bl.length() >= cct->_conf->osd_max_omap_bytes_per_request) { - truncated = true; - break; - } - encode(iter->key(), bl); - encode(iter->value(), bl); + using omap_iter_seek_t = ObjectStore::omap_iter_seek_t; + result = osd->store->omap_iterate( + ch, ghobject_t(soid), + // try to seek as many keys-at-once as possible for the sake of performance. + // note complexity should be logarithmic, so seek(n/2) + seek(n/2) is worse + // than just seek(n). + ObjectStore::omap_iter_seek_t{ + .seek_position = std::max(start_after, filter_prefix), + .seek_type = filter_prefix > start_after ? omap_iter_seek_t::LOWER_BOUND + : omap_iter_seek_t::UPPER_BOUND + }, + [&bl, &truncated, &filter_prefix, &num, max_return, + max_bytes=cct->_conf->osd_max_omap_bytes_per_request] + (std::string_view key, std::string_view value) mutable { + if (key.substr(0, filter_prefix.size()) != filter_prefix) { + return ObjectStore::omap_iter_ret_t::STOP; + } + if (num >= max_return || bl.length() >= max_bytes) { + truncated = true; + return ObjectStore::omap_iter_ret_t::STOP; + } + encode(key, bl); + encode(value, bl); + ++num; + return ObjectStore::omap_iter_ret_t::NEXT; + }); + if (result < 0) { + goto fail; } } // else return empty out_set encode(num, osd_op.outdata); diff --git a/src/osd/PrimaryLogPG.h b/src/osd/PrimaryLogPG.h index f66b5c6e16a..bf55d539821 100644 --- a/src/osd/PrimaryLogPG.h +++ b/src/osd/PrimaryLogPG.h @@ -622,6 +622,12 @@ public: Message *m, const ConnectionRef& con) override { osd->send_message_osd_cluster(m, con); } + void start_mon_command( + const std::vector<std::string>& cmd, const bufferlist& inbl, + bufferlist *outbl, std::string *outs, + Context *onfinish) override { + osd->monc->start_mon_command(cmd, inbl, outbl, outs, onfinish); + } ConnectionRef get_con_osd_cluster(int peer, epoch_t from_epoch) override; entity_name_t get_cluster_msgr_name() override { return osd->get_cluster_msgr_name(); @@ -1993,6 +1999,7 @@ public: private: DynamicPerfStats m_dynamic_perf_stats; + }; inline ostream& operator<<(ostream& out, const PrimaryLogPG::RepGather& repop) @@ -2021,5 +2028,4 @@ inline ostream& operator<<(ostream& out, void intrusive_ptr_add_ref(PrimaryLogPG::RepGather *repop); void intrusive_ptr_release(PrimaryLogPG::RepGather *repop); - #endif diff --git a/src/osd/Session.h b/src/osd/Session.h index 9fa9c655456..05a0119d31e 100644 --- a/src/osd/Session.h +++ b/src/osd/Session.h @@ -136,7 +136,7 @@ struct Session : public RefCountedObject { ceph::mutex session_dispatch_lock = ceph::make_mutex("Session::session_dispatch_lock"); - boost::intrusive::list<OpRequest> waiting_on_map; + boost::intrusive::list<OpRequest, boost::intrusive::constant_time_size<false>> waiting_on_map; ceph::spinlock projected_epoch_lock; epoch_t projected_epoch = 0; diff --git a/src/osd/osd_types.h b/src/osd/osd_types.h index 1e92d5cd3d6..485fddead7a 100644 --- a/src/osd/osd_types.h +++ b/src/osd/osd_types.h @@ -1151,9 +1151,8 @@ public: bool is_set(key_t key) const; template<typename T> - void set(key_t key, const T &val) { - value_t value = val; - opts[key] = value; + void set(key_t key, T &&val) { + opts.insert_or_assign(key, std::forward<T>(val)); } template<typename T> diff --git a/src/osdc/Objecter.cc b/src/osdc/Objecter.cc index 087b623333b..82d43bb3dde 100644 --- a/src/osdc/Objecter.cc +++ b/src/osdc/Objecter.cc @@ -1393,7 +1393,7 @@ void Objecter::handle_osd_map(MOSDMap *m) for (auto& [c, ec] : p->second) { asio::post(service.get_executor(), asio::append(std::move(c), ec)); } - waiting_for_map.erase(p++); + p = waiting_for_map.erase(p); } monc->sub_got("osdmap", osdmap->get_epoch()); diff --git a/src/pybind/mgr/cephadm/inventory.py b/src/pybind/mgr/cephadm/inventory.py index f1c56d75378..550604fc55b 100644 --- a/src/pybind/mgr/cephadm/inventory.py +++ b/src/pybind/mgr/cephadm/inventory.py @@ -2036,8 +2036,8 @@ class CertKeyStore(): var = service_name if entity in self.service_name_cert else host j = {} self.known_certs[entity][var] = cert_obj - for service_name in self.known_certs[entity].keys(): - j[var] = Cert.to_json(self.known_certs[entity][var]) + for cert_key in self.known_certs[entity]: + j[cert_key] = Cert.to_json(self.known_certs[entity][cert_key]) else: self.known_certs[entity] = cert_obj j = Cert.to_json(cert_obj) diff --git a/src/pybind/mgr/cephadm/module.py b/src/pybind/mgr/cephadm/module.py index bf14f8d1715..6690153d435 100644 --- a/src/pybind/mgr/cephadm/module.py +++ b/src/pybind/mgr/cephadm/module.py @@ -2460,7 +2460,7 @@ Then run the following: @handle_orch_error def service_action(self, action: str, service_name: str) -> List[str]: - if service_name not in self.spec_store.all_specs.keys(): + if service_name not in self.spec_store.all_specs.keys() and service_name != 'osd': raise OrchestratorError(f'Invalid service name "{service_name}".' + ' View currently running services using "ceph orch ls"') dds: List[DaemonDescription] = self.cache.get_daemons_by_service(service_name) @@ -3925,6 +3925,50 @@ Then run the following: return self.to_remove_osds.all_osds() @handle_orch_error + def set_osd_spec(self, service_name: str, osd_ids: List[str]) -> str: + """ + Update unit.meta file for osd with service name + """ + if service_name not in self.spec_store: + raise OrchestratorError(f"Cannot find service '{service_name}' in the inventory. " + "Please try again after applying an OSD service that matches " + "the service name to which you want to attach OSDs.") + + daemons: List[orchestrator.DaemonDescription] = self.cache.get_daemons_by_type('osd') + update_osd = defaultdict(list) + for daemon in daemons: + if daemon.daemon_id in osd_ids and daemon.hostname: + update_osd[daemon.hostname].append(daemon.daemon_id) + + if not update_osd: + raise OrchestratorError(f"Unable to find OSDs: {osd_ids}") + + failed_osds = [] + success_osds = [] + for host in update_osd: + osds = ",".join(update_osd[host]) + # run cephadm command with all host osds on specific host, + # if it fails, continue with other hosts + try: + with self.async_timeout_handler(host): + outs, errs, _code = self.wait_async( + CephadmServe(self)._run_cephadm(host, + cephadmNoImage, + 'update-osd-service', + ['--service-name', service_name, '--osd-ids', osds])) + if _code: + self.log.error(f"Failed to update service for {osds} osd. Cephadm error: {errs}") + failed_osds.extend(update_osd[host]) + else: + success_osds.extend(update_osd[host]) + except Exception: + self.log.exception(f"Failed to set service name for {osds}") + failed_osds.extend(update_osd[host]) + self.cache.invalidate_host_daemons(host) + self._kick_serve_loop() + return f"Updated service for osd {','.join(success_osds)}" + (f" and failed for {','.join(failed_osds)}" if failed_osds else "") + + @handle_orch_error @host_exists() def drain_host(self, hostname: str, force: bool = False, keep_conf_keyring: bool = False, zap_osd_devices: bool = False) -> str: """ diff --git a/src/pybind/mgr/cephadm/schedule.py b/src/pybind/mgr/cephadm/schedule.py index 98d2fe99897..04d3712c50a 100644 --- a/src/pybind/mgr/cephadm/schedule.py +++ b/src/pybind/mgr/cephadm/schedule.py @@ -385,6 +385,8 @@ class HostAssignment(object): def find_ip_on_host(self, hostname: str, subnets: List[str]) -> Optional[str]: for subnet in subnets: + # to normalize subnet + subnet = str(ipaddress.ip_network(subnet)) ips: List[str] = [] # following is to allow loopback interfaces for both ipv4 and ipv6. Since we # only have the subnet (and no IP) we assume default loopback IP address. diff --git a/src/pybind/mgr/cephadm/services/cephadmservice.py b/src/pybind/mgr/cephadm/services/cephadmservice.py index 04f5af28a9b..4f83d7bb0fb 100644 --- a/src/pybind/mgr/cephadm/services/cephadmservice.py +++ b/src/pybind/mgr/cephadm/services/cephadmservice.py @@ -1157,6 +1157,14 @@ class RgwService(CephService): 'value': str(spec.rgw_bucket_counters_cache_size), }) + if getattr(spec, 'disable_multisite_sync_traffic', None) is not None: + ret, out, err = self.mgr.check_mon_command({ + 'prefix': 'config set', + 'who': daemon_name, + 'name': 'rgw_run_sync_thread', + 'value': 'false' if spec.disable_multisite_sync_traffic else 'true', + }) + daemon_spec.keyring = keyring daemon_spec.final_config, daemon_spec.deps = self.generate_config(daemon_spec) diff --git a/src/pybind/mgr/cephadm/services/monitoring.py b/src/pybind/mgr/cephadm/services/monitoring.py index 1b9cf618570..9c5b5a112f3 100644 --- a/src/pybind/mgr/cephadm/services/monitoring.py +++ b/src/pybind/mgr/cephadm/services/monitoring.py @@ -3,6 +3,7 @@ import logging import os import socket from typing import List, Any, Tuple, Dict, Optional, cast +import ipaddress from mgr_module import HandleCommandResult @@ -57,6 +58,8 @@ class GrafanaService(CephadmService): if ip_to_bind_to: daemon_spec.port_ips = {str(grafana_port): ip_to_bind_to} grafana_ip = ip_to_bind_to + if ipaddress.ip_network(grafana_ip).version == 6: + grafana_ip = f"[{grafana_ip}]" domain = self.mgr.get_fqdn(daemon_spec.host) mgmt_gw_ips = [] @@ -354,6 +357,13 @@ class AlertmanagerService(CephadmService): addr = self.mgr.get_fqdn(dd.hostname) peers.append(build_url(host=addr, port=port).lstrip('/')) + ip_to_bind_to = '' + if spec.only_bind_port_on_networks and spec.networks: + assert daemon_spec.host is not None + ip_to_bind_to = self.mgr.get_first_matching_network_ip(daemon_spec.host, spec) or '' + if ip_to_bind_to: + daemon_spec.port_ips = {str(port): ip_to_bind_to} + deps.append(f'secure_monitoring_stack:{self.mgr.secure_monitoring_stack}') if security_enabled: alertmanager_user, alertmanager_password = self.mgr._get_alertmanager_credentials() @@ -376,7 +386,8 @@ class AlertmanagerService(CephadmService): }, 'peers': peers, 'web_config': '/etc/alertmanager/web.yml', - 'use_url_prefix': mgmt_gw_enabled + 'use_url_prefix': mgmt_gw_enabled, + 'ip_to_bind_to': ip_to_bind_to }, sorted(deps) else: return { @@ -384,7 +395,8 @@ class AlertmanagerService(CephadmService): "alertmanager.yml": yml }, "peers": peers, - 'use_url_prefix': mgmt_gw_enabled + 'use_url_prefix': mgmt_gw_enabled, + 'ip_to_bind_to': ip_to_bind_to }, sorted(deps) def get_active_daemon(self, daemon_descrs: List[DaemonDescription]) -> DaemonDescription: diff --git a/src/pybind/mgr/cephadm/services/nvmeof.py b/src/pybind/mgr/cephadm/services/nvmeof.py index b3fd526815e..8acec94f382 100644 --- a/src/pybind/mgr/cephadm/services/nvmeof.py +++ b/src/pybind/mgr/cephadm/services/nvmeof.py @@ -47,6 +47,7 @@ class NvmeofService(CephService): # TODO: check if we can force jinja2 to generate dicts with double quotes instead of using json.dumps transport_tcp_options = json.dumps(spec.transport_tcp_options) if spec.transport_tcp_options else None + iobuf_options = json.dumps(spec.iobuf_options) if spec.iobuf_options else None name = '{}.{}'.format(utils.name_to_config_section('nvmeof'), nvmeof_gw_id) rados_id = name[len('client.'):] if name.startswith('client.') else name @@ -67,6 +68,7 @@ class NvmeofService(CephService): 'rpc_socket_dir': '/var/tmp/', 'rpc_socket_name': 'spdk.sock', 'transport_tcp_options': transport_tcp_options, + 'iobuf_options': iobuf_options, 'rados_id': rados_id } gw_conf = self.mgr.template.render('services/nvmeof/ceph-nvmeof.conf.j2', context) diff --git a/src/pybind/mgr/cephadm/ssh.py b/src/pybind/mgr/cephadm/ssh.py index 1622cb001ab..acb5a77c51b 100644 --- a/src/pybind/mgr/cephadm/ssh.py +++ b/src/pybind/mgr/cephadm/ssh.py @@ -358,7 +358,7 @@ class SSHManager: await self._check_execute_command(host, chown, addr=addr) chmod = RemoteCommand(Executables.CHMOD, [oct(mode)[2:], tmp_path]) await self._check_execute_command(host, chmod, addr=addr) - mv = RemoteCommand(Executables.MV, [tmp_path, path]) + mv = RemoteCommand(Executables.MV, ['-Z', tmp_path, path]) await self._check_execute_command(host, mv, addr=addr) except Exception as e: msg = f"Unable to write {host}:{path}: {e}" diff --git a/src/pybind/mgr/cephadm/templates/services/alertmanager/alertmanager.yml.j2 b/src/pybind/mgr/cephadm/templates/services/alertmanager/alertmanager.yml.j2 index de993cb6ce3..b6955caf616 100644 --- a/src/pybind/mgr/cephadm/templates/services/alertmanager/alertmanager.yml.j2 +++ b/src/pybind/mgr/cephadm/templates/services/alertmanager/alertmanager.yml.j2 @@ -8,6 +8,8 @@ global: tls_config: {% if security_enabled %} ca_file: root_cert.pem + cert_file: alertmanager.crt + key_file: alertmanager.key {% else %} insecure_skip_verify: true {% endif %} diff --git a/src/pybind/mgr/cephadm/templates/services/mgmt-gateway/nginx.conf.j2 b/src/pybind/mgr/cephadm/templates/services/mgmt-gateway/nginx.conf.j2 index b9773ceeeb3..14af0fd48ca 100644 --- a/src/pybind/mgr/cephadm/templates/services/mgmt-gateway/nginx.conf.j2 +++ b/src/pybind/mgr/cephadm/templates/services/mgmt-gateway/nginx.conf.j2 @@ -9,6 +9,7 @@ events { http { #access_log /dev/stdout; + error_log /dev/stderr info; client_header_buffer_size 32K; large_client_header_buffers 4 32k; proxy_busy_buffers_size 512k; diff --git a/src/pybind/mgr/cephadm/templates/services/nvmeof/ceph-nvmeof.conf.j2 b/src/pybind/mgr/cephadm/templates/services/nvmeof/ceph-nvmeof.conf.j2 index 37f2db52732..2a9ab309568 100644 --- a/src/pybind/mgr/cephadm/templates/services/nvmeof/ceph-nvmeof.conf.j2 +++ b/src/pybind/mgr/cephadm/templates/services/nvmeof/ceph-nvmeof.conf.j2 @@ -86,6 +86,9 @@ transport_tcp_options = {{ transport_tcp_options }} {% if spec.tgt_cmd_extra_args %} tgt_cmd_extra_args = {{ spec.tgt_cmd_extra_args }} {% endif %} +{% if iobuf_options %} +iobuf_options = {{ iobuf_options }} +{% endif %} [monitor] timeout = {{ spec.monitor_timeout }} diff --git a/src/pybind/mgr/cephadm/templates/services/prometheus/prometheus.yml.j2 b/src/pybind/mgr/cephadm/templates/services/prometheus/prometheus.yml.j2 index ecfd899af71..961da145dac 100644 --- a/src/pybind/mgr/cephadm/templates/services/prometheus/prometheus.yml.j2 +++ b/src/pybind/mgr/cephadm/templates/services/prometheus/prometheus.yml.j2 @@ -28,6 +28,8 @@ alerting: password: {{ service_discovery_password }} tls_config: ca_file: root_cert.pem + cert_file: prometheus.crt + key_file: prometheus.key {% else %} - scheme: http http_sd_configs: @@ -56,6 +58,8 @@ scrape_configs: password: {{ service_discovery_password }} tls_config: ca_file: root_cert.pem + cert_file: prometheus.crt + key_file: prometheus.key {% else %} honor_labels: true http_sd_configs: @@ -81,6 +85,8 @@ scrape_configs: password: {{ service_discovery_password }} tls_config: ca_file: root_cert.pem + cert_file: prometheus.crt + key_file: prometheus.key {% else %} http_sd_configs: - url: {{ node_exporter_sd_url }} @@ -104,6 +110,8 @@ scrape_configs: password: {{ service_discovery_password }} tls_config: ca_file: root_cert.pem + cert_file: prometheus.crt + key_file: prometheus.key {% else %} http_sd_configs: - url: {{ haproxy_sd_url }} @@ -128,6 +136,8 @@ scrape_configs: password: {{ service_discovery_password }} tls_config: ca_file: root_cert.pem + cert_file: prometheus.crt + key_file: prometheus.key {% else %} honor_labels: true http_sd_configs: @@ -149,6 +159,8 @@ scrape_configs: password: {{ service_discovery_password }} tls_config: ca_file: root_cert.pem + cert_file: prometheus.crt + key_file: prometheus.key {% else %} http_sd_configs: - url: {{ nvmeof_sd_url }} @@ -169,6 +181,8 @@ scrape_configs: password: {{ service_discovery_password }} tls_config: ca_file: root_cert.pem + cert_file: prometheus.crt + key_file: prometheus.key {% else %} http_sd_configs: - url: {{ nfs_sd_url }} @@ -189,6 +203,8 @@ scrape_configs: password: {{ service_discovery_password }} tls_config: ca_file: root_cert.pem + cert_file: prometheus.crt + key_file: prometheus.key {% else %} http_sd_configs: - url: {{ smb_sd_url }} diff --git a/src/pybind/mgr/cephadm/tests/test_cephadm.py b/src/pybind/mgr/cephadm/tests/test_cephadm.py index b81510504d9..22bd26def91 100644 --- a/src/pybind/mgr/cephadm/tests/test_cephadm.py +++ b/src/pybind/mgr/cephadm/tests/test_cephadm.py @@ -1741,16 +1741,23 @@ class TestCephadm(object): nvmeof_client_cert = 'fake-nvmeof-client-cert' nvmeof_server_cert = 'fake-nvmeof-server-cert' nvmeof_root_ca_cert = 'fake-nvmeof-root-ca-cert' + grafana_cert_host_1 = 'grafana-cert-host-1' + grafana_cert_host_2 = 'grafana-cert-host-2' cephadm_module.cert_key_store.save_cert('rgw_frontend_ssl_cert', rgw_frontend_rgw_foo_host2_cert, service_name='rgw.foo', user_made=True) cephadm_module.cert_key_store.save_cert('nvmeof_server_cert', nvmeof_server_cert, service_name='nvmeof.foo', user_made=True) cephadm_module.cert_key_store.save_cert('nvmeof_client_cert', nvmeof_client_cert, service_name='nvmeof.foo', user_made=True) cephadm_module.cert_key_store.save_cert('nvmeof_root_ca_cert', nvmeof_root_ca_cert, service_name='nvmeof.foo', user_made=True) + cephadm_module.cert_key_store.save_cert('grafana_cert', grafana_cert_host_1, host='host-1', user_made=True) + cephadm_module.cert_key_store.save_cert('grafana_cert', grafana_cert_host_2, host='host-2', user_made=True) expected_calls = [ mock.call(f'{CERT_STORE_CERT_PREFIX}rgw_frontend_ssl_cert', json.dumps({'rgw.foo': Cert(rgw_frontend_rgw_foo_host2_cert, True).to_json()})), mock.call(f'{CERT_STORE_CERT_PREFIX}nvmeof_server_cert', json.dumps({'nvmeof.foo': Cert(nvmeof_server_cert, True).to_json()})), mock.call(f'{CERT_STORE_CERT_PREFIX}nvmeof_client_cert', json.dumps({'nvmeof.foo': Cert(nvmeof_client_cert, True).to_json()})), mock.call(f'{CERT_STORE_CERT_PREFIX}nvmeof_root_ca_cert', json.dumps({'nvmeof.foo': Cert(nvmeof_root_ca_cert, True).to_json()})), + mock.call(f'{CERT_STORE_CERT_PREFIX}grafana_cert', json.dumps({'host-1': Cert(grafana_cert_host_1, True).to_json()})), + mock.call(f'{CERT_STORE_CERT_PREFIX}grafana_cert', json.dumps({'host-1': Cert(grafana_cert_host_1, True).to_json(), + 'host-2': Cert(grafana_cert_host_2, True).to_json()})) ] _set_store.assert_has_calls(expected_calls) @@ -1795,17 +1802,20 @@ class TestCephadm(object): cephadm_module.cert_key_store._init_known_cert_key_dicts() grafana_host1_key = 'fake-grafana-host1-key' + grafana_host2_key = 'fake-grafana-host2-key' nvmeof_client_key = 'nvmeof-client-key' nvmeof_server_key = 'nvmeof-server-key' nvmeof_encryption_key = 'nvmeof-encryption-key' - grafana_host1_key = 'fake-grafana-host1-cert' cephadm_module.cert_key_store.save_key('grafana_key', grafana_host1_key, host='host1') + cephadm_module.cert_key_store.save_key('grafana_key', grafana_host2_key, host='host2') cephadm_module.cert_key_store.save_key('nvmeof_client_key', nvmeof_client_key, service_name='nvmeof.foo') cephadm_module.cert_key_store.save_key('nvmeof_server_key', nvmeof_server_key, service_name='nvmeof.foo') cephadm_module.cert_key_store.save_key('nvmeof_encryption_key', nvmeof_encryption_key, service_name='nvmeof.foo') expected_calls = [ mock.call(f'{CERT_STORE_KEY_PREFIX}grafana_key', json.dumps({'host1': PrivKey(grafana_host1_key).to_json()})), + mock.call(f'{CERT_STORE_KEY_PREFIX}grafana_key', json.dumps({'host1': PrivKey(grafana_host1_key).to_json(), + 'host2': PrivKey(grafana_host2_key).to_json()})), mock.call(f'{CERT_STORE_KEY_PREFIX}nvmeof_client_key', json.dumps({'nvmeof.foo': PrivKey(nvmeof_client_key).to_json()})), mock.call(f'{CERT_STORE_KEY_PREFIX}nvmeof_server_key', json.dumps({'nvmeof.foo': PrivKey(nvmeof_server_key).to_json()})), mock.call(f'{CERT_STORE_KEY_PREFIX}nvmeof_encryption_key', json.dumps({'nvmeof.foo': PrivKey(nvmeof_encryption_key).to_json()})), diff --git a/src/pybind/mgr/cephadm/tests/test_services.py b/src/pybind/mgr/cephadm/tests/test_services.py index 0d89657ac8c..d872219df80 100644 --- a/src/pybind/mgr/cephadm/tests/test_services.py +++ b/src/pybind/mgr/cephadm/tests/test_services.py @@ -581,7 +581,14 @@ class TestMonitoring: mock_getfqdn.return_value = purl.hostname with with_host(cephadm_module, "test"): - with with_service(cephadm_module, AlertManagerSpec()): + cephadm_module.cache.update_host_networks('test', { + '1.2.3.0/24': { + 'if0': ['1.2.3.1'] + }, + }) + with with_service(cephadm_module, AlertManagerSpec('alertmanager', + networks=['1.2.3.0/24'], + only_bind_port_on_networks=True)): y = dedent(self._get_config(expected_yaml_url)).lstrip() _run_cephadm.assert_called_with( 'test', @@ -595,11 +602,12 @@ class TestMonitoring: "deploy_arguments": [], "params": { 'tcp_ports': [9093, 9094], + 'port_ips': {"9094": "1.2.3.1"}, }, "meta": { 'service_name': 'alertmanager', 'ports': [9093, 9094], - 'ip': None, + 'ip': '1.2.3.1', 'deployed_by': [], 'rank': None, 'rank_generation': None, @@ -612,6 +620,7 @@ class TestMonitoring: }, "peers": [], "use_url_prefix": False, + "ip_to_bind_to": "1.2.3.1", } }), error_ok=True, @@ -634,8 +643,16 @@ class TestMonitoring: cephadm_module.secure_monitoring_stack = True cephadm_module.set_store(AlertmanagerService.USER_CFG_KEY, 'alertmanager_user') cephadm_module.set_store(AlertmanagerService.PASS_CFG_KEY, 'alertmanager_plain_password') + + cephadm_module.cache.update_host_networks('test', { + 'fd12:3456:789a::/64': { + 'if0': ['fd12:3456:789a::10'] + }, + }) with with_service(cephadm_module, MgmtGatewaySpec("mgmt-gateway")) as _, \ - with_service(cephadm_module, AlertManagerSpec()): + with_service(cephadm_module, AlertManagerSpec('alertmanager', + networks=['fd12:3456:789a::/64'], + only_bind_port_on_networks=True)): y = dedent(""" # This file is generated by cephadm. @@ -646,6 +663,8 @@ class TestMonitoring: http_config: tls_config: ca_file: root_cert.pem + cert_file: alertmanager.crt + key_file: alertmanager.key route: receiver: 'default' @@ -686,11 +705,12 @@ class TestMonitoring: "deploy_arguments": [], "params": { 'tcp_ports': [9093, 9094], + 'port_ips': {"9094": "fd12:3456:789a::10"} }, "meta": { 'service_name': 'alertmanager', 'ports': [9093, 9094], - 'ip': None, + 'ip': 'fd12:3456:789a::10', 'deployed_by': [], 'rank': None, 'rank_generation': None, @@ -708,6 +728,7 @@ class TestMonitoring: 'peers': [], 'web_config': '/etc/alertmanager/web.yml', "use_url_prefix": True, + "ip_to_bind_to": "fd12:3456:789a::10", } }), error_ok=True, @@ -741,6 +762,8 @@ class TestMonitoring: http_config: tls_config: ca_file: root_cert.pem + cert_file: alertmanager.crt + key_file: alertmanager.key route: receiver: 'default' @@ -801,6 +824,7 @@ class TestMonitoring: 'peers': [], 'web_config': '/etc/alertmanager/web.yml', "use_url_prefix": False, + "ip_to_bind_to": "", } }), error_ok=True, @@ -1170,6 +1194,8 @@ class TestMonitoring: password: sd_password tls_config: ca_file: root_cert.pem + cert_file: prometheus.crt + key_file: prometheus.key scrape_configs: - job_name: 'ceph' @@ -1191,6 +1217,8 @@ class TestMonitoring: password: sd_password tls_config: ca_file: root_cert.pem + cert_file: prometheus.crt + key_file: prometheus.key - job_name: 'node' relabel_configs: @@ -1209,6 +1237,8 @@ class TestMonitoring: password: sd_password tls_config: ca_file: root_cert.pem + cert_file: prometheus.crt + key_file: prometheus.key - job_name: 'haproxy' relabel_configs: @@ -1225,6 +1255,8 @@ class TestMonitoring: password: sd_password tls_config: ca_file: root_cert.pem + cert_file: prometheus.crt + key_file: prometheus.key - job_name: 'ceph-exporter' relabel_configs: @@ -1242,6 +1274,8 @@ class TestMonitoring: password: sd_password tls_config: ca_file: root_cert.pem + cert_file: prometheus.crt + key_file: prometheus.key - job_name: 'nvmeof' honor_labels: true @@ -1255,6 +1289,8 @@ class TestMonitoring: password: sd_password tls_config: ca_file: root_cert.pem + cert_file: prometheus.crt + key_file: prometheus.key - job_name: 'nfs' honor_labels: true @@ -1268,6 +1304,8 @@ class TestMonitoring: password: sd_password tls_config: ca_file: root_cert.pem + cert_file: prometheus.crt + key_file: prometheus.key - job_name: 'smb' honor_labels: true @@ -1281,6 +1319,8 @@ class TestMonitoring: password: sd_password tls_config: ca_file: root_cert.pem + cert_file: prometheus.crt + key_file: prometheus.key """).lstrip() @@ -2071,6 +2111,26 @@ class TestRGWService: }) assert f == expected + @pytest.mark.parametrize( + "disable_sync_traffic", + [ + (True), + (False), + ] + ) + @patch("cephadm.serve.CephadmServe._run_cephadm", _run_cephadm('{}')) + def test_rgw_disable_sync_traffic(self, disable_sync_traffic, cephadm_module: CephadmOrchestrator): + with with_host(cephadm_module, 'host1'): + s = RGWSpec(service_id="foo", + disable_multisite_sync_traffic=disable_sync_traffic) + with with_service(cephadm_module, s) as dds: + _, f, _ = cephadm_module.check_mon_command({ + 'prefix': 'config get', + 'who': f'client.{dds[0]}', + 'key': 'rgw_run_sync_thread', + }) + assert f == ('false' if disable_sync_traffic else 'true') + class TestMonService: @@ -3874,6 +3934,7 @@ class TestMgmtGateway: http { #access_log /dev/stdout; + error_log /dev/stderr info; client_header_buffer_size 32K; large_client_header_buffers 4 32k; proxy_busy_buffers_size 512k; @@ -4121,6 +4182,7 @@ class TestMgmtGateway: http { #access_log /dev/stdout; + error_log /dev/stderr info; client_header_buffer_size 32K; large_client_header_buffers 4 32k; proxy_busy_buffers_size 512k; diff --git a/src/pybind/mgr/dashboard/HACKING.rst b/src/pybind/mgr/dashboard/HACKING.rst index 39c3d6744b9..6da428a0d5f 100644 --- a/src/pybind/mgr/dashboard/HACKING.rst +++ b/src/pybind/mgr/dashboard/HACKING.rst @@ -4,7 +4,7 @@ Ceph Dashboard Developer Documentation Note: The content of this file has been moved into the Ceph Developer Guide. If you're interested in helping with the development of the dashboard, please -see ``/doc/dev/developer_guide/dash_devel.rst`` or the `online version +see ``/doc/dev/developer_guide/dash-devel.rst`` or the `online version <https://ceph.readthedocs.io/en/latest/dev/developer_guide/dash-devel/>`_ for details on how to set up a development environment and other development-related topics. diff --git a/src/pybind/mgr/orchestrator/_interface.py b/src/pybind/mgr/orchestrator/_interface.py index a505801eea5..4fbc975ae9f 100644 --- a/src/pybind/mgr/orchestrator/_interface.py +++ b/src/pybind/mgr/orchestrator/_interface.py @@ -747,6 +747,10 @@ class Orchestrator(object): """ raise NotImplementedError() + def set_osd_spec(self, service_name: str, osd_ids: List[str]) -> OrchResult: + """ set service of osd """ + raise NotImplementedError() + def blink_device_light(self, ident_fault: str, on: bool, locations: List['DeviceLightLoc']) -> OrchResult[List[str]]: """ Instructs the orchestrator to enable or disable either the ident or the fault LED. diff --git a/src/pybind/mgr/orchestrator/module.py b/src/pybind/mgr/orchestrator/module.py index 332bc75d862..d5a1bb3da2b 100644 --- a/src/pybind/mgr/orchestrator/module.py +++ b/src/pybind/mgr/orchestrator/module.py @@ -1472,6 +1472,14 @@ Usage: return HandleCommandResult(stdout=out) + @_cli_write_command('orch osd set-spec-affinity') + def _osd_set_spec(self, service_name: str, osd_id: List[str]) -> HandleCommandResult: + """Set service spec affinity for osd""" + completion = self.set_osd_spec(service_name, osd_id) + res = raise_if_exception(completion) + + return HandleCommandResult(stdout=res) + @_cli_write_command('orch daemon add') def daemon_add_misc(self, daemon_type: Optional[ServiceType] = None, @@ -1666,7 +1674,13 @@ Usage: specs: List[Union[ServiceSpec, HostSpec]] = [] # YAML '---' document separator with no content generates # None entries in the output. Let's skip them silently. - content = [o for o in yaml_objs if o is not None] + try: + content = [o for o in yaml_objs if o is not None] + except yaml.scanner.ScannerError as e: + msg = f"Invalid YAML received : {str(e)}" + self.log.exception(msg) + return HandleCommandResult(-errno.EINVAL, stderr=msg) + for s in content: try: spec = json_to_generic_spec(s) @@ -2191,7 +2205,13 @@ Usage: specs: List[TunedProfileSpec] = [] # YAML '---' document separator with no content generates # None entries in the output. Let's skip them silently. - content = [o for o in yaml_objs if o is not None] + try: + content = [o for o in yaml_objs if o is not None] + except yaml.scanner.ScannerError as e: + msg = f"Invalid YAML received : {str(e)}" + self.log.exception(msg) + return HandleCommandResult(-errno.EINVAL, stderr=msg) + for spec in content: specs.append(TunedProfileSpec.from_json(spec)) else: diff --git a/src/python-common/ceph/deployment/service_spec.py b/src/python-common/ceph/deployment/service_spec.py index 8a2a38b86ee..6869d5b2188 100644 --- a/src/python-common/ceph/deployment/service_spec.py +++ b/src/python-common/ceph/deployment/service_spec.py @@ -1231,6 +1231,7 @@ class RGWSpec(ServiceSpec): rgw_bucket_counters_cache: Optional[bool] = False, rgw_bucket_counters_cache_size: Optional[int] = None, generate_cert: bool = False, + disable_multisite_sync_traffic: Optional[bool] = None, ): assert service_type == 'rgw', service_type @@ -1283,6 +1284,8 @@ class RGWSpec(ServiceSpec): self.rgw_bucket_counters_cache_size = rgw_bucket_counters_cache_size #: Whether we should generate a cert/key for the user if not provided self.generate_cert = generate_cert + #: Used to make RGW not do multisite replication so it can dedicate to IO + self.disable_multisite_sync_traffic = disable_multisite_sync_traffic def get_port_start(self) -> List[int]: return [self.get_port()] @@ -1381,6 +1384,7 @@ class NvmeofServiceSpec(ServiceSpec): transport_tcp_options: Optional[Dict[str, int]] = {"in_capsule_data_size": 8192, "max_io_qpairs_per_ctrlr": 7}, tgt_cmd_extra_args: Optional[str] = None, + iobuf_options: Optional[Dict[str, int]] = None, discovery_addr: Optional[str] = None, discovery_addr_map: Optional[Dict[str, str]] = None, discovery_port: Optional[int] = None, @@ -1517,6 +1521,8 @@ class NvmeofServiceSpec(ServiceSpec): self.transport_tcp_options: Optional[Dict[str, int]] = transport_tcp_options #: ``tgt_cmd_extra_args`` extra arguments for the nvmf_tgt process self.tgt_cmd_extra_args = tgt_cmd_extra_args + #: List of extra arguments for SPDK iobuf in the form opt=value + self.iobuf_options: Optional[Dict[str, int]] = iobuf_options #: ``discovery_addr`` address of the discovery service self.discovery_addr = discovery_addr #: ``discovery_addr_map`` per node address map of the discovery service @@ -2328,6 +2334,7 @@ class AlertManagerSpec(MonitoringSpec): user_data: Optional[Dict[str, Any]] = None, config: Optional[Dict[str, str]] = None, networks: Optional[List[str]] = None, + only_bind_port_on_networks: bool = False, port: Optional[int] = None, secure: bool = False, extra_container_args: Optional[GeneralArgList] = None, @@ -2358,6 +2365,7 @@ class AlertManagerSpec(MonitoringSpec): # <webhook_configs> configuration. self.user_data = user_data or {} self.secure = secure + self.only_bind_port_on_networks = only_bind_port_on_networks def get_port_start(self) -> List[int]: return [self.get_port(), 9094] @@ -2404,7 +2412,7 @@ class GrafanaSpec(MonitoringSpec): self.protocol = protocol # whether ports daemons for this service bind to should - # bind to only hte networks listed in networks param, or + # bind to only the networks listed in networks param, or # to all networks. Defaults to false which is saying to bind # on all networks. self.only_bind_port_on_networks = only_bind_port_on_networks diff --git a/src/rgw/driver/daos/rgw_sal_daos.cc b/src/rgw/driver/daos/rgw_sal_daos.cc index a87d88c4b85..92dd7afe2fb 100644 --- a/src/rgw/driver/daos/rgw_sal_daos.cc +++ b/src/rgw/driver/daos/rgw_sal_daos.cc @@ -858,8 +858,6 @@ bool DaosZone::is_writeable() { return true; } bool DaosZone::get_redirect_endpoint(std::string* endpoint) { return false; } -bool DaosZone::has_zonegroup_api(const std::string& api) const { return false; } - const std::string& DaosZone::get_current_period_id() { return current_period->get_id(); } diff --git a/src/rgw/driver/daos/rgw_sal_daos.h b/src/rgw/driver/daos/rgw_sal_daos.h index e382fdb04ae..5515579a441 100644 --- a/src/rgw/driver/daos/rgw_sal_daos.h +++ b/src/rgw/driver/daos/rgw_sal_daos.h @@ -484,7 +484,6 @@ class DaosZone : public StoreZone { virtual const std::string& get_name() const override; virtual bool is_writeable() override; virtual bool get_redirect_endpoint(std::string* endpoint) override; - virtual bool has_zonegroup_api(const std::string& api) const override; virtual const std::string& get_current_period_id() override; virtual const RGWAccessKey& get_system_key() { return zone_params->system_key; diff --git a/src/rgw/driver/motr/rgw_sal_motr.cc b/src/rgw/driver/motr/rgw_sal_motr.cc index b999673ac18..463ea8c5b11 100644 --- a/src/rgw/driver/motr/rgw_sal_motr.cc +++ b/src/rgw/driver/motr/rgw_sal_motr.cc @@ -1111,11 +1111,6 @@ bool MotrZone::get_redirect_endpoint(std::string* endpoint) return false; } -bool MotrZone::has_zonegroup_api(const std::string& api) const -{ - return (zonegroup.group.api_name == api); -} - const std::string& MotrZone::get_current_period_id() { return current_period->get_id(); diff --git a/src/rgw/driver/motr/rgw_sal_motr.h b/src/rgw/driver/motr/rgw_sal_motr.h index f92074b9d94..0f99ae48e86 100644 --- a/src/rgw/driver/motr/rgw_sal_motr.h +++ b/src/rgw/driver/motr/rgw_sal_motr.h @@ -525,7 +525,6 @@ class MotrZone : public StoreZone { virtual const std::string& get_name() const override; virtual bool is_writeable() override; virtual bool get_redirect_endpoint(std::string* endpoint) override; - virtual bool has_zonegroup_api(const std::string& api) const override; virtual const std::string& get_current_period_id() override; virtual const RGWAccessKey& get_system_key() { return zone_params->system_key; } virtual const std::string& get_realm_name() { return realm->get_name(); } diff --git a/src/rgw/driver/posix/rgw_sal_posix.cc b/src/rgw/driver/posix/rgw_sal_posix.cc index 1345468210f..9d76462baa0 100644 --- a/src/rgw/driver/posix/rgw_sal_posix.cc +++ b/src/rgw/driver/posix/rgw_sal_posix.cc @@ -2893,6 +2893,14 @@ int POSIXObject::copy_object(const ACLOwner& owner, return dobj->set_obj_attrs(dpp, &attrs, nullptr, y, rgw::sal::FLAG_LOG_OP); } +int POSIXObject::list_parts(const DoutPrefixProvider* dpp, CephContext* cct, + int max_parts, int marker, int* next_marker, + bool* truncated, list_parts_each_t each_func, + optional_yield y) +{ + return -EOPNOTSUPP; +} + int POSIXObject::load_obj_state(const DoutPrefixProvider* dpp, optional_yield y, bool follow_olh) { int ret = stat(dpp); diff --git a/src/rgw/driver/posix/rgw_sal_posix.h b/src/rgw/driver/posix/rgw_sal_posix.h index 8ec72bbc1bc..bf3478ad6ab 100644 --- a/src/rgw/driver/posix/rgw_sal_posix.h +++ b/src/rgw/driver/posix/rgw_sal_posix.h @@ -653,6 +653,13 @@ public: const DoutPrefixProvider* dpp, optional_yield y) override; virtual RGWAccessControlPolicy& get_acl(void) override { return acls; } virtual int set_acl(const RGWAccessControlPolicy& acl) override { acls = acl; return 0; } + + /** If multipart, enumerate (a range [marker..marker+[min(max_parts, parts_count-1)] of) parts of the object */ + virtual int list_parts(const DoutPrefixProvider* dpp, CephContext* cct, + int max_parts, int marker, int* next_marker, + bool* truncated, list_parts_each_t each_func, + optional_yield y) override; + virtual int load_obj_state(const DoutPrefixProvider* dpp, optional_yield y, bool follow_olh = true) override; virtual int set_obj_attrs(const DoutPrefixProvider* dpp, Attrs* setattrs, Attrs* delattrs, optional_yield y, uint32_t flags) override; diff --git a/src/rgw/driver/rados/rgw_period.cc b/src/rgw/driver/rados/rgw_period.cc index f18e8e46bc5..aacb9b6a09a 100644 --- a/src/rgw/driver/rados/rgw_period.cc +++ b/src/rgw/driver/rados/rgw_period.cc @@ -68,20 +68,6 @@ int RGWPeriod::delete_obj(const DoutPrefixProvider *dpp, optional_yield y) return ret; } -int RGWPeriod::add_zonegroup(const DoutPrefixProvider *dpp, const RGWZoneGroup& zonegroup, optional_yield y) -{ - if (zonegroup.realm_id != realm_id) { - return 0; - } - int ret = period_map.update(zonegroup, cct); - if (ret < 0) { - ldpp_dout(dpp, 0) << "ERROR: updating period map: " << cpp_strerror(-ret) << dendl; - return ret; - } - - return store_info(dpp, false, y); -} - int RGWPeriod::update(const DoutPrefixProvider *dpp, optional_yield y) { auto zone_svc = sysobj_svc->get_zone_svc(); diff --git a/src/rgw/driver/rados/rgw_rados.cc b/src/rgw/driver/rados/rgw_rados.cc index 0b77bca1da7..69075c506f1 100644 --- a/src/rgw/driver/rados/rgw_rados.cc +++ b/src/rgw/driver/rados/rgw_rados.cc @@ -6962,13 +6962,13 @@ int RGWRados::set_attrs(const DoutPrefixProvider *dpp, RGWObjectCtx* octx, RGWBu } return 0; -} +} /* RGWRados::set_attrs() */ -static int get_part_obj_state(const DoutPrefixProvider* dpp, optional_yield y, - RGWRados* store, RGWBucketInfo& bucket_info, - RGWObjectCtx* rctx, RGWObjManifest* manifest, - int part_num, int* parts_count, bool prefetch, - RGWObjState** pstate, RGWObjManifest** pmanifest) +int RGWRados::get_part_obj_state(const DoutPrefixProvider* dpp, optional_yield y, + RGWRados* store, RGWBucketInfo& bucket_info, + RGWObjectCtx* rctx, RGWObjManifest* manifest, + int part_num, int* parts_count, bool prefetch, + RGWObjState** pstate, RGWObjManifest** pmanifest) { if (!manifest) { return -ERR_INVALID_PART; @@ -7047,6 +7047,9 @@ static int get_part_obj_state(const DoutPrefixProvider* dpp, optional_yield y, // update the object size sm->state.size = part_manifest.get_obj_size(); + if (!sm->state.attrset.count(RGW_ATTR_COMPRESSION)) { + sm->state.accounted_size = sm->state.size; + } *pmanifest = &part_manifest; return 0; diff --git a/src/rgw/driver/rados/rgw_rados.h b/src/rgw/driver/rados/rgw_rados.h index b24823b60dc..fe79916392f 100644 --- a/src/rgw/driver/rados/rgw_rados.h +++ b/src/rgw/driver/rados/rgw_rados.h @@ -1071,6 +1071,12 @@ public: }; // class RGWRados::Bucket::List }; // class RGWRados::Bucket + static int get_part_obj_state(const DoutPrefixProvider* dpp, optional_yield y, + RGWRados* store, RGWBucketInfo& bucket_info, + RGWObjectCtx* rctx, RGWObjManifest* manifest, + int part_num, int* parts_count, bool prefetch, + RGWObjState** pstate, RGWObjManifest** pmanifest); + int on_last_entry_in_listing(const DoutPrefixProvider *dpp, RGWBucketInfo& bucket_info, const std::string& obj_prefix, diff --git a/src/rgw/driver/rados/rgw_sal_rados.cc b/src/rgw/driver/rados/rgw_sal_rados.cc index 88da446c3de..4c05421653b 100644 --- a/src/rgw/driver/rados/rgw_sal_rados.cc +++ b/src/rgw/driver/rados/rgw_sal_rados.cc @@ -429,6 +429,10 @@ int RadosBucket::remove(const DoutPrefixProvider* dpp, ldpp_dout(dpp, -1) << "ERROR: unable to remove notifications from bucket. ret=" << ps_ret << dendl; } + if (ret = rgw::bucketlogging::bucket_deletion_cleanup(dpp, store, this, y); ret < 0) { + ldpp_dout(dpp, 1) << "WARNING: could not cleanup bucket logging configuration and pending objects, ret = " << ret << dendl; + } + ret = store->ctl()->bucket->unlink_bucket(rados, info.owner, info.bucket, y, dpp, false); if (ret < 0) { @@ -1024,15 +1028,15 @@ int RadosBucket::remove_topics(RGWObjVersionTracker* objv_tracker, objv_tracker, y); } -int RadosBucket::get_logging_object_name(std::string& obj_name, - const std::string& prefix, - optional_yield y, +int RadosBucket::get_logging_object_name(std::string& obj_name, + const std::string& prefix, + optional_yield y, const DoutPrefixProvider *dpp, RGWObjVersionTracker* objv_tracker) { rgw_pool data_pool; const auto obj_name_oid = bucketlogging::object_name_oid(this, prefix); if (!store->getRados()->get_obj_data_pool(get_placement_rule(), rgw_obj{get_key(), obj_name_oid}, &data_pool)) { - ldpp_dout(dpp, 1) << "failed to get data pool for bucket '" << get_name() << + ldpp_dout(dpp, 1) << "ERROR: failed to get data pool for bucket '" << get_name() << "' when getting logging object name" << dendl; return -EIO; } @@ -1048,23 +1052,23 @@ int RadosBucket::get_logging_object_name(std::string& obj_name, nullptr, nullptr); if (ret < 0) { - ldpp_dout(dpp, 1) << "failed to get logging object name from '" << obj_name_oid << "'. ret = " << ret << dendl; + ldpp_dout(dpp, 1) << "ERROR: failed to get logging object name from '" << obj_name_oid << "'. ret = " << ret << dendl; return ret; } obj_name = bl.to_str(); return 0; } -int RadosBucket::set_logging_object_name(const std::string& obj_name, - const std::string& prefix, - optional_yield y, - const DoutPrefixProvider *dpp, +int RadosBucket::set_logging_object_name(const std::string& obj_name, + const std::string& prefix, + optional_yield y, + const DoutPrefixProvider *dpp, bool new_obj, RGWObjVersionTracker* objv_tracker) { rgw_pool data_pool; const auto obj_name_oid = bucketlogging::object_name_oid(this, prefix); if (!store->getRados()->get_obj_data_pool(get_placement_rule(), rgw_obj{get_key(), obj_name_oid}, &data_pool)) { - ldpp_dout(dpp, 1) << "failed to get data pool for bucket '" << get_name() << + ldpp_dout(dpp, 1) << "ERROR: failed to get data pool for bucket '" << get_name() << "' when setting logging object name" << dendl; return -EIO; } @@ -1080,28 +1084,65 @@ int RadosBucket::set_logging_object_name(const std::string& obj_name, y, nullptr); if (ret == -EEXIST) { - ldpp_dout(dpp, 20) << "race detected in initializing '" << obj_name_oid << "' with logging object name:'" << obj_name << "'. ret = " << ret << dendl; + ldpp_dout(dpp, 20) << "INFO: race detected in initializing '" << obj_name_oid << "' with logging object name:'" << obj_name << "'. ret = " << ret << dendl; } else if (ret == -ECANCELED) { - ldpp_dout(dpp, 20) << "race detected in updating logging object name '" << obj_name << "' at '" << obj_name_oid << "'. ret = " << ret << dendl; + ldpp_dout(dpp, 20) << "INFO: race detected in updating logging object name '" << obj_name << "' at '" << obj_name_oid << "'. ret = " << ret << dendl; } else if (ret < 0) { - ldpp_dout(dpp, 1) << "failed to set logging object name '" << obj_name << "' at '" << obj_name_oid << "'. ret = " << ret << dendl; + ldpp_dout(dpp, 1) << "ERROR: failed to set logging object name '" << obj_name << "' at '" << obj_name_oid << "'. ret = " << ret << dendl; } return ret; } +int RadosBucket::remove_logging_object_name(const std::string& prefix, + optional_yield y, + const DoutPrefixProvider *dpp, + RGWObjVersionTracker* objv_tracker) { + rgw_pool data_pool; + const auto obj_name_oid = bucketlogging::object_name_oid(this, prefix); + if (!store->getRados()->get_obj_data_pool(get_placement_rule(), rgw_obj{get_key(), obj_name_oid}, &data_pool)) { + ldpp_dout(dpp, 1) << "ERROR: failed to get data pool for bucket '" << get_name() << + "' when setting logging object name" << dendl; + return -EIO; + } + return rgw_delete_system_obj(dpp, store->svc()->sysobj, + data_pool, + obj_name_oid, + objv_tracker, + y); +} + std::string to_temp_object_name(const rgw::sal::Bucket* bucket, const std::string& obj_name) { return fmt::format("{}__shadow_{}0", bucket->get_bucket_id(), obj_name); } +int RadosBucket::remove_logging_object(const std::string& obj_name, optional_yield y, const DoutPrefixProvider *dpp) { + rgw_pool data_pool; + const rgw_obj head_obj{get_key(), obj_name}; + const auto placement_rule = get_placement_rule(); + + if (!store->getRados()->get_obj_data_pool(placement_rule, head_obj, &data_pool)) { + ldpp_dout(dpp, 1) << "ERROR: failed to get data pool for bucket '" << get_name() << + "' when deleting logging object" << dendl; + return -EIO; + } + + const auto temp_obj_name = to_temp_object_name(this, obj_name); + return rgw_delete_system_obj(dpp, store->svc()->sysobj, + data_pool, + temp_obj_name, + nullptr, + y); +} + int RadosBucket::commit_logging_object(const std::string& obj_name, optional_yield y, const DoutPrefixProvider *dpp) { rgw_pool data_pool; const rgw_obj head_obj{get_key(), obj_name}; const auto placement_rule = get_placement_rule(); if (!store->getRados()->get_obj_data_pool(placement_rule, head_obj, &data_pool)) { - ldpp_dout(dpp, 1) << "failed to get data pool for bucket '" << get_name() << + ldpp_dout(dpp, 1) << "ERROR: failed to get data pool for bucket '" << get_name() << "' when comitting logging object" << dendl; return -EIO; } @@ -1110,7 +1151,6 @@ int RadosBucket::commit_logging_object(const std::string& obj_name, optional_yie std::map<string, bufferlist> obj_attrs; ceph::real_time mtime; bufferlist bl_data; - // TODO: this is needed only for etag calculation if (const auto ret = rgw_get_system_obj(store->svc()->sysobj, data_pool, temp_obj_name, @@ -1120,10 +1160,13 @@ int RadosBucket::commit_logging_object(const std::string& obj_name, optional_yie y, dpp, &obj_attrs, - nullptr); ret < 0) { - ldpp_dout(dpp, 1) << "faild to read logging data when comitting to object '" << temp_obj_name + nullptr); ret < 0 && ret != -ENOENT) { + ldpp_dout(dpp, 1) << "ERROR: failed to read logging data when comitting object '" << temp_obj_name << ". error: " << ret << dendl; return ret; + } else if (ret == -ENOENT) { + ldpp_dout(dpp, 1) << "WARNING: temporary logging object '" << temp_obj_name << "' does not exists" << dendl; + return 0; } uint64_t size = bl_data.length(); @@ -1137,13 +1180,13 @@ int RadosBucket::commit_logging_object(const std::string& obj_name, optional_yie nullptr, // no special placment for tail get_key(), head_obj); ret < 0) { - ldpp_dout(dpp, 1) << "failed to create manifest when comitting logging object. error: " << + ldpp_dout(dpp, 1) << "ERROR: failed to create manifest when comitting logging object. error: " << ret << dendl; return ret; } if (const auto ret = manifest_gen.create_next(size); ret < 0) { - ldpp_dout(dpp, 1) << "failed to add object to manifest when comitting logging object. error: " << + ldpp_dout(dpp, 1) << "ERROR: failed to add object to manifest when comitting logging object. error: " << ret << dendl; return ret; } @@ -1151,7 +1194,7 @@ int RadosBucket::commit_logging_object(const std::string& obj_name, optional_yie if (const auto expected_temp_obj = manifest_gen.get_cur_obj(store->getRados()); temp_obj_name != expected_temp_obj.oid) { // TODO: cleanup temporary object, commit would never succeed - ldpp_dout(dpp, 1) << "temporary logging object name mismatch: '" << + ldpp_dout(dpp, 1) << "ERROR: temporary logging object name mismatch: '" << temp_obj_name << "' != '" << expected_temp_obj.oid << "'" << dendl; return -EINVAL; } @@ -1182,11 +1225,11 @@ int RadosBucket::commit_logging_object(const std::string& obj_name, optional_yie const req_context rctx{dpp, y, nullptr}; jspan_context trace{false, false}; if (const auto ret = head_obj_wop.write_meta(0, size, obj_attrs, rctx, trace); ret < 0) { - ldpp_dout(dpp, 1) << "failed to commit logging object '" << temp_obj_name << - "' to bucket id '" << get_bucket_id() <<"'. error: " << ret << dendl; + ldpp_dout(dpp, 1) << "ERROR: failed to commit logging object '" << temp_obj_name << + "' to bucket id '" << get_info().bucket <<"'. error: " << ret << dendl; return ret; } - ldpp_dout(dpp, 20) << "committed logging object '" << temp_obj_name << + ldpp_dout(dpp, 20) << "INFO: committed logging object '" << temp_obj_name << "' with size of " << size << " bytes, to bucket '" << get_key() << "' as '" << obj_name << "'" << dendl; return 0; @@ -1204,30 +1247,30 @@ void bucket_logging_completion(rados_completion_t completion, void* args) { auto* aio_comp = reinterpret_cast<librados::AioCompletionImpl*>(completion); std::unique_ptr<BucketLoggingCompleteArg> logging_args(reinterpret_cast<BucketLoggingCompleteArg*>(args)); if (aio_comp->get_return_value() < 0) { - ldout(logging_args->cct, 1) << "failed to complete append to logging object '" << logging_args->obj_name << + ldout(logging_args->cct, 1) << "ERROR: failed to complete append to logging object '" << logging_args->obj_name << "'. ret = " << aio_comp->get_return_value() << dendl; } else { - ldout(logging_args->cct, 20) << "wrote " << logging_args->size << " bytes to logging object '" << + ldout(logging_args->cct, 20) << "INFO: wrote " << logging_args->size << " bytes to logging object '" << logging_args->obj_name << "'" << dendl; } } -int RadosBucket::write_logging_object(const std::string& obj_name, - const std::string& record, - optional_yield y, +int RadosBucket::write_logging_object(const std::string& obj_name, + const std::string& record, + optional_yield y, const DoutPrefixProvider *dpp, bool async_completion) { const auto temp_obj_name = to_temp_object_name(this, obj_name); rgw_pool data_pool; rgw_obj obj{get_key(), obj_name}; if (!store->getRados()->get_obj_data_pool(get_placement_rule(), obj, &data_pool)) { - ldpp_dout(dpp, 1) << "failed to get data pool for bucket '" << get_name() << + ldpp_dout(dpp, 1) << "ERROR: failed to get data pool for bucket '" << get_name() << "' when writing logging object" << dendl; return -EIO; } librados::IoCtx io_ctx; if (const auto ret = rgw_init_ioctx(dpp, store->getRados()->get_rados_handle(), data_pool, io_ctx); ret < 0) { - ldpp_dout(dpp, 1) << "failed to get IO context for logging object from data pool:" << data_pool.to_str() << dendl; + ldpp_dout(dpp, 1) << "ERROR: failed to get IO context for logging object from data pool:" << data_pool.to_str() << dendl; return -EIO; } bufferlist bl; @@ -1242,7 +1285,7 @@ int RadosBucket::write_logging_object(const std::string& obj_name, auto arg = std::make_unique<BucketLoggingCompleteArg>(temp_obj_name, record.length(), store->ctx()); completion->set_complete_callback(arg.get(), bucket_logging_completion); if (const auto ret = io_ctx.aio_operate(temp_obj_name, completion.get(), &op); ret < 0) { - ldpp_dout(dpp, 1) << "failed to append to logging object '" << temp_obj_name << + ldpp_dout(dpp, 1) << "ERROR: failed to append to logging object '" << temp_obj_name << "'. ret = " << ret << dendl; return ret; } @@ -1251,11 +1294,11 @@ int RadosBucket::write_logging_object(const std::string& obj_name, return 0; } if (const auto ret = rgw_rados_operate(dpp, io_ctx, temp_obj_name, &op, y); ret < 0) { - ldpp_dout(dpp, 1) << "failed to append to logging object '" << temp_obj_name << + ldpp_dout(dpp, 1) << "ERROR: failed to append to logging object '" << temp_obj_name << "'. ret = " << ret << dendl; return ret; } - ldpp_dout(dpp, 20) << "wrote " << record.length() << " bytes to logging object '" << + ldpp_dout(dpp, 20) << "INFO: wrote " << record.length() << " bytes to logging object '" << temp_obj_name << "'" << dendl; return 0; } @@ -2471,7 +2514,108 @@ bool RadosObject::is_sync_completed(const DoutPrefixProvider* dpp, const rgw_bi_log_entry& earliest_marker = entries.front(); return earliest_marker.timestamp > obj_mtime; -} +} /* is_sync_completed */ + +int RadosObject::list_parts(const DoutPrefixProvider* dpp, CephContext* cct, + int max_parts, int marker, int* next_marker, + bool* truncated, list_parts_each_t each_func, + optional_yield y) +{ + int ret{0}; + + /* require an object with a manifest, so call to get_obj_state() must precede this */ + if (! manifest) { + return -EINVAL; + } + + RGWObjManifest::obj_iterator end = manifest->obj_end(dpp); + if (end.get_cur_part_id() == 0) { // not multipart + ldpp_dout(dpp, 20) << __func__ << " object does not have a multipart manifest" + << dendl; + return 0; + } + + auto end_part_id = end.get_cur_part_id(); + auto parts_count = (end_part_id == 1) ? 1 : end_part_id - 1; + if (marker > (parts_count - 1)) { + return 0; + } + + RGWObjManifest::obj_iterator part_iter = manifest->obj_begin(dpp); + + if (marker != 0) { + ldpp_dout_fmt(dpp, 20, + "{} seeking to part #{} in the object manifest", + __func__, marker); + + part_iter = manifest->obj_find_part(dpp, marker + 1); + + if (part_iter == end) { + ldpp_dout_fmt(dpp, 5, + "{} failed to find part #{} in the object manifest", + __func__, marker + 1); + return 0; + } + } + + RGWObjectCtx& obj_ctx = get_ctx(); + RGWBucketInfo& bucket_info = get_bucket()->get_info(); + + Object::Part obj_part{}; + for (; part_iter != manifest->obj_end(dpp); ++part_iter) { + + /* we're only interested in the first object in each logical part */ + auto cur_part_id = part_iter.get_cur_part_id(); + if (cur_part_id == obj_part.part_number) { + continue; + } + + if (max_parts < 1) { + *truncated = true; + break; + } + + /* get_part_obj_state alters the passed manifest** to point to a part + * manifest, which we don't want to leak out here */ + RGWObjManifest* obj_m = manifest; + RGWObjState* astate; + bool part_prefetch = false; + ret = RGWRados::get_part_obj_state(dpp, y, store->getRados(), bucket_info, &obj_ctx, + obj_m, cur_part_id, &parts_count, + part_prefetch, &astate, &obj_m); + + if (ret < 0) { + ldpp_dout_fmt(dpp, 4, + "{} get_part_obj_state() failed ret={}", + __func__, ret); + break; + } + + obj_part.part_number = part_iter.get_cur_part_id(); + obj_part.part_size = astate->accounted_size; + + if (auto iter = astate->attrset.find(RGW_ATTR_CKSUM); + iter != astate->attrset.end()) { + try { + rgw::cksum::Cksum part_cksum; + auto ck_iter = iter->second.cbegin(); + part_cksum.decode(ck_iter); + obj_part.cksum = std::move(part_cksum); + } catch (buffer::error& err) { + ldpp_dout_fmt(dpp, 4, + "WARN: {} could not decode stored cksum, " + "caught buffer::error", + __func__); + } + } + + each_func(obj_part); + *next_marker = ++marker; + --max_parts; + } /* each part */ + + return ret; +} /* RadosObject::list_parts */ int RadosObject::load_obj_state(const DoutPrefixProvider* dpp, optional_yield y, bool follow_olh) { @@ -4500,11 +4644,6 @@ bool RadosZone::get_redirect_endpoint(std::string* endpoint) return true; } -bool RadosZone::has_zonegroup_api(const std::string& api) const -{ - return store->svc()->zone->has_zonegroup_api(api); -} - const std::string& RadosZone::get_current_period_id() { return store->svc()->zone->get_current_period_id(); diff --git a/src/rgw/driver/rados/rgw_sal_rados.h b/src/rgw/driver/rados/rgw_sal_rados.h index 23d81a934b0..e65c3c0050e 100644 --- a/src/rgw/driver/rados/rgw_sal_rados.h +++ b/src/rgw/driver/rados/rgw_sal_rados.h @@ -107,7 +107,6 @@ class RadosZone : public StoreZone { virtual const std::string& get_name() const override; virtual bool is_writeable() override; virtual bool get_redirect_endpoint(std::string* endpoint) override; - virtual bool has_zonegroup_api(const std::string& api) const override; virtual const std::string& get_current_period_id() override; virtual const RGWAccessKey& get_system_key() override; virtual const std::string& get_realm_name() override; @@ -593,12 +592,18 @@ class RadosObject : public StoreObject { StoreObject::set_compressed(); } - virtual bool is_sync_completed(const DoutPrefixProvider* dpp, const ceph::real_time& obj_mtime) override; /* For rgw_admin.cc */ RGWObjState& get_state() { return state; } virtual int load_obj_state(const DoutPrefixProvider* dpp, optional_yield y, bool follow_olh = true) override; + + /** If multipart, enumerate (a range [marker..marker+[min(max_parts, parts_count-1)] of) parts of the object */ + virtual int list_parts(const DoutPrefixProvider* dpp, CephContext* cct, + int max_parts, int marker, int* next_marker, + bool* truncated, list_parts_each_t each_func, + optional_yield y) override; + virtual int set_obj_attrs(const DoutPrefixProvider* dpp, Attrs* setattrs, Attrs* delattrs, optional_yield y, uint32_t flags) override; virtual int get_obj_attrs(optional_yield y, const DoutPrefixProvider* dpp, rgw_obj* target_obj = NULL) override; virtual int modify_obj_attrs(const char* attr_name, bufferlist& attr_val, optional_yield y, const DoutPrefixProvider* dpp) override; @@ -775,18 +780,23 @@ class RadosBucket : public StoreBucket { optional_yield y, const DoutPrefixProvider *dpp) override; int remove_topics(RGWObjVersionTracker* objv_tracker, optional_yield y, const DoutPrefixProvider *dpp) override; - int get_logging_object_name(std::string& obj_name, - const std::string& prefix, - optional_yield y, - const DoutPrefixProvider *dpp, + int get_logging_object_name(std::string& obj_name, + const std::string& prefix, + optional_yield y, + const DoutPrefixProvider *dpp, + RGWObjVersionTracker* objv_tracker) override; + int set_logging_object_name(const std::string& obj_name, + const std::string& prefix, + optional_yield y, + const DoutPrefixProvider *dpp, + bool new_obj, RGWObjVersionTracker* objv_tracker) override; - int set_logging_object_name(const std::string& obj_name, - const std::string& prefix, - optional_yield y, - const DoutPrefixProvider *dpp, - bool new_obj, + int remove_logging_object_name(const std::string& prefix, + optional_yield y, + const DoutPrefixProvider *dpp, RGWObjVersionTracker* objv_tracker) override; int commit_logging_object(const std::string& obj_name, optional_yield y, const DoutPrefixProvider *dpp) override; + int remove_logging_object(const std::string& obj_name, optional_yield y, const DoutPrefixProvider *dpp) override; int write_logging_object(const std::string& obj_name, const std::string& record, optional_yield y, const DoutPrefixProvider *dpp, bool async_completion) override; private: diff --git a/src/rgw/driver/rados/rgw_tools.cc b/src/rgw/driver/rados/rgw_tools.cc index 79d2be0bcfa..bf7a309e864 100644 --- a/src/rgw/driver/rados/rgw_tools.cc +++ b/src/rgw/driver/rados/rgw_tools.cc @@ -339,21 +339,35 @@ int rgw_list_pool(const DoutPrefixProvider *dpp, ldpp_dout(dpp, 10) << "failed to parse cursor: " << marker << dendl; return -EINVAL; } - - auto iter = ioctx.nobjects_begin(oc); + librados::NObjectIterator iter; + try { + iter = ioctx.nobjects_begin(oc); + } catch (const std::system_error& e) { + ldpp_dout(dpp, 1) << "rgw_list_pool: Failed to begin iteration of pool " + << ioctx.get_pool_name() << " with error " + << e.what() << dendl; + return ceph::from_error_code(e.code()); + } /// Pool_iterate if (iter == ioctx.nobjects_end()) return -ENOENT; - for (; oids->size() < max && iter != ioctx.nobjects_end(); ++iter) { - string oid = iter->get_oid(); - ldpp_dout(dpp, 20) << "RGWRados::pool_iterate: got " << oid << dendl; + try { + for (; oids->size() < max && iter != ioctx.nobjects_end(); ++iter) { + string oid = iter->get_oid(); + ldpp_dout(dpp, 20) << "RGWRados::pool_iterate: got " << oid << dendl; - // fill it in with initial values; we may correct later - if (filter && !filter(oid, oid)) - continue; + // fill it in with initial values; we may correct later + if (filter && !filter(oid, oid)) + continue; - oids->push_back(oid); + oids->push_back(oid); + } + } catch (const std::system_error& e) { + ldpp_dout(dpp, 1) << "rgw_list_pool: Failed iterating pool " + << ioctx.get_pool_name() << " with error " + << e.what() << dendl; + return ceph::from_error_code(e.code()); } marker = iter.get_cursor().to_str(); diff --git a/src/rgw/driver/rados/rgw_zone.h b/src/rgw/driver/rados/rgw_zone.h index c542abc76d6..5fb2b4b8096 100644 --- a/src/rgw/driver/rados/rgw_zone.h +++ b/src/rgw/driver/rados/rgw_zone.h @@ -769,7 +769,6 @@ public: int create(const DoutPrefixProvider *dpp, optional_yield y, bool exclusive = true); int delete_obj(const DoutPrefixProvider *dpp, optional_yield y); int store_info(const DoutPrefixProvider *dpp, bool exclusive, optional_yield y); - int add_zonegroup(const DoutPrefixProvider *dpp, const RGWZoneGroup& zonegroup, optional_yield y); void fork(); int update(const DoutPrefixProvider *dpp, optional_yield y); diff --git a/src/rgw/radosgw-admin/radosgw-admin.cc b/src/rgw/radosgw-admin/radosgw-admin.cc index 182e42b8e31..13936c87952 100644 --- a/src/rgw/radosgw-admin/radosgw-admin.cc +++ b/src/rgw/radosgw-admin/radosgw-admin.cc @@ -171,7 +171,8 @@ void usage() cout << " bucket sync disable disable bucket sync\n"; cout << " bucket sync enable enable bucket sync\n"; cout << " bucket radoslist list rados objects backing bucket's objects\n"; - cout << " bucket logging flush flush pending log records object of source bucket to the log bucket to bucket\n"; + cout << " bucket logging flush flush pending log records object of source bucket to the log bucket\n"; + cout << " bucket logging info get info on bucket logging configuration on source bucket or list of sources in log bucket\n"; cout << " bi get retrieve bucket index object entries\n"; cout << " bi put store bucket index object entries\n"; cout << " bi list list raw bucket index entries\n"; @@ -701,6 +702,7 @@ enum class OPT { BUCKET_OBJECT_SHARD, BUCKET_RESYNC_ENCRYPTED_MULTIPART, BUCKET_LOGGING_FLUSH, + BUCKET_LOGGING_INFO, POLICY, LOG_LIST, LOG_SHOW, @@ -940,6 +942,7 @@ static SimpleCmd::Commands all_cmds = { { "bucket object shard", OPT::BUCKET_OBJECT_SHARD }, { "bucket resync encrypted multipart", OPT::BUCKET_RESYNC_ENCRYPTED_MULTIPART }, { "bucket logging flush", OPT::BUCKET_LOGGING_FLUSH }, + { "bucket logging info", OPT::BUCKET_LOGGING_INFO }, { "policy", OPT::POLICY }, { "log list", OPT::LOG_LIST }, { "log show", OPT::LOG_SHOW }, @@ -2540,8 +2543,8 @@ static void sync_status(Formatter *formatter) struct indented { int w; // indent width - std::string_view header; - indented(int w, std::string_view header = "") : w(w), header(header) {} + std::string header; + indented(int w, std::string header = "") : w(w), header(header) {} }; std::ostream& operator<<(std::ostream& out, const indented& h) { return out << std::setw(h.w) << h.header << std::setw(1) << ' '; @@ -2549,10 +2552,10 @@ std::ostream& operator<<(std::ostream& out, const indented& h) { struct bucket_source_sync_info { const RGWZone& _source; - std::string_view error; + std::string error; std::map<int,std::string> shards_behind; int total_shards; - std::string_view status; + std::string status; rgw_bucket bucket_source; bucket_source_sync_info(const RGWZone& source): _source(source) {} @@ -3072,14 +3075,12 @@ static int bucket_sync_status(rgw::sal::Driver* driver, const RGWBucketInfo& inf } if (pipe.source.zone.value_or(rgw_zone_id()) == z->second.id) { bucket_source_sync_info source_sync_info(z->second); - auto ret = bucket_source_sync_status(dpp(), static_cast<rgw::sal::RadosStore*>(driver), static_cast<rgw::sal::RadosStore*>(driver)->svc()->zone->get_zone(), z->second, + bucket_source_sync_status(dpp(), static_cast<rgw::sal::RadosStore*>(driver), static_cast<rgw::sal::RadosStore*>(driver)->svc()->zone->get_zone(), z->second, c->second, info, pipe, source_sync_info); - if (ret == 0) { - bucket_sync_info.source_status_info.emplace_back(std::move(source_sync_info)); - } + bucket_sync_info.source_status_info.emplace_back(std::move(source_sync_info)); } } } @@ -7750,6 +7751,47 @@ int main(int argc, const char **argv) return 0; } + if (opt_cmd == OPT::BUCKET_LOGGING_INFO) { + if (bucket_name.empty()) { + cerr << "ERROR: bucket not specified" << std::endl; + return EINVAL; + } + int ret = init_bucket(tenant, bucket_name, bucket_id, &bucket); + if (ret < 0) { + return -ret; + } + const auto& bucket_attrs = bucket->get_attrs(); + auto iter = bucket_attrs.find(RGW_ATTR_BUCKET_LOGGING); + if (iter != bucket_attrs.end()) { + rgw::bucketlogging::configuration configuration; + try { + configuration.enabled = true; + decode(configuration, iter->second); + } catch (buffer::error& err) { + cerr << "ERROR: failed to decode logging attribute '" << RGW_ATTR_BUCKET_LOGGING + << "'. error: " << err.what() << std::endl; + return EINVAL; + } + encode_json("logging", configuration, formatter.get()); + formatter->flush(cout); + } + iter = bucket_attrs.find(RGW_ATTR_BUCKET_LOGGING_SOURCES); + if (iter != bucket_attrs.end()) { + rgw::bucketlogging::source_buckets sources; + try { + decode(sources, iter->second); + } catch (buffer::error& err) { + cerr << "ERROR: failed to decode logging sources attribute '" << RGW_ATTR_BUCKET_LOGGING_SOURCES + << "'. error: " << err.what() << std::endl; + return EINVAL; + } + encode_json("logging_sources", sources, formatter.get()); + formatter->flush(cout); + } + + return 0; + } + if (opt_cmd == OPT::LOG_LIST) { // filter by date? if (date.size() && date.size() != 10) { diff --git a/src/rgw/rgw_auth.cc b/src/rgw/rgw_auth.cc index f188e7975b3..a0b494eb9c5 100644 --- a/src/rgw/rgw_auth.cc +++ b/src/rgw/rgw_auth.cc @@ -188,7 +188,8 @@ int load_account_and_policies(const DoutPrefixProvider* dpp, static auto transform_old_authinfo(const RGWUserInfo& user, std::optional<RGWAccountInfo> account, - std::vector<IAM::Policy> policies) + std::vector<IAM::Policy> policies, + sal::Driver* driver) -> std::unique_ptr<rgw::auth::Identity> { /* This class is not intended for public use. Should be removed altogether @@ -198,6 +199,7 @@ static auto transform_old_authinfo(const RGWUserInfo& user, /* For this particular case it's OK to use rgw_user structure to convey * the identity info as this was the policy for doing that before the * new auth. */ + sal::Driver* driver; const rgw_user id; const std::string display_name; const std::string path; @@ -208,8 +210,10 @@ static auto transform_old_authinfo(const RGWUserInfo& user, public: DummyIdentityApplier(const RGWUserInfo& user, std::optional<RGWAccountInfo> account, - std::vector<IAM::Policy> policies) - : id(user.user_id), + std::vector<IAM::Policy> policies, + sal::Driver* driver) + : driver(driver), + id(user.user_id), display_name(user.display_name), path(user.path), is_admin(user.admin), @@ -294,9 +298,9 @@ static auto transform_old_authinfo(const RGWUserInfo& user, << ", is_admin=" << is_admin << ")"; } - void load_acct_info(const DoutPrefixProvider* dpp, - RGWUserInfo& user_info) const override { + auto load_acct_info(const DoutPrefixProvider* dpp) const -> std::unique_ptr<rgw::sal::User> override { // noop, this user info was passed in on construction + return driver->get_user(id); } void modify_request_state(const DoutPrefixProvider* dpp, req_state* s) const { @@ -307,7 +311,7 @@ static auto transform_old_authinfo(const RGWUserInfo& user, }; return std::make_unique<DummyIdentityApplier>( - user, std::move(account), std::move(policies)); + user, std::move(account), std::move(policies), driver); } auto transform_old_authinfo(const DoutPrefixProvider* dpp, @@ -332,7 +336,7 @@ auto transform_old_authinfo(const DoutPrefixProvider* dpp, if (policies_) { // return policies to caller if requested *policies_ = policies; } - return transform_old_authinfo(info, std::move(account), std::move(policies)); + return transform_old_authinfo(info, std::move(account), std::move(policies), driver); } } /* namespace auth */ @@ -527,7 +531,7 @@ rgw::auth::Strategy::apply(const DoutPrefixProvider *dpp, const rgw::auth::Strat /* Account used by a given RGWOp is decoupled from identity employed * in the authorization phase (RGWOp::verify_permissions). */ - applier->load_acct_info(dpp, s->user->get_info()); + s->user = applier->load_acct_info(dpp); s->perm_mask = applier->get_perm_mask(); /* This is the single place where we pass req_state as a pointer @@ -635,36 +639,36 @@ void rgw::auth::WebIdentityApplier::create_account(const DoutPrefixProvider* dpp user_info = user->get_info(); } -void rgw::auth::WebIdentityApplier::load_acct_info(const DoutPrefixProvider* dpp, RGWUserInfo& user_info) const { +auto rgw::auth::WebIdentityApplier::load_acct_info(const DoutPrefixProvider* dpp) const -> std::unique_ptr<rgw::sal::User> { rgw_user federated_user; federated_user.id = this->sub; federated_user.tenant = role_tenant; federated_user.ns = "oidc"; + std::unique_ptr<rgw::sal::User> user = driver->get_user(federated_user); if (account) { // we don't need shadow users for account roles because bucket ownership, // quota, and stats are tracked by the account instead of the user - user_info.user_id = std::move(federated_user); + RGWUserInfo& user_info = user->get_info(); user_info.display_name = user_name; user_info.type = TYPE_WEB; - return; + // the user_info.user_id is initialized by driver->get_user(...) + return user; } - std::unique_ptr<rgw::sal::User> user = driver->get_user(federated_user); - //Check in oidc namespace if (user->load_user(dpp, null_yield) >= 0) { /* Succeeded. */ - user_info = user->get_info(); - return; + // the user_info in user is initialized by user->load_user(...) + return user; } user->clear_ns(); //Check for old users which wouldn't have been created in oidc namespace if (user->load_user(dpp, null_yield) >= 0) { /* Succeeded. */ - user_info = user->get_info(); - return; + // the user_info in user is initialized by user->load_user(...) + return user; } //Check if user_id.buckets already exists, may have been from the time, when shadow users didnt exist @@ -675,7 +679,7 @@ void rgw::auth::WebIdentityApplier::load_acct_info(const DoutPrefixProvider* dpp last_synced, last_updated); if (ret < 0 && ret != -ENOENT) { ldpp_dout(dpp, 0) << "ERROR: reading stats for the user returned error " << ret << dendl; - return; + return user; } if (ret == -ENOENT) { /* in case of ENOENT, which means user doesnt have buckets */ //In this case user will be created in oidc namespace @@ -688,7 +692,8 @@ void rgw::auth::WebIdentityApplier::load_acct_info(const DoutPrefixProvider* dpp } ldpp_dout(dpp, 0) << "NOTICE: couldn't map oidc federated user " << federated_user << dendl; - create_account(dpp, federated_user, this->user_name, user_info); + create_account(dpp, federated_user, this->user_name, user->get_info()); + return user; } void rgw::auth::WebIdentityApplier::modify_request_state(const DoutPrefixProvider *dpp, req_state* s) const @@ -940,7 +945,7 @@ void rgw::auth::RemoteApplier::write_ops_log_entry(rgw_log_entry& entry) const } /* TODO(rzarzynski): we need to handle display_name changes. */ -void rgw::auth::RemoteApplier::load_acct_info(const DoutPrefixProvider* dpp, RGWUserInfo& user_info) const /* out */ +auto rgw::auth::RemoteApplier::load_acct_info(const DoutPrefixProvider* dpp) const -> std::unique_ptr<rgw::sal::User> /* out */ { /* It's supposed that RGWRemoteAuthApplier tries to load account info * that belongs to the authenticated identity. Another policy may be @@ -979,9 +984,9 @@ void rgw::auth::RemoteApplier::load_acct_info(const DoutPrefixProvider* dpp, RGW (void) load_account_and_policies(dpp, null_yield, driver, user->get_info(), user->get_attrs(), account, policies); - user_info = std::move(user->get_info()); owner_acct_user = std::move(tenanted_uid); - return; + // the user_info in user is initialized by user->load_user(...) + return user; } } @@ -994,15 +999,16 @@ void rgw::auth::RemoteApplier::load_acct_info(const DoutPrefixProvider* dpp, RGW (void) load_account_and_policies(dpp, null_yield, driver, user->get_info(), user->get_attrs(), account, policies); - user_info = std::move(user->get_info()); owner_acct_user = acct_user; - return; + // the user_info in user is initialized by user->load_user(...) + return user; } ldpp_dout(dpp, 0) << "NOTICE: couldn't map swift user " << acct_user << dendl; - create_account(dpp, acct_user, implicit_tenant, user_info); + create_account(dpp, acct_user, implicit_tenant, user->get_info()); /* Succeeded if we are here (create_account() hasn't throwed). */ + return user; } void rgw::auth::RemoteApplier::modify_request_state(const DoutPrefixProvider* dpp, req_state* s) const @@ -1102,11 +1108,11 @@ uint32_t rgw::auth::LocalApplier::get_perm_mask(const std::string& subuser_name, } } -void rgw::auth::LocalApplier::load_acct_info(const DoutPrefixProvider* dpp, RGWUserInfo& user_info) const /* out */ +auto rgw::auth::LocalApplier::load_acct_info(const DoutPrefixProvider* dpp) const -> std::unique_ptr<rgw::sal::User> /* out */ { /* Load the account that belongs to the authenticated identity. An extra call * to RADOS may be safely skipped in this case. */ - user_info = this->user_info; + return std::unique_ptr<rgw::sal::User>(user.release()); } void rgw::auth::LocalApplier::modify_request_state(const DoutPrefixProvider* dpp, req_state* s) const @@ -1125,6 +1131,22 @@ void rgw::auth::LocalApplier::write_ops_log_entry(rgw_log_entry& entry) const } } +rgw::auth::LocalApplier::LocalApplier(CephContext* const cct, + std::unique_ptr<rgw::sal::User> user, + std::optional<RGWAccountInfo> account, + std::vector<IAM::Policy> policies, + std::string subuser, + const std::optional<uint32_t>& perm_mask, + const std::string access_key_id) + : user_info(user->get_info()), + user(std::move(user)), + account(std::move(account)), + policies(std::move(policies)), + subuser(std::move(subuser)), + perm_mask(perm_mask.value_or(RGW_PERM_INVALID)), + access_key_id(access_key_id) { +} + ACLOwner rgw::auth::RoleApplier::get_aclowner() const { ACLOwner owner; @@ -1187,10 +1209,11 @@ bool rgw::auth::RoleApplier::is_identity(const Principal& p) const { return false; } -void rgw::auth::RoleApplier::load_acct_info(const DoutPrefixProvider* dpp, RGWUserInfo& user_info) const /* out */ +auto rgw::auth::RoleApplier::load_acct_info(const DoutPrefixProvider* dpp) const -> std::unique_ptr<rgw::sal::User> /* out */ { /* Load the user id */ - user_info.user_id = this->token_attrs.user_id; + std::unique_ptr<rgw::sal::User> user = driver->get_user(this->token_attrs.user_id); + return user; } void rgw::auth::RoleApplier::write_ops_log_entry(rgw_log_entry& entry) const @@ -1271,9 +1294,10 @@ rgw::auth::AnonymousEngine::authenticate(const DoutPrefixProvider* dpp, const re } else { RGWUserInfo user_info; rgw_get_anon_user(user_info); - + std::unique_ptr<rgw::sal::User> user = s->user->clone(); + user->get_info() = user_info; auto apl = \ - apl_factory->create_apl_local(cct, s, user_info, std::nullopt, {}, + apl_factory->create_apl_local(cct, s, std::move(user), std::nullopt, {}, rgw::auth::LocalApplier::NO_SUBUSER, std::nullopt, rgw::auth::LocalApplier::NO_ACCESS_KEY); return result_t::grant(std::move(apl)); diff --git a/src/rgw/rgw_auth.h b/src/rgw/rgw_auth.h index dcbd5f70f33..22b0816bac9 100644 --- a/src/rgw/rgw_auth.h +++ b/src/rgw/rgw_auth.h @@ -140,7 +140,7 @@ public: * * XXX: be aware that the "account" term refers to rgw_user. The naming * is legacy. */ - virtual void load_acct_info(const DoutPrefixProvider* dpp, RGWUserInfo& user_info) const = 0; /* out */ + virtual auto load_acct_info(const DoutPrefixProvider* dpp) const -> std::unique_ptr<rgw::sal::User> = 0; /* out */ /* Apply any changes to request state. This method will be most useful for * TempURL of Swift API. */ @@ -485,7 +485,7 @@ public: bool is_identity(const Principal& p) const override; - void load_acct_info(const DoutPrefixProvider* dpp, RGWUserInfo& user_info) const override; + auto load_acct_info(const DoutPrefixProvider* dpp) const -> std::unique_ptr<rgw::sal::User> override; uint32_t get_identity_type() const override { return TYPE_WEB; @@ -657,7 +657,7 @@ public: uint32_t get_perm_mask() const override { return info.perm_mask; } void to_str(std::ostream& out) const override; - void load_acct_info(const DoutPrefixProvider* dpp, RGWUserInfo& user_info) const override; /* out */ + auto load_acct_info(const DoutPrefixProvider* dpp) const -> std::unique_ptr<rgw::sal::User> override; /* out */ void modify_request_state(const DoutPrefixProvider* dpp, req_state* s) const override; void write_ops_log_entry(rgw_log_entry& entry) const override; uint32_t get_identity_type() const override { return info.acct_type; } @@ -684,7 +684,7 @@ public: /* rgw::auth::LocalApplier targets those auth engines that base on the data - * enclosed in the RGWUserInfo control structure. As a side effect of doing + * enclosed in the rgw::sal::User->RGWUserInfo control structure. As a side effect of doing * the authentication process, they must have it loaded. Leveraging this is * a way to avoid unnecessary calls to underlying RADOS store. */ class LocalApplier : public IdentityApplier { @@ -692,6 +692,7 @@ class LocalApplier : public IdentityApplier { protected: const RGWUserInfo user_info; + mutable std::unique_ptr<rgw::sal::User> user; const std::optional<RGWAccountInfo> account; const std::vector<IAM::Policy> policies; const std::string subuser; @@ -706,19 +707,12 @@ public: static const std::string NO_ACCESS_KEY; LocalApplier(CephContext* const cct, - const RGWUserInfo& user_info, + std::unique_ptr<rgw::sal::User> user, std::optional<RGWAccountInfo> account, std::vector<IAM::Policy> policies, std::string subuser, const std::optional<uint32_t>& perm_mask, - const std::string access_key_id) - : user_info(user_info), - account(std::move(account)), - policies(std::move(policies)), - subuser(std::move(subuser)), - perm_mask(perm_mask.value_or(RGW_PERM_INVALID)), - access_key_id(access_key_id) { - } + const std::string access_key_id); ACLOwner get_aclowner() const override; uint32_t get_perms_from_aclspec(const DoutPrefixProvider* dpp, const aclspec_t& aclspec) const override; @@ -733,7 +727,7 @@ public: } } void to_str(std::ostream& out) const override; - void load_acct_info(const DoutPrefixProvider* dpp, RGWUserInfo& user_info) const override; /* out */ + auto load_acct_info(const DoutPrefixProvider* dpp) const -> std::unique_ptr<rgw::sal::User> override; /* out */ void modify_request_state(const DoutPrefixProvider* dpp, req_state* s) const override; uint32_t get_identity_type() const override { return user_info.type; } std::string get_acct_name() const override { return {}; } @@ -751,7 +745,7 @@ public: virtual ~Factory() {} virtual aplptr_t create_apl_local(CephContext* cct, const req_state* s, - const RGWUserInfo& user_info, + std::unique_ptr<rgw::sal::User> user, std::optional<RGWAccountInfo> account, std::vector<IAM::Policy> policies, const std::string& subuser, @@ -780,15 +774,20 @@ public: std::vector<std::pair<std::string, std::string>> principal_tags; }; protected: + CephContext* const cct; + rgw::sal::Driver* driver; Role role; TokenAttrs token_attrs; public: RoleApplier(CephContext* const cct, + rgw::sal::Driver* driver, const Role& role, const TokenAttrs& token_attrs) - : role(role), + : cct(cct), + driver(driver), + role(role), token_attrs(token_attrs) {} ACLOwner get_aclowner() const override; @@ -804,7 +803,7 @@ public: return RGW_PERM_NONE; } void to_str(std::ostream& out) const override; - void load_acct_info(const DoutPrefixProvider* dpp, RGWUserInfo& user_info) const override; /* out */ + auto load_acct_info(const DoutPrefixProvider* dpp) const -> std::unique_ptr<rgw::sal::User> override; /* out */ uint32_t get_identity_type() const override { return TYPE_ROLE; } std::string get_acct_name() const override { return {}; } std::string get_subuser() const override { return {}; } diff --git a/src/rgw/rgw_auth_filters.h b/src/rgw/rgw_auth_filters.h index a93641e8b8e..7d264197c52 100644 --- a/src/rgw/rgw_auth_filters.h +++ b/src/rgw/rgw_auth_filters.h @@ -117,8 +117,8 @@ public: return get_decoratee().get_account(); } - void load_acct_info(const DoutPrefixProvider* dpp, RGWUserInfo& user_info) const override { /* out */ - return get_decoratee().load_acct_info(dpp, user_info); + auto load_acct_info(const DoutPrefixProvider* dpp) const -> std::unique_ptr<rgw::sal::User> override { /* out */ + return get_decoratee().load_acct_info(dpp); } void modify_request_state(const DoutPrefixProvider* dpp, req_state * s) const override { /* in/out */ @@ -152,7 +152,7 @@ public: } void to_str(std::ostream& out) const override; - void load_acct_info(const DoutPrefixProvider* dpp, RGWUserInfo& user_info) const override; /* out */ + auto load_acct_info(const DoutPrefixProvider* dpp) const -> std::unique_ptr<rgw::sal::User> override; /* out */ }; /* static declaration: UNKNOWN_ACCT will be an empty rgw_user that is a result @@ -169,23 +169,25 @@ void ThirdPartyAccountApplier<T>::to_str(std::ostream& out) const } template <typename T> -void ThirdPartyAccountApplier<T>::load_acct_info(const DoutPrefixProvider* dpp, RGWUserInfo& user_info) const +auto ThirdPartyAccountApplier<T>::load_acct_info(const DoutPrefixProvider* dpp) const -> std::unique_ptr<rgw::sal::User> { + std::unique_ptr<rgw::sal::User> luser; if (UNKNOWN_ACCT == acct_user_override) { /* There is no override specified by the upper layer. This means that we'll * load the account owned by the authenticated identity (aka auth_user). */ - DecoratedApplier<T>::load_acct_info(dpp, user_info); + luser = DecoratedApplier<T>::load_acct_info(dpp); } else if (DecoratedApplier<T>::is_owner_of(acct_user_override)) { /* The override has been specified but the account belongs to the authenticated * identity. We may safely forward the call to a next stage. */ - DecoratedApplier<T>::load_acct_info(dpp, user_info); + luser = DecoratedApplier<T>::load_acct_info(dpp); } else if (this->is_anonymous()) { /* If the user was authed by the anonymous engine then scope the ANON user * to the correct tenant */ + luser = driver->get_user(rgw_user(RGW_USER_ANON_ID)); if (acct_user_override.tenant.empty()) - user_info.user_id = rgw_user(acct_user_override.id, RGW_USER_ANON_ID); + luser->get_info().user_id = rgw_user(acct_user_override.id, RGW_USER_ANON_ID); else - user_info.user_id = rgw_user(acct_user_override.tenant, RGW_USER_ANON_ID); + luser->get_info().user_id = rgw_user(acct_user_override.tenant, RGW_USER_ANON_ID); } else { /* Compatibility mechanism for multi-tenancy. For more details refer to * load_acct_info method of rgw::auth::RemoteApplier. */ @@ -196,9 +198,10 @@ void ThirdPartyAccountApplier<T>::load_acct_info(const DoutPrefixProvider* dpp, user = driver->get_user(tenanted_uid); if (user->load_user(dpp, null_yield) >= 0) { - user_info = user->get_info(); + // the user_info in luser is initialized by user->load_user(...) + luser = user->clone(); /* Succeeded. */ - return; + return luser; } } @@ -213,8 +216,10 @@ void ThirdPartyAccountApplier<T>::load_acct_info(const DoutPrefixProvider* dpp, throw ret; } } - user_info = user->get_info(); + // the user_info in luser is initialized by user->load_user(...) + luser = user->clone(); } + return luser; } template <typename T> static inline @@ -248,7 +253,7 @@ public: } void to_str(std::ostream& out) const override; - void load_acct_info(const DoutPrefixProvider* dpp, RGWUserInfo& user_info) const override; /* out */ + auto load_acct_info(const DoutPrefixProvider* dpp) const -> std::unique_ptr<rgw::sal::User> override; /* out */ void modify_request_state(const DoutPrefixProvider* dpp, req_state* s) const override; /* in/out */ ACLOwner get_aclowner() const override { @@ -271,10 +276,10 @@ void SysReqApplier<T>::to_str(std::ostream& out) const } template <typename T> -void SysReqApplier<T>::load_acct_info(const DoutPrefixProvider* dpp, RGWUserInfo& user_info) const +auto SysReqApplier<T>::load_acct_info(const DoutPrefixProvider* dpp) const -> std::unique_ptr<rgw::sal::User> { - DecoratedApplier<T>::load_acct_info(dpp, user_info); - is_system = user_info.system; + std::unique_ptr<rgw::sal::User> user = DecoratedApplier<T>::load_acct_info(dpp); + is_system = user->get_info().system; if (is_system) { //ldpp_dout(dpp, 20) << "system request" << dendl; @@ -285,7 +290,7 @@ void SysReqApplier<T>::load_acct_info(const DoutPrefixProvider* dpp, RGWUserInfo effective_owner->id = parse_owner(str); if (const auto* uid = std::get_if<rgw_user>(&effective_owner->id); uid) { - std::unique_ptr<rgw::sal::User> user = driver->get_user(*uid); + user = driver->get_user(*uid); if (user->load_user(dpp, null_yield) < 0) { //ldpp_dout(dpp, 0) << "User lookup failed!" << dendl; throw -EACCES; @@ -294,14 +299,14 @@ void SysReqApplier<T>::load_acct_info(const DoutPrefixProvider* dpp, RGWUserInfo } } } + return user; } template <typename T> void SysReqApplier<T>::modify_request_state(const DoutPrefixProvider* dpp, req_state* const s) const { if (boost::logic::indeterminate(is_system)) { - RGWUserInfo unused_info; - load_acct_info(dpp, unused_info); + std::unique_ptr<rgw::sal::User> unused_user{ load_acct_info(dpp) }; } if (is_system) { diff --git a/src/rgw/rgw_auth_s3.h b/src/rgw/rgw_auth_s3.h index 2f7fd2d7598..5815a520e02 100644 --- a/src/rgw/rgw_auth_s3.h +++ b/src/rgw/rgw_auth_s3.h @@ -55,14 +55,14 @@ class STSAuthStrategy : public rgw::auth::Strategy, aplptr_t create_apl_local(CephContext* const cct, const req_state* const s, - const RGWUserInfo& user_info, + std::unique_ptr<rgw::sal::User> user, std::optional<RGWAccountInfo> account, std::vector<IAM::Policy> policies, const std::string& subuser, const std::optional<uint32_t>& perm_mask, const std::string& access_key_id) const override { auto apl = rgw::auth::add_sysreq(cct, driver, s, - LocalApplier(cct, user_info, std::move(account), std::move(policies), + LocalApplier(cct, std::move(user), std::move(account), std::move(policies), subuser, perm_mask, access_key_id)); return aplptr_t(new decltype(apl)(std::move(apl))); } @@ -72,7 +72,7 @@ class STSAuthStrategy : public rgw::auth::Strategy, RoleApplier::Role role, RoleApplier::TokenAttrs token_attrs) const override { auto apl = rgw::auth::add_sysreq(cct, driver, s, - rgw::auth::RoleApplier(cct, std::move(role), std::move(token_attrs))); + rgw::auth::RoleApplier(cct, driver, std::move(role), std::move(token_attrs))); return aplptr_t(new decltype(apl)(std::move(apl))); } @@ -176,14 +176,14 @@ class AWSAuthStrategy : public rgw::auth::Strategy, aplptr_t create_apl_local(CephContext* const cct, const req_state* const s, - const RGWUserInfo& user_info, + std::unique_ptr<rgw::sal::User> user, std::optional<RGWAccountInfo> account, std::vector<IAM::Policy> policies, const std::string& subuser, const std::optional<uint32_t>& perm_mask, const std::string& access_key_id) const override { auto apl = rgw::auth::add_sysreq(cct, driver, s, - LocalApplier(cct, user_info, std::move(account), std::move(policies), + LocalApplier(cct, std::move(user), std::move(account), std::move(policies), subuser, perm_mask, access_key_id)); /* TODO(rzarzynski): replace with static_ptr. */ return aplptr_t(new decltype(apl)(std::move(apl))); diff --git a/src/rgw/rgw_bucket_logging.cc b/src/rgw/rgw_bucket_logging.cc index d24a53024f1..dd407f26e8c 100644 --- a/src/rgw/rgw_bucket_logging.cc +++ b/src/rgw/rgw_bucket_logging.cc @@ -192,7 +192,7 @@ ceph::coarse_real_time time_from_name(const std::string& obj_name, const DoutPre ldpp_dout(dpp, 1) << "ERROR: logging object name too short: " << obj_name << dendl; return extracted_time; } - const auto time_start_pos = obj_name_length - (time_format_length + UniqueStringLength + 1); + const auto time_start_pos = obj_name_length - (time_format_length + UniqueStringLength + 1); // note: +1 is for the dash between the timestamp and the unique string std::string time_str = obj_name.substr(time_start_pos, time_format_length); @@ -206,6 +206,13 @@ ceph::coarse_real_time time_from_name(const std::string& obj_name, const DoutPre return extracted_time; } +std::string full_bucket_name(const std::unique_ptr<rgw::sal::Bucket>& bucket) { + if (bucket->get_tenant().empty()) { + return bucket->get_name(); + } + return fmt::format("{}:{}", bucket->get_tenant(), bucket->get_name()); +} + int new_logging_object(const configuration& conf, const std::unique_ptr<rgw::sal::Bucket>& bucket, std::string& obj_name, @@ -235,23 +242,22 @@ int new_logging_object(const configuration& conf, conf.target_prefix, to_string(bucket->get_owner()), source_region, - bucket->get_name(), + full_bucket_name(bucket), t, t, unique); } break; } - int ret = bucket->set_logging_object_name(obj_name, conf.target_prefix, y, dpp, init_obj, objv_tracker); if (ret == -EEXIST || ret == -ECANCELED) { if (ret = bucket->get_logging_object_name(obj_name, conf.target_prefix, y, dpp, nullptr); ret < 0) { ldpp_dout(dpp, 1) << "ERROR: failed to get name of logging object of bucket '" << - conf.target_bucket << "'. ret = " << ret << dendl; + conf.target_bucket << "' and prefix '" << conf.target_prefix << "', ret = " << ret << dendl; return ret; } ldpp_dout(dpp, 20) << "INFO: name already set. got name of logging object '" << obj_name << "' of bucket '" << - conf.target_bucket << "'" << dendl; + conf.target_bucket << "' and prefix '" << conf.target_prefix << "'" << dendl; return -ECANCELED; } else if (ret < 0) { ldpp_dout(dpp, 1) << "ERROR: failed to write name of logging object '" << obj_name << "' of bucket '" << @@ -263,6 +269,44 @@ int new_logging_object(const configuration& conf, return 0; } +int commit_logging_object(const configuration& conf, + const DoutPrefixProvider *dpp, + rgw::sal::Driver* driver, + const std::string& tenant_name, + optional_yield y) { + std::string target_bucket_name; + std::string target_tenant_name; + auto ret = rgw_parse_url_bucket(conf.target_bucket, tenant_name, target_tenant_name, target_bucket_name); + if (ret < 0) { + ldpp_dout(dpp, 1) << "ERROR: failed to parse target bucket '" << conf.target_bucket << "' when commiting logging object, ret = " + << ret << dendl; + return ret; + } + const rgw_bucket target_bucket_id(target_tenant_name, target_bucket_name); + std::unique_ptr<rgw::sal::Bucket> target_bucket; + ret = driver->load_bucket(dpp, target_bucket_id, + &target_bucket, y); + if (ret < 0) { + ldpp_dout(dpp, 1) << "ERROR: failed to get target logging bucket '" << target_bucket_id << "' when commiting logging object, ret = " + << ret << dendl; + return ret; + } + return commit_logging_object(conf, target_bucket, dpp, y); +} + +int commit_logging_object(const configuration& conf, + const std::unique_ptr<rgw::sal::Bucket>& target_bucket, + const DoutPrefixProvider *dpp, + optional_yield y) { + std::string obj_name; + if (const auto ret = target_bucket->get_logging_object_name(obj_name, conf.target_prefix, y, dpp, nullptr); ret < 0) { + ldpp_dout(dpp, 1) << "ERROR: failed to get name of logging object of bucket '" << + target_bucket->get_info().bucket << "'. ret = " << ret << dendl; + return ret; + } + return target_bucket->commit_logging_object(obj_name, y, dpp); +} + int rollover_logging_object(const configuration& conf, const std::unique_ptr<rgw::sal::Bucket>& bucket, std::string& obj_name, @@ -270,12 +314,16 @@ int rollover_logging_object(const configuration& conf, optional_yield y, bool must_commit, RGWObjVersionTracker* objv_tracker) { - if (conf.target_bucket != bucket->get_name()) { - ldpp_dout(dpp, 1) << "ERROR: bucket name mismatch: '" << conf.target_bucket << "' != '" << bucket->get_name() << "'" << dendl; + std::string target_bucket_name; + std::string target_tenant_name; + std::ignore = rgw_parse_url_bucket(conf.target_bucket, bucket->get_tenant(), target_tenant_name, target_bucket_name); + if (target_bucket_name != bucket->get_name() || target_tenant_name != bucket->get_tenant()) { + ldpp_dout(dpp, 1) << "ERROR: bucket name mismatch. conf= '" << conf.target_bucket << + "', bucket= '" << bucket->get_info().bucket << "'" << dendl; return -EINVAL; } const auto old_obj = obj_name; - const auto ret = new_logging_object(conf, bucket, obj_name, dpp, y, false, objv_tracker); + const auto ret = new_logging_object(conf, bucket, obj_name, dpp, y, false, objv_tracker); if (ret == -ECANCELED) { ldpp_dout(dpp, 20) << "INFO: rollover already performed for '" << old_obj << "' to bucket '" << conf.target_bucket << "'. ret = " << ret << dendl; @@ -342,14 +390,14 @@ S3 bucket short (ceph) log record - eTag };*/ -int log_record(rgw::sal::Driver* driver, +int log_record(rgw::sal::Driver* driver, const sal::Object* obj, - const req_state* s, - const std::string& op_name, - const std::string& etag, + const req_state* s, + const std::string& op_name, + const std::string& etag, size_t size, const configuration& conf, - const DoutPrefixProvider *dpp, + const DoutPrefixProvider *dpp, optional_yield y, bool async_completion, bool log_source_bucket) { @@ -357,11 +405,19 @@ int log_record(rgw::sal::Driver* driver, ldpp_dout(dpp, 1) << "ERROR: only bucket operations are logged" << dendl; return -EINVAL; } + std::string target_bucket_name; + std::string target_tenant_name; + auto ret = rgw_parse_url_bucket(conf.target_bucket, s->bucket_tenant, target_tenant_name, target_bucket_name); + if (ret < 0) { + ldpp_dout(dpp, 1) << "ERROR: failed to parse target bucket '" << conf.target_bucket << "', ret = " << ret << dendl; + return ret; + } + const rgw_bucket target_bucket_id(target_tenant_name, target_bucket_name); std::unique_ptr<rgw::sal::Bucket> target_bucket; - auto ret = driver->load_bucket(dpp, rgw_bucket(s->bucket_tenant, conf.target_bucket), + ret = driver->load_bucket(dpp, target_bucket_id, &target_bucket, y); if (ret < 0) { - ldpp_dout(dpp, 1) << "ERROR: failed to get target logging bucket '" << conf.target_bucket << "'. ret = " << ret << dendl; + ldpp_dout(dpp, 1) << "ERROR: failed to get target logging bucket '" << target_bucket_id << "'. ret = " << ret << dendl; return ret; } std::string obj_name; @@ -382,12 +438,14 @@ int log_record(rgw::sal::Driver* driver, // try to create the temporary log object for the first time ret = new_logging_object(conf, target_bucket, obj_name, dpp, y, true, nullptr); if (ret == 0) { - ldpp_dout(dpp, 20) << "INFO: first time logging for bucket '" << conf.target_bucket << "'" << dendl; + ldpp_dout(dpp, 20) << "INFO: first time logging for bucket '" << conf.target_bucket << "' and prefix '" << + conf.target_prefix << "'" << dendl; } else if (ret == -ECANCELED) { - ldpp_dout(dpp, 20) << "INFO: logging object '" << obj_name << "' already exists for bucket '" << conf.target_bucket << "', will be used" << dendl; + ldpp_dout(dpp, 20) << "INFO: logging object '" << obj_name << "' already exists for bucket '" << conf.target_bucket << "' and prefix" << + conf.target_prefix << "'" << dendl; } else { ldpp_dout(dpp, 1) << "ERROR: failed to create logging object of bucket '" << - conf.target_bucket << "' for the first time. ret = " << ret << dendl; + conf.target_bucket << "' and prefix '" << conf.target_prefix << "' for the first time. ret = " << ret << dendl; return ret; } } else { @@ -420,7 +478,7 @@ int log_record(rgw::sal::Driver* driver, bucket_name = s->src_bucket_name; } else { bucket_owner = to_string( s->bucket->get_owner()); - bucket_name = s->bucket->get_name(); + bucket_name = full_bucket_name(s->bucket); } switch (conf.logging_type) { @@ -459,7 +517,7 @@ int log_record(rgw::sal::Driver* driver, case LoggingType::Journal: record = fmt::format("{} {} [{:%d/%b/%Y:%H:%M:%S %z}] {} {} {} {} {}", dash_if_empty(to_string(s->bucket->get_owner())), - dash_if_empty(s->bucket->get_name()), + dash_if_empty(full_bucket_name(s->bucket)), t, op_name, dash_if_empty_or_null(obj, obj->get_name()), @@ -512,12 +570,12 @@ std::string object_name_oid(const rgw::sal::Bucket* bucket, const std::string& p int log_record(rgw::sal::Driver* driver, LoggingType type, const sal::Object* obj, - const req_state* s, - const std::string& op_name, - const std::string& etag, - size_t size, - const DoutPrefixProvider *dpp, - optional_yield y, + const req_state* s, + const std::string& op_name, + const std::string& etag, + size_t size, + const DoutPrefixProvider *dpp, + optional_yield y, bool async_completion, bool log_source_bucket) { if (!s->bucket) { @@ -534,7 +592,7 @@ int log_record(rgw::sal::Driver* driver, try { configuration.enabled = true; auto bl_iter = iter->second.cbegin(); - decode(configuration, bl_iter); + decode(configuration, bl_iter); if (type != LoggingType::Any && configuration.logging_type != type) { return 0; } @@ -543,20 +601,199 @@ int log_record(rgw::sal::Driver* driver, return 0; } } - ldpp_dout(dpp, 20) << "INFO: found matching logging configuration of bucket '" << s->bucket->get_name() << + ldpp_dout(dpp, 20) << "INFO: found matching logging configuration of bucket '" << s->bucket->get_info().bucket << "' configuration: " << configuration.to_json_str() << dendl; - if (auto ret = log_record(driver, obj, s, op_name, etag, size, configuration, dpp, y, async_completion, log_source_bucket); ret < 0) { - ldpp_dout(dpp, 1) << "ERROR: failed to perform logging for bucket '" << s->bucket->get_name() << + if (auto ret = log_record(driver, obj, s, op_name, etag, size, configuration, dpp, y, async_completion, log_source_bucket); ret < 0) { + ldpp_dout(dpp, 1) << "ERROR: failed to perform logging for bucket '" << s->bucket->get_info().bucket << "'. ret=" << ret << dendl; return ret; } } catch (buffer::error& err) { - ldpp_dout(dpp, 1) << "ERROR: failed to decode logging attribute '" << RGW_ATTR_BUCKET_LOGGING + ldpp_dout(dpp, 1) << "ERROR: failed to decode logging attribute '" << RGW_ATTR_BUCKET_LOGGING << "'. error: " << err.what() << dendl; return -EINVAL; } return 0; } +int get_bucket_id(const std::string& bucket_name, const std::string& tenant_name, rgw_bucket& bucket_id) { + std::string parsed_bucket_name; + std::string parsed_tenant_name; + if (const auto ret = rgw_parse_url_bucket(bucket_name, tenant_name, parsed_tenant_name, parsed_bucket_name); ret < 0) { + return ret; + } + bucket_id = rgw_bucket{parsed_tenant_name, parsed_bucket_name}; + return 0; +} + +int update_bucket_logging_sources(const DoutPrefixProvider* dpp, rgw::sal::Driver* driver, const rgw_bucket& target_bucket_id, const rgw_bucket& src_bucket_id, bool add, optional_yield y) { + std::unique_ptr<rgw::sal::Bucket> target_bucket; + const auto ret = driver->load_bucket(dpp, target_bucket_id, &target_bucket, y); + if (ret < 0) { + ldpp_dout(dpp, 1) << "WARNING: failed to get target bucket '" << target_bucket_id << "', ret = " << ret << dendl; + return ret; + } + return update_bucket_logging_sources(dpp, target_bucket, src_bucket_id, add, y); +} + +int update_bucket_logging_sources(const DoutPrefixProvider* dpp, std::unique_ptr<rgw::sal::Bucket>& bucket, const rgw_bucket& src_bucket_id, bool add, optional_yield y) { + return retry_raced_bucket_write(dpp, bucket.get(), [dpp, &bucket, &src_bucket_id, add, y] { + auto& attrs = bucket->get_attrs(); + auto iter = attrs.find(RGW_ATTR_BUCKET_LOGGING_SOURCES); + if (iter == attrs.end()) { + if (!add) { + ldpp_dout(dpp, 20) << "INFO: no logging sources attribute '" << RGW_ATTR_BUCKET_LOGGING_SOURCES + << "' for bucket '" << bucket->get_info().bucket << "', nothing to remove" << dendl; + return 0; + } + source_buckets sources{src_bucket_id}; + bufferlist bl; + ceph::encode(sources, bl); + attrs.insert(std::make_pair(RGW_ATTR_BUCKET_LOGGING_SOURCES, std::move(bl))); + return bucket->merge_and_store_attrs(dpp, attrs, y); + } + try { + source_buckets sources; + ceph::decode(sources, iter->second); + if ((add && sources.insert(src_bucket_id).second) || + (!add && sources.erase(src_bucket_id) > 0)) { + bufferlist bl; + ceph::encode(sources, bl); + iter->second = std::move(bl); + return bucket->merge_and_store_attrs(dpp, attrs, y); + } + } catch (buffer::error& err) { + ldpp_dout(dpp, 1) << "WARNING: failed to decode logging sources attribute '" << RGW_ATTR_BUCKET_LOGGING_SOURCES + << "' for bucket '" << bucket->get_info().bucket << "', error: " << err.what() << dendl; + } + ldpp_dout(dpp, 20) << "INFO: logging source '" << src_bucket_id << "' already " << + (add ? "added to" : "removed from") << " bucket '" << bucket->get_info().bucket << "'" << dendl; + return 0; + }, y); +} + + +int bucket_deletion_cleanup(const DoutPrefixProvider* dpp, + sal::Driver* driver, + sal::Bucket* bucket, + optional_yield y) { + // if the bucket is used a log bucket, we should delete all pending log objects + // and also delete the object holding the pending object name + auto& attrs = bucket->get_attrs(); + if (const auto iter = attrs.find(RGW_ATTR_BUCKET_LOGGING_SOURCES); iter != attrs.end()) { + try { + source_buckets sources; + ceph::decode(sources, iter->second); + for (const auto& source : sources) { + std::unique_ptr<rgw::sal::Bucket> src_bucket; + if (const auto ret = driver->load_bucket(dpp, source, &src_bucket, y); ret < 0) { + ldpp_dout(dpp, 1) << "WARNING: failed to get logging source bucket '" << source << "' for log bucket '" << + bucket->get_info().bucket << "', ret = " << ret << dendl; + continue; + } + auto& src_attrs = src_bucket->get_attrs(); + if (const auto iter = src_attrs.find(RGW_ATTR_BUCKET_LOGGING); iter != src_attrs.end()) { + configuration conf; + try { + auto bl_iter = iter->second.cbegin(); + decode(conf, bl_iter); + std::string obj_name; + RGWObjVersionTracker objv; + if (const auto ret = bucket->get_logging_object_name(obj_name, conf.target_prefix, y, dpp, &objv); ret < 0) { + ldpp_dout(dpp, 1) << "WARNING: failed to get logging object name for log bucket '" << bucket->get_info().bucket << + "', ret = " << ret << dendl; + continue; + } + if (const auto ret = bucket->remove_logging_object(obj_name, y, dpp); ret < 0) { + ldpp_dout(dpp, 1) << "WARNING: failed to delete pending logging object '" << obj_name << "' for log bucket '" << + bucket->get_info().bucket << "', ret = " << ret << dendl; + continue; + } + ldpp_dout(dpp, 20) << "INFO: successfully deleted pending logging object '" << obj_name << "' from deleted log bucket '" << + bucket->get_info().bucket << "'" << dendl; + if (const auto ret = bucket->remove_logging_object_name(conf.target_prefix, y, dpp, &objv); ret < 0) { + ldpp_dout(dpp, 1) << "WARNING: failed to delete object holding bucket logging object name for log bucket '" << + bucket->get_info().bucket << "', ret = " << ret << dendl; + continue; + } + ldpp_dout(dpp, 20) << "INFO: successfully deleted object holding bucket logging object name from deleted log bucket '" << + bucket->get_info().bucket << "'" << dendl; + } catch (buffer::error& err) { + ldpp_dout(dpp, 1) << "WARNING: failed to decode logging attribute '" << RGW_ATTR_BUCKET_LOGGING + << "' of bucket '" << src_bucket->get_info().bucket << "', error: " << err.what() << dendl; + } + } + } + } catch (buffer::error& err) { + ldpp_dout(dpp, 1) << "WARNING: failed to decode logging sources attribute '" << RGW_ATTR_BUCKET_LOGGING_SOURCES + << "' for bucket '" << bucket->get_info().bucket << "', error: " << err.what() << dendl; + return -EIO; + } + } + + return source_bucket_cleanup(dpp, driver, bucket, false, y); +} + +int source_bucket_cleanup(const DoutPrefixProvider* dpp, + sal::Driver* driver, + sal::Bucket* bucket, + bool remove_attr, + optional_yield y) { + std::optional<configuration> conf; + const auto& info = bucket->get_info(); + if (const auto ret = retry_raced_bucket_write(dpp, bucket, [dpp, bucket, &conf, &info, remove_attr, y] { + auto& attrs = bucket->get_attrs(); + if (auto iter = attrs.find(RGW_ATTR_BUCKET_LOGGING); iter != attrs.end()) { + try { + auto bl_iter = iter->second.cbegin(); + configuration tmp_conf; + tmp_conf.enabled = true; + decode(tmp_conf, bl_iter); + conf = std::move(tmp_conf); + } catch (buffer::error& err) { + ldpp_dout(dpp, 1) << "WARNING: failed to decode existing logging attribute '" << RGW_ATTR_BUCKET_LOGGING + << "' of bucket '" << info.bucket << "', error: " << err.what() << dendl; + return -EIO; + } + if (remove_attr) { + attrs.erase(iter); + return bucket->merge_and_store_attrs(dpp, attrs, y); + } + } + // nothing to remove or no need to remove + return 0; + }, y); ret < 0) { + if (remove_attr) { + ldpp_dout(dpp, 1) << "ERROR: failed to remove logging attribute '" << RGW_ATTR_BUCKET_LOGGING << "' from bucket '" << + info.bucket << "', ret = " << ret << dendl; + } + return ret; + } + if (!conf) { + // no logging attribute found + return 0; + } + if (const auto ret = commit_logging_object(*conf, dpp, driver, info.bucket.tenant, y); ret < 0) { + ldpp_dout(dpp, 1) << "WARNING: could not commit pending logging object of bucket '" << + info.bucket << "', ret = " << ret << dendl; + } else { + ldpp_dout(dpp, 20) << "INFO: successfully committed pending logging object of bucket '" << info.bucket << "'" << dendl; + } + rgw_bucket target_bucket_id; + rgw_bucket src_bucket_id{info.bucket.tenant, info.bucket.name}; + if (const auto ret = get_bucket_id(conf->target_bucket, info.bucket.tenant, target_bucket_id); ret < 0) { + ldpp_dout(dpp, 1) << "WARNING: failed to parse target bucket '" << conf->target_bucket << "', ret = " << ret << dendl; + return 0; + } + if (const auto ret = update_bucket_logging_sources(dpp, driver, target_bucket_id, src_bucket_id, false, y); ret < 0) { + ldpp_dout(dpp, 1) << "WARNING: could not update bucket logging source '" << + info.bucket << "', ret = " << ret << dendl; + return 0; + } + ldpp_dout(dpp, 20) << "INFO: successfully updated bucket logging source '" << + info.bucket << "'"<< dendl; + return 0; +} + } // namespace rgw::bucketlogging diff --git a/src/rgw/rgw_bucket_logging.h b/src/rgw/rgw_bucket_logging.h index d4877bafb0f..cbdb8b55f88 100644 --- a/src/rgw/rgw_bucket_logging.h +++ b/src/rgw/rgw_bucket_logging.h @@ -4,7 +4,6 @@ #pragma once #include <string> -#include <optional> #include <cstdint> #include "rgw_sal_fwd.h" #include "include/buffer.h" @@ -16,7 +15,7 @@ class XMLObj; namespace ceph { class Formatter; } class DoutPrefixProvider; struct req_state; -class RGWObjVersionTracker; +struct RGWObjVersionTracker; class RGWOp; namespace rgw::bucketlogging { @@ -66,6 +65,17 @@ enum class LoggingType {Standard, Journal, Any}; enum class PartitionDateSource {DeliveryTime, EventTime}; struct configuration { + bool operator==(const configuration& rhs) const { + return enabled == rhs.enabled && + target_bucket == rhs.target_bucket && + obj_key_format == rhs.obj_key_format && + target_prefix == rhs.target_prefix && + obj_roll_time == rhs.obj_roll_time && + logging_type == rhs.logging_type && + records_batch_size == rhs.records_batch_size && + date_source == rhs.date_source && + key_filter == rhs.key_filter; + } uint32_t default_obj_roll_time = 300; bool enabled = false; std::string target_bucket; @@ -129,6 +139,8 @@ struct configuration { }; WRITE_CLASS_ENCODER(configuration) +using source_buckets = std::set<rgw_bucket>; + constexpr unsigned MAX_BUCKET_LOGGING_BUFFER = 1000; using bucket_logging_records = std::array<std::string, MAX_BUCKET_LOGGING_BUFFER>; @@ -155,7 +167,7 @@ int log_record(rgw::sal::Driver* driver, bool async_completion, bool log_source_bucket); -// commit the pending log objec tto the log bucket +// commit the pending log objec to the log bucket // and create a new pending log object // if "must_commit" is "false" the function will return success even if the pending log object was not committed int rollover_logging_object(const configuration& conf, @@ -166,6 +178,23 @@ int rollover_logging_object(const configuration& conf, bool must_commit, RGWObjVersionTracker* objv_tracker); +// commit the pending log object to the log bucket +// use this for cleanup, when new pending object is not needed +// and target bucket is known +int commit_logging_object(const configuration& conf, + const std::unique_ptr<rgw::sal::Bucket>& target_bucket, + const DoutPrefixProvider *dpp, + optional_yield y); + +// commit the pending log object to the log bucket +// use this for cleanup, when new pending object is not needed +// and target bucket shoud be loaded based on the configuration +int commit_logging_object(const configuration& conf, + const DoutPrefixProvider *dpp, + rgw::sal::Driver* driver, + const std::string& tenant_name, + optional_yield y); + // return the oid of the object holding the name of the temporary logging object // bucket - log bucket // prefix - logging prefix from configuration. should be used when multiple buckets log into the same log bucket @@ -185,5 +214,37 @@ int log_record(rgw::sal::Driver* driver, optional_yield y, bool async_completion, bool log_source_bucket); + +// return (by ref) an rgw_bucket object with the bucket name and tenant name +// fails if the bucket name is not in the format: [tenant name:]<bucket name> +int get_bucket_id(const std::string& bucket_name, const std::string& tenant_name, rgw_bucket& bucket_id); + +// update (add or remove) a source bucket from the list of source buckets in the target bucket +// use this function when the target bucket is already loaded +int update_bucket_logging_sources(const DoutPrefixProvider* dpp, std::unique_ptr<rgw::sal::Bucket>& bucket, + const rgw_bucket& src_bucket, bool add, optional_yield y); + +// update (add or remove) a source bucket from the list of source buckets in the target bucket +// use this function when the target bucket is not known and needs to be loaded +int update_bucket_logging_sources(const DoutPrefixProvider* dpp, rgw::sal::Driver* driver, const rgw_bucket& target_bucket_id, + const rgw_bucket& src_bucket_id, bool add, optional_yield y); + +// when source bucket is deleted, all pending log objects should be comitted to the log bucket +// when the target bucket is deleted, all pending log objects should be deleted, as well as the object holding the pending log object name +int bucket_deletion_cleanup(const DoutPrefixProvider* dpp, + sal::Driver* driver, + sal::Bucket* bucket, + optional_yield y); + +// if bucket has bucket logging configuration associated with it then: +// if "remove_attr" is true, the bucket logging configuration should be removed from the bucket +// in addition: +// any pending log objects should be comitted to the log bucket +// and the log bucket should be updated to remove the bucket as a source +int source_bucket_cleanup(const DoutPrefixProvider* dpp, + sal::Driver* driver, + sal::Bucket* bucket, + bool remove_attr, + optional_yield y); } // namespace rgw::bucketlogging diff --git a/src/rgw/rgw_cksum_pipe.cc b/src/rgw/rgw_cksum_pipe.cc index e06957e2715..0bec8d341af 100644 --- a/src/rgw/rgw_cksum_pipe.cc +++ b/src/rgw/rgw_cksum_pipe.cc @@ -18,6 +18,7 @@ #include <string> #include <fmt/format.h> #include <boost/algorithm/string.hpp> +#include "rgw_cksum.h" #include "rgw_common.h" #include "common/dout.h" #include "rgw_client_io.h" @@ -34,7 +35,8 @@ namespace rgw::putobj { {} std::unique_ptr<RGWPutObj_Cksum> RGWPutObj_Cksum::Factory( - rgw::sal::DataProcessor* next, const RGWEnv& env) + rgw::sal::DataProcessor* next, const RGWEnv& env, + rgw::cksum::Type override_type) { /* look for matching headers */ auto algo_header = cksum_algorithm_hdr(env); @@ -49,6 +51,13 @@ namespace rgw::putobj { throw rgw::io::Exception(EINVAL, std::system_category()); } /* no checksum header */ + if (override_type != rgw::cksum::Type::none) { + /* XXXX safe? do we need to fixup env as well? */ + auto algo_header = cksum_algorithm_hdr(override_type); + return + std::make_unique<RGWPutObj_Cksum>( + next, override_type, std::move(algo_header)); + } return std::unique_ptr<RGWPutObj_Cksum>(); } diff --git a/src/rgw/rgw_cksum_pipe.h b/src/rgw/rgw_cksum_pipe.h index fddcd283c84..c459d156335 100644 --- a/src/rgw/rgw_cksum_pipe.h +++ b/src/rgw/rgw_cksum_pipe.h @@ -20,6 +20,7 @@ #include <tuple> #include <cstring> #include <boost/algorithm/string/case_conv.hpp> +#include "rgw_cksum.h" #include "rgw_cksum_digest.h" #include "rgw_common.h" #include "rgw_putobj.h" @@ -29,6 +30,38 @@ namespace rgw::putobj { namespace cksum = rgw::cksum; using cksum_hdr_t = std::pair<const char*, const char*>; + static inline const cksum_hdr_t cksum_algorithm_hdr(rgw::cksum::Type t) { + static constexpr std::string_view hdr = + "HTTP_X_AMZ_SDK_CHECKSUM_ALGORITHM"; + using rgw::cksum::Type; + switch (t) { + case Type::sha256: + return cksum_hdr_t(hdr.data(), "SHA256"); + break; + case Type::crc32: + return cksum_hdr_t(hdr.data(), "CRC32"); + break; + case Type::crc32c: + return cksum_hdr_t(hdr.data(), "CRC32C"); + break; + case Type::xxh3: + return cksum_hdr_t(hdr.data(), "XX3"); + break; + case Type::sha1: + return cksum_hdr_t(hdr.data(), "SHA1"); + break; + case Type::sha512: + return cksum_hdr_t(hdr.data(), "SHA512"); + break; + case Type::blake3: + return cksum_hdr_t(hdr.data(), "BLAKE3"); + break; + default: + break; + }; + return cksum_hdr_t(nullptr, nullptr);; + } + static inline const cksum_hdr_t cksum_algorithm_hdr(const RGWEnv& env) { /* If the individual checksum value you provide through x-amz-checksum-algorithm doesn't match the checksum algorithm @@ -102,7 +135,8 @@ namespace rgw::putobj { using VerifyResult = std::tuple<bool, const cksum::Cksum&>; static std::unique_ptr<RGWPutObj_Cksum> Factory( - rgw::sal::DataProcessor* next, const RGWEnv&); + rgw::sal::DataProcessor* next, const RGWEnv&, + rgw::cksum::Type override_type); RGWPutObj_Cksum(rgw::sal::DataProcessor* next, rgw::cksum::Type _type, cksum_hdr_t&& _hdr); diff --git a/src/rgw/rgw_common.cc b/src/rgw/rgw_common.cc index 97c46f12bd0..6610538542c 100644 --- a/src/rgw/rgw_common.cc +++ b/src/rgw/rgw_common.cc @@ -63,6 +63,7 @@ rgw_http_errors rgw_http_s3_errors({ { ERR_INVALID_DIGEST, {400, "InvalidDigest" }}, { ERR_BAD_DIGEST, {400, "BadDigest" }}, { ERR_INVALID_LOCATION_CONSTRAINT, {400, "InvalidLocationConstraint" }}, + { ERR_ILLEGAL_LOCATION_CONSTRAINT_EXCEPTION, {400, "IllegalLocationConstraintException" }}, { ERR_ZONEGROUP_DEFAULT_PLACEMENT_MISCONFIGURATION, {400, "ZonegroupDefaultPlacementMisconfiguration" }}, { ERR_INVALID_BUCKET_NAME, {400, "InvalidBucketName" }}, { ERR_INVALID_OBJECT_NAME, {400, "InvalidObjectName" }}, diff --git a/src/rgw/rgw_common.h b/src/rgw/rgw_common.h index f0bd41494c3..99f7db4f569 100644 --- a/src/rgw/rgw_common.h +++ b/src/rgw/rgw_common.h @@ -108,6 +108,7 @@ using ceph::crypto::MD5; #define RGW_ATTR_X_ROBOTS_TAG RGW_ATTR_PREFIX "x-robots-tag" #define RGW_ATTR_STORAGE_CLASS RGW_ATTR_PREFIX "storage_class" #define RGW_ATTR_BUCKET_LOGGING RGW_ATTR_PREFIX "logging" +#define RGW_ATTR_BUCKET_LOGGING_SOURCES RGW_ATTR_PREFIX "logging-sources" /* S3 Object Lock*/ #define RGW_ATTR_OBJECT_LOCK RGW_ATTR_PREFIX "object-lock" @@ -337,6 +338,7 @@ inline constexpr const char* RGW_REST_STS_XMLNS = #define ERR_PRESIGNED_URL_EXPIRED 2223 #define ERR_PRESIGNED_URL_DISABLED 2224 #define ERR_AUTHORIZATION 2225 // SNS 403 AuthorizationError +#define ERR_ILLEGAL_LOCATION_CONSTRAINT_EXCEPTION 2226 #define ERR_BUSY_RESHARDING 2300 // also in cls_rgw_types.h, don't change! #define ERR_NO_SUCH_ENTITY 2301 diff --git a/src/rgw/rgw_iam_policy.cc b/src/rgw/rgw_iam_policy.cc index 2a5c9cd313e..ef6761d4222 100644 --- a/src/rgw/rgw_iam_policy.cc +++ b/src/rgw/rgw_iam_policy.cc @@ -94,6 +94,8 @@ static const actpair actpairs[] = { "s3:GetPublicAccessBlock", s3GetPublicAccessBlock }, { "s3:GetObjectAcl", s3GetObjectAcl }, { "s3:GetObject", s3GetObject }, + { "s3:GetObjectAttributes", s3GetObjectAttributes }, + { "s3:GetObjectVersionAttributes", s3GetObjectVersionAttributes }, { "s3:GetObjectTorrent", s3GetObjectTorrent }, { "s3:GetObjectVersionAcl", s3GetObjectVersionAcl }, { "s3:GetObjectVersion", s3GetObjectVersion }, @@ -1335,6 +1337,7 @@ const char* action_bit_string(uint64_t action) { case s3ListBucketVersions: return "s3:ListBucketVersions"; + case s3ListAllMyBuckets: return "s3:ListAllMyBuckets"; @@ -1479,6 +1482,12 @@ const char* action_bit_string(uint64_t action) { case s3BypassGovernanceRetention: return "s3:BypassGovernanceRetention"; + case s3GetObjectAttributes: + return "s3:GetObjectAttributes"; + + case s3GetObjectVersionAttributes: + return "s3:GetObjectVersionAttributes"; + case s3DescribeJob: return "s3:DescribeJob"; diff --git a/src/rgw/rgw_iam_policy.h b/src/rgw/rgw_iam_policy.h index 0476926143f..dd323ee4b9c 100644 --- a/src/rgw/rgw_iam_policy.h +++ b/src/rgw/rgw_iam_policy.h @@ -115,6 +115,8 @@ enum { s3GetBucketEncryption, s3PutBucketEncryption, s3DescribeJob, + s3GetObjectAttributes, + s3GetObjectVersionAttributes, s3All, s3objectlambdaGetObject, @@ -247,6 +249,8 @@ inline int op_to_perm(std::uint64_t op) { case s3GetObjectVersionTagging: case s3GetObjectRetention: case s3GetObjectLegalHold: + case s3GetObjectAttributes: + case s3GetObjectVersionAttributes: case s3ListAllMyBuckets: case s3ListBucket: case s3ListBucketMultipartUploads: diff --git a/src/rgw/rgw_op.cc b/src/rgw/rgw_op.cc index 252adab7c0d..7b0ca3134a3 100644 --- a/src/rgw/rgw_op.cc +++ b/src/rgw/rgw_op.cc @@ -25,8 +25,10 @@ #include "common/ceph_json.h" #include "common/static_ptr.h" #include "common/perf_counters_key.h" +#include "rgw_cksum.h" #include "rgw_cksum_digest.h" #include "rgw_common.h" +#include "common/split.h" #include "rgw_tracer.h" #include "rgw_rados.h" @@ -3558,54 +3560,62 @@ void RGWCreateBucket::execute(optional_yield y) const rgw::SiteConfig& site = *s->penv.site; const std::optional<RGWPeriod>& period = site.get_period(); const RGWZoneGroup& my_zonegroup = site.get_zonegroup(); - - if (s->system_request) { - // allow system requests to override the target zonegroup. for forwarded - // requests, we'll create the bucket for the originating zonegroup - createparams.zonegroup_id = s->info.args.get(RGW_SYS_PARAM_PREFIX "zonegroup"); - } - + const std::string rgwx_zonegroup = s->info.args.get(RGW_SYS_PARAM_PREFIX "zonegroup"); const RGWZoneGroup* bucket_zonegroup = &my_zonegroup; - if (createparams.zonegroup_id.empty()) { - // default to the local zonegroup - createparams.zonegroup_id = my_zonegroup.id; - } else if (period) { - auto z = period->period_map.zonegroups.find(createparams.zonegroup_id); - if (z == period->period_map.zonegroups.end()) { - ldpp_dout(this, 0) << "could not find zonegroup " - << createparams.zonegroup_id << " in current period" << dendl; - op_ret = -ENOENT; - return; - } - bucket_zonegroup = &z->second; - } else if (createparams.zonegroup_id != my_zonegroup.id) { - ldpp_dout(this, 0) << "zonegroup does not match current zonegroup " - << createparams.zonegroup_id << dendl; - op_ret = -ENOENT; - return; - } - // validate the LocationConstraint + // Validate LocationConstraint if it's provided and enforcement is strict if (!location_constraint.empty() && !relaxed_region_enforcement) { - // on the master zonegroup, allow any valid api_name. otherwise it has to - // match the bucket's zonegroup - if (period && my_zonegroup.is_master) { - if (!period->period_map.zonegroups_by_api.count(location_constraint)) { + if (period) { + auto location_iter = period->period_map.zonegroups_by_api.find(location_constraint); + if (location_iter == period->period_map.zonegroups_by_api.end()) { ldpp_dout(this, 0) << "location constraint (" << location_constraint << ") can't be found." << dendl; op_ret = -ERR_INVALID_LOCATION_CONSTRAINT; - s->err.message = "The specified location-constraint is not valid"; + s->err.message = fmt::format("The {} location constraint is not valid.", + location_constraint); return; } - } else if (bucket_zonegroup->api_name != location_constraint) { + bucket_zonegroup = &location_iter->second; + } else if (location_constraint != my_zonegroup.api_name) { // if we don't have a period, we can only use the current zonegroup - so check if the location matches by api name here ldpp_dout(this, 0) << "location constraint (" << location_constraint - << ") doesn't match zonegroup (" << bucket_zonegroup->api_name - << ')' << dendl; - op_ret = -ERR_INVALID_LOCATION_CONSTRAINT; - s->err.message = "The specified location-constraint is not valid"; + << ") doesn't match zonegroup (" << my_zonegroup.api_name << ")" << dendl; + op_ret = -ERR_ILLEGAL_LOCATION_CONSTRAINT_EXCEPTION; + s->err.message = fmt::format("The {} location constraint is incompatible " + "for the region specific endpoint this request was sent to.", + location_constraint); return; } } + // If it's a system request, use the provided zonegroup if available + else if (s->system_request && !rgwx_zonegroup.empty()) { + if (period) { + auto zonegroup_iter = period->period_map.zonegroups.find(rgwx_zonegroup); + if (zonegroup_iter == period->period_map.zonegroups.end()) { + ldpp_dout(this, 0) << "could not find zonegroup " << rgwx_zonegroup + << " in current period" << dendl; + op_ret = -ENOENT; + return; + } + bucket_zonegroup = &zonegroup_iter->second; + } + } + + const bool enforce_location_match = + !period || // No period: no multisite, so no need to enforce location match. + !s->system_request || // All user requests are enforced to match zonegroup's location. + !my_zonegroup.is_master; // but if it's a system request (forwarded) only allow remote creation on master zonegroup. + if (enforce_location_match && !my_zonegroup.equals(bucket_zonegroup->get_id())) { + ldpp_dout(this, 0) << "location constraint (" << bucket_zonegroup->api_name + << ") doesn't match zonegroup (" << my_zonegroup.api_name << ")" << dendl; + op_ret = -ERR_ILLEGAL_LOCATION_CONSTRAINT_EXCEPTION; + s->err.message = fmt::format("The {} location constraint is incompatible " + "for the region specific endpoint this request was sent to.", + bucket_zonegroup->api_name); + return; + } + + // Set the final zonegroup ID + createparams.zonegroup_id = bucket_zonegroup->id; // select and validate the placement target op_ret = select_bucket_placement(this, *bucket_zonegroup, s->user->get_info(), @@ -3614,7 +3624,7 @@ void RGWCreateBucket::execute(optional_yield y) return; } - if (bucket_zonegroup == &my_zonegroup) { + if (my_zonegroup.equals(bucket_zonegroup->get_id())) { // look up the zone placement pool createparams.zone_placement = rgw::find_zone_placement( this, site.get_zone_params(), createparams.placement_rule); @@ -3703,7 +3713,6 @@ void RGWCreateBucket::execute(optional_yield y) if (!driver->is_meta_master()) { // apply bucket creation on the master zone first - bufferlist in_data; JSONParser jp; op_ret = rgw_forward_request_to_master(this, *s->penv.site, s->owner.id, &in_data, &jp, s->info, y); @@ -4334,6 +4343,9 @@ void RGWPutObj::execute(optional_yield y) } return; } + + multipart_cksum_type = upload->cksum_type; + /* upload will go out of scope, so copy the dest placement for later use */ s->dest_placement = *pdest_placement; pdest_placement = &s->dest_placement; @@ -4464,11 +4476,12 @@ void RGWPutObj::execute(optional_yield y) /* optional streaming checksum */ try { cksum_filter = - rgw::putobj::RGWPutObj_Cksum::Factory(filter, *s->info.env); + rgw::putobj::RGWPutObj_Cksum::Factory(filter, *s->info.env, multipart_cksum_type); } catch (const rgw::io::Exception& e) { op_ret = -e.code().value(); return; } + if (cksum_filter) { filter = &*cksum_filter; } @@ -4615,10 +4628,12 @@ void RGWPutObj::execute(optional_yield y) if (cksum_filter) { const auto& hdr = cksum_filter->header(); + auto expected_ck = cksum_filter->expected(*s->info.env); auto cksum_verify = cksum_filter->verify(*s->info.env); // valid or no supplied cksum cksum = get<1>(cksum_verify); - if (std::get<0>(cksum_verify)) { + if ((!expected_ck) || + std::get<0>(cksum_verify)) { buffer::list cksum_bl; ldpp_dout_fmt(this, 16, @@ -4626,14 +4641,13 @@ void RGWPutObj::execute(optional_yield y) "\n\tcomputed={} == \n\texpected={}", hdr.second, cksum->to_armor(), - cksum_filter->expected(*s->info.env)); + (!!expected_ck) ? expected_ck : "(checksum unavailable)"); cksum->encode(cksum_bl); emplace_attr(RGW_ATTR_CKSUM, std::move(cksum_bl)); } else { /* content checksum mismatch */ auto computed_ck = cksum->to_armor(); - auto expected_ck = cksum_filter->expected(*s->info.env); ldpp_dout_fmt(this, 4, "{} content checksum mismatch" @@ -4836,7 +4850,8 @@ void RGWPostObj::execute(optional_yield y) /* optional streaming checksum */ try { cksum_filter = - rgw::putobj::RGWPutObj_Cksum::Factory(filter, *s->info.env); + rgw::putobj::RGWPutObj_Cksum::Factory( + filter, *s->info.env, rgw::cksum::Type::none /* no override */); } catch (const rgw::io::Exception& e) { op_ret = -e.code().value(); return; @@ -5975,8 +5990,6 @@ void RGWGetACLs::execute(optional_yield y) acls = ss.str(); } - - int RGWPutACLs::verify_permission(optional_yield y) { bool perm; @@ -5998,6 +6011,74 @@ int RGWPutACLs::verify_permission(optional_yield y) return 0; } +uint16_t RGWGetObjAttrs::recognize_attrs(const std::string& hdr, uint16_t deflt) +{ + auto attrs{deflt}; + auto sa = ceph::split(hdr, ","); + for (auto& k : sa) { + if (boost::iequals(k, "etag")) { + attrs |= as_flag(ReqAttributes::Etag); + } + if (boost::iequals(k, "checksum")) { + attrs |= as_flag(ReqAttributes::Checksum); + } + if (boost::iequals(k, "objectparts")) { + attrs |= as_flag(ReqAttributes::ObjectParts); + } + if (boost::iequals(k, "objectsize")) { + attrs |= as_flag(ReqAttributes::ObjectSize); + } + if (boost::iequals(k, "storageclass")) { + attrs |= as_flag(ReqAttributes::StorageClass); + } + } + return attrs; +} /* RGWGetObjAttrs::recognize_attrs */ + +int RGWGetObjAttrs::verify_permission(optional_yield y) +{ + bool perm = false; + auto [has_s3_existing_tag, has_s3_resource_tag] = + rgw_check_policy_condition(this, s); + + if (! rgw::sal::Object::empty(s->object.get())) { + + auto iam_action1 = s->object->get_instance().empty() ? + rgw::IAM::s3GetObject : + rgw::IAM::s3GetObjectVersion; + + auto iam_action2 = s->object->get_instance().empty() ? + rgw::IAM::s3GetObjectAttributes : + rgw::IAM::s3GetObjectVersionAttributes; + + if (has_s3_existing_tag || has_s3_resource_tag) { + rgw_iam_add_objtags(this, s, has_s3_existing_tag, has_s3_resource_tag); + } + + /* XXXX the following conjunction should be &&--but iam_action2 is currently not + * hooked up and always fails (but should succeed if the requestor has READ + * acess to the object) */ + perm = (verify_object_permission(this, s, iam_action1) || /* && */ + verify_object_permission(this, s, iam_action2)); + } + + if (! perm) { + return -EACCES; + } + + return 0; +} + +void RGWGetObjAttrs::pre_exec() +{ + rgw_bucket_object_pre_exec(s); +} + +void RGWGetObjAttrs::execute(optional_yield y) +{ + RGWGetObj::execute(y); +} /* RGWGetObjAttrs::execute */ + int RGWGetLC::verify_permission(optional_yield y) { auto [has_s3_existing_tag, has_s3_resource_tag] = rgw_check_policy_condition(this, s, false); @@ -6665,6 +6746,14 @@ try_sum_part_cksums(const DoutPrefixProvider *dpp, ++parts_ix; auto& part_cksum = part.second->get_cksum(); + if (! part_cksum) { + ldpp_dout_fmt(dpp, 0, + "ERROR: multipart part checksum not present (ix=={})", + parts_ix); + op_ret = -ERR_INVALID_REQUEST; + return op_ret; + } + ldpp_dout_fmt(dpp, 16, "INFO: {} iterate part: {} {} {}", __func__, parts_ix, part_cksum->type_string(), diff --git a/src/rgw/rgw_op.h b/src/rgw/rgw_op.h index 9f747501729..dcf64c31572 100644 --- a/src/rgw/rgw_op.h +++ b/src/rgw/rgw_op.h @@ -12,6 +12,7 @@ #pragma once +#include <cstdint> #include <limits.h> #include <array> @@ -1111,6 +1112,7 @@ class RGWCreateBucket : public RGWOp { bool relaxed_region_enforcement = false; RGWCORSConfiguration cors_config; std::set<std::string> rmattr_names; + bufferlist in_data; virtual bool need_metadata_upload() const { return false; } @@ -1237,6 +1239,7 @@ protected: std::string multipart_upload_id; std::string multipart_part_str; int multipart_part_num = 0; + rgw::cksum::Type multipart_cksum_type{rgw::cksum::Type::none}; jspan_ptr multipart_trace; boost::optional<ceph::real_time> delete_at; @@ -1644,6 +1647,50 @@ public: uint32_t op_mask() override { return RGW_OP_TYPE_WRITE; } }; +class RGWGetObjAttrs : public RGWGetObj { +protected: + std::string version_id; + std::string expected_bucket_owner; + std::optional<int> marker; + std::optional<int> max_parts; + uint16_t requested_attributes{0}; +#if 0 + /* used to decrypt attributes for objects stored with SSE-C */ + x-amz-server-side-encryption-customer-algorithm + x-amz-server-side-encryption-customer-key + x-amz-server-side-encryption-customer-key-MD5 +#endif +public: + + enum class ReqAttributes : uint16_t { + None = 0, + Etag, + Checksum, + ObjectParts, + StorageClass, + ObjectSize + }; + + static uint16_t as_flag(ReqAttributes attr) { + return 1 << (uint16_t(attr) ? uint16_t(attr) - 1 : 0); + } + + static uint16_t recognize_attrs(const std::string& hdr, uint16_t deflt = 0); + + RGWGetObjAttrs() : RGWGetObj() + { + RGWGetObj::get_data = false; // it's extra false + } + + int verify_permission(optional_yield y) override; + void pre_exec() override; + void execute(optional_yield y) override; + void send_response() override = 0; + const char* name() const override { return "get_obj_attrs"; } + RGWOpType get_type() override { return RGW_OP_GET_OBJ_ATTRS; } + uint32_t op_mask() override { return RGW_OP_TYPE_READ; } +}; /* RGWGetObjAttrs */ + class RGWGetLC : public RGWOp { protected: diff --git a/src/rgw/rgw_op_type.h b/src/rgw/rgw_op_type.h index 49faea6403d..2c8225d289e 100644 --- a/src/rgw/rgw_op_type.h +++ b/src/rgw/rgw_op_type.h @@ -30,6 +30,7 @@ enum RGWOpType { RGW_OP_COPY_OBJ, RGW_OP_GET_ACLS, RGW_OP_PUT_ACLS, + RGW_OP_GET_OBJ_ATTRS, RGW_OP_GET_CORS, RGW_OP_PUT_CORS, RGW_OP_DELETE_CORS, diff --git a/src/rgw/rgw_rest.h b/src/rgw/rgw_rest.h index aa33080af56..9111696453e 100644 --- a/src/rgw/rgw_rest.h +++ b/src/rgw/rgw_rest.h @@ -403,6 +403,17 @@ public: virtual std::string canonical_name() const override { return fmt::format("REST.{}.ACL", s->info.method); } }; +class RGWGetObjAttrs_ObjStore : public RGWGetObjAttrs { +public: + RGWGetObjAttrs_ObjStore() {} + ~RGWGetObjAttrs_ObjStore() override {} + + int get_params(optional_yield y) = 0; + /* not actually used */ + int send_response_data_error(optional_yield y) override { return 0; }; + int send_response_data(bufferlist& bl, off_t ofs, off_t len) override { return 0; }; +}; + class RGWGetLC_ObjStore : public RGWGetLC { public: RGWGetLC_ObjStore() {} diff --git a/src/rgw/rgw_rest_bucket_logging.cc b/src/rgw/rgw_rest_bucket_logging.cc index ed12ce855a9..afd79b0a548 100644 --- a/src/rgw/rgw_rest_bucket_logging.cc +++ b/src/rgw/rgw_rest_bucket_logging.cc @@ -58,30 +58,29 @@ public: return; } - std::unique_ptr<rgw::sal::Bucket> bucket; - op_ret = driver->load_bucket(this, rgw_bucket(s->bucket_tenant, s->bucket_name), - &bucket, y); + const rgw_bucket src_bucket_id(s->bucket_tenant, s->bucket_name); + std::unique_ptr<rgw::sal::Bucket> src_bucket; + op_ret = driver->load_bucket(this, src_bucket_id, + &src_bucket, y); if (op_ret < 0) { - ldpp_dout(this, 1) << "ERROR: failed to get bucket '" << - (s->bucket_tenant.empty() ? s->bucket_name : s->bucket_tenant + ":" + s->bucket_name) << - "' info, ret = " << op_ret << dendl; + ldpp_dout(this, 1) << "ERROR: failed to get bucket '" << src_bucket_id << "', ret = " << op_ret << dendl; return; } - if (auto iter = bucket->get_attrs().find(RGW_ATTR_BUCKET_LOGGING); iter != bucket->get_attrs().end()) { + if (auto iter = src_bucket->get_attrs().find(RGW_ATTR_BUCKET_LOGGING); iter != src_bucket->get_attrs().end()) { try { configuration.enabled = true; decode(configuration, iter->second); } catch (buffer::error& err) { - ldpp_dout(this, 1) << "ERROR: failed to decode attribute '" << RGW_ATTR_BUCKET_LOGGING - << "'. error: " << err.what() << dendl; + ldpp_dout(this, 1) << "WARNING: failed to decode logging attribute '" << RGW_ATTR_BUCKET_LOGGING + << "' for bucket '" << src_bucket_id << "', error: " << err.what() << dendl; op_ret = -EIO; return; } } else { - ldpp_dout(this, 5) << "WARNING: no logging configuration on bucket '" << bucket->get_name() << "'" << dendl; + ldpp_dout(this, 5) << "WARNING: no logging configuration on bucket '" << src_bucket_id << "'" << dendl; return; } - ldpp_dout(this, 20) << "INFO: found logging configuration on bucket '" << bucket->get_name() << "'" + ldpp_dout(this, 20) << "INFO: found logging configuration on bucket '" << src_bucket_id << "'" << "'. configuration: " << configuration.to_json_str() << dendl; } @@ -159,58 +158,125 @@ class RGWPutBucketLoggingOp : public RGWDefaultResponseOp { return; } - std::unique_ptr<rgw::sal::Bucket> bucket; - op_ret = driver->load_bucket(this, rgw_bucket(s->bucket_tenant, s->bucket_name), - &bucket, y); + const rgw_bucket src_bucket_id(s->bucket_tenant, s->bucket_name); + std::unique_ptr<rgw::sal::Bucket> src_bucket; + op_ret = driver->load_bucket(this, src_bucket_id, + &src_bucket, y); if (op_ret < 0) { - ldpp_dout(this, 1) << "ERROR: failed to get bucket '" << s->bucket_name << "', ret = " << op_ret << dendl; + ldpp_dout(this, 1) << "ERROR: failed to get bucket '" << src_bucket_id << "', ret = " << op_ret << dendl; return; } - - auto& attrs = bucket->get_attrs(); if (!configuration.enabled) { - if (auto iter = attrs.find(RGW_ATTR_BUCKET_LOGGING); iter != attrs.end()) { - attrs.erase(iter); - } - } else { - std::unique_ptr<rgw::sal::Bucket> target_bucket; - op_ret = driver->load_bucket(this, rgw_bucket(s->bucket_tenant, configuration.target_bucket), - &target_bucket, y); - if (op_ret < 0) { - ldpp_dout(this, 1) << "ERROR: failed to get target bucket '" << configuration.target_bucket << "', ret = " << op_ret << dendl; - return; - } - const auto& target_attrs = target_bucket->get_attrs(); - if (target_attrs.find(RGW_ATTR_BUCKET_LOGGING) != target_attrs.end()) { - // target bucket must not have logging set on it - ldpp_dout(this, 1) << "ERROR: logging target bucket '" << configuration.target_bucket << "', is configured with bucket logging" << dendl; - op_ret = -EINVAL; - return; - } - // TODO: verify target bucket does not have encryption - bufferlist conf_bl; - encode(configuration, conf_bl); - attrs[RGW_ATTR_BUCKET_LOGGING] = conf_bl; - // TODO: should we add attribute to target bucket indicating it is target to bucket logging? - // if we do, how do we maintain it when bucket logging changes? + op_ret = rgw::bucketlogging::source_bucket_cleanup(this, driver, src_bucket.get(), true, y); + return; + } + + // set logging configuration + rgw_bucket target_bucket_id; + if (op_ret = rgw::bucketlogging::get_bucket_id(configuration.target_bucket, s->bucket_tenant, target_bucket_id); op_ret < 0) { + ldpp_dout(this, 1) << "ERROR: failed to parse target bucket '" << configuration.target_bucket << "', ret = " << op_ret << dendl; + return; + } + + if (target_bucket_id == src_bucket_id) { + ldpp_dout(this, 1) << "ERROR: target bucket '" << target_bucket_id << "' must be different from source bucket" << dendl; + op_ret = -EINVAL; + return; + } + std::unique_ptr<rgw::sal::Bucket> target_bucket; + op_ret = driver->load_bucket(this, target_bucket_id, + &target_bucket, y); + if (op_ret < 0) { + ldpp_dout(this, 1) << "ERROR: failed to get target bucket '" << target_bucket_id << "', ret = " << op_ret << dendl; + return; + } + auto& target_attrs = target_bucket->get_attrs(); + if (target_attrs.find(RGW_ATTR_BUCKET_LOGGING) != target_attrs.end()) { + // target bucket must not have logging set on it + ldpp_dout(this, 1) << "ERROR: logging target bucket '" << target_bucket_id << "', is configured with bucket logging" << dendl; + op_ret = -EINVAL; + return; } - // TODO: use retry_raced_bucket_write from rgw_op.cc - op_ret = bucket->merge_and_store_attrs(this, attrs, y); + // verify target bucket does not have encryption + if (target_attrs.find(RGW_ATTR_BUCKET_ENCRYPTION_POLICY) != target_attrs.end()) { + ldpp_dout(this, 1) << "ERROR: logging target bucket '" << target_bucket_id << "', is configured with encryption" << dendl; + op_ret = -EINVAL; + return; + } + std::optional<rgw::bucketlogging::configuration> old_conf; + bufferlist conf_bl; + encode(configuration, conf_bl); + op_ret = retry_raced_bucket_write(this, src_bucket.get(), [this, &conf_bl, &src_bucket, &old_conf, &configuration, y] { + auto& attrs = src_bucket->get_attrs(); + auto it = attrs.find(RGW_ATTR_BUCKET_LOGGING); + if (it != attrs.end()) { + try { + rgw::bucketlogging::configuration tmp_conf; + tmp_conf.enabled = true; + decode(tmp_conf, it->second); + old_conf = std::move(tmp_conf); + } catch (buffer::error& err) { + ldpp_dout(this, 1) << "WARNING: failed to decode existing logging attribute '" << RGW_ATTR_BUCKET_LOGGING + << "' for bucket '" << src_bucket->get_info().bucket << "', error: " << err.what() << dendl; + } + if (!old_conf || (old_conf && *old_conf != configuration)) { + // conf changed (or was unknown) - update + it->second = conf_bl; + return src_bucket->merge_and_store_attrs(this, attrs, y); + } + // nothing to update + return 0; + } + // conf was added + attrs.insert(std::make_pair(RGW_ATTR_BUCKET_LOGGING, conf_bl)); + return src_bucket->merge_and_store_attrs(this, attrs, y); + }, y); if (op_ret < 0) { ldpp_dout(this, 1) << "ERROR: failed to set logging attribute '" << RGW_ATTR_BUCKET_LOGGING << "' to bucket '" << - bucket->get_name() << "', ret = " << op_ret << dendl; + src_bucket_id << "', ret = " << op_ret << dendl; return; } - - ldpp_dout(this, 20) << "INFO: " << (configuration.enabled ? "wrote" : "removed") - << " logging configuration. bucket '" << bucket->get_name() << "'. configuration: " << - configuration.to_json_str() << dendl; + if (!old_conf) { + ldpp_dout(this, 20) << "INFO: new logging configuration added to bucket '" << src_bucket_id << "'. configuration: " << + configuration.to_json_str() << dendl; + if (const auto ret = rgw::bucketlogging::update_bucket_logging_sources(this, target_bucket, src_bucket_id, true, y); ret < 0) { + ldpp_dout(this, 1) << "WARNING: failed to add source bucket '" << src_bucket_id << "' to logging sources of target bucket '" << + target_bucket_id << "', ret = " << ret << dendl; + } + } else if (*old_conf != configuration) { + // conf changed - do cleanup + if (const auto ret = commit_logging_object(*old_conf, target_bucket, this, y); ret < 0) { + ldpp_dout(this, 1) << "WARNING: could not commit pending logging object when updating logging configuration of bucket '" << + src_bucket->get_info().bucket << "', ret = " << ret << dendl; + } else { + ldpp_dout(this, 20) << "INFO: committed pending logging object when updating logging configuration of bucket '" << + src_bucket->get_info().bucket << "'" << dendl; + } + if (old_conf->target_bucket != configuration.target_bucket) { + rgw_bucket old_target_bucket_id; + if (const auto ret = rgw::bucketlogging::get_bucket_id(old_conf->target_bucket, s->bucket_tenant, old_target_bucket_id); ret < 0) { + ldpp_dout(this, 1) << "ERROR: failed to parse target bucket '" << old_conf->target_bucket << "', ret = " << ret << dendl; + return; + } + if (const auto ret = rgw::bucketlogging::update_bucket_logging_sources(this, driver, old_target_bucket_id, src_bucket_id, false, y); ret < 0) { + ldpp_dout(this, 1) << "WARNING: failed to remove source bucket '" << src_bucket_id << "' from logging sources of original target bucket '" << + old_target_bucket_id << "', ret = " << ret << dendl; + } + if (const auto ret = rgw::bucketlogging::update_bucket_logging_sources(this, target_bucket, src_bucket_id, true, y); ret < 0) { + ldpp_dout(this, 1) << "WARNING: failed to add source bucket '" << src_bucket_id << "' to logging sources of target bucket '" << + target_bucket_id << "', ret = " << ret << dendl; + } + } + ldpp_dout(this, 20) << "INFO: wrote logging configuration to bucket '" << src_bucket_id << "'. configuration: " << + configuration.to_json_str() << dendl; + } else { + ldpp_dout(this, 20) << "INFO: logging configuration of bucket '" << src_bucket_id << "' did not change" << dendl; + } } }; // Post /<bucket name>/?logging -// actual configuration is XML encoded in the body of the message class RGWPostBucketLoggingOp : public RGWDefaultResponseOp { int verify_permission(optional_yield y) override { auto [has_s3_existing_tag, has_s3_resource_tag] = rgw_check_policy_condition(this, s, false); @@ -234,17 +300,18 @@ class RGWPostBucketLoggingOp : public RGWDefaultResponseOp { return; } - std::unique_ptr<rgw::sal::Bucket> bucket; - op_ret = driver->load_bucket(this, rgw_bucket(s->bucket_tenant, s->bucket_name), - &bucket, y); + const rgw_bucket src_bucket_id(s->bucket_tenant, s->bucket_name); + std::unique_ptr<rgw::sal::Bucket> src_bucket; + op_ret = driver->load_bucket(this, src_bucket_id, + &src_bucket, y); if (op_ret < 0) { - ldpp_dout(this, 1) << "ERROR: failed to get bucket '" << s->bucket_name << "', ret = " << op_ret << dendl; + ldpp_dout(this, 1) << "ERROR: failed to get bucket '" << src_bucket_id << "', ret = " << op_ret << dendl; return; } - const auto& bucket_attrs = bucket->get_attrs(); + const auto& bucket_attrs = src_bucket->get_attrs(); auto iter = bucket_attrs.find(RGW_ATTR_BUCKET_LOGGING); if (iter == bucket_attrs.end()) { - ldpp_dout(this, 1) << "WARNING: no logging configured on bucket" << dendl; + ldpp_dout(this, 1) << "WARNING: no logging configured on bucket '" << src_bucket_id << "'" << dendl; return; } rgw::bucketlogging::configuration configuration; @@ -252,33 +319,38 @@ class RGWPostBucketLoggingOp : public RGWDefaultResponseOp { configuration.enabled = true; decode(configuration, iter->second); } catch (buffer::error& err) { - ldpp_dout(this, 1) << "ERROR: failed to decode logging attribute '" << RGW_ATTR_BUCKET_LOGGING - << "'. error: " << err.what() << dendl; + ldpp_dout(this, 1) << "WARNING: failed to decode logging attribute '" << RGW_ATTR_BUCKET_LOGGING + << "' for bucket '" << src_bucket_id << "', error: " << err.what() << dendl; op_ret = -EINVAL; return; } + rgw_bucket target_bucket_id; + if (op_ret = rgw::bucketlogging::get_bucket_id(configuration.target_bucket, s->bucket_tenant, target_bucket_id); op_ret < 0) { + ldpp_dout(this, 1) << "ERROR: failed to parse target bucket '" << configuration.target_bucket << "', ret = " << op_ret << dendl; + return; + } std::unique_ptr<rgw::sal::Bucket> target_bucket; - op_ret = driver->load_bucket(this, rgw_bucket(s->bucket_tenant, configuration.target_bucket), + op_ret = driver->load_bucket(this, target_bucket_id, &target_bucket, y); if (op_ret < 0) { - ldpp_dout(this, 1) << "ERROR: failed to get target bucket '" << configuration.target_bucket << "', ret = " << op_ret << dendl; + ldpp_dout(this, 1) << "ERROR: failed to get target bucket '" << target_bucket_id << "', ret = " << op_ret << dendl; return; } std::string obj_name; RGWObjVersionTracker objv_tracker; op_ret = target_bucket->get_logging_object_name(obj_name, configuration.target_prefix, null_yield, this, &objv_tracker); if (op_ret < 0) { - ldpp_dout(this, 1) << "ERROR: failed to get pending logging object name from target bucket '" << configuration.target_bucket << "'" << dendl; + ldpp_dout(this, 1) << "ERROR: failed to get pending logging object name from target bucket '" << target_bucket_id << "'" << dendl; return; } op_ret = rgw::bucketlogging::rollover_logging_object(configuration, target_bucket, obj_name, this, null_yield, true, &objv_tracker); if (op_ret < 0) { ldpp_dout(this, 1) << "ERROR: failed to flush pending logging object '" << obj_name - << "' to target bucket '" << configuration.target_bucket << "'" << dendl; + << "' to target bucket '" << target_bucket_id << "'" << dendl; return; } - ldpp_dout(this, 20) << "flushed pending logging object '" << obj_name + ldpp_dout(this, 20) << "INFO: flushed pending logging object '" << obj_name << "' to target bucket '" << configuration.target_bucket << "'" << dendl; } }; diff --git a/src/rgw/rgw_rest_s3.cc b/src/rgw/rgw_rest_s3.cc index 30ebe8e8965..885991244a6 100644 --- a/src/rgw/rgw_rest_s3.cc +++ b/src/rgw/rgw_rest_s3.cc @@ -9,6 +9,7 @@ #include <string_view> #include "common/ceph_crypto.h" +#include "common/dout.h" #include "common/split.h" #include "common/Formatter.h" #include "common/utf8.h" @@ -807,7 +808,6 @@ void RGWGetObjTags_ObjStore_S3::send_response_data(bufferlist& bl) } } - int RGWPutObjTags_ObjStore_S3::get_params(optional_yield y) { RGWXMLParser parser; @@ -2533,6 +2533,10 @@ int RGWCreateBucket_ObjStore_S3::get_params(optional_yield y) if ((op_ret < 0) && (op_ret != -ERR_LENGTH_REQUIRED)) return op_ret; + if (!driver->is_meta_master()) { + in_data.append(data); + } + if (data.length()) { RGWCreateBucketParser parser; @@ -3815,6 +3819,196 @@ void RGWPutACLs_ObjStore_S3::send_response() dump_start(s); } +int RGWGetObjAttrs_ObjStore_S3::get_params(optional_yield y) +{ + string err; + auto& env = s->info.env; + version_id = s->info.args.get("versionId"); + + auto hdr = env->get_optional("HTTP_X_AMZ_EXPECTED_BUCKET_OWNER"); + if (hdr) { + expected_bucket_owner = *hdr; + } + + hdr = env->get_optional("HTTP_X_AMZ_MAX_PARTS"); + if (hdr) { + max_parts = strict_strtol(hdr->c_str(), 10, &err); + if (!err.empty()) { + s->err.message = "Invalid value for MaxParts: " + err; + ldpp_dout(s, 10) << "Invalid value for MaxParts " << *hdr << ": " + << err << dendl; + return -ERR_INVALID_PART; + } + max_parts = std::min(*max_parts, 1000); + } + + hdr = env->get_optional("HTTP_X_AMZ_PART_NUMBER_MARKER"); + if (hdr) { + marker = strict_strtol(hdr->c_str(), 10, &err); + if (!err.empty()) { + s->err.message = "Invalid value for PartNumberMarker: " + err; + ldpp_dout(s, 10) << "Invalid value for PartNumberMarker " << *hdr << ": " + << err << dendl; + return -ERR_INVALID_PART; + } + } + + hdr = env->get_optional("HTTP_X_AMZ_OBJECT_ATTRIBUTES"); + if (hdr) { + requested_attributes = recognize_attrs(*hdr); + } + + /* XXX skipping SSE-C params for now */ + + return 0; +} /* RGWGetObjAttrs_ObjStore_S3::get_params(...) */ + +int RGWGetObjAttrs_ObjStore_S3::get_decrypt_filter( + std::unique_ptr<RGWGetObj_Filter> *filter, + RGWGetObj_Filter* cb, bufferlist* manifest_bl) +{ + // we aren't actually decrypting the data, but for objects encrypted with + // SSE-C we do need to verify that required headers are present and valid + // + // in the SSE-KMS and SSE-S3 cases, this unfortunately causes us to fetch + // decryption keys which we don't need :( + std::unique_ptr<BlockCrypt> block_crypt; // ignored + std::map<std::string, std::string> crypt_http_responses; // ignored + return rgw_s3_prepare_decrypt(s, s->yield, attrs, &block_crypt, + crypt_http_responses); +} + +void RGWGetObjAttrs_ObjStore_S3::send_response() +{ + if (op_ret) + set_req_state_err(s, op_ret); + dump_errno(s); + + if (op_ret == 0) { + version_id = s->object->get_instance(); + + // x-amz-delete-marker: DeleteMarker // not sure we can plausibly do this? + dump_last_modified(s, lastmod); + dump_header_if_nonempty(s, "x-amz-version-id", version_id); + // x-amz-request-charged: RequestCharged + } + + end_header(s, this, to_mime_type(s->format)); + dump_start(s); + + if (op_ret == 0) { + s->formatter->open_object_section("GetObjectAttributes"); + if (requested_attributes & as_flag(ReqAttributes::Etag)) { + if (lo_etag.empty()) { + auto iter = attrs.find(RGW_ATTR_ETAG); + if (iter != attrs.end()) { + lo_etag = iter->second.to_str(); + } + } + s->formatter->dump_string("ETag", lo_etag); + } + + if (requested_attributes & as_flag(ReqAttributes::Checksum)) { + s->formatter->open_object_section("Checksum"); + auto iter = attrs.find(RGW_ATTR_CKSUM); + if (iter != attrs.end()) { + try { + rgw::cksum::Cksum cksum; + auto bliter = iter->second.cbegin(); + cksum.decode(bliter); + if (multipart_parts_count && multipart_parts_count > 0) { + s->formatter->dump_string(cksum.element_name(), + fmt::format("{}-{}", cksum.to_armor(), *multipart_parts_count)); + } else { + s->formatter->dump_string(cksum.element_name(), cksum.to_armor()); + } + } catch (buffer::error& err) { + ldpp_dout(this, 0) + << "ERROR: could not decode stored cksum, caught buffer::error" << dendl; + } + } + s->formatter->close_section(); /* Checksum */ + } /* Checksum */ + + if (requested_attributes & as_flag(ReqAttributes::ObjectParts)) { + if (multipart_parts_count && multipart_parts_count > 0) { + + /* XXX the following was needed to see a manifest at list_parts()! */ + op_ret = s->object->load_obj_state(s, s->yield); + if (op_ret < 0) { + ldpp_dout_fmt(this, 0, + "ERROR: {} load_obj_state() failed ret={}", __func__, + op_ret); + } + + ldpp_dout_fmt(this, 16, + "{} attr flags={} parts_count={}", + __func__, requested_attributes, *multipart_parts_count); + + s->formatter->open_object_section("ObjectParts"); + + bool truncated = false; + int next_marker; + + using namespace rgw::sal; + + int ret = + s->object->list_parts( + this, s->cct, + max_parts ? *max_parts : 1000, + marker ? *marker : 0, + &next_marker, &truncated, + [&](const Object::Part& part) -> int { + s->formatter->open_object_section("Part"); + s->formatter->dump_int("PartNumber", part.part_number); + s->formatter->dump_unsigned("Size", part.part_size); + if (part.cksum.type != rgw::cksum::Type::none) { + s->formatter->dump_string(part.cksum.element_name(), part.cksum.to_armor()); + } + s->formatter->close_section(); /* Part */ + return 0; + }, s->yield); + + if (ret < 0) { + ldpp_dout_fmt(this, 0, + "ERROR: {} list-parts failed for {}", + __func__, s->object->get_name()); + } + /* AWS docs disagree on the name of this element */ + s->formatter->dump_int("PartsCount", *multipart_parts_count); + s->formatter->dump_int("TotalPartsCount", *multipart_parts_count); + s->formatter->dump_bool("IsTruncated", truncated); + if (max_parts) { + s->formatter->dump_int("MaxParts", *max_parts); + } + if(truncated) { + s->formatter->dump_int("NextPartNumberMarker", next_marker); + } + if (marker) { + s->formatter->dump_int("PartNumberMarker", *marker); + } + s->formatter->close_section(); + } /* multipart_parts_count positive */ + } /* ObjectParts */ + + if (requested_attributes & as_flag(ReqAttributes::ObjectSize)) { + s->formatter->dump_int("ObjectSize", s->obj_size); + } + + if (requested_attributes & as_flag(ReqAttributes::StorageClass)) { + auto iter = attrs.find(RGW_ATTR_STORAGE_CLASS); + if (iter != attrs.end()) { + s->formatter->dump_string("StorageClass", iter->second.to_str()); + } else { + s->formatter->dump_string("StorageClass", "STANDARD"); + } + } + s->formatter->close_section(); + } /* op_ret == 0 */ + + rgw_flush_formatter_and_reset(s, s->formatter); +} /* RGWGetObjAttrs_ObjStore_S3::send_response */ + void RGWGetLC_ObjStore_S3::execute(optional_yield y) { config.set_ctx(s->cct); @@ -4794,6 +4988,7 @@ RGWOp *RGWHandler_REST_Bucket_S3::get_obj_op(bool get_data) const RGWOp *RGWHandler_REST_Bucket_S3::op_get() { + /* XXX maybe we could replace this with an indexing operation */ if (s->info.args.sub_resource_exists("encryption")) return nullptr; @@ -4990,6 +5185,8 @@ RGWOp *RGWHandler_REST_Obj_S3::op_get() return new RGWGetObjLayout_ObjStore_S3; } else if (is_tagging_op()) { return new RGWGetObjTags_ObjStore_S3; + } else if (is_attributes_op()) { + return new RGWGetObjAttrs_ObjStore_S3; } else if (is_obj_retention_op()) { return new RGWGetObjRetention_ObjStore_S3; } else if (is_obj_legal_hold_op()) { @@ -6535,7 +6732,7 @@ rgw::auth::s3::LocalEngine::authenticate( /* Ignore signature for HTTP OPTIONS */ if (s->op_type == RGW_OP_OPTIONS_CORS) { auto apl = apl_factory->create_apl_local( - cct, s, user->get_info(), std::move(account), std::move(policies), + cct, s, std::move(user), std::move(account), std::move(policies), k.subuser, std::nullopt, access_key_id); return result_t::grant(std::move(apl), completer_factory(k.key)); } @@ -6556,7 +6753,7 @@ rgw::auth::s3::LocalEngine::authenticate( } auto apl = apl_factory->create_apl_local( - cct, s, user->get_info(), std::move(account), std::move(policies), + cct, s, std::move(user), std::move(account), std::move(policies), k.subuser, std::nullopt, access_key_id); return result_t::grant(std::move(apl), completer_factory(k.key)); } @@ -6765,7 +6962,7 @@ rgw::auth::s3::STSEngine::authenticate( string subuser; auto apl = local_apl_factory->create_apl_local( - cct, s, user->get_info(), std::move(account), std::move(policies), + cct, s, std::move(user), std::move(account), std::move(policies), subuser, token.perm_mask, std::string(_access_key_id)); return result_t::grant(std::move(apl), completer_factory(token.secret_access_key)); } diff --git a/src/rgw/rgw_rest_s3.h b/src/rgw/rgw_rest_s3.h index 50160d79a42..e8fdc69751c 100644 --- a/src/rgw/rgw_rest_s3.h +++ b/src/rgw/rgw_rest_s3.h @@ -374,6 +374,18 @@ public: int get_params(optional_yield y) override; }; +class RGWGetObjAttrs_ObjStore_S3 : public RGWGetObjAttrs_ObjStore { +public: + RGWGetObjAttrs_ObjStore_S3() {} + ~RGWGetObjAttrs_ObjStore_S3() override {} + + int get_params(optional_yield y) override; + int get_decrypt_filter(std::unique_ptr<RGWGetObj_Filter>* filter, + RGWGetObj_Filter* cb, + bufferlist* manifest_bl) override; + void send_response() override; +}; + class RGWGetLC_ObjStore_S3 : public RGWGetLC_ObjStore { protected: RGWLifecycleConfiguration_S3 config; @@ -701,6 +713,9 @@ protected: bool is_acl_op() const { return s->info.args.exists("acl"); } + bool is_attributes_op() const { + return s->info.args.exists("attributes"); + } bool is_cors_op() const { return s->info.args.exists("cors"); } @@ -759,6 +774,9 @@ protected: bool is_acl_op() const { return s->info.args.exists("acl"); } + bool is_attributes_op() const { + return s->info.args.exists("attributes"); + } bool is_tagging_op() const { return s->info.args.exists("tagging"); } diff --git a/src/rgw/rgw_s3_filter.h b/src/rgw/rgw_s3_filter.h index 9bbc4ef0088..0273da9a364 100644 --- a/src/rgw/rgw_s3_filter.h +++ b/src/rgw/rgw_s3_filter.h @@ -9,6 +9,7 @@ class XMLObj; struct rgw_s3_key_filter { + bool operator==(const rgw_s3_key_filter& rhs) const = default; std::string prefix_rule; std::string suffix_rule; std::string regex_rule; diff --git a/src/rgw/rgw_sal.h b/src/rgw/rgw_sal.h index e098c4decf7..97e25179fc9 100644 --- a/src/rgw/rgw_sal.h +++ b/src/rgw/rgw_sal.h @@ -15,6 +15,7 @@ #pragma once +#include <cstdint> #include <optional> #include <boost/intrusive_ptr.hpp> #include <boost/smart_ptr/intrusive_ref_counter.hpp> @@ -26,6 +27,7 @@ #include "rgw_notify_event_type.h" #include "rgw_req_context.h" #include "include/random.h" +#include "include/function2.hpp" // FIXME: following subclass dependencies #include "driver/rados/rgw_user.h" @@ -1004,20 +1006,27 @@ class Bucket { optional_yield y, const DoutPrefixProvider *dpp) = 0; /** Read the name of the pending bucket logging object name */ - virtual int get_logging_object_name(std::string& obj_name, - const std::string& prefix, - optional_yield y, + virtual int get_logging_object_name(std::string& obj_name, + const std::string& prefix, + optional_yield y, const DoutPrefixProvider *dpp, RGWObjVersionTracker* objv_tracker) = 0; /** Update the name of the pending bucket logging object name */ - virtual int set_logging_object_name(const std::string& obj_name, - const std::string& prefix, - optional_yield y, - const DoutPrefixProvider *dpp, + virtual int set_logging_object_name(const std::string& obj_name, + const std::string& prefix, + optional_yield y, + const DoutPrefixProvider *dpp, bool new_obj, RGWObjVersionTracker* objv_tracker) = 0; + /** Remove the object holding the name of the pending bucket logging object */ + virtual int remove_logging_object_name(const std::string& prefix, + optional_yield y, + const DoutPrefixProvider *dpp, + RGWObjVersionTracker* objv_tracker) = 0; /** Move the pending bucket logging object into the bucket */ virtual int commit_logging_object(const std::string& obj_name, optional_yield y, const DoutPrefixProvider *dpp) = 0; + //** Remove the pending bucket logging object */ + virtual int remove_logging_object(const std::string& obj_name, optional_yield y, const DoutPrefixProvider *dpp) = 0; /** Write a record to the pending bucket logging object */ virtual int write_logging_object(const std::string& obj_name, const std::string& record, optional_yield y, const DoutPrefixProvider *dpp, bool async_completion) = 0; @@ -1169,6 +1178,9 @@ class Object { std::string* version_id, std::string* tag, std::string* etag, void (*progress_cb)(off_t, void *), void* progress_data, const DoutPrefixProvider* dpp, optional_yield y) = 0; + + /** return logging subsystem */ + virtual unsigned get_subsys() { return ceph_subsys_rgw; }; /** Get the ACL for this object */ virtual RGWAccessControlPolicy& get_acl(void) = 0; /** Set the ACL for this object */ @@ -1249,6 +1261,28 @@ class Object { /** Dump driver-specific object layout info in JSON */ virtual int dump_obj_layout(const DoutPrefixProvider *dpp, optional_yield y, Formatter* f) = 0; + /* A transfer data type describing metadata specific to one part of a + * completed multipart upload object, following the GetObjectAttributes + * response syntax for Object::Parts here: + * https://docs.aws.amazon.com/AmazonS3/latest/API/API_GetObjectAttributes.html */ + class Part + { + public: + int part_number; + uint32_t part_size; + rgw::cksum::Cksum cksum; + }; /* Part */ + + /* callback function/object used by list_parts */ + using list_parts_each_t = + const fu2::unique_function<int(const Part&) const>; + + /** If multipart, enumerate (a range [marker..marker+[min(max_parts, parts_count-1)] of) parts of the object */ + virtual int list_parts(const DoutPrefixProvider* dpp, CephContext* cct, + int max_parts, int marker, int* next_marker, + bool* truncated, list_parts_each_t each_func, + optional_yield y) = 0; + /** Get the cached attributes for this object */ virtual Attrs& get_attrs(void) = 0; /** Get the (const) cached attributes for this object */ @@ -1447,7 +1481,7 @@ public: virtual int init(const DoutPrefixProvider* dpp, optional_yield y, ACLOwner& owner, rgw_placement_rule& dest_placement, rgw::sal::Attrs& attrs) = 0; /** List all the parts of this upload, filling the parts cache */ virtual int list_parts(const DoutPrefixProvider* dpp, CephContext* cct, - int num_parts, int marker, + int max_parts, int marker, int* next_marker, bool* truncated, optional_yield y, bool assume_unsorted = false) = 0; /** Abort this upload */ @@ -1751,8 +1785,6 @@ class Zone { virtual bool is_writeable() = 0; /** Get the URL for the endpoint for redirecting to this zone */ virtual bool get_redirect_endpoint(std::string* endpoint) = 0; - /** Check to see if the given API is supported in this zone */ - virtual bool has_zonegroup_api(const std::string& api) const = 0; /** Get the current period ID for this zone */ virtual const std::string& get_current_period_id() = 0; /** Get thes system access key for this zone */ diff --git a/src/rgw/rgw_sal_dbstore.cc b/src/rgw/rgw_sal_dbstore.cc index 0e4f95846d1..02fd7a49cda 100644 --- a/src/rgw/rgw_sal_dbstore.cc +++ b/src/rgw/rgw_sal_dbstore.cc @@ -458,14 +458,6 @@ namespace rgw::sal { return false; } - bool DBZone::has_zonegroup_api(const std::string& api) const - { - if (api == "default") - return true; - - return false; - } - const std::string& DBZone::get_current_period_id() { return current_period->get_id(); @@ -496,6 +488,14 @@ namespace rgw::sal { return std::make_unique<DBLuaManager>(this); } + int DBObject::list_parts(const DoutPrefixProvider* dpp, CephContext* cct, + int max_parts, int marker, int* next_marker, + bool* truncated, list_parts_each_t each_func, + optional_yield y) + { + return -EOPNOTSUPP; + } + int DBObject::load_obj_state(const DoutPrefixProvider* dpp, optional_yield y, bool follow_olh) { RGWObjState* astate; diff --git a/src/rgw/rgw_sal_dbstore.h b/src/rgw/rgw_sal_dbstore.h index b54249df031..4df10d1dce1 100644 --- a/src/rgw/rgw_sal_dbstore.h +++ b/src/rgw/rgw_sal_dbstore.h @@ -303,7 +303,6 @@ protected: virtual const std::string& get_name() const override; virtual bool is_writeable() override; virtual bool get_redirect_endpoint(std::string* endpoint) override; - virtual bool has_zonegroup_api(const std::string& api) const override; virtual const std::string& get_current_period_id() override; virtual const RGWAccessKey& get_system_key() override; virtual const std::string& get_realm_name() override; @@ -529,6 +528,7 @@ protected: DBObject(DBObject& _o) = default; + virtual unsigned get_subsys() { return ceph_subsys_rgw_dbstore; }; virtual int delete_object(const DoutPrefixProvider* dpp, optional_yield y, uint32_t flags, @@ -554,6 +554,13 @@ protected: virtual int set_acl(const RGWAccessControlPolicy& acl) override { acls = acl; return 0; } virtual int set_obj_attrs(const DoutPrefixProvider* dpp, Attrs* setattrs, Attrs* delattrs, optional_yield y, uint32_t flags) override; + + /** If multipart, enumerate (a range [marker..marker+[min(max_parts, parts_count-1)] of) parts of the object */ + virtual int list_parts(const DoutPrefixProvider* dpp, CephContext* cct, + int max_parts, int marker, int* next_marker, + bool* truncated, list_parts_each_t each_func, + optional_yield y) override; + virtual int load_obj_state(const DoutPrefixProvider* dpp, optional_yield y, bool follow_olh = true) override; virtual int get_obj_attrs(optional_yield y, const DoutPrefixProvider* dpp, rgw_obj* target_obj = NULL) override; virtual int modify_obj_attrs(const char* attr_name, bufferlist& attr_val, optional_yield y, const DoutPrefixProvider* dpp) override; diff --git a/src/rgw/rgw_sal_filter.cc b/src/rgw/rgw_sal_filter.cc index 733bfa39ee2..15da580988e 100644 --- a/src/rgw/rgw_sal_filter.cc +++ b/src/rgw/rgw_sal_filter.cc @@ -1046,6 +1046,17 @@ RGWAccessControlPolicy& FilterObject::get_acl() return next->get_acl(); } +int FilterObject::list_parts(const DoutPrefixProvider* dpp, CephContext* cct, + int max_parts, int marker, int* next_marker, + bool* truncated, list_parts_each_t each_func, + optional_yield y) +{ + return next->list_parts(dpp, cct, max_parts, marker, next_marker, + truncated, + sal::Object::list_parts_each_t(each_func), + y); +} + int FilterObject::load_obj_state(const DoutPrefixProvider *dpp, optional_yield y, bool follow_olh) { return next->load_obj_state(dpp, y, follow_olh); diff --git a/src/rgw/rgw_sal_filter.h b/src/rgw/rgw_sal_filter.h index 43a440e8b10..b6b6ed42b8f 100644 --- a/src/rgw/rgw_sal_filter.h +++ b/src/rgw/rgw_sal_filter.h @@ -108,9 +108,6 @@ public: virtual bool get_redirect_endpoint(std::string* endpoint) override { return next->get_redirect_endpoint(endpoint); } - virtual bool has_zonegroup_api(const std::string& api) const override { - return next->has_zonegroup_api(api); - } virtual const std::string& get_current_period_id() override { return next->get_current_period_id(); } @@ -669,24 +666,33 @@ public: optional_yield y, const DoutPrefixProvider *dpp) override { return next->remove_topics(objv_tracker, y, dpp); } - int get_logging_object_name(std::string& obj_name, - const std::string& prefix, - optional_yield y, + int get_logging_object_name(std::string& obj_name, + const std::string& prefix, + optional_yield y, const DoutPrefixProvider *dpp, RGWObjVersionTracker* objv_tracker) override { return next->get_logging_object_name(obj_name, prefix, y, dpp, objv_tracker); } - int set_logging_object_name(const std::string& obj_name, - const std::string& prefix, - optional_yield y, - const DoutPrefixProvider *dpp, + int set_logging_object_name(const std::string& obj_name, + const std::string& prefix, + optional_yield y, + const DoutPrefixProvider *dpp, bool new_obj, RGWObjVersionTracker* objv_track) override { - return next->set_logging_object_name(obj_name, prefix, y, dpp, new_obj, objv_track); + return next->set_logging_object_name(obj_name, prefix, y, dpp, new_obj, objv_track); + } + int remove_logging_object_name(const std::string& prefix, + optional_yield y, + const DoutPrefixProvider *dpp, + RGWObjVersionTracker* objv_tracker) override { + return next->remove_logging_object_name(prefix, y, dpp, objv_tracker); } int commit_logging_object(const std::string& obj_name, optional_yield y, const DoutPrefixProvider *dpp)override { return next->commit_logging_object(obj_name, y, dpp); } + int remove_logging_object(const std::string& obj_name, optional_yield y, const DoutPrefixProvider *dpp) override { + return next->remove_logging_object(obj_name, y, dpp); + } int write_logging_object(const std::string& obj_name, const std::string& record, optional_yield y, const DoutPrefixProvider *dpp, bool async_completion) override { return next->write_logging_object(obj_name, record, y, dpp, async_completion); } @@ -781,6 +787,12 @@ public: virtual bool empty() const override { return next->empty(); } virtual const std::string &get_name() const override { return next->get_name(); } + /** If multipart, enumerate (a range [marker..marker+[min(max_parts, parts_count-1)] of) parts of the object */ + virtual int list_parts(const DoutPrefixProvider* dpp, CephContext* cct, + int max_parts, int marker, int* next_marker, + bool* truncated, list_parts_each_t each_func, + optional_yield y) override; + virtual int load_obj_state(const DoutPrefixProvider *dpp, optional_yield y, bool follow_olh = true) override; virtual int set_obj_attrs(const DoutPrefixProvider* dpp, Attrs* setattrs, diff --git a/src/rgw/rgw_sal_store.h b/src/rgw/rgw_sal_store.h index 5cb98d23158..99b90564997 100644 --- a/src/rgw/rgw_sal_store.h +++ b/src/rgw/rgw_sal_store.h @@ -253,18 +253,23 @@ class StoreBucket : public Bucket { optional_yield y, const DoutPrefixProvider *dpp) override {return 0;} int remove_topics(RGWObjVersionTracker* objv_tracker, optional_yield y, const DoutPrefixProvider *dpp) override {return 0;} - int get_logging_object_name(std::string& obj_name, - const std::string& prefix, - optional_yield y, + int get_logging_object_name(std::string& obj_name, + const std::string& prefix, + optional_yield y, const DoutPrefixProvider *dpp, RGWObjVersionTracker* objv_tracker) override { return 0; } - int set_logging_object_name(const std::string& obj_name, - const std::string& prefix, - optional_yield y, - const DoutPrefixProvider *dpp, + int set_logging_object_name(const std::string& obj_name, + const std::string& prefix, + optional_yield y, + const DoutPrefixProvider *dpp, bool new_obj, RGWObjVersionTracker* objv_tracker) override { return 0; } + int remove_logging_object_name(const std::string& prefix, + optional_yield y, + const DoutPrefixProvider *dpp, + RGWObjVersionTracker* objv_tracker) override { return 0; } int commit_logging_object(const std::string& obj_name, optional_yield y, const DoutPrefixProvider *dpp) override { return 0; } + int remove_logging_object(const std::string& obj_name, optional_yield y, const DoutPrefixProvider *dpp) override { return 0; } int write_logging_object(const std::string& obj_name, const std::string& record, optional_yield y, const DoutPrefixProvider *dpp, bool async_completion) override { return 0; } diff --git a/src/rgw/rgw_swift_auth.cc b/src/rgw/rgw_swift_auth.cc index 032b3734bf9..937f74601b3 100644 --- a/src/rgw/rgw_swift_auth.cc +++ b/src/rgw/rgw_swift_auth.cc @@ -522,7 +522,7 @@ ExternalTokenEngine::authenticate(const DoutPrefixProvider* dpp, } auto apl = apl_factory->create_apl_local( - cct, s, user->get_info(), std::move(account), + cct, s, std::move(user), std::move(account), std::move(policies), extract_swift_subuser(swift_user), std::nullopt, LocalApplier::NO_ACCESS_KEY); return result_t::grant(std::move(apl)); @@ -685,7 +685,7 @@ SignedTokenEngine::authenticate(const DoutPrefixProvider* dpp, } auto apl = apl_factory->create_apl_local( - cct, s, user->get_info(), std::move(account), + cct, s, std::move(user), std::move(account), std::move(policies), extract_swift_subuser(swift_user), std::nullopt, LocalApplier::NO_ACCESS_KEY); return result_t::grant(std::move(apl)); diff --git a/src/rgw/rgw_swift_auth.h b/src/rgw/rgw_swift_auth.h index 9049c54f5ca..c27a24a2619 100644 --- a/src/rgw/rgw_swift_auth.h +++ b/src/rgw/rgw_swift_auth.h @@ -23,8 +23,8 @@ namespace swift { class TempURLApplier : public rgw::auth::LocalApplier { public: TempURLApplier(CephContext* const cct, - const RGWUserInfo& user_info) - : LocalApplier(cct, user_info, std::nullopt, {}, LocalApplier::NO_SUBUSER, + std::unique_ptr<rgw::sal::User> user) + : LocalApplier(cct, std::move(user), std::nullopt, {}, LocalApplier::NO_SUBUSER, std::nullopt, LocalApplier::NO_ACCESS_KEY) {} @@ -155,8 +155,8 @@ public: class SwiftAnonymousApplier : public rgw::auth::LocalApplier { public: SwiftAnonymousApplier(CephContext* const cct, - const RGWUserInfo& user_info) - : LocalApplier(cct, user_info, std::nullopt, {}, LocalApplier::NO_SUBUSER, + std::unique_ptr<rgw::sal::User> user) + : LocalApplier(cct, std::move(user), std::nullopt, {}, LocalApplier::NO_SUBUSER, std::nullopt, LocalApplier::NO_ACCESS_KEY) { } bool is_admin_of(const rgw_owner& o) const {return false;} @@ -238,7 +238,7 @@ class DefaultStrategy : public rgw::auth::Strategy, aplptr_t create_apl_local(CephContext* const cct, const req_state* const s, - const RGWUserInfo& user_info, + std::unique_ptr<rgw::sal::User> user, std::optional<RGWAccountInfo> account, std::vector<IAM::Policy> policies, const std::string& subuser, @@ -247,7 +247,7 @@ class DefaultStrategy : public rgw::auth::Strategy, auto apl = \ rgw::auth::add_3rdparty(driver, rgw_user(s->account_name), rgw::auth::add_sysreq(cct, driver, s, - LocalApplier(cct, user_info, std::move(account), std::move(policies), + LocalApplier(cct, std::move(user), std::move(account), std::move(policies), subuser, perm_mask, access_key_id))); /* TODO(rzarzynski): replace with static_ptr. */ return aplptr_t(new decltype(apl)(std::move(apl))); @@ -259,7 +259,9 @@ class DefaultStrategy : public rgw::auth::Strategy, /* TempURL doesn't need any user account override. It's a Swift-specific * mechanism that requires account name internally, so there is no * business with delegating the responsibility outside. */ - return aplptr_t(new rgw::auth::swift::TempURLApplier(cct, user_info)); + std::unique_ptr<rgw::sal::User> user = s->user->clone(); + user->get_info() = user_info; + return aplptr_t(new rgw::auth::swift::TempURLApplier(cct, std::move(user))); } public: diff --git a/src/rgw/services/svc_zone.cc b/src/rgw/services/svc_zone.cc index 61360135dd9..97d81550058 100644 --- a/src/rgw/services/svc_zone.cc +++ b/src/rgw/services/svc_zone.cc @@ -657,18 +657,6 @@ const string& RGWSI_Zone::get_current_period_id() const return current_period->get_id(); } -bool RGWSI_Zone::has_zonegroup_api(const std::string& api) const -{ - if (!current_period->get_id().empty()) { - const auto& zonegroups_by_api = current_period->get_map().zonegroups_by_api; - if (zonegroups_by_api.find(api) != zonegroups_by_api.end()) - return true; - } else if (zonegroup->api_name == api) { - return true; - } - return false; -} - bool RGWSI_Zone::zone_is_writeable() { return writeable_zone && !get_zone().is_read_only(); diff --git a/src/rgw/services/svc_zone.h b/src/rgw/services/svc_zone.h index 1b3f49587a3..719546eb8db 100644 --- a/src/rgw/services/svc_zone.h +++ b/src/rgw/services/svc_zone.h @@ -96,7 +96,6 @@ public: uint32_t get_zone_short_id() const; const std::string& get_current_period_id() const; - bool has_zonegroup_api(const std::string& api) const; bool zone_is_writeable(); bool zone_syncs_from(const RGWZone& target_zone, const RGWZone& source_zone) const; diff --git a/src/test/ObjectMap/KeyValueDBMemory.cc b/src/test/ObjectMap/KeyValueDBMemory.cc index 234e963397e..cfe25930d6a 100644 --- a/src/test/ObjectMap/KeyValueDBMemory.cc +++ b/src/test/ObjectMap/KeyValueDBMemory.cc @@ -132,12 +132,26 @@ public: return ""; } + string_view key_as_sv() override { + if (valid()) + return (*it).first.second; + else + return ""; + } + pair<string,string> raw_key() override { if (valid()) return (*it).first; else return make_pair("", ""); } + + pair<string_view,string_view> raw_key_as_sv() override { + if (valid()) + return (*it).first; + else + return make_pair("", ""); + } bool raw_key_is_prefixed(const string &prefix) override { return prefix == (*it).first.first; @@ -150,6 +164,13 @@ public: return bufferlist(); } + std::string_view value_as_sv() override { + if (valid()) + return std::string_view{it->second.c_str(), it->second.length()}; + else + return std::string_view(); + } + int status() override { return 0; } diff --git a/src/test/cli/radosgw-admin/help.t b/src/test/cli/radosgw-admin/help.t index 8b7c6d6e3db..c1675d11a80 100644 --- a/src/test/cli/radosgw-admin/help.t +++ b/src/test/cli/radosgw-admin/help.t @@ -43,7 +43,8 @@ bucket sync disable disable bucket sync bucket sync enable enable bucket sync bucket radoslist list rados objects backing bucket's objects - bucket logging flush flush pending log records object of source bucket to the log bucket to bucket + bucket logging flush flush pending log records object of source bucket to the log bucket + bucket logging info get info on bucket logging configuration on source bucket or list of sources in log bucket bi get retrieve bucket index object entries bi put store bucket index object entries bi list list raw bucket index entries diff --git a/src/test/librbd/migration/test_mock_HttpClient.cc b/src/test/librbd/migration/test_mock_HttpClient.cc index f3888755c79..901c4231dd0 100644 --- a/src/test/librbd/migration/test_mock_HttpClient.cc +++ b/src/test/librbd/migration/test_mock_HttpClient.cc @@ -307,7 +307,7 @@ TEST_F(TestMockMigrationHttpClient, OpenCloseHttps) { boost::asio::ssl::context ssl_context{boost::asio::ssl::context::tlsv12}; load_server_certificate(ssl_context); - boost::beast::ssl_stream<boost::beast::tcp_stream> ssl_stream{ + boost::asio::ssl::stream<boost::asio::ip::tcp::socket> ssl_stream{ std::move(socket), ssl_context}; C_SaferCond on_ssl_handshake_ctx; @@ -341,7 +341,7 @@ TEST_F(TestMockMigrationHttpClient, OpenHttpsHandshakeFail) { boost::asio::ssl::context ssl_context{boost::asio::ssl::context::tlsv12}; load_server_certificate(ssl_context); - boost::beast::ssl_stream<boost::beast::tcp_stream> ssl_stream{ + boost::asio::ssl::stream<boost::asio::ip::tcp::socket> ssl_stream{ std::move(socket), ssl_context}; C_SaferCond on_ssl_handshake_ctx; diff --git a/src/test/objectstore/ObjectStoreImitator.h b/src/test/objectstore/ObjectStoreImitator.h index d71d7f2fe58..875f9041b83 100644 --- a/src/test/objectstore/ObjectStoreImitator.h +++ b/src/test/objectstore/ObjectStoreImitator.h @@ -347,6 +347,16 @@ public: ) override { return {}; } + + int omap_iterate(CollectionHandle &c, ///< [in] collection + const ghobject_t &oid, ///< [in] object + /// [in] where the iterator should point to at the beginning + omap_iter_seek_t start_from, + std::function<omap_iter_ret_t(std::string_view, std::string_view)> f + ) override { + return 0; + } + void set_fsid(uuid_d u) override {} uuid_d get_fsid() override { return {}; } uint64_t estimate_objects_overhead(uint64_t num_objects) override { diff --git a/src/test/objectstore/allocsim/ops_replayer.cc b/src/test/objectstore/allocsim/ops_replayer.cc index fd947f5c454..c5908d9f576 100644 --- a/src/test/objectstore/allocsim/ops_replayer.cc +++ b/src/test/objectstore/allocsim/ops_replayer.cc @@ -1,4 +1,5 @@ #include <algorithm> +#include <functional> #include <boost/program_options/value_semantic.hpp> #include <cassert> #include <cctype> @@ -13,26 +14,46 @@ #include <fstream> #include <filesystem> #include <mutex> -#include "include/rados/buffer_fwd.h" -#include "include/rados/librados.hpp" #include <atomic> -#include <fmt/format.h> #include <map> #include <memory> #include <random> #include <string> #include <iostream> #include <vector> +#include <format> + +#include <fmt/format.h> #include <boost/program_options/variables_map.hpp> #include <boost/program_options/parsers.hpp> +#include "include/rados/buffer_fwd.h" +#include "include/rados/librados.hpp" + namespace po = boost::program_options; using namespace std; using namespace ceph; +namespace settings { + +// Returns a function which restricts a value to a specified range by throwing if it is not in range: +// (Note: std::clamp() does not throw.) +auto clamp_or_throw(auto min, auto max) +{ + return [=](auto& x) { + if(std::less<>{}(x, min) or std::greater<>{}(x, max)) { + throw std::out_of_range(fmt::format("value expected between {} and {}, but got {}", min, max, x)); + } + + return x; + }; +} + +} // namespace settings + // compare shared_ptr<string> struct StringPtrCompare { @@ -338,8 +359,8 @@ int main(int argc, char** argv) { // options uint64_t io_depth = 8; - uint64_t nparser_threads = 16; - uint64_t nworker_threads = 16; + int nparser_threads = 16; + int nworker_threads = 16; string file("input.txt"); string ceph_conf_path("./ceph.conf"); string pool("test_pool"); @@ -351,8 +372,8 @@ int main(int argc, char** argv) { ("input-files,i", po::value<vector<string>>()->multitoken(), "List of input files (output of op_scraper.py). Multiple files will be merged and sorted by time order") ("ceph-conf", po::value<string>(&ceph_conf_path)->default_value("ceph.conf"), "Path to ceph conf") ("io-depth", po::value<uint64_t>(&io_depth)->default_value(64), "I/O depth") - ("parser-threads", po::value<uint64_t>(&nparser_threads)->default_value(16), "Number of parser threads") - ("worker-threads", po::value<uint64_t>(&nworker_threads)->default_value(16), "Number of I/O worker threads") + ("parser-threads", po::value<int>(&nparser_threads)->default_value(16)->notifier(settings::clamp_or_throw(1, 256)), "Number of parser threads") + ("worker-threads", po::value<int>(&nworker_threads)->default_value(16)->notifier(settings::clamp_or_throw(1, 256)), "Number of I/O worker threads") ("pool", po::value<string>(&pool)->default_value("test_pool"), "Pool to use for I/O") ("skip-do-ops", po::bool_switch(&skip_do_ops)->default_value(false), "Skip doing operations") ; diff --git a/src/test/objectstore/test_bluefs.cc b/src/test/objectstore/test_bluefs.cc index d3b0d0ac3a4..32173d61afe 100644 --- a/src/test/objectstore/test_bluefs.cc +++ b/src/test/objectstore/test_bluefs.cc @@ -1426,6 +1426,87 @@ TEST(BlueFS, test_concurrent_dir_link_and_compact_log_56210) { } } +TEST(BlueFS, truncate_drops_allocations) { + constexpr uint64_t K = 1024; + constexpr uint64_t M = 1024 * K; + uuid_d fsid; + const char* DIR_NAME="dir"; + const char* FILE_NAME="file1"; + struct { + uint64_t preallocated_size; + uint64_t write_size; + uint64_t truncate_to; + uint64_t allocated_after_truncate; + uint64_t slow_size = 0; + uint64_t slow_alloc_size = 64*K; + uint64_t db_size = 128*M; + uint64_t db_alloc_size = 1*M; + } scenarios [] = { + // on DB(which is SLOW) : 1 => 1, 64K remains + { 1*M, 1, 1, 64*K }, + // on DB(which is SLOW), alloc 4K : 1 => 1, 4K remains + { 1*M, 1, 1, 4*K, 0, 4*K }, + // on DB(which is SLOW), truncation on AU boundary : 128K => 128K, 128K remains + { 1*M, 128*K, 128*K, 128*K }, + // on DB(which is SLOW), no prealloc, truncation to 0 : 1666K => 0, 0 remains + { 0, 1666*K, 0, 0 }, + // on DB, truncate to 123K, expect 1M occupied + { 1234*K, 123*K, 123*K, 1*M, 128*M, 64*K, 10*M, 1*M }, + // on DB, truncate to 0, expect 0 occupied + { 1234*K, 345*K, 0, 0, 128*M, 64*K, 10*M, 1*M }, + // on DB, truncate to AU boundary, expect exactly 1M occupied + { 1234*K, 1123*K, 1*M, 1*M, 128*M, 64*K, 10*M, 1*M }, + // on DB and SLOW, truncate only data on SLOW + { 0, 10*M+1, 10*M+1, 10*M+64*K, 128*M, 64*K, 10*M, 1*M }, + // on DB and SLOW, preallocate and truncate only data on SLOW + { 6*M, 12*M, 10*M+1, 10*M+64*K, 128*M, 64*K, 10*M, 1*M }, + // on DB and SLOW, preallocate and truncate all in SLOW and some on DB + // note! prealloc 6M is important, one allocation for 12M will fallback to SLOW + // in 6M + 6M we can be sure that 6M is on DB and 6M is on SLOW + { 6*M, 12*M, 3*M+1, 4*M, 128*M, 64*K, 11*M, 1*M }, + }; + for (auto& s : scenarios) { + ConfSaver conf(g_ceph_context->_conf); + conf.SetVal("bluefs_shared_alloc_size", stringify(s.slow_alloc_size).c_str()); + conf.SetVal("bluefs_alloc_size", stringify(s.db_alloc_size).c_str()); + + g_ceph_context->_conf.set_val("bluefs_shared_alloc_size", stringify(s.slow_alloc_size)); + g_ceph_context->_conf.set_val("bluefs_alloc_size", stringify(s.db_alloc_size)); + TempBdev bdev_db{s.db_size}; + TempBdev bdev_slow{s.slow_size}; + + BlueFS fs(g_ceph_context); + if (s.db_size != 0) { + ASSERT_EQ(0, fs.add_block_device(BlueFS::BDEV_DB, bdev_db.path, false, 0)); + } + if (s.slow_size != 0) { + ASSERT_EQ(0, fs.add_block_device(BlueFS::BDEV_SLOW, bdev_slow.path, false, 0)); + } + + ASSERT_EQ(0, fs.mkfs(fsid, {BlueFS::BDEV_DB, false, false})); + ASSERT_EQ(0, fs.mount()); + ASSERT_EQ(0, fs.maybe_verify_layout({BlueFS::BDEV_DB, false, false})); + BlueFS::FileWriter *h; + ASSERT_EQ(0, fs.mkdir("dir")); + ASSERT_EQ(0, fs.open_for_write(DIR_NAME, FILE_NAME, &h, false)); + uint64_t pre = fs.get_used(); + ASSERT_EQ(0, fs.preallocate(h->file, 0, s.preallocated_size)); + const std::string content(s.write_size, 'x'); + h->append(content.c_str(), content.length()); + fs.fsync(h); + ASSERT_EQ(0, fs.truncate(h, s.truncate_to)); + fs.fsync(h); + uint64_t post = fs.get_used(); + fs.close_writer(h); + EXPECT_EQ(pre, post - s.allocated_after_truncate); + + fs.umount(); + } +} + + + + TEST(BlueFS, test_log_runway) { uint64_t max_log_runway = 65536; ConfSaver conf(g_ceph_context->_conf); @@ -1608,6 +1689,91 @@ TEST(BlueFS, test_log_runway_advance_seq) { fs.compact_log(); } +TEST(BlueFS, test_69481_truncate_corrupts_log) { + uint64_t size = 1048576 * 128; + TempBdev bdev{size}; + BlueFS fs(g_ceph_context); + ASSERT_EQ(0, fs.add_block_device(BlueFS::BDEV_DB, bdev.path, false)); + uuid_d fsid; + ASSERT_EQ(0, fs.mkfs(fsid, { BlueFS::BDEV_DB, false, false })); + ASSERT_EQ(0, fs.mount()); + ASSERT_EQ(0, fs.maybe_verify_layout({ BlueFS::BDEV_DB, false, false })); + + BlueFS::FileWriter *f = nullptr; + BlueFS::FileWriter *a = nullptr; + ASSERT_EQ(0, fs.mkdir("dir")); + ASSERT_EQ(0, fs.open_for_write("dir", "test-file", &f, false)); + ASSERT_EQ(0, fs.open_for_write("dir", "just-allocate", &a, false)); + + // create 4 distinct extents in file f + // a is here only to prevent f from merging extents together + fs.preallocate(f->file, 0, 0x10000); + fs.preallocate(a->file, 0, 0x10000); + fs.preallocate(f->file, 0, 0x20000); + fs.preallocate(a->file, 0, 0x20000); + fs.preallocate(f->file, 0, 0x30000); + fs.preallocate(a->file, 0, 0x30000); + fs.preallocate(f->file, 0, 0x40000); + fs.preallocate(a->file, 0, 0x40000); + fs.close_writer(a); + + fs.truncate(f, 0); + fs.fsync(f); + + bufferlist bl; + bl.append(std::string(" ", 0x15678)); + f->append(bl); + fs.truncate(f, 0x15678); + fs.fsync(f); + fs.close_writer(f); + + fs.umount(); + // remount to verify + ASSERT_EQ(0, fs.mount()); + fs.umount(); +} + +TEST(BlueFS, test_69481_truncate_asserts) { + uint64_t size = 1048576 * 128; + TempBdev bdev{size}; + BlueFS fs(g_ceph_context); + ASSERT_EQ(0, fs.add_block_device(BlueFS::BDEV_DB, bdev.path, false)); + uuid_d fsid; + ASSERT_EQ(0, fs.mkfs(fsid, { BlueFS::BDEV_DB, false, false })); + ASSERT_EQ(0, fs.mount()); + ASSERT_EQ(0, fs.maybe_verify_layout({ BlueFS::BDEV_DB, false, false })); + + BlueFS::FileWriter *f = nullptr; + BlueFS::FileWriter *a = nullptr; + ASSERT_EQ(0, fs.mkdir("dir")); + ASSERT_EQ(0, fs.open_for_write("dir", "test-file", &f, false)); + ASSERT_EQ(0, fs.open_for_write("dir", "just-allocate", &a, false)); + + // create 4 distinct extents in file f + // a is here only to prevent f from merging extents together + fs.preallocate(f->file, 0, 0x10000); + fs.preallocate(a->file, 0, 0x10000); + fs.preallocate(f->file, 0, 0x20000); + fs.preallocate(a->file, 0, 0x20000); + fs.preallocate(f->file, 0, 0x30000); + fs.preallocate(a->file, 0, 0x30000); + fs.preallocate(f->file, 0, 0x40000); + fs.preallocate(a->file, 0, 0x40000); + fs.close_writer(a); + + fs.truncate(f, 0); + fs.fsync(f); + + bufferlist bl; + bl.append(std::string(" ", 0x35678)); + f->append(bl); + fs.truncate(f, 0x35678); + fs.fsync(f); + fs.close_writer(f); + + fs.umount(); +} + int main(int argc, char **argv) { auto args = argv_to_vec(argc, argv); map<string,string> defaults = { diff --git a/src/test/osd/CMakeLists.txt b/src/test/osd/CMakeLists.txt index f2d1471e22e..798558ebbe0 100644 --- a/src/test/osd/CMakeLists.txt +++ b/src/test/osd/CMakeLists.txt @@ -22,7 +22,7 @@ install(TARGETS add_executable(ceph_test_rados_io_sequence ${CMAKE_CURRENT_SOURCE_DIR}/ceph_test_rados_io_sequence.cc) target_link_libraries(ceph_test_rados_io_sequence - librados global object_io_exerciser) + librados global object_io_exerciser json_structures) install(TARGETS ceph_test_rados_io_sequence DESTINATION ${CMAKE_INSTALL_BINDIR}) diff --git a/src/test/osd/ceph_test_rados_io_sequence.cc b/src/test/osd/ceph_test_rados_io_sequence.cc index 4a768a016e2..96808ea37e5 100644 --- a/src/test/osd/ceph_test_rados_io_sequence.cc +++ b/src/test/osd/ceph_test_rados_io_sequence.cc @@ -1,83 +1,104 @@ #include "ceph_test_rados_io_sequence.h" +#include <boost/asio/io_context.hpp> #include <iostream> #include <vector> -#include <boost/asio/io_context.hpp> - -#include "include/random.h" - -#include "librados/librados_asio.h" -#include "common/ceph_argparse.h" -#include "include/interval_set.h" -#include "global/global_init.h" -#include "global/global_context.h" +#include "common/Formatter.h" #include "common/Thread.h" +#include "common/ceph_argparse.h" +#include "common/ceph_json.h" #include "common/debug.h" #include "common/dout.h" #include "common/split.h" #include "common/strtol.h" // for strict_iecstrtoll() +#include "common/ceph_json.h" +#include "common/Formatter.h" #include "common/io_exerciser/DataGenerator.h" +#include "common/io_exerciser/EcIoSequence.h" +#include "common/io_exerciser/IoOp.h" +#include "common/io_exerciser/IoSequence.h" #include "common/io_exerciser/Model.h" #include "common/io_exerciser/ObjectModel.h" #include "common/io_exerciser/RadosIo.h" -#include "common/io_exerciser/IoOp.h" -#include "common/io_exerciser/IoSequence.h" +#include "common/json/BalancerStructures.h" +#include "common/json/ConfigStructures.h" +#include "common/json/OSDStructures.h" +#include "fmt/format.h" +#include "global/global_context.h" +#include "global/global_init.h" +#include "include/interval_set.h" +#include "include/random.h" +#include "json_spirit/json_spirit.h" +#include "librados/librados_asio.h" #define dout_subsys ceph_subsys_rados #define dout_context g_ceph_context +using OpType = ceph::io_exerciser::OpType; + +using DoneOp = ceph::io_exerciser::DoneOp; +using BarrierOp = ceph::io_exerciser::BarrierOp; +using CreateOp = ceph::io_exerciser::CreateOp; +using RemoveOp = ceph::io_exerciser::RemoveOp; +using SingleReadOp = ceph::io_exerciser::SingleReadOp; +using DoubleReadOp = ceph::io_exerciser::DoubleReadOp; +using TripleReadOp = ceph::io_exerciser::TripleReadOp; +using SingleWriteOp = ceph::io_exerciser::SingleWriteOp; +using DoubleWriteOp = ceph::io_exerciser::DoubleWriteOp; +using TripleWriteOp = ceph::io_exerciser::TripleWriteOp; +using SingleFailedWriteOp = ceph::io_exerciser::SingleFailedWriteOp; +using DoubleFailedWriteOp = ceph::io_exerciser::DoubleFailedWriteOp; +using TripleFailedWriteOp = ceph::io_exerciser::TripleFailedWriteOp; + namespace { - struct Size {}; - void validate(boost::any& v, const std::vector<std::string>& values, - Size *target_type, int) { - po::validators::check_first_occurrence(v); - const std::string &s = po::validators::get_single_string(values); - - std::string parse_error; - uint64_t size = strict_iecstrtoll(s, &parse_error); - if (!parse_error.empty()) { - throw po::validation_error(po::validation_error::invalid_option_value); - } - v = boost::any(size); - } - - struct Pair {}; - void validate(boost::any& v, const std::vector<std::string>& values, - Pair *target_type, int) { - po::validators::check_first_occurrence(v); - const std::string &s = po::validators::get_single_string(values); - auto part = ceph::split(s).begin(); - std::string parse_error; - int first = strict_iecstrtoll(*part++, &parse_error); - int second = strict_iecstrtoll(*part, &parse_error); - if (!parse_error.empty()) { - throw po::validation_error(po::validation_error::invalid_option_value); - } - v = boost::any(std::pair<int,int>{first,second}); - } - - struct PluginString {}; - void validate(boost::any& v, const std::vector<std::string>& values, - PluginString *target_type, int) { - po::validators::check_first_occurrence(v); - const std::string &s = po::validators::get_single_string(values); - - const std::string_view* pluginIt = std::find( - ceph::io_sequence::tester::pluginChoices.begin(), - ceph::io_sequence::tester::pluginChoices.end(), - s - ); - if(ceph::io_sequence::tester::pluginChoices.end() == pluginIt) - { - throw po::validation_error(po::validation_error::invalid_option_value); - } +struct Size {}; +void validate(boost::any& v, const std::vector<std::string>& values, + Size* target_type, int) { + po::validators::check_first_occurrence(v); + const std::string& s = po::validators::get_single_string(values); - v = boost::any(*pluginIt); + std::string parse_error; + uint64_t size = strict_iecstrtoll(s, &parse_error); + if (!parse_error.empty()) { + throw po::validation_error(po::validation_error::invalid_option_value); } + v = boost::any(size); +} + +struct Pair {}; +void validate(boost::any& v, const std::vector<std::string>& values, + Pair* target_type, int) { + po::validators::check_first_occurrence(v); + const std::string& s = po::validators::get_single_string(values); + auto part = ceph::split(s).begin(); + std::string parse_error; + int first = strict_iecstrtoll(*part++, &parse_error); + int second = strict_iecstrtoll(*part, &parse_error); + if (!parse_error.empty()) { + throw po::validation_error(po::validation_error::invalid_option_value); + } + v = boost::any(std::pair<int, int>{first, second}); +} + +struct PluginString {}; +void validate(boost::any& v, const std::vector<std::string>& values, + PluginString* target_type, int) { + po::validators::check_first_occurrence(v); + const std::string& s = po::validators::get_single_string(values); + + const std::string_view* pluginIt = + std::find(ceph::io_sequence::tester::pluginChoices.begin(), + ceph::io_sequence::tester::pluginChoices.end(), s); + if (ceph::io_sequence::tester::pluginChoices.end() == pluginIt) { + throw po::validation_error(po::validation_error::invalid_option_value); + } + + v = boost::any(*pluginIt); +} - constexpr std::string_view usage[] = { +constexpr std::string_view usage[] = { "Basic usage:", "", "ceph_test_rados_io_sequence", @@ -119,103 +140,99 @@ namespace { "\t are specified with unit of blocksize. Supported commands:", "\t\t create <len>", "\t\t remove", - "\t\t read|write <off> <len>", - "\t\t read2|write2 <off> <len> <off> <len>", - "\t\t read3|write3 <off> <len> <off> <len> <off> <len>", - "\t\t done" - }; - - po::options_description get_options_description() - { - po::options_description desc("ceph_test_rados_io options"); - desc.add_options() - ("help,h", - "show help message") - ("listsequence,l", - "show list of sequences") - ("dryrun,d", - "test sequence, do not issue any I/O") - ("verbose", - "more verbose output during test") - ("sequence,s", po::value<int>(), - "test specified sequence") - ("seed", po::value<int>(), - "seed for whole test") - ("seqseed", po::value<int>(), - "seed for sequence") - ("blocksize,b", po::value<Size>(), - "block size (default 2048)") - ("chunksize,c", po::value<Size>(), - "chunk size (default 4096)") - ("pool,p", po::value<std::string>(), - "pool name") - ("object,o", po::value<std::string>()->default_value("test"), - "object name") - ("km", po::value<Pair>(), - "k,m EC pool profile (default 2,2)") - ("plugin", po::value<PluginString>(), - "EC plugin (isa or jerasure)") - ("objectsize", po::value<Pair>(), - "min,max object size in blocks (default 1,32)") - ("threads,t", po::value<int>(), - "number of threads of I/O per object (default 1)") - ("parallel,p", po::value<int>()->default_value(1), - "number of objects to exercise in parallel") - ("interactive", - "interactive mode, execute IO commands from stdin"); - - return desc; - } - - int parse_io_seq_options( - po::variables_map& vm, - int argc, - char** argv) - { - std::vector<std::string> unrecognized_options; - try { - po::options_description desc = get_options_description(); - - auto parsed = po::command_line_parser(argc, argv) - .options(desc) - .allow_unregistered() - .run(); - po::store(parsed, vm); - po::notify(vm); - unrecognized_options = po::collect_unrecognized(parsed.options, - po::include_positional); - - if (!unrecognized_options.empty()) - { - std::stringstream ss; - ss << "Unrecognised command options supplied: "; - while (unrecognized_options.size() > 1) - { - ss << unrecognized_options.back().c_str() << ", "; - unrecognized_options.pop_back(); - } - ss << unrecognized_options.back(); - dout(0) << ss.str() << dendl; - return 1; + "\t\t read|write|failedwrite <off> <len>", + "\t\t read2|write2|failedwrite2 <off> <len> <off> <len>", + "\t\t read3|write3|failedwrite3 <off> <len> <off> <len> <off> <len>", + "\t\t injecterror <type> <shard> <good_count> <fail_count>", + "\t\t clearinject <type> <shard>", + "\t\t done"}; + +po::options_description get_options_description() { + po::options_description desc("ceph_test_rados_io options"); + desc.add_options()("help,h", "show help message")("listsequence,l", + "show list of sequences")( + "dryrun,d", "test sequence, do not issue any I/O")( + "verbose", "more verbose output during test")( + "sequence,s", po::value<int>(), "test specified sequence")( + "seed", po::value<int>(), "seed for whole test")( + "seqseed", po::value<int>(), "seed for sequence")( + "blocksize,b", po::value<Size>(), "block size (default 2048)")( + "chunksize,c", po::value<Size>(), "chunk size (default 4096)")( + "pool,p", po::value<std::string>(), "pool name")( + "object,o", po::value<std::string>()->default_value("test"), + "object name")("km", po::value<Pair>(), + "k,m EC pool profile (default 2,2)")( + "plugin", po::value<PluginString>(), "EC plugin (isa or jerasure)")( + "objectsize", po::value<Pair>(), + "min,max object size in blocks (default 1,32)")( + "threads,t", po::value<int>(), + "number of threads of I/O per object (default 1)")( + "parallel,p", po::value<int>()->default_value(1), + "number of objects to exercise in parallel")( + "testrecovery", + "Inject errors during sequences to test recovery processes of OSDs")( + "interactive", "interactive mode, execute IO commands from stdin")( + "allow_pool_autoscaling", + "Allows pool autoscaling. Disabled by default.")( + "allow_pool_balancer", "Enables pool balancing. Disabled by default.")( + "allow_pool_deep_scrubbing", + "Enables pool deep scrub. Disabled by default.")( + "allow_pool_scrubbing", "Enables pool scrubbing. Disabled by default."); + + return desc; +} + +int parse_io_seq_options(po::variables_map& vm, int argc, char** argv) { + std::vector<std::string> unrecognized_options; + try { + po::options_description desc = get_options_description(); + + auto parsed = po::command_line_parser(argc, argv) + .options(desc) + .allow_unregistered() + .run(); + po::store(parsed, vm); + po::notify(vm); + unrecognized_options = + po::collect_unrecognized(parsed.options, po::include_positional); + + if (!unrecognized_options.empty()) { + std::stringstream ss; + ss << "Unrecognised command options supplied: "; + while (unrecognized_options.size() > 1) { + ss << unrecognized_options.back().c_str() << ", "; + unrecognized_options.pop_back(); } - } catch(const po::error& e) { - std::cerr << "error: " << e.what() << std::endl; + ss << unrecognized_options.back(); + dout(0) << ss.str() << dendl; return 1; } - - return 0; + } catch (const po::error& e) { + std::cerr << "error: " << e.what() << std::endl; + return 1; } + + return 0; } +template <typename S> +int send_mon_command(S& s, librados::Rados& rados, const char* name, + ceph::buffer::list& inbl, ceph::buffer::list* outbl, Formatter* f) { + std::ostringstream oss; + encode_json(name, s, f); + f->flush(oss); + int rc = rados.mon_command(oss.str(), inbl, outbl, nullptr); + return rc; +} + +} // namespace + template <typename T, int N, const std::array<T, N>& Ts> -ceph::io_sequence::tester::ProgramOptionSelector<T, N, Ts> - ::ProgramOptionSelector(ceph::util::random_number_generator<int>& rng, - po::variables_map vm, - const std::string& option_name, - bool set_forced, - bool select_first) - : rng(rng), - option_name(option_name) { +ceph::io_sequence::tester::ProgramOptionSelector<T, N, Ts>:: + ProgramOptionSelector(ceph::util::random_number_generator<int>& rng, + po::variables_map vm, const std::string& option_name, + bool set_forced, bool select_first) + : rng(rng), option_name(option_name) { if (set_forced && vm.count(option_name)) { force_value = vm[option_name].as<T>(); } @@ -226,76 +243,54 @@ ceph::io_sequence::tester::ProgramOptionSelector<T, N, Ts> } template <typename T, int N, const std::array<T, N>& Ts> -bool ceph::io_sequence::tester::ProgramOptionSelector<T, N, Ts>::isForced() -{ +bool ceph::io_sequence::tester::ProgramOptionSelector<T, N, Ts>::isForced() { return force_value.has_value(); } template <typename T, int N, const std::array<T, N>& Ts> -const T ceph::io_sequence::tester::ProgramOptionSelector<T, N, Ts>::choose() -{ +const T ceph::io_sequence::tester::ProgramOptionSelector<T, N, Ts>::choose() { if (force_value.has_value()) { return *force_value; } else if (first_value.has_value()) { return *std::exchange(first_value, std::nullopt); } else { - return choices[rng(N-1)]; + return choices[rng(N - 1)]; } } - - ceph::io_sequence::tester::SelectObjectSize::SelectObjectSize( - ceph::util::random_number_generator<int>& rng, - po::variables_map vm) - : ProgramOptionSelector(rng, vm, "objectsize", true, true) -{ -} - - + ceph::util::random_number_generator<int>& rng, po::variables_map vm) + : ProgramOptionSelector(rng, vm, "objectsize", true, true) {} ceph::io_sequence::tester::SelectBlockSize::SelectBlockSize( - ceph::util::random_number_generator<int>& rng, - po::variables_map vm) - : ProgramOptionSelector(rng, vm, "blocksize", true, true) -{ -} - - + ceph::util::random_number_generator<int>& rng, po::variables_map vm) + : ProgramOptionSelector(rng, vm, "blocksize", true, true) {} ceph::io_sequence::tester::SelectNumThreads::SelectNumThreads( - ceph::util::random_number_generator<int>& rng, - po::variables_map vm) - : ProgramOptionSelector(rng, vm, "threads", true, true) -{ -} - - + ceph::util::random_number_generator<int>& rng, po::variables_map vm) + : ProgramOptionSelector(rng, vm, "threads", true, true) {} ceph::io_sequence::tester::SelectSeqRange::SelectSeqRange( - ceph::util::random_number_generator<int>& rng, - po::variables_map vm) - : ProgramOptionSelector(rng, vm, "sequence", false, false) -{ + ceph::util::random_number_generator<int>& rng, po::variables_map vm) + : ProgramOptionSelector(rng, vm, "sequence", false, false) { if (vm.count(option_name)) { ceph::io_exerciser::Sequence s = - static_cast<ceph::io_exerciser::Sequence>(vm["sequence"].as<int>()); + static_cast<ceph::io_exerciser::Sequence>(vm["sequence"].as<int>()); if (s < ceph::io_exerciser::Sequence::SEQUENCE_BEGIN || s >= ceph::io_exerciser::Sequence::SEQUENCE_END) { dout(0) << "Sequence argument out of range" << dendl; throw po::validation_error(po::validation_error::invalid_option_value); } ceph::io_exerciser::Sequence e = s; - force_value = std::make_optional<std::pair<ceph::io_exerciser::Sequence, - ceph::io_exerciser::Sequence>>( - std::make_pair(s, ++e)); + force_value = std::make_optional< + std::pair<ceph::io_exerciser::Sequence, ceph::io_exerciser::Sequence>>( + std::make_pair(s, ++e)); } } -const std::pair<ceph::io_exerciser::Sequence,ceph::io_exerciser::Sequence> - ceph::io_sequence::tester::SelectSeqRange::choose() { - if (force_value.has_value()) - { +const std::pair<ceph::io_exerciser::Sequence, ceph::io_exerciser::Sequence> +ceph::io_sequence::tester::SelectSeqRange::choose() { + if (force_value.has_value()) { return *force_value; } else { return std::make_pair(ceph::io_exerciser::Sequence::SEQUENCE_BEGIN, @@ -303,45 +298,34 @@ const std::pair<ceph::io_exerciser::Sequence,ceph::io_exerciser::Sequence> } } - - ceph::io_sequence::tester::SelectErasureKM::SelectErasureKM( - ceph::util::random_number_generator<int>& rng, - po::variables_map vm) - : ProgramOptionSelector(rng, vm, "km", true, true) -{ -} - - + ceph::util::random_number_generator<int>& rng, po::variables_map vm) + : ProgramOptionSelector(rng, vm, "km", true, true) {} ceph::io_sequence::tester::SelectErasurePlugin::SelectErasurePlugin( - ceph::util::random_number_generator<int>& rng, - po::variables_map vm) - : ProgramOptionSelector(rng, vm, "plugin", true, false) -{ -} - - - -ceph::io_sequence::tester::SelectErasureChunkSize::SelectErasureChunkSize(ceph::util::random_number_generator<int>& rng, po::variables_map vm) - : ProgramOptionSelector(rng, vm, "stripe_unit", true, false) -{ -} - + ceph::util::random_number_generator<int>& rng, po::variables_map vm) + : ProgramOptionSelector(rng, vm, "plugin", true, false) {} +ceph::io_sequence::tester::SelectErasureChunkSize::SelectErasureChunkSize( + ceph::util::random_number_generator<int>& rng, po::variables_map vm) + : ProgramOptionSelector(rng, vm, "chunksize", true, true) {} ceph::io_sequence::tester::SelectECPool::SelectECPool( - ceph::util::random_number_generator<int>& rng, - po::variables_map vm, - librados::Rados& rados, - bool dry_run) - : ProgramOptionSelector(rng, vm, "pool", false, false), - rados(rados), - dry_run(dry_run), - skm(SelectErasureKM(rng, vm)), - spl(SelectErasurePlugin(rng, vm)), - scs(SelectErasureChunkSize(rng, vm)) -{ + ceph::util::random_number_generator<int>& rng, po::variables_map vm, + librados::Rados& rados, bool dry_run, bool allow_pool_autoscaling, + bool allow_pool_balancer, bool allow_pool_deep_scrubbing, + bool allow_pool_scrubbing, bool test_recovery) + : ProgramOptionSelector(rng, vm, "pool", false, false), + rados(rados), + dry_run(dry_run), + allow_pool_autoscaling(allow_pool_autoscaling), + allow_pool_balancer(allow_pool_balancer), + allow_pool_deep_scrubbing(allow_pool_deep_scrubbing), + allow_pool_scrubbing(allow_pool_scrubbing), + test_recovery(test_recovery), + skm(SelectErasureKM(rng, vm)), + spl(SelectErasurePlugin(rng, vm)), + scs(SelectErasureChunkSize(rng, vm)) { if (!skm.isForced()) { if (vm.count("pool")) { force_value = vm["pool"].as<std::string>(); @@ -349,147 +333,239 @@ ceph::io_sequence::tester::SelectECPool::SelectECPool( } } -const std::string ceph::io_sequence::tester::SelectECPool::choose() -{ - std::pair<int,int> value; +const std::string ceph::io_sequence::tester::SelectECPool::choose() { + std::pair<int, int> value; if (!skm.isForced() && force_value.has_value()) { + int rc; + bufferlist inbl, outbl; + auto formatter = std::make_unique<JSONFormatter>(false); + + ceph::messaging::osd::OSDPoolGetRequest osdPoolGetRequest{*force_value}; + rc = send_mon_command(osdPoolGetRequest, rados, "OSDPoolGetRequest", inbl, + &outbl, formatter.get()); + ceph_assert(rc == 0); + + JSONParser p; + bool success = p.parse(outbl.c_str(), outbl.length()); + ceph_assert(success); + + ceph::messaging::osd::OSDPoolGetReply osdPoolGetReply; + osdPoolGetReply.decode_json(&p); + + ceph::messaging::osd::OSDECProfileGetRequest osdECProfileGetRequest{ + osdPoolGetReply.erasure_code_profile}; + rc = send_mon_command(osdECProfileGetRequest, rados, + "OSDECProfileGetRequest", inbl, &outbl, + formatter.get()); + ceph_assert(rc == 0); + + success = p.parse(outbl.c_str(), outbl.length()); + ceph_assert(success); + + ceph::messaging::osd::OSDECProfileGetReply reply; + reply.decode_json(&p); + k = reply.k; + m = reply.m; return *force_value; } else { value = skm.choose(); } - int k = value.first; - int m = value.second; + k = value.first; + m = value.second; const std::string plugin = std::string(spl.choose()); const uint64_t chunk_size = scs.choose(); - std::string pool_name = "ec_" + plugin + - "_cs" + std::to_string(chunk_size) + - "_k" + std::to_string(k) + - "_m" + std::to_string(m); - if (!dry_run) - { + std::string pool_name = "ec_" + plugin + "_cs" + std::to_string(chunk_size) + + "_k" + std::to_string(k) + "_m" + std::to_string(m); + if (!dry_run) { create_pool(rados, pool_name, plugin, chunk_size, k, m); } return pool_name; } void ceph::io_sequence::tester::SelectECPool::create_pool( - librados::Rados& rados, - const std::string& pool_name, - const std::string& plugin, - uint64_t chunk_size, - int k, int m) -{ + librados::Rados& rados, const std::string& pool_name, + const std::string& plugin, uint64_t chunk_size, int k, int m) { int rc; bufferlist inbl, outbl; - std::string profile_create = - "{\"prefix\": \"osd erasure-code-profile set\", \ - \"name\": \"testprofile-" + pool_name + "\", \ - \"profile\": [ \"plugin=" + plugin + "\", \ - \"k=" + std::to_string(k) + "\", \ - \"m=" + std::to_string(m) + "\", \ - \"stripe_unit=" + std::to_string(chunk_size) + "\", \ - \"crush-failure-domain=osd\"]}"; - rc = rados.mon_command(profile_create, inbl, &outbl, nullptr); + auto formatter = std::make_unique<JSONFormatter>(false); + + ceph::messaging::osd::OSDECProfileSetRequest ecProfileSetRequest{ + fmt::format("testprofile-{}", pool_name), + {fmt::format("plugin={}", plugin), fmt::format("k={}", k), + fmt::format("m={}", m), fmt::format("stripe_unit={}", chunk_size), + fmt::format("crush-failure-domain=osd")}}; + rc = send_mon_command(ecProfileSetRequest, rados, "OSDECProfileSetRequest", + inbl, &outbl, formatter.get()); ceph_assert(rc == 0); - std::string cmdstr = - "{\"prefix\": \"osd pool create\", \ - \"pool\": \"" + pool_name + "\", \ - \"pool_type\": \"erasure\", \ - \"pg_num\": 8, \ - \"pgp_num\": 8, \ - \"erasure_code_profile\": \"testprofile-" + pool_name + "\"}"; - rc = rados.mon_command(cmdstr, inbl, &outbl, nullptr); + + ceph::messaging::osd::OSDECPoolCreateRequest poolCreateRequest{ + pool_name, "erasure", 8, 8, fmt::format("testprofile-{}", pool_name)}; + rc = send_mon_command(poolCreateRequest, rados, "OSDECPoolCreateRequest", + inbl, &outbl, formatter.get()); ceph_assert(rc == 0); -} + if (allow_pool_autoscaling) { + ceph::messaging::osd::OSDSetRequest setNoAutoscaleRequest{"noautoscale", + std::nullopt}; + rc = send_mon_command(setNoAutoscaleRequest, rados, "OSDSetRequest", inbl, + &outbl, formatter.get()); + ceph_assert(rc == 0); + } + + if (allow_pool_balancer) { + ceph::messaging::balancer::BalancerOffRequest balancerOffRequest{}; + rc = send_mon_command(balancerOffRequest, rados, "BalancerOffRequest", inbl, + &outbl, formatter.get()); + ceph_assert(rc == 0); + + ceph::messaging::balancer::BalancerStatusRequest balancerStatusRequest{}; + rc = send_mon_command(balancerStatusRequest, rados, "BalancerStatusRequest", + inbl, &outbl, formatter.get()); + ceph_assert(rc == 0); + + JSONParser p; + bool success = p.parse(outbl.c_str(), outbl.length()); + ceph_assert(success); + + ceph::messaging::balancer::BalancerStatusReply reply; + reply.decode_json(&p); + ceph_assert(!reply.active); + } + if (allow_pool_deep_scrubbing) { + ceph::messaging::osd::OSDSetRequest setNoDeepScrubRequest{"nodeep-scrub", + std::nullopt}; + rc = send_mon_command(setNoDeepScrubRequest, rados, "setNoDeepScrubRequest", + inbl, &outbl, formatter.get()); + ceph_assert(rc == 0); + } + + if (allow_pool_scrubbing) { + ceph::messaging::osd::OSDSetRequest setNoScrubRequest{"noscrub", + std::nullopt}; + rc = send_mon_command(setNoScrubRequest, rados, "OSDSetRequest", inbl, + &outbl, formatter.get()); + ceph_assert(rc == 0); + } + + if (test_recovery) { + ceph::messaging::config::ConfigSetRequest configSetBluestoreDebugRequest{ + "global", "bluestore_debug_inject_read_err", "true", std::nullopt}; + rc = send_mon_command(configSetBluestoreDebugRequest, rados, + "ConfigSetRequest", inbl, &outbl, + formatter.get()); + ceph_assert(rc == 0); + + ceph::messaging::config::ConfigSetRequest configSetMaxMarkdownRequest{ + "global", "osd_max_markdown_count", "99999999", std::nullopt}; + rc = + send_mon_command(configSetMaxMarkdownRequest, rados, "ConfigSetRequest", + inbl, &outbl, formatter.get()); + ceph_assert(rc == 0); + } +} -ceph::io_sequence::tester::TestObject::TestObject( const std::string oid, - librados::Rados& rados, - boost::asio::io_context& asio, - SelectBlockSize& sbs, - SelectECPool& spo, - SelectObjectSize& sos, - SelectNumThreads& snt, - SelectSeqRange& ssr, - ceph::util::random_number_generator<int>& rng, - ceph::mutex& lock, - ceph::condition_variable& cond, - bool dryrun, - bool verbose, - std::optional<int> seqseed) : - rng(rng), verbose(verbose), seqseed(seqseed) -{ +ceph::io_sequence::tester::TestObject::TestObject( + const std::string oid, librados::Rados& rados, + boost::asio::io_context& asio, SelectBlockSize& sbs, SelectECPool& spo, + SelectObjectSize& sos, SelectNumThreads& snt, SelectSeqRange& ssr, + ceph::util::random_number_generator<int>& rng, ceph::mutex& lock, + ceph::condition_variable& cond, bool dryrun, bool verbose, + std::optional<int> seqseed, bool testrecovery) + : rng(rng), verbose(verbose), seqseed(seqseed), testrecovery(testrecovery) { if (dryrun) { - verbose = true; - exerciser_model = std::make_unique<ceph::io_exerciser::ObjectModel>(oid, - sbs.choose(), - rng()); + exerciser_model = std::make_unique<ceph::io_exerciser::ObjectModel>( + oid, sbs.choose(), rng()); } else { const std::string pool = spo.choose(); + poolK = spo.getChosenK(); + poolM = spo.getChosenM(); + int threads = snt.choose(); - exerciser_model = std::make_unique<ceph::io_exerciser::RadosIo>(rados, - asio, - pool, - oid, - sbs.choose(), - rng(), - threads, - lock, - cond); - dout(0) << "= " << oid << " pool=" << pool - << " threads=" << threads - << " blocksize=" << exerciser_model->get_block_size() - << " =" << dendl; + + bufferlist inbl, outbl; + auto formatter = std::make_unique<JSONFormatter>(false); + + std::optional<std::vector<int>> cached_shard_order = std::nullopt; + + if (!spo.get_allow_pool_autoscaling() && !spo.get_allow_pool_balancer() && + !spo.get_allow_pool_deep_scrubbing() && + !spo.get_allow_pool_scrubbing()) { + ceph::messaging::osd::OSDMapRequest osdMapRequest{pool, oid, ""}; + int rc = send_mon_command(osdMapRequest, rados, "OSDMapRequest", inbl, + &outbl, formatter.get()); + ceph_assert(rc == 0); + + JSONParser p; + bool success = p.parse(outbl.c_str(), outbl.length()); + ceph_assert(success); + + ceph::messaging::osd::OSDMapReply reply{}; + reply.decode_json(&p); + cached_shard_order = reply.acting; + } + + exerciser_model = std::make_unique<ceph::io_exerciser::RadosIo>( + rados, asio, pool, oid, cached_shard_order, sbs.choose(), rng(), + threads, lock, cond); + dout(0) << "= " << oid << " pool=" << pool << " threads=" << threads + << " blocksize=" << exerciser_model->get_block_size() << " =" + << dendl; } obj_size_range = sos.choose(); seq_range = ssr.choose(); curseq = seq_range.first; - seq = ceph::io_exerciser::IoSequence::generate_sequence(curseq, - obj_size_range, - seqseed.value_or(rng())); + + if (testrecovery) { + seq = ceph::io_exerciser::EcIoSequence::generate_sequence( + curseq, obj_size_range, poolK, poolM, seqseed.value_or(rng())); + } else { + seq = ceph::io_exerciser::IoSequence::generate_sequence( + curseq, obj_size_range, seqseed.value_or(rng())); + } + op = seq->next(); done = false; - dout(0) << "== " << exerciser_model->get_oid() << " " - << curseq << " " - << seq->get_name() - << " ==" <<dendl; + dout(0) << "== " << exerciser_model->get_oid() << " " << curseq << " " + << seq->get_name_with_seqseed() << " ==" << dendl; } -bool ceph::io_sequence::tester::TestObject::readyForIo() -{ +bool ceph::io_sequence::tester::TestObject::readyForIo() { return exerciser_model->readyForIoOp(*op); } -bool ceph::io_sequence::tester::TestObject::next() -{ +bool ceph::io_sequence::tester::TestObject::next() { if (!done) { if (verbose) { - dout(0) << exerciser_model->get_oid() - << " Step " << seq->get_step() << ": " - << op->to_string(exerciser_model->get_block_size()) << dendl; + dout(0) << exerciser_model->get_oid() << " Step " << seq->get_step() + << ": " << op->to_string(exerciser_model->get_block_size()) + << dendl; } else { - dout(5) << exerciser_model->get_oid() - << " Step " << seq->get_step() << ": " - << op->to_string(exerciser_model->get_block_size()) << dendl; + dout(5) << exerciser_model->get_oid() << " Step " << seq->get_step() + << ": " << op->to_string(exerciser_model->get_block_size()) + << dendl; } exerciser_model->applyIoOp(*op); - if (op->done()) { - ++curseq; - if (curseq == seq_range.second) { + if (op->getOpType() == ceph::io_exerciser::OpType::Done) { + curseq = seq->getNextSupportedSequenceId(); + if (curseq >= seq_range.second) { done = true; dout(0) << exerciser_model->get_oid() << " Number of IOs = " << exerciser_model->get_num_io() << dendl; } else { - seq = ceph::io_exerciser::IoSequence::generate_sequence(curseq, - obj_size_range, - seqseed.value_or(rng())); - dout(0) << "== " << exerciser_model->get_oid() << " " - << curseq << " " << seq->get_name() - << " ==" <<dendl; + if (testrecovery) { + seq = ceph::io_exerciser::EcIoSequence::generate_sequence( + curseq, obj_size_range, poolK, poolM, seqseed.value_or(rng())); + } else { + seq = ceph::io_exerciser::IoSequence::generate_sequence( + curseq, obj_size_range, seqseed.value_or(rng())); + } + + dout(0) << "== " << exerciser_model->get_oid() << " " << curseq << " " + << seq->get_name_with_seqseed() << " ==" << dendl; op = seq->next(); } } else { @@ -499,27 +575,30 @@ bool ceph::io_sequence::tester::TestObject::next() return done; } -bool ceph::io_sequence::tester::TestObject::finished() -{ - return done; -} +bool ceph::io_sequence::tester::TestObject::finished() { return done; } -int ceph::io_sequence::tester::TestObject::get_num_io() -{ +int ceph::io_sequence::tester::TestObject::get_num_io() { return exerciser_model->get_num_io(); } ceph::io_sequence::tester::TestRunner::TestRunner(po::variables_map& vm, - librados::Rados& rados) : - rados(rados), - seed(vm.contains("seed") ? vm["seed"].as<int>() : time(nullptr)), - rng(ceph::util::random_number_generator<int>(seed)), - sbs{rng, vm}, - sos{rng, vm}, - spo{rng, vm, rados, vm.contains("dryrun")}, - snt{rng, vm}, - ssr{rng, vm} -{ + librados::Rados& rados) + : rados(rados), + seed(vm.contains("seed") ? vm["seed"].as<int>() : time(nullptr)), + rng(ceph::util::random_number_generator<int>(seed)), + sbs{rng, vm}, + sos{rng, vm}, + spo{rng, + vm, + rados, + vm.contains("dryrun"), + vm.contains("allow_pool_autoscaling"), + vm.contains("allow_pool_balancer"), + vm.contains("allow_pool_deep_scrubbing"), + vm.contains("allow_pool_scrubbing"), + vm.contains("test_recovery")}, + snt{rng, vm}, + ssr{rng, vm} { dout(0) << "Test using seed " << seed << dendl; verbose = vm.contains("verbose"); @@ -532,19 +611,23 @@ ceph::io_sequence::tester::TestRunner::TestRunner(po::variables_map& vm, num_objects = vm["parallel"].as<int>(); object_name = vm["object"].as<std::string>(); interactive = vm.contains("interactive"); + testrecovery = vm.contains("testrecovery"); + + allow_pool_autoscaling = vm.contains("allow_pool_autoscaling"); + allow_pool_balancer = vm.contains("allow_pool_balancer"); + allow_pool_deep_scrubbing = vm.contains("allow_pool_deep_scrubbing"); + allow_pool_scrubbing = vm.contains("allow_pool_scrubbing"); - if (!dryrun) - { + if (!dryrun) { guard.emplace(boost::asio::make_work_guard(asio)); - thread = make_named_thread("io_thread",[&asio = asio] { asio.run(); }); + thread = make_named_thread("io_thread", [&asio = asio] { asio.run(); }); } show_help = vm.contains("help"); show_sequence = vm.contains("listsequence"); } -ceph::io_sequence::tester::TestRunner::~TestRunner() -{ +ceph::io_sequence::tester::TestRunner::~TestRunner() { if (!dryrun) { guard = std::nullopt; asio.stop(); @@ -553,34 +636,38 @@ ceph::io_sequence::tester::TestRunner::~TestRunner() } } -void ceph::io_sequence::tester::TestRunner::help() -{ +void ceph::io_sequence::tester::TestRunner::help() { std::cout << get_options_description() << std::endl; for (auto line : usage) { std::cout << line << std::endl; } } -void ceph::io_sequence::tester::TestRunner::list_sequence() -{ +void ceph::io_sequence::tester::TestRunner::list_sequence(bool testrecovery) { // List seqeunces - std::pair<int,int> obj_size_range = sos.choose(); - for (ceph::io_exerciser::Sequence s - = ceph::io_exerciser::Sequence::SEQUENCE_BEGIN; - s < ceph::io_exerciser::Sequence::SEQUENCE_END; ++s) { - std::unique_ptr<ceph::io_exerciser::IoSequence> seq = - ceph::io_exerciser::IoSequence::generate_sequence(s, - obj_size_range, - seqseed.value_or(rng())); - dout(0) << s << " " << seq->get_name() << dendl; + std::pair<int, int> obj_size_range = sos.choose(); + ceph::io_exerciser::Sequence s = ceph::io_exerciser::Sequence::SEQUENCE_BEGIN; + std::unique_ptr<ceph::io_exerciser::IoSequence> seq; + if (testrecovery) { + seq = ceph::io_exerciser::EcIoSequence::generate_sequence( + s, obj_size_range, spo.getChosenK(), spo.getChosenM(), + seqseed.value_or(rng())); + } else { + seq = ceph::io_exerciser::IoSequence::generate_sequence( + s, obj_size_range, seqseed.value_or(rng())); } + + do { + dout(0) << s << " " << seq->get_name_with_seqseed() << dendl; + s = seq->getNextSupportedSequenceId(); + } while (s != ceph::io_exerciser::Sequence::SEQUENCE_END); } -std::string ceph::io_sequence::tester::TestRunner::get_token() -{ - static std::string line; - static ceph::split split = ceph::split(""); - static ceph::spliterator tokens; +void ceph::io_sequence::tester::TestRunner::clear_tokens() { + tokens = split.end(); +} + +std::string ceph::io_sequence::tester::TestRunner::get_token() { while (line.empty() || tokens == split.end()) { if (!std::getline(std::cin, line)) { throw std::runtime_error("End of input"); @@ -591,127 +678,211 @@ std::string ceph::io_sequence::tester::TestRunner::get_token() return std::string(*tokens++); } -uint64_t ceph::io_sequence::tester::TestRunner::get_numeric_token() -{ +std::optional<std::string> +ceph::io_sequence::tester::TestRunner ::get_optional_token() { + std::optional<std::string> ret = std::nullopt; + if (tokens != split.end()) { + ret = std::string(*tokens++); + } + return ret; +} + +uint64_t ceph::io_sequence::tester::TestRunner::get_numeric_token() { std::string parse_error; std::string token = get_token(); uint64_t num = strict_iecstrtoll(token, &parse_error); if (!parse_error.empty()) { - throw std::runtime_error("Invalid number "+token); + throw std::runtime_error("Invalid number " + token); } return num; } -bool ceph::io_sequence::tester::TestRunner::run_test() -{ - if (show_help) - { +std::optional<uint64_t> +ceph::io_sequence::tester::TestRunner ::get_optional_numeric_token() { + std::string parse_error; + std::optional<std::string> token = get_optional_token(); + if (token) { + uint64_t num = strict_iecstrtoll(*token, &parse_error); + if (!parse_error.empty()) { + throw std::runtime_error("Invalid number " + *token); + } + return num; + } + + return std::optional<uint64_t>(std::nullopt); +} + +bool ceph::io_sequence::tester::TestRunner::run_test() { + if (show_help) { help(); return true; - } - else if (show_sequence) - { - list_sequence(); + } else if (show_sequence) { + list_sequence(testrecovery); return true; - } - else if (interactive) - { + } else if (interactive) { return run_interactive_test(); - } - else - { + } else { return run_automated_test(); } } -bool ceph::io_sequence::tester::TestRunner::run_interactive_test() -{ +bool ceph::io_sequence::tester::TestRunner::run_interactive_test() { bool done = false; std::unique_ptr<ceph::io_exerciser::IoOp> ioop; std::unique_ptr<ceph::io_exerciser::Model> model; if (dryrun) { - model = std::make_unique<ceph::io_exerciser::ObjectModel>(object_name, - sbs.choose(), - rng()); + model = std::make_unique<ceph::io_exerciser::ObjectModel>( + object_name, sbs.choose(), rng()); } else { const std::string pool = spo.choose(); - model = std::make_unique<ceph::io_exerciser::RadosIo>(rados, asio, pool, - object_name, sbs.choose(), - rng(), 1, // 1 thread - lock, cond); + + bufferlist inbl, outbl; + auto formatter = std::make_unique<JSONFormatter>(false); + + ceph::messaging::osd::OSDMapRequest osdMapRequest{pool, object_name, ""}; + int rc = send_mon_command(osdMapRequest, rados, "OSDMapRequest", inbl, + &outbl, formatter.get()); + ceph_assert(rc == 0); + + JSONParser p; + bool success = p.parse(outbl.c_str(), outbl.length()); + ceph_assert(success); + + ceph::messaging::osd::OSDMapReply reply{}; + reply.decode_json(&p); + + model = std::make_unique<ceph::io_exerciser::RadosIo>( + rados, asio, pool, object_name, reply.acting, sbs.choose(), rng(), + 1, // 1 thread + lock, cond); } while (!done) { const std::string op = get_token(); - if (!op.compare("done") || !op.compare("q") || !op.compare("quit")) { - ioop = ceph::io_exerciser::IoOp::generate_done(); - } else if (!op.compare("create")) { - ioop = ceph::io_exerciser::IoOp::generate_create(get_numeric_token()); - } else if (!op.compare("remove") || !op.compare("delete")) { - ioop = ceph::io_exerciser::IoOp::generate_remove(); - } else if (!op.compare("read")) { + if (op == "done" || op == "q" || op == "quit") { + ioop = ceph::io_exerciser::DoneOp::generate(); + } else if (op == "create") { + ioop = ceph::io_exerciser::CreateOp::generate(get_numeric_token()); + } else if (op == "remove" || op == "delete") { + ioop = ceph::io_exerciser::RemoveOp::generate(); + } else if (op == "read") { uint64_t offset = get_numeric_token(); uint64_t length = get_numeric_token(); - ioop = ceph::io_exerciser::IoOp::generate_read(offset, length); - } else if (!op.compare("read2")) { + ioop = ceph::io_exerciser::SingleReadOp::generate(offset, length); + } else if (op == "read2") { uint64_t offset1 = get_numeric_token(); uint64_t length1 = get_numeric_token(); uint64_t offset2 = get_numeric_token(); uint64_t length2 = get_numeric_token(); - ioop = ceph::io_exerciser::IoOp::generate_read2(offset1, length1, - offset2, length2); - } else if (!op.compare("read3")) { + ioop = DoubleReadOp::generate(offset1, length1, offset2, length2); + } else if (op == "read3") { uint64_t offset1 = get_numeric_token(); uint64_t length1 = get_numeric_token(); uint64_t offset2 = get_numeric_token(); uint64_t length2 = get_numeric_token(); uint64_t offset3 = get_numeric_token(); uint64_t length3 = get_numeric_token(); - ioop = ceph::io_exerciser::IoOp::generate_read3(offset1, length1, - offset2, length2, - offset3, length3); - } else if (!op.compare("write")) { + ioop = TripleReadOp::generate(offset1, length1, offset2, length2, offset3, + length3); + } else if (op == "write") { uint64_t offset = get_numeric_token(); uint64_t length = get_numeric_token(); - ioop = ceph::io_exerciser::IoOp::generate_write(offset, length); - } else if (!op.compare("write2")) { + ioop = SingleWriteOp::generate(offset, length); + } else if (op == "write2") { uint64_t offset1 = get_numeric_token(); uint64_t length1 = get_numeric_token(); uint64_t offset2 = get_numeric_token(); uint64_t length2 = get_numeric_token(); - ioop = ceph::io_exerciser::IoOp::generate_write2(offset1, length1, - offset2, length2); - } else if (!op.compare("write3")) { + ioop = DoubleWriteOp::generate(offset1, length1, offset2, length2); + } else if (op == "write3") { uint64_t offset1 = get_numeric_token(); uint64_t length1 = get_numeric_token(); uint64_t offset2 = get_numeric_token(); uint64_t length2 = get_numeric_token(); uint64_t offset3 = get_numeric_token(); uint64_t length3 = get_numeric_token(); - ioop = ceph::io_exerciser::IoOp::generate_write3(offset1, length1, - offset2, length2, - offset3, length3); + ioop = TripleWriteOp::generate(offset1, length1, offset2, length2, + offset3, length3); + } else if (op == "failedwrite") { + uint64_t offset = get_numeric_token(); + uint64_t length = get_numeric_token(); + ioop = SingleFailedWriteOp::generate(offset, length); + } else if (op == "failedwrite2") { + uint64_t offset1 = get_numeric_token(); + uint64_t length1 = get_numeric_token(); + uint64_t offset2 = get_numeric_token(); + uint64_t length2 = get_numeric_token(); + ioop = DoubleFailedWriteOp::generate(offset1, length1, offset2, length2); + } else if (op == "failedwrite3") { + uint64_t offset1 = get_numeric_token(); + uint64_t length1 = get_numeric_token(); + uint64_t offset2 = get_numeric_token(); + uint64_t length2 = get_numeric_token(); + uint64_t offset3 = get_numeric_token(); + uint64_t length3 = get_numeric_token(); + ioop = TripleFailedWriteOp::generate(offset1, length1, offset2, length2, + offset3, length3); + } else if (op == "injecterror") { + std::string inject_type = get_token(); + int shard = get_numeric_token(); + std::optional<int> type = get_optional_numeric_token(); + std::optional<int> when = get_optional_numeric_token(); + std::optional<int> duration = get_optional_numeric_token(); + if (inject_type == "read") { + ioop = ceph::io_exerciser::InjectReadErrorOp::generate(shard, type, + when, duration); + } else if (inject_type == "write") { + ioop = ceph::io_exerciser::InjectWriteErrorOp::generate(shard, type, + when, duration); + } else { + clear_tokens(); + ioop.reset(); + dout(0) << fmt::format("Invalid error inject {}. No action performed.", + inject_type) + << dendl; + } + } else if (op == "clearinject") { + std::string inject_type = get_token(); + int shard = get_numeric_token(); + std::optional<int> type = get_optional_numeric_token(); + if (inject_type == "read") { + ioop = + ceph::io_exerciser::ClearReadErrorInjectOp::generate(shard, type); + } else if (inject_type == "write") { + ioop = + ceph::io_exerciser::ClearWriteErrorInjectOp::generate(shard, type); + } else { + clear_tokens(); + ioop.reset(); + dout(0) << fmt::format("Invalid error inject {}. No action performed.", + inject_type) + << dendl; + } } else { - throw std::runtime_error("Invalid operation "+op); + clear_tokens(); + ioop.reset(); + dout(0) << fmt::format("Invalid op {}. No action performed.", op) + << dendl; } - dout(0) << ioop->to_string(model->get_block_size()) << dendl; - model->applyIoOp(*ioop); - done = ioop->done(); - if (!done) { - ioop = ceph::io_exerciser::IoOp::generate_barrier(); + if (ioop) { + dout(0) << ioop->to_string(model->get_block_size()) << dendl; model->applyIoOp(*ioop); + done = ioop->getOpType() == ceph::io_exerciser::OpType::Done; + if (!done) { + ioop = ceph::io_exerciser::BarrierOp::generate(); + model->applyIoOp(*ioop); + } } } return true; } -bool ceph::io_sequence::tester::TestRunner::run_automated_test() -{ +bool ceph::io_sequence::tester::TestRunner::run_automated_test() { // Create a test for each object - std::vector<std::shared_ptr< - ceph::io_sequence::tester::TestObject>> test_objects; + std::vector<std::shared_ptr<ceph::io_sequence::tester::TestObject>> + test_objects; for (int obj = 0; obj < num_objects; obj++) { std::string name; @@ -721,15 +892,9 @@ bool ceph::io_sequence::tester::TestRunner::run_automated_test() name = object_name + std::to_string(obj); } test_objects.push_back( - std::make_shared<ceph::io_sequence::tester::TestObject>( - name, - rados, asio, - sbs, spo, sos, snt, ssr, - rng, lock, cond, - dryrun, verbose, - seqseed - ) - ); + std::make_shared<ceph::io_sequence::tester::TestObject>( + name, rados, asio, sbs, spo, sos, snt, ssr, rng, lock, cond, dryrun, + verbose, seqseed, testrecovery)); } if (!dryrun) { rados.wait_for_latest_osdmap(); @@ -748,16 +913,15 @@ bool ceph::io_sequence::tester::TestRunner::run_automated_test() for (auto obj = test_objects.begin(); obj != test_objects.end(); ++obj) { std::shared_ptr<ceph::io_sequence::tester::TestObject> to = *obj; if (!to->finished()) { - lock.lock(); - bool ready = to->readyForIo(); - lock.unlock(); - if (ready) - { - to->next(); - started_io = true; - } else { - need_wait = true; - } + lock.lock(); + bool ready = to->readyForIo(); + lock.unlock(); + if (ready) { + to->next(); + started_io = true; + } else { + need_wait = true; + } } } if (!started_io && need_wait) { @@ -767,8 +931,7 @@ bool ceph::io_sequence::tester::TestRunner::run_automated_test() std::shared_ptr<ceph::io_sequence::tester::TestObject> to = *obj; if (!to->finished()) { need_wait = !to->readyForIo(); - if (!need_wait) - { + if (!need_wait) { break; } } @@ -788,18 +951,16 @@ bool ceph::io_sequence::tester::TestRunner::run_automated_test() return true; } -int main(int argc, char **argv) -{ +int main(int argc, char** argv) { auto args = argv_to_vec(argc, argv); env_to_vec(args); auto cct = global_init(NULL, args, CEPH_ENTITY_TYPE_CLIENT, - CODE_ENVIRONMENT_UTILITY, 0); + CODE_ENVIRONMENT_UTILITY, 0); common_init_finish(cct.get()); po::variables_map vm; int rc = parse_io_seq_options(vm, argc, argv); - if (rc != 0) - { + if (rc != 0) { return rc; } @@ -814,7 +975,7 @@ int main(int argc, char **argv) std::unique_ptr<ceph::io_sequence::tester::TestRunner> runner; try { runner = std::make_unique<ceph::io_sequence::tester::TestRunner>(vm, rados); - } catch(const po::error& e) { + } catch (const po::error& e) { return 1; } runner->run_test(); diff --git a/src/test/osd/ceph_test_rados_io_sequence.h b/src/test/osd/ceph_test_rados_io_sequence.h index 4e21d025700..9af5f706b2f 100644 --- a/src/test/osd/ceph_test_rados_io_sequence.h +++ b/src/test/osd/ceph_test_rados_io_sequence.h @@ -1,34 +1,36 @@ +#include <boost/program_options.hpp> +#include <optional> #include <utility> -#include "include/random.h" - -#include "global/global_init.h" -#include "global/global_context.h" - #include "common/io_exerciser/IoOp.h" #include "common/io_exerciser/IoSequence.h" #include "common/io_exerciser/Model.h" - +#include "common/split.h" +#include "global/global_context.h" +#include "global/global_init.h" +#include "include/random.h" #include "librados/librados_asio.h" #include <boost/asio/io_context.hpp> #include <boost/program_options.hpp> +#include <optional> + /* Overview * * class ProgramOptionSelector - * Base class for selector objects below with common code for + * Base class for selector objects below with common code for * selecting options - * + * * class SelectObjectSize * Selects min and max object sizes for a test * * class SelectErasureKM * Selects an EC k and m value for a test - * + * * class SelectErasurePlugin * Selects an plugin for a test - * + * * class SelectECPool * Selects an EC pool (plugin,k and m) for a test. Also creates the * pool as well. @@ -58,287 +60,279 @@ namespace po = boost::program_options; -namespace ceph -{ - namespace io_sequence::tester - { - // Choices for min and max object size - inline constexpr size_t objectSizeSize = 10; - inline constexpr std::array<std::pair<int,int>,objectSizeSize> - objectSizeChoices = {{ - {1,32}, // Default - best for boundary checking - {12,14}, - {28,30}, - {36,38}, - {42,44}, - {52,54}, - {66,68}, - {72,74}, - {83,83}, - {97,97} - }}; - - // Choices for block size - inline constexpr int blockSizeSize = 5; - inline constexpr std::array<uint64_t, blockSizeSize> blockSizeChoices = {{ - 2048, // Default - test boundaries for EC 4K chunk size - 512, - 3767, - 4096, - 32768 - }}; - - // Choices for number of threads - inline constexpr int threadArraySize = 4; - inline constexpr std::array<int, threadArraySize> threadCountChoices = {{ - 1, // Default - 2, - 4, - 8 - }}; - - // Choices for EC k+m profile - inline constexpr int kmSize = 6; - inline constexpr std::array<std::pair<int,int>, kmSize> kmChoices = {{ - {2,2}, // Default - reasonable coverage - {2,1}, - {2,3}, - {3,2}, - {4,2}, - {5,1} - }}; - - // Choices for EC chunk size - inline constexpr int chunkSizeSize = 3; - inline constexpr std::array<uint64_t, chunkSizeSize> chunkSizeChoices = {{ - 4*1024, - 64*1024, - 256*1024 - }}; - - // Choices for plugin - inline constexpr int pluginListSize = 2; - inline constexpr std::array<std::string_view, - pluginListSize> pluginChoices = {{ - "jerasure", - "isa" - }}; - - inline constexpr std::array<std::pair<ceph::io_exerciser::Sequence, - ceph::io_exerciser::Sequence>, - 0> sequencePairs = {{}}; - - inline constexpr std::array<std::string, 0> poolChoices = {{}}; - - template <typename T, int N, const std::array<T, N>& Ts> - class ProgramOptionSelector - { - public: - ProgramOptionSelector(ceph::util::random_number_generator<int>& rng, - po::variables_map vm, - const std::string& option_name, - bool set_forced, - bool select_first - ); - virtual ~ProgramOptionSelector() = default; - bool isForced(); - virtual const T choose(); - - protected: - ceph::util::random_number_generator<int>& rng; - static constexpr std::array<T, N> choices = Ts; - - std::optional<T> force_value; - std::optional<T> first_value; - - std::string option_name; - }; - - class SelectObjectSize - : public ProgramOptionSelector<std::pair<int, int>, - io_sequence::tester::objectSizeSize, - io_sequence::tester::objectSizeChoices> - { - public: - SelectObjectSize(ceph::util::random_number_generator<int>& rng, - po::variables_map vm); - }; - - class SelectBlockSize - : public ProgramOptionSelector<uint64_t, - io_sequence::tester::blockSizeSize, - io_sequence::tester::blockSizeChoices> - { - public: - SelectBlockSize(ceph::util::random_number_generator<int>& rng, - po::variables_map vm); - }; - - class SelectNumThreads - : public ProgramOptionSelector<int, - io_sequence::tester::threadArraySize, - io_sequence::tester::threadCountChoices> - { - public: - SelectNumThreads(ceph::util::random_number_generator<int>& rng, - po::variables_map vm); - }; - - class SelectSeqRange - : public ProgramOptionSelector<std::pair<ceph::io_exerciser::Sequence, - ceph::io_exerciser::Sequence>, - 0, io_sequence::tester::sequencePairs> - { - public: - SelectSeqRange(ceph::util::random_number_generator<int>& rng, - po::variables_map vm); - - const std::pair<ceph::io_exerciser::Sequence, - ceph::io_exerciser::Sequence> choose() override; - }; - - class SelectErasureKM - : public ProgramOptionSelector<std::pair<int,int>, - io_sequence::tester::kmSize, - io_sequence::tester::kmChoices> - { - public: - SelectErasureKM(ceph::util::random_number_generator<int>& rng, +namespace ceph { +namespace io_sequence::tester { +// Choices for min and max object size +inline constexpr size_t objectSizeSize = 10; +inline constexpr std::array<std::pair<int, int>, objectSizeSize> + objectSizeChoices = {{{1, 32}, // Default - best for boundary checking + {12, 14}, + {28, 30}, + {36, 38}, + {42, 44}, + {52, 54}, + {66, 68}, + {72, 74}, + {83, 83}, + {97, 97}}}; + +// Choices for block size +inline constexpr int blockSizeSize = 5; +inline constexpr std::array<uint64_t, blockSizeSize> blockSizeChoices = { + {2048, // Default - test boundaries for EC 4K chunk size + 512, 3767, 4096, 32768}}; + +// Choices for number of threads +inline constexpr int threadArraySize = 4; +inline constexpr std::array<int, threadArraySize> threadCountChoices = { + {1, // Default + 2, 4, 8}}; + +// Choices for EC k+m profile +inline constexpr int kmSize = 6; +inline constexpr std::array<std::pair<int, int>, kmSize> kmChoices = { + {{2, 2}, // Default - reasonable coverage + {2, 1}, + {2, 3}, + {3, 2}, + {4, 2}, + {5, 1}}}; + +// Choices for EC chunk size +inline constexpr int chunkSizeSize = 3; +inline constexpr std::array<uint64_t, chunkSizeSize> chunkSizeChoices = { + {4 * 1024, 64 * 1024, 256 * 1024}}; + +// Choices for plugin +inline constexpr int pluginListSize = 2; +inline constexpr std::array<std::string_view, pluginListSize> pluginChoices = { + {"jerasure", "isa"}}; + +inline constexpr std::array< + std::pair<ceph::io_exerciser::Sequence, ceph::io_exerciser::Sequence>, 0> + sequencePairs = {{}}; + +inline constexpr std::array<std::string, 0> poolChoices = {{}}; + +template <typename T, int N, const std::array<T, N>& Ts> +class ProgramOptionSelector { + public: + ProgramOptionSelector(ceph::util::random_number_generator<int>& rng, + po::variables_map vm, const std::string& option_name, + bool set_forced, bool select_first); + virtual ~ProgramOptionSelector() = default; + bool isForced(); + virtual const T choose(); + + protected: + ceph::util::random_number_generator<int>& rng; + static constexpr std::array<T, N> choices = Ts; + + std::optional<T> force_value; + std::optional<T> first_value; + + std::string option_name; +}; + +class SelectObjectSize + : public ProgramOptionSelector<std::pair<int, int>, + io_sequence::tester::objectSizeSize, + io_sequence::tester::objectSizeChoices> { + public: + SelectObjectSize(ceph::util::random_number_generator<int>& rng, + po::variables_map vm); +}; + +class SelectBlockSize + : public ProgramOptionSelector<uint64_t, io_sequence::tester::blockSizeSize, + io_sequence::tester::blockSizeChoices> { + public: + SelectBlockSize(ceph::util::random_number_generator<int>& rng, + po::variables_map vm); +}; + +class SelectNumThreads + : public ProgramOptionSelector<int, io_sequence::tester::threadArraySize, + io_sequence::tester::threadCountChoices> { + public: + SelectNumThreads(ceph::util::random_number_generator<int>& rng, + po::variables_map vm); +}; + +class SelectSeqRange + : public ProgramOptionSelector< + std::pair<ceph::io_exerciser::Sequence, ceph::io_exerciser::Sequence>, + 0, io_sequence::tester::sequencePairs> { + public: + SelectSeqRange(ceph::util::random_number_generator<int>& rng, + po::variables_map vm); + + const std::pair<ceph::io_exerciser::Sequence, ceph::io_exerciser::Sequence> + choose() override; +}; + +class SelectErasureKM + : public ProgramOptionSelector<std::pair<int, int>, + io_sequence::tester::kmSize, + io_sequence::tester::kmChoices> { + public: + SelectErasureKM(ceph::util::random_number_generator<int>& rng, + po::variables_map vm); +}; + +class SelectErasurePlugin + : public ProgramOptionSelector<std::string_view, + io_sequence::tester::pluginListSize, + io_sequence::tester::pluginChoices> { + public: + SelectErasurePlugin(ceph::util::random_number_generator<int>& rng, po::variables_map vm); - }; - - class SelectErasurePlugin - : public ProgramOptionSelector<std::string_view, - io_sequence::tester::pluginListSize, - io_sequence::tester::pluginChoices> - { - public: - SelectErasurePlugin(ceph::util::random_number_generator<int>& rng, - po::variables_map vm); - }; - - class SelectErasureChunkSize - : public ProgramOptionSelector<uint64_t, - io_sequence::tester::chunkSizeSize, - io_sequence::tester::chunkSizeChoices> - { - public: - SelectErasureChunkSize(ceph::util::random_number_generator<int>& rng, po::variables_map vm); - }; - - class SelectECPool - : public ProgramOptionSelector<std::string, - 0, - io_sequence::tester::poolChoices> - { - public: - SelectECPool(ceph::util::random_number_generator<int>& rng, - po::variables_map vm, - librados::Rados& rados, - bool dry_run); - const std::string choose() override; - - private: - void create_pool(librados::Rados& rados, - const std::string& pool_name, - const std::string& plugin, - uint64_t chunk_size, - int k, int m); - - protected: - librados::Rados& rados; - bool dry_run; - - SelectErasureKM skm; - SelectErasurePlugin spl; - SelectErasureChunkSize scs; - }; - - class TestObject - { - public: - TestObject( const std::string oid, - librados::Rados& rados, - boost::asio::io_context& asio, - ceph::io_sequence::tester::SelectBlockSize& sbs, - ceph::io_sequence::tester::SelectECPool& spl, - ceph::io_sequence::tester::SelectObjectSize& sos, - ceph::io_sequence::tester::SelectNumThreads& snt, - ceph::io_sequence::tester::SelectSeqRange& ssr, - ceph::util::random_number_generator<int>& rng, - ceph::mutex& lock, - ceph::condition_variable& cond, - bool dryrun, - bool verbose, - std::optional<int> seqseed); - - int get_num_io(); - bool readyForIo(); - bool next(); - bool finished(); - - protected: - std::unique_ptr<ceph::io_exerciser::Model> exerciser_model; - std::pair<int,int> obj_size_range; - std::pair<ceph::io_exerciser::Sequence, - ceph::io_exerciser::Sequence> seq_range; - ceph::io_exerciser::Sequence curseq; - std::unique_ptr<ceph::io_exerciser::IoSequence> seq; - std::unique_ptr<ceph::io_exerciser::IoOp> op; - bool done; - ceph::util::random_number_generator<int>& rng; - bool verbose; - std::optional<int> seqseed; - }; - - class TestRunner - { - public: - TestRunner(po::variables_map& vm, librados::Rados& rados); - ~TestRunner(); - - bool run_test(); - - private: - librados::Rados& rados; - int seed; - ceph::util::random_number_generator<int> rng; - - ceph::io_sequence::tester::SelectBlockSize sbs; - ceph::io_sequence::tester::SelectObjectSize sos; - ceph::io_sequence::tester::SelectECPool spo; - ceph::io_sequence::tester::SelectNumThreads snt; - ceph::io_sequence::tester::SelectSeqRange ssr; - - boost::asio::io_context asio; - std::thread thread; - std::optional<boost::asio::executor_work_guard< - boost::asio::io_context::executor_type>> guard; - ceph::mutex lock = ceph::make_mutex("RadosIo::lock"); - ceph::condition_variable cond; - - bool input_valid; - - bool verbose; - bool dryrun; - std::optional<int> seqseed; - bool interactive; - - bool show_sequence; - bool show_help; - - int num_objects; - std::string object_name; - - std::string get_token(); - uint64_t get_numeric_token(); - - bool run_automated_test(); - - bool run_interactive_test(); - - void help(); - void list_sequence(); - }; - } -} +}; + +class SelectErasureChunkSize + : public ProgramOptionSelector<uint64_t, io_sequence::tester::chunkSizeSize, + io_sequence::tester::chunkSizeChoices> { + public: + SelectErasureChunkSize(ceph::util::random_number_generator<int>& rng, + po::variables_map vm); +}; + +class SelectECPool + : public ProgramOptionSelector<std::string, 0, + io_sequence::tester::poolChoices> { + public: + SelectECPool(ceph::util::random_number_generator<int>& rng, + po::variables_map vm, librados::Rados& rados, bool dry_run, + bool allow_pool_autoscaling, bool allow_pool_balancer, + bool allow_pool_deep_scrubbing, bool allow_pool_scrubbing, + bool test_recovery); + const std::string choose() override; + + bool get_allow_pool_autoscaling() { return allow_pool_autoscaling; } + bool get_allow_pool_balancer() { return allow_pool_balancer; } + bool get_allow_pool_deep_scrubbing() { return allow_pool_deep_scrubbing; } + bool get_allow_pool_scrubbing() { return allow_pool_scrubbing; } + int getChosenK() const { return k; } + int getChosenM() const { return m; } + + private: + void create_pool(librados::Rados& rados, const std::string& pool_name, + const std::string& plugin, uint64_t chunk_size, int k, + int m); + + protected: + librados::Rados& rados; + bool dry_run; + bool allow_pool_autoscaling; + bool allow_pool_balancer; + bool allow_pool_deep_scrubbing; + bool allow_pool_scrubbing; + bool test_recovery; + int k; + int m; + + SelectErasureKM skm; + SelectErasurePlugin spl; + SelectErasureChunkSize scs; +}; + +class TestObject { + public: + TestObject(const std::string oid, librados::Rados& rados, + boost::asio::io_context& asio, + ceph::io_sequence::tester::SelectBlockSize& sbs, + ceph::io_sequence::tester::SelectECPool& spl, + ceph::io_sequence::tester::SelectObjectSize& sos, + ceph::io_sequence::tester::SelectNumThreads& snt, + ceph::io_sequence::tester::SelectSeqRange& ssr, + ceph::util::random_number_generator<int>& rng, ceph::mutex& lock, + ceph::condition_variable& cond, bool dryrun, bool verbose, + std::optional<int> seqseed, bool testRecovery); + + int get_num_io(); + bool readyForIo(); + bool next(); + bool finished(); + + protected: + std::unique_ptr<ceph::io_exerciser::Model> exerciser_model; + std::pair<int, int> obj_size_range; + std::pair<ceph::io_exerciser::Sequence, ceph::io_exerciser::Sequence> + seq_range; + ceph::io_exerciser::Sequence curseq; + std::unique_ptr<ceph::io_exerciser::IoSequence> seq; + std::unique_ptr<ceph::io_exerciser::IoOp> op; + bool done; + ceph::util::random_number_generator<int>& rng; + bool verbose; + std::optional<int> seqseed; + int poolK; + int poolM; + bool testrecovery; +}; + +class TestRunner { + public: + TestRunner(po::variables_map& vm, librados::Rados& rados); + ~TestRunner(); + + bool run_test(); + + private: + librados::Rados& rados; + int seed; + ceph::util::random_number_generator<int> rng; + + ceph::io_sequence::tester::SelectBlockSize sbs; + ceph::io_sequence::tester::SelectObjectSize sos; + ceph::io_sequence::tester::SelectECPool spo; + ceph::io_sequence::tester::SelectNumThreads snt; + ceph::io_sequence::tester::SelectSeqRange ssr; + + boost::asio::io_context asio; + std::thread thread; + std::optional< + boost::asio::executor_work_guard<boost::asio::io_context::executor_type>> + guard; + ceph::mutex lock = ceph::make_mutex("RadosIo::lock"); + ceph::condition_variable cond; + + bool input_valid; + + bool verbose; + bool dryrun; + std::optional<int> seqseed; + bool interactive; + + bool testrecovery; + + bool allow_pool_autoscaling; + bool allow_pool_balancer; + bool allow_pool_deep_scrubbing; + bool allow_pool_scrubbing; + + bool show_sequence; + bool show_help; + + int num_objects; + std::string object_name; + + std::string line; + ceph::split split = ceph::split(""); + ceph::spliterator tokens; + + void clear_tokens(); + std::string get_token(); + std::optional<std::string> get_optional_token(); + uint64_t get_numeric_token(); + std::optional<uint64_t> get_optional_numeric_token(); + + bool run_automated_test(); + + bool run_interactive_test(); + + void help(); + void list_sequence(bool testrecovery); +}; +} // namespace io_sequence::tester +} // namespace ceph diff --git a/src/test/pybind/pytest.ini b/src/test/pybind/pytest.ini index dccf2a346dc..97569e88299 100644 --- a/src/test/pybind/pytest.ini +++ b/src/test/pybind/pytest.ini @@ -7,3 +7,4 @@ markers = stats tier watch + wait diff --git a/src/test/pybind/test_ceph_argparse.py b/src/test/pybind/test_ceph_argparse.py index 3039223abdf..630e6046b24 100755 --- a/src/test/pybind/test_ceph_argparse.py +++ b/src/test/pybind/test_ceph_argparse.py @@ -217,7 +217,7 @@ class TestPG(TestArgparse): def test_pg_missing_args_output(self): ret, _, stderr = self._capture_output(['pg'], stderr=True) self.assertEqual({}, ret) - self.assertRegexpMatches(stderr, re.compile('no valid command found.* closest matches')) + self.assertRegex(stderr, re.compile('no valid command found.* closest matches')) def test_pg_wrong_arg_output(self): ret, _, stderr = self._capture_output(['pg', 'map', 'bad-pgid'], @@ -416,10 +416,10 @@ class TestMDS(TestArgparse): class TestFS(TestArgparse): - + def test_dump(self): self.check_0_or_1_natural_arg('fs', 'dump') - + def test_fs_new(self): self._assert_valid_command(['fs', 'new', 'default', 'metadata', 'data']) @@ -912,7 +912,7 @@ class TestOSD(TestArgparse): '1.2.3.4/567', '600.40']) self._assert_valid_command(['osd', 'blocklist', action, '1.2.3.4', '600.40']) - + self._assert_valid_command(['osd', 'blocklist', action, 'v1:1.2.3.4', '600.40']) self._assert_valid_command(['osd', 'blocklist', action, @@ -925,7 +925,7 @@ class TestOSD(TestArgparse): 'v2:[2607:f298:4:2243::5522]:0/0', '600.40']) self._assert_valid_command(['osd', 'blocklist', action, '[2001:0db8::85a3:0000:8a2e:0370:7334]:0/0', '600.40']) - + self.assertEqual({}, validate_command(sigdict, ['osd', 'blocklist', action, 'invalid', diff --git a/src/test/pybind/test_rados.py b/src/test/pybind/test_rados.py index cb2a4f96101..25423bd8dcb 100644 --- a/src/test/pybind/test_rados.py +++ b/src/test/pybind/test_rados.py @@ -207,7 +207,7 @@ class TestRados(object): def test_get_fsid(self): fsid = self.rados.get_fsid() - assert re.match('[0-9a-f\-]{36}', fsid, re.I) + assert re.match(r'[0-9a-f\-]{36}', fsid, re.I) def test_blocklist_add(self): self.rados.blocklist_add("1.2.3.4/123", 1) diff --git a/src/test/rgw/rgw_multi/tests.py b/src/test/rgw/rgw_multi/tests.py index d95feb5aa95..433cd034fe0 100644 --- a/src/test/rgw/rgw_multi/tests.py +++ b/src/test/rgw/rgw_multi/tests.py @@ -15,6 +15,7 @@ import boto import boto.s3.connection from boto.s3.website import WebsiteConfiguration from boto.s3.cors import CORSConfiguration +from botocore.exceptions import ClientError from nose.tools import eq_ as eq from nose.tools import assert_not_equal, assert_equal, assert_true, assert_false @@ -3638,4 +3639,23 @@ def test_copy_object_different_bucket(): CopySource = source_bucket.name + '/' + objname) zonegroup_bucket_checkpoint(zonegroup_conns, dest_bucket.name) - + +def test_bucket_create_location_constraint(): + for zonegroup in realm.current_period.zonegroups: + zonegroup_conns = ZonegroupConns(zonegroup) + for zg in realm.current_period.zonegroups: + z = zonegroup_conns.rw_zones[0] + bucket_name = gen_bucket_name() + if zg.name == zonegroup.name: + # my zonegroup should pass + z.s3_client.create_bucket(Bucket=bucket_name, CreateBucketConfiguration={'LocationConstraint': zg.name}) + # check bucket location + response = z.s3_client.get_bucket_location(Bucket=bucket_name) + assert_equal(response['LocationConstraint'], zg.name) + else: + # other zonegroup should fail with 400 + e = assert_raises(ClientError, + z.s3_client.create_bucket, + Bucket=bucket_name, + CreateBucketConfiguration={'LocationConstraint': zg.name}) + assert e.response['ResponseMetadata']['HTTPStatusCode'] == 400 diff --git a/src/test/rgw/test_rgw_iam_policy.cc b/src/test/rgw/test_rgw_iam_policy.cc index 7dadb7812ff..1d13c2aa013 100644 --- a/src/test/rgw/test_rgw_iam_policy.cc +++ b/src/test/rgw/test_rgw_iam_policy.cc @@ -75,6 +75,8 @@ using rgw::IAM::s3GetObjectTagging; using rgw::IAM::s3GetObjectVersion; using rgw::IAM::s3GetObjectVersionTagging; using rgw::IAM::s3GetObjectVersionTorrent; +using rgw::IAM::s3GetObjectAttributes; +using rgw::IAM::s3GetObjectVersionAttributes; using rgw::IAM::s3GetPublicAccessBlock; using rgw::IAM::s3GetReplicationConfiguration; using rgw::IAM::s3ListAllMyBuckets; @@ -419,6 +421,8 @@ TEST_F(PolicyTest, Parse3) { act2[s3GetObjectVersionAcl] = 1; act2[s3GetObjectTorrent] = 1; act2[s3GetObjectVersionTorrent] = 1; + act2[s3GetObjectAttributes] = 1; + act2[s3GetObjectVersionAttributes] = 1; act2[s3GetAccelerateConfiguration] = 1; act2[s3GetBucketAcl] = 1; act2[s3GetBucketOwnershipControls] = 1; @@ -487,6 +491,8 @@ TEST_F(PolicyTest, Eval3) { s3allow[s3GetObjectVersion] = 1; s3allow[s3GetObjectAcl] = 1; s3allow[s3GetObjectVersionAcl] = 1; + s3allow[s3GetObjectAttributes] = 1; + s3allow[s3GetObjectVersionAttributes] = 1; s3allow[s3GetObjectTorrent] = 1; s3allow[s3GetObjectVersionTorrent] = 1; s3allow[s3GetAccelerateConfiguration] = 1; @@ -883,6 +889,8 @@ TEST_F(ManagedPolicyTest, AmazonS3ReadOnlyAccess) act[s3GetObjectVersionAcl] = 1; act[s3GetObjectTorrent] = 1; act[s3GetObjectVersionTorrent] = 1; + act[s3GetObjectAttributes] = 1; + act[s3GetObjectVersionAttributes] = 1; act[s3GetAccelerateConfiguration] = 1; act[s3GetBucketAcl] = 1; act[s3GetBucketOwnershipControls] = 1; diff --git a/src/test/test_ipaddr.cc b/src/test/test_ipaddr.cc index 49038815318..21df1d4056b 100644 --- a/src/test/test_ipaddr.cc +++ b/src/test/test_ipaddr.cc @@ -995,3 +995,158 @@ TEST(pick_address, ipv4_ipv6_enabled2) ASSERT_EQ(-1, r); } } + +// Test for IPv4 address +TEST(is_addr_in_subnet, ipv4) +{ + std::string public_network = "10.1.1.0/24"; + entity_addr_t addr; + addr.parse("10.1.1.2", nullptr); + + boost::intrusive_ptr<CephContext> cct(new CephContext(CEPH_ENTITY_TYPE_OSD), false); + cct->_conf._clear_safe_to_start_threads(); + cct->_conf.set_val("ms_bind_ipv4", "true"); + cct->_conf.set_val("ms_bind_ipv6", "false"); + + bool r = is_addr_in_subnet(cct.get(), public_network, addr); + ASSERT_EQ(true, r); +} + +// Test for IPv6 address +TEST(is_addr_in_subnet, ipv6) +{ + std::string public_network = "2001:db8::/64"; + entity_addr_t addr; + addr.parse("2001:db8::1", nullptr); + + boost::intrusive_ptr<CephContext> cct(new CephContext(CEPH_ENTITY_TYPE_OSD), false); + cct->_conf._clear_safe_to_start_threads(); + cct->_conf.set_val("ms_bind_ipv6", "true"); + cct->_conf.set_val("ms_bind_ipv4", "false"); + + bool r = is_addr_in_subnet(cct.get(), public_network, addr); + ASSERT_EQ(true, r); +} + +// Test for invalid address +TEST(is_addr_in_subnet, invalid_address) +{ + std::string public_network = "10.1.1.0/24"; + entity_addr_t addr; + addr.parse("192.168.1.1", nullptr); + + boost::intrusive_ptr<CephContext> cct(new CephContext(CEPH_ENTITY_TYPE_OSD), false); + cct->_conf._clear_safe_to_start_threads(); + cct->_conf.set_val("ms_bind_ipv4", "true"); + cct->_conf.set_val("ms_bind_ipv6", "false"); + + bool r = is_addr_in_subnet(cct.get(), public_network, addr); + ASSERT_EQ(false, r); +} + +// Test for malformed address +TEST(is_addr_in_subnet, malformed_address) +{ + std::string public_network = "10.1.1.0/24"; + entity_addr_t addr; + addr.parse("invalid_address", nullptr); + + boost::intrusive_ptr<CephContext> cct(new CephContext(CEPH_ENTITY_TYPE_OSD), false); + cct->_conf._clear_safe_to_start_threads(); + cct->_conf.set_val("ms_bind_ipv4", "true"); + cct->_conf.set_val("ms_bind_ipv6", "false"); + + // Test with a malformed address + bool r = is_addr_in_subnet(cct.get(), public_network, addr); + ASSERT_EQ(false, r); +} + +TEST(is_addr_in_subnet, boundary_ipv4) +{ + std::string public_network = "10.1.1.0/24"; + entity_addr_t addr_low; + addr_low.parse("10.1.1.0", nullptr); + entity_addr_t addr_high; + addr_high.parse("10.1.1.255", nullptr); + entity_addr_t addr_out; + addr_out.parse("10.1.2.0", nullptr); + + boost::intrusive_ptr<CephContext> cct(new CephContext(CEPH_ENTITY_TYPE_OSD), false); + cct->_conf._clear_safe_to_start_threads(); + cct->_conf.set_val("ms_bind_ipv4", "true"); + cct->_conf.set_val("ms_bind_ipv6", "false"); + + ASSERT_TRUE(is_addr_in_subnet(cct.get(), public_network, addr_low)); + ASSERT_TRUE(is_addr_in_subnet(cct.get(), public_network, addr_high)); + ASSERT_FALSE(is_addr_in_subnet(cct.get(), public_network, addr_out)); +} + +TEST(is_addr_in_subnet, boundary_ipv6) +{ + std::string public_network = "2001:db8::/64"; + entity_addr_t addr_low; + addr_low.parse("2001:db8::", nullptr); + entity_addr_t addr_high; + addr_high.parse("2001:db8:0:0:ffff:ffff:ffff:ffff", nullptr); + entity_addr_t addr_out; + addr_out.parse("2001:db9::", nullptr); + + boost::intrusive_ptr<CephContext> cct(new CephContext(CEPH_ENTITY_TYPE_OSD), false); + cct->_conf._clear_safe_to_start_threads(); + cct->_conf.set_val("ms_bind_ipv6", "true"); + cct->_conf.set_val("ms_bind_ipv4", "false"); + + ASSERT_TRUE(is_addr_in_subnet(cct.get(), public_network, addr_low)); + ASSERT_TRUE(is_addr_in_subnet(cct.get(), public_network, addr_high)); + ASSERT_FALSE(is_addr_in_subnet(cct.get(), public_network, addr_out)); +} + +TEST(is_addr_in_subnet, overlapping_subnets) +{ + std::string public_network_1 = "10.1.1.0/24"; + std::string public_network_2 = "10.1.2.0/24"; + entity_addr_t addr; + addr.parse("10.1.1.5", nullptr); + + boost::intrusive_ptr<CephContext> cct(new CephContext(CEPH_ENTITY_TYPE_OSD), false); + cct->_conf._clear_safe_to_start_threads(); + cct->_conf.set_val("ms_bind_ipv4", "true"); + cct->_conf.set_val("ms_bind_ipv6", "false"); + + ASSERT_TRUE(is_addr_in_subnet(cct.get(), public_network_1, addr)); + ASSERT_FALSE(is_addr_in_subnet(cct.get(), public_network_2, addr)); +} + +TEST(is_addr_in_subnet, mismatched_family) +{ + std::string public_network_1 = "2001:db8::/64"; + entity_addr_t addr_1; + addr_1.parse("10.1.1.5", nullptr); + + std::string public_network_2 = "10.1.1.0/24"; + entity_addr_t addr_2; + addr_2.parse("2001:db8::1", nullptr); + + boost::intrusive_ptr<CephContext> cct(new CephContext(CEPH_ENTITY_TYPE_OSD), false); + cct->_conf._clear_safe_to_start_threads(); + cct->_conf.set_val("ms_bind_ipv4", "true"); + cct->_conf.set_val("ms_bind_ipv6", "true"); + + ASSERT_FALSE(is_addr_in_subnet(cct.get(), public_network_1, addr_1)); + ASSERT_FALSE(is_addr_in_subnet(cct.get(), public_network_2, addr_2)); +} + +TEST(is_addr_in_subnet, invalid_subnets) +{ + std::string public_network_1 = "10.1.1.0/33"; + std::string public_network_2 = "25.0.0.99/10"; + entity_addr_t addr; + addr.parse("10.1.1.2", nullptr); + + boost::intrusive_ptr<CephContext> cct(new CephContext(CEPH_ENTITY_TYPE_OSD), false); + cct->_conf._clear_safe_to_start_threads(); + + ASSERT_FALSE(is_addr_in_subnet(cct.get(), public_network_1, addr)); // Invalid prefix + ASSERT_FALSE(is_addr_in_subnet(cct.get(), public_network_2, addr)); // Invalid subnet string +} + diff --git a/src/tools/cephfs/top/cephfs-top b/src/tools/cephfs/top/cephfs-top index 9ecc47fc2d5..45900f9a025 100755 --- a/src/tools/cephfs/top/cephfs-top +++ b/src/tools/cephfs/top/cephfs-top @@ -148,7 +148,7 @@ def wrap(s, sl): """return a '+' suffixed wrapped string""" if len(s) < sl: return s - return f'{s[0:sl-1]}+' + return f'{s[0:sl - 1]}+' class FSTopBase(object): diff --git a/src/vstart.sh b/src/vstart.sh index b445e250a00..a992f33c856 100755 --- a/src/vstart.sh +++ b/src/vstart.sh @@ -159,6 +159,7 @@ smallmds=0 short=0 crimson=0 ec=0 +cephexporter=0 cephadm=0 parallel=true restart=1 @@ -233,6 +234,7 @@ options: -G disable Kerberos/GSSApi authentication --hitset <pool> <hit_set_type>: enable hitset tracking -e : create an erasure pool + --cephexporter: start the ceph-exporter daemon -o config add extra config parameters to all sections --rgw_port specify ceph rgw http listen port --rgw_frontend specify the rgw frontend configuration @@ -372,6 +374,9 @@ case $1 in -e) ec=1 ;; + --cephexporter) + cephexporter=1 + ;; --new | -n) new=1 ;; @@ -1140,6 +1145,17 @@ EOF fi } +start_cephexporter() { + debug echo "Starting Ceph exporter daemon..." + + # Define socket directory for the exporter + # Start the exporter daemon + prunb ceph-exporter \ + -c "$conf_fn" \ + --sock-dir "$CEPH_ASOK_DIR" \ + --addrs "$IP" +} + start_osd() { if [ $inc_osd_num -gt 0 ]; then old_maxosd=$($CEPH_BIN/ceph osd getmaxosd | sed -e 's/max_osd = //' -e 's/ in epoch.*//') @@ -1738,6 +1754,10 @@ if [ $CEPH_NUM_MDS -gt 0 ]; then ceph_adm fs authorize \* "client.fs" / rwp >> "$keyring_fn" fi +if [ "$cephexporter" -eq 1 ]; then + start_cephexporter +fi + # Don't set max_mds until all the daemons are started, otherwise # the intended standbys might end up in active roles. if [ "$CEPH_MAX_MDS" -gt 1 ]; then |
