summaryrefslogtreecommitdiffstats
path: root/src (follow)
Commit message (Collapse)AuthorAgeFilesLines
* mds: dump log segment in segment expiry callbackVenky Shankar2024-08-201-0/+1
| | | | Signed-off-by: Venky Shankar <vshankar@redhat.com>
* mds: dump log segment end along with offsetVenky Shankar2024-08-201-1/+1
| | | | Signed-off-by: Venky Shankar <vshankar@redhat.com>
* Merge pull request #58594 from jamiepryde/isa-xor-raidYuri Weinstein2024-08-196-382/+81
|\ | | | | | | | | | | erasure-code/isa: Use isa/raid's xor_gen() instead of the region_xor(… Reviewed-by: Mark Nelson <mnelson@redhat.com>
| * erasure-code/isa: Use isa/raid's xor_gen() instead of the region_xor() ↵Jamie Pryde2024-07-186-382/+81
| | | | | | | | | | | | optimisation Signed-off-by: Jamie Pryde <jamiepry@uk.ibm.com>
* | Merge pull request #59239 from yuvalif/wip-yuval-67513Yuval Lifshitz2024-08-191-6/+2
|\ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Reviewed-By: Casey Bodley <cbodley@ibm.com> test/rgw/notification: use real ip address instead of localhost based on that comment: https://tracker.ceph.com/issues/67206#note-6 the address used by the endpoint is taken as the real IP address of the host where the test script is running and not localhost. we also changed the rabbitmq-server conf to allow "guest" user to connect over non localhost address Fixes: https://tracker.ceph.com/issues/67206 Signed-off-by: Yuval Lifshitz <ylifshit@ibm.com>
| * | test/rgw/notification: use real ip address instead of localhostYuval Lifshitz2024-08-161-6/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | based on that comment: https://tracker.ceph.com/issues/67206#note-6 the address used by the endpoint is taken as the real IP address of the host where the test script is running and not localhost. we also changed the rabbitmq-server conf to allow "guest" user to connect over non localhost address Fixes: https://tracker.ceph.com/issues/67206 Signed-off-by: Yuval Lifshitz <ylifshit@ibm.com>
* | | Merge pull request #59200 from ifed01/wip-ifed-fix-store-test-col-refIgor Fedotov2024-08-191-1/+13
|\ \ \ | | | | | | | | | | | | | | | | test/store_test: fix assertions due to unclosed collection refs. Reviewd-by: Pere Diaz Bou <pere-altea@hotmail.com>
| * | | test/store_test: fix assertions due to unclosed collection refs.Igor Fedotov2024-08-131-1/+13
| | | | | | | | | | | | | | | | Signed-off-by: Igor Fedotov <igor.fedotov@croit.io>
* | | | Merge pull request #59212 from cyx1231st/wip-seastore-more-reportsYingxin2024-08-1913-176/+551
|\ \ \ \ | | | | | | | | | | | | | | | | | | | | | | | | | crimson/os/seastore/cache: report lru usage/in/out with trans and extent type Reviewed-by: Samuel Just <sjust@redhat.com> Reviewed-by: Xuehan Xu <xuxuehan@qianxin.com>
| * | | | crimson/os/seastore/cache: report lru usage/in/out with trans and extent typeYingxin Cheng2024-08-157-10/+332
| | | | | | | | | | | | | | | | | | | | Signed-off-by: Yingxin Cheng <yingxin.cheng@intel.com>
| * | | | crimson/os/seastore: cleanup periodical reportingYingxin Cheng2024-08-155-34/+37
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Consolidate time into a single place per SeaStore::Shard. Signed-off-by: Yingxin Cheng <yingxin.cheng@intel.com>
| * | | | crimson/os/seastore/cache/lru: renamesYingxin Cheng2024-08-152-16/+16
| | | | | | | | | | | | | | | | | | | | Signed-off-by: Yingxin Cheng <yingxin.cheng@intel.com>
| * | | | crimson/os/seastore/cache: refine lru logicsYingxin Cheng2024-08-151-25/+25
| | | | | | | | | | | | | | | | | | | | Signed-off-by: Yingxin Cheng <yingxin.cheng@intel.com>
| * | | | crimson/os/seastore: move counter_by_extent_t definitionYingxin Cheng2024-08-152-12/+12
| | | | | | | | | | | | | | | | | | | | Signed-off-by: Yingxin Cheng <yingxin.cheng@intel.com>
| * | | | crimson/os/seastore/seastore_types: unify checks to the extent typesYingxin Cheng2024-08-159-52/+98
| | | | | | | | | | | | | | | | | | | | Signed-off-by: Yingxin Cheng <yingxin.cheng@intel.com>
| * | | | crimson/os/seastore/cache: pass missing src to touch_extent()Yingxin Cheng2024-08-142-10/+15
| | | | | | | | | | | | | | | | | | | | Signed-off-by: Yingxin Cheng <yingxin.cheng@intel.com>
| * | | | crimson/os/seastore/cache: cleanup add_extent()Yingxin Cheng2024-08-142-20/+24
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Move add_to_dirty() and touch_extent() out of add_extent(), this removes duplicated calls to touch_extent() from the on_cache callback. Signed-off-by: Yingxin Cheng <yingxin.cheng@intel.com>
| * | | | crimson/os/seastore/cache: cleanup remove_from_dirty()Yingxin Cheng2024-08-141-8/+5
| | | | | | | | | | | | | | | | | | | | Signed-off-by: Yingxin Cheng <yingxin.cheng@intel.com>
| * | | | crimson/os/seastore: drop duplicated calls to touch_extent()Yingxin Cheng2024-08-141-2/+0
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The extent is already PRESENT, which means it was already touched in this transaction. Signed-off-by: Yingxin Cheng <yingxin.cheng@intel.com>
| * | | | crimson/os/seastore/cached_extent: rename primary_ref_listYingxin Cheng2024-08-142-3/+3
| | | | | | | | | | | | | | | | | | | | Signed-off-by: Yingxin Cheng <yingxin.cheng@intel.com>
* | | | | Merge pull request #58355 from batrick/ceph-backport-fetchheadVenky Shankar2024-08-161-5/+5
|\ \ \ \ \ | | | | | | | | | | | | | | | | | | | | | | | | script/ceph-backport: robustness adjustments for local git repo quirks Reviewed-by: Venky Shankar <vshankar@redhat.com>
| * | | | | script/ceph-backport: only fetch the merge sha1Patrick Donnelly2024-06-281-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Rather than doing a full fetch every time. Signed-off-by: Patrick Donnelly <pdonnell@redhat.com>
| * | | | | script/ceph-backport: do not assume ref layout for checkoutPatrick Donnelly2024-06-281-4/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The local repository may have a different layout from the defaults for remote repository references. As for myself, I have: [remote "upstream"] url = git@github.com:ceph/ceph.git fetch = +refs/*:refs/remotes/upstream/* So I have a local mirror of the full ceph.git repsository and upstream branches are available via `refs/remotes/upstream/heads/<branch>`. So, fetch the desired branch and use FETCH_HEAD instead. This is not 100% the same as the merge branch for the wip- branch becomes: [branch "wip-66572-squid"] remote = origin merge = refs/heads/wip-66572-squid So the remote tracking branch is now the origin. Rebasing to a newer <release> branch must be done manually: git rebase upstream/heads/<release> Signed-off-by: Patrick Donnelly <pdonnell@redhat.com>
* | | | | | Merge PR #58896 into mainVenky Shankar2024-08-161-0/+2
|\ \ \ \ \ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | * refs/pull/58896/head: client: flush the caps release in filesystem sync Reviewed-by: Venky Shankar <vshankar@redhat.com> Reviewed-by: Dhairya Parmar <dparmar@redhat.com>
| * | | | | | client: flush the caps release in filesystem syncXiubo Li2024-08-161-0/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | We have hit a race between cap releases and cap revoke request that will cause the check_caps() to miss sending a cap revoke ack to MDS. And the client will depend on the cap release to release that revoking caps, which could be delayed for some unknown reasons. In Kclient we have figured out the RCA about race and we need a way to explictly trigger this manually could help to get rid of the caps revoke stuck issue. Fixes: https://tracker.ceph.com/issues/67221 Signed-off-by: Xiubo Li <xiubli@redhat.com>
* | | | | | | Merge pull request #59205 from xxhdx1985126/wip-seastore-find-pending-versionYingxin2024-08-161-1/+1
|\ \ \ \ \ \ \ | |/ / / / / / |/| | | | | | | | | | | | | | | | | | | | crimson/os/seastore/btree: fix minor corner case issue Reviewed-by: Yingxin Cheng <yingxin.cheng@intel.com>
| * | | | | | crimson/os/seastore/btree: fix minor corner case issueXuehan Xu2024-08-141-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | Signed-off-by: Xuehan Xu <xuxuehan@qianxin.com>
* | | | | | | Merge pull request #59220 from ivoalmeida/carbon-datatable-cleanupsIvo Almeida2024-08-154-30/+31
|\ \ \ \ \ \ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | mgr/dashboard: carbon datatables impr and cleanups Reviewed-by: Nizamudeen A <nia@redhat.com>
| * | | | | | | mgr/dashboard: carbon datatables impr and cleanupsIvo Almeida2024-08-144-30/+31
| | |_|/ / / / | |/| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Fixes: https://tracker.ceph.com/issues/67544, https://tracker.ceph.com/issues/67538, https://tracker.ceph.com/issues/67542, https://tracker.ceph.com/issues/67545, https://tracker.ceph.com/issues/67546 Signed-off-by: Ivo Almeida <ialmeida@redhat.com>
* | | | | | | Merge pull request #59218 from yuvalif/wip-yuval-67525J. Eric Ivancich2024-08-152-9/+37
|\ \ \ \ \ \ \ | |_|_|_|_|/ / |/| | | | | | | | | | | | | | | | | | | | rgw/notifications: fixing radosgw-admin notification json Reviewed-by: Casey Bodley <cbodley@redhat.com>
| * | | | | | rgw/notifications: fixing radosgw-admin notification jsonYuval Lifshitz2024-08-142-9/+37
| |/ / / / / | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Fixes: https://tracker.ceph.com/issues/67525 Signed-off-by: Yuval Lifshitz <ylifshit@ibm.com>
* | | | | | crimson/osd/backfill_state: support backfilling cancellationXuehan Xu2024-08-155-2/+43
| | | | | | | | | | | | | | | | | | | | | | | | Signed-off-by: Xuehan Xu <xuxuehan@qianxin.com>
* | | | | | crimson/osd/pg_recovery: reset backfill_state when backfill finishedXuehan Xu2024-08-151-0/+1
| | | | | | | | | | | | | | | | | | | | | | | | Signed-off-by: Xuehan Xu <xuxuehan@qianxin.com>
* | | | | | Merge pull request #57966 from ↵Matan Breizman2024-08-154-48/+29
|\ \ \ \ \ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | xxhdx1985126/wip-crimson-concurrent-recover-missing crimson/osd/osd_operations: make the "recover_missing" phase concurrent Reviewed-by: Yingxin Cheng <yingxin.cheng@intel.com> Reviewed-by: Matan Breizman <mbreizma@redhat.com>
| * | | | | | crimson/osd/osd_operations/client_request: check already complete in theXuehan Xu2024-08-084-6/+27
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | "check_already_complete_get_obc" phase Otherwise, the replies can go out-of-order Signed-off-by: Xuehan Xu <xuxuehan@qianxin.com>
| * | | | | | crimson/osd/osd_operations/client_request: merge recover_missing,Xuehan Xu2024-08-073-54/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | recover_missing_lock_obc and recover_missing_snaps into a single OrderedConcurrentPhase The reasons for this change are as follows: 1. the pipeline phase in which the obc loading is done has to be entered "synchronouly", however, the leaving of an OrderedConcurrentPhase can't be so, which means we can't enter_sync an OrderedConcurrentPhase from an earlier OrderedConcurrentPhase directly; 2. on the other hand, the whole missing object/snaps recovery procedure can and should be a OrderedConcurrentPhase. Signed-off-by: Xuehan Xu <xuxuehan@qianxin.com>
| * | | | | | crimson/osd/osd_operations: make the "recover_missing" phase concurrentXuehan Xu2024-08-072-1/+13
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Otherwise, UrgentRecovery requests within the same pg can only be processed sequentially Signed-off-by: Xuehan Xu <xuxuehan@qianxin.com>
* | | | | | | Merge pull request #53151 from xxhdx1985126/wip-crimson-backfill-fixesMatan Breizman2024-08-155-12/+40
|\ \ \ \ \ \ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | crimson/osd/backfill_state: fixes two corner cases in backfilling Reviewed-by: Radosław Zarzyński <rzarzyns@redhat.com>
| * | | | | | | crimson/osd/backfill_state: set backfill_infos when the last round ofXuehan Xu2023-08-282-4/+10
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | scan doesn't produce any object that needs to be backkfilled Signed-off-by: Xuehan Xu <xxhdx1985126@gmail.com>
| * | | | | | | crimson/osd/backfill_state: consider backfills as complete when allXuehan Xu2023-08-285-8/+30
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | replicas have acknowledged the finish of the backfill Signed-off-by: Xuehan Xu <xuxuehan@qianxin.com>
* | | | | | | | Merge pull request #58911 from yuvalif/wip-yuval-67229Yuval Lifshitz2024-08-152-15/+35
|\ \ \ \ \ \ \ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | test/cls_2pc_queue: prevent list+remove race between consumers Reviewed-By: Casey Bodley <cbodley@ibm.com>
| * | | | | | | | test/cls_2pc_queue: prevent list+remove race between consumersYuval Lifshitz2024-08-052-15/+35
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | * make sure that the queue full condition is covered * add cls debugging to test Fixes: https://tracker.ceph.com/issues/67229 Signed-off-by: Yuval Lifshitz <ylifshit@ibm.com>
* | | | | | | | | Merge pull request #59028 from cbodley/wip-67326Casey Bodley2024-08-141-2/+2
|\ \ \ \ \ \ \ \ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | rgw/notify: visit() returns copy of owner string Reviewed-by: Adam Emerson <aemerson@redhat.com>
| * | | | | | | | | rgw/notify: visit() returns copy of owner stringCasey Bodley2024-08-051-2/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | return a copy of the owner string to work around compiler warning: ceph/src/rgw/driver/rados/rgw_notify.cc: In function ‘int rgw::notify::publish_reserve(const DoutPrefixProvider*, const rgw::SiteConfig&, const EventTypeList&, reservation_t&, const RGWObjTags*)’: ceph/src/rgw/driver/rados/rgw_notify.cc:1113:26: warning: possibly dangling reference to a temporary [-Wdangling-reference] 1113 | const std::string& topic_tenant = std::visit(fu2::overload( | ^~~~~~~~~~~~ ceph/src/rgw/driver/rados/rgw_notify.cc:1113:51: note: the temporary was destroyed at the end of the full expression ‘std::visit<fu2::abi_310::detail::overloading::overload_impl<rgw::notify::publish_reserve(const DoutPrefixProvider*, const rgw::SiteConfig&, const EventTypeList&, reservation_t&, const RGWObjTags*)::<lambda(const rgw_user&)>, rgw::notify::publish_reserve(const DoutPrefixProvider*, const rgw::SiteConfig&, const EventTypeList&, reservation_t&, const RGWObjTags*)::<lambda(const rgw_account_id&)> >, variant<rgw_user, rgw_account_id>&>(fu2::overload<rgw::notify::publish_reserve(const DoutPrefixProvider*, const rgw::SiteConfig&, const EventTypeList&, reservation_t&, const RGWObjTags*)::<lambda(const rgw_user&)>, rgw::notify::publish_reserve(const DoutPrefixProvider*, const rgw::SiteConfig&, const EventTypeList&, reservation_t&, const RGWObjTags*)::<lambda(const rgw_account_id&)> >(<lambda closure object>rgw::notify::publish_reserve(const DoutPrefixProvider*, const rgw::SiteConfig&, const EventTypeList&, reservation_t&, const RGWObjTags*)::<lambda(const rgw_user&)>(), <lambda closure object>rgw::notify::publish_reserve(const DoutPrefixProvider*, const rgw::SiteConfig&, const EventTypeList&, reservation_t&, const RGWObjTags*)::<lambda(const rgw_account_id&)>()), topic_cfg.rgw_pubsub_topic::owner)’ 1113 | const std::string& topic_tenant = std::visit(fu2::overload( | ~~~~~~~~~~^~~~~~~~~~~~~~~ 1114 | [] (const rgw_user& u) -> const std::string& { return u.tenant; }, | ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 1115 | [] (const rgw_account_id& a) -> const std::string& { return a; } | ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 1116 | ), topic_cfg.owner); | ~~~~~~~~~~~~~~~~~~~ Fixes: https://tracker.ceph.com/issues/67326 Signed-off-by: Casey Bodley <cbodley@redhat.com>
* | | | | | | | | | Merge pull request #58448 from cbodley/wip-rgw-lc-asyncCasey Bodley2024-08-1414-212/+295
|\ \ \ \ \ \ \ \ \ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | cls/rgw: define lc ops in terms of ObjectOperation instead of IoCtx Reviewed-by: Matt Benjamin <mbenjamin@redhat.com>
| * | | | | | | | | | cls/rgw: define lc ops in terms of ObjectOperation instead of IoCtxCasey Bodley2024-07-233-82/+128
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | clean up the lc functions that were supposed to be hidden by CLS_CLIENT_HIDE_IOCTX this allows rgw to use them asynchonously with rgw_rados_operate() and optional_yield, and warn about blocking calls that should be async Signed-off-by: Casey Bodley <cbodley@redhat.com>
| * | | | | | | | | | rgw/sal: add dpp and optional_yield to lifecycle opsCasey Bodley2024-07-2312-131/+168
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Signed-off-by: Casey Bodley <cbodley@redhat.com>
* | | | | | | | | | | Merge pull request #58965 from linuxbox2/wip-lcgt-typoCasey Bodley2024-08-141-1/+1
|\ \ \ \ \ \ \ \ \ \ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | rgwlc: fix typo in getlc (ObjectSizeGreaterThan) Reviewed-by: Casey Bodley <cbodley@redhat.com>
| * | | | | | | | | | | rgwlc: fix typo in getlc (ObjectSizeGreaterThan)Matt Benjamin2024-07-311-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
* | | | | | | | | | | | Merge pull request #59169 from cbodley/wip-67464Casey Bodley2024-08-141-13/+11
|\ \ \ \ \ \ \ \ \ \ \ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | rgw: revert account-related changes to get_iam_policy_from_attr() Reviewed-by: Pritha Srivastava <prsrivas@redhat.com>
generated by cgit v1.2.3 (git 2.39.1) at 2025-01-19 12:19:00 +0100