summaryrefslogtreecommitdiffstats
Commit message (Collapse)AuthorAgeFilesLines
* librbd: bump versionJosh Durgin2012-09-101-1/+1
| | | | | | This marks the availability of the cloning and locking functions. Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
* cls_rbd: remove locking methodsJosh Durgin2012-09-084-435/+0
| | | | | | | These are unnecessary now that librbd is using the generic cls_lock. Fixes: #2951 Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
* rbd: add locking commandsJosh Durgin2012-09-086-18/+480
| | | | | | | | The locker (entity_name_t) will be different each time the rbd command line tool is run, so 'lock remove' is always breaking a lock. Fixes: #2556 Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
* qa: update rbd tests and runnerJosh Durgin2012-09-082-5/+3
| | | | | | | | * no longer need to wait for watch timeout since #2948 was fixed * use --format 2 instead of --new-format * add test_cls_rbd to run-rbd-tests script Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
* librbd: use generic cls_lock instead of cls_rbd's lockingJosh Durgin2012-09-0812-96/+512
| | | | | | | | | | | | | Update the librbd locking api to make more sense: * Add an optional tag to shared locking * only make shared vs exclusive different functions in the user-visible api * return a list of structs instead of a set of pairs * fix incorrect range checking in the C api * rename locks to lockers to be consistent with the generic locking class * rename other_locker parameter to client, to match the list_lockers usage Fixes: #2952 Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
* cls_lock_client: add ObjectOperation-based get_lock_infoJosh Durgin2012-09-012-16/+35
| | | | | | | This will be used by librbd to grab lock info along with the rest of its header information in a single request. Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
* cls_lock_types: add missing includeJosh Durgin2012-09-011-1/+2
| | | | | | msg_types defines entity-related types used here. Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
* cls_lock_client: return error when decoding failsJosh Durgin2012-08-311-2/+2
| | | | | | Library code shouldn't be using cerr either. Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
* cls_lock_client: fix indentationJosh Durgin2012-08-311-52/+51
| | | | | | Add indentation settings to header, and reindent. Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
* cls_lock_client: change modified reference parameters to pointersJosh Durgin2012-08-315-95/+98
| | | | | | | This makes it clear which parameters are modified, as our style guide states. Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
* cls_lock_client: clean up reference parametersJosh Durgin2012-08-314-50/+59
| | | | | | | These should all be const. The remaining reference parameters will be converted to pointers in another commit. Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
* cls_lock: fix some spacingJosh Durgin2012-08-311-3/+4
| | | | Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
* Merge branch 'wip-rbd-children'Josh Durgin2012-08-3113-65/+588
|\
| * doc: clarify rbd man page (esp. layering)Josh Durgin2012-08-302-16/+118
| | | | | | | | | | | | | | | | | | | | | | * a clone's size can't be overridden * note which commands require format 2 * clarify details of copy * add examples for cloning * add pool to map example for consistency * fix a couple warnings and re-sync man page with rst Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
| * rbd: add --format optionJosh Durgin2012-08-304-44/+94
| | | | | | | | | | | | | | This chooses whether to use the original (supported by krbd) or the new (supports layering) format. Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
| * librbd: prevent racing clone and snap unprotectJosh Durgin2012-08-301-0/+18
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | If the following sequence of events occured, a clone could be created of an unprotected snapshot: 1. A: begin clone - check that snap foo is protected 2. B: rbd unprotect snap foo 3. B: check that all pools have no clones of foo 4. B: unprotect snap foo 5. A: finish creating clone of foo, add it as a child To stop this from happening, check at the beginning and end of cloning that the parent snapshot is protected. If it is not, or checking protection status fails (possibly because the parent snapshot was removed), remove the clone and return an error. Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
| * rbd: add "children" command, update cli test filesDan Mick2012-08-304-5/+51
| | | | | | | | | | | | Fixes: #2720 Signed-off-by: Dan Mick <dan.mick@inktank.com> Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
| * librbd: add {rbd_}list_children() methodsDan Mick2012-08-308-0/+307
| | | | | | | | | | | | | | | | These iterate over all pools and check for children of a particular snapshot. Signed-off-by: Josh Durgin <josh.durgin@inktank.com> Reviewed-by: Dan Mick <dan.mick@inktank.com>
* | client: renew/submit subs on startupSage Weil2012-08-301-0/+1
| | | | | | | | | | | | | | | | This fixes a delay in getting the initial MDSMap during startup (we wait for the MonClient tick()). Reported-by: Noah Watkins <jayhawk@cs.ucsc.edu> Signed-off-by: Sage Weil <sage@inktank.com>
* | :doc: Added constraints and revised a description per joshd.John Wilkins2012-08-301-1/+3
| | | | | | | | Signed-off-by: John Wilkins <john.wilkins@inktank.com>
* | upstart, ceph-create-keys: Make client.admin key generation automatic.Tommi Virtanen2012-08-305-2/+158
| | | | | | | | | | | | | | | | | | | | | | | | This should help simplify Chef etc deployments. Now (when using the Upstart jobs), when a ceph-mon is started, ceph-create-admin-key is triggered. If /etc/ceph/$cluster.client.admin.keyring already exists, it does nothing; otherwise, it waits for ceph-mon to reach quorum, and then does a "ceph auth get-or-create" to create the key, and writes it atomically to disk. The equivalent code can be removed from the Chef cookbook once this is in.
* | upstart: Make instance jobs export their cluster and id variables.Tommi Virtanen2012-08-304-0/+8
| | | | | | | | | | | | | | This allows other jobs listening to Upstart "started ceph-mon" events to see what instance started. Signed-off-by: Tommi Virtanen <tv@inktank.com>
* | config: Add a per-name default keyring to front of keyring search path.Tommi Virtanen2012-08-301-1/+1
| | | | | | | | | | | | | | | | This lets us have e.g. /etc/ceph/ceph.client.admin.keyring that is owned by root:admin and mode u=rw,g=r,o= without making every non-root run of the command line tools complain and fail. This is what the Chef cookbook has been doing for a while already.
* | doc: Modified index page with table. Pools and Auth will go to Ops.John Wilkins2012-08-301-2/+47
| | | | | | | | Signed-off-by: John Wilkins <john.wilkins@inktank.com>
* | doc: Some improvements. This still needs review.John Wilkins2012-08-301-21/+101
| | | | | | | | Signed-off-by: John Wilkins <john.wilkins@inktank.com>
* | doc: Added additional note to mount data disk to data path.John Wilkins2012-08-301-5/+12
| | | | | | | | Signed-off-by: John Wilkins <john.wilkins@inktank.com>
* | doc: Added a document for general config settings.John Wilkins2012-08-301-0/+109
| | | | | | | | Signed-off-by: John Wilkins <john.wilkins@inktank.com>
* | doc: Added a doc for filestore settings.John Wilkins2012-08-301-0/+234
| | | | | | | | Signed-off-by: John Wilkins <john.wilkins@inktank.com>
* | doc: Added a document for RBD cache settings.John Wilkins2012-08-301-0/+73
| | | | | | | | Signed-off-by: John Wilkins <john.wilkins@inktank.com>
* | doc: Added substantial detail to OSD setting descriptions.John Wilkins2012-08-301-253/+229
| | | | | | | | Signed-off-by: John Wilkins <john.wilkins@inktank.com>
* | doc: minor edit to use # for comments.John Wilkins2012-08-301-2/+2
| | | | | | | | Signed-off-by: John Wilkins <john.wilkins@inktank.com>
* | doc: Restructured ceph config. Added network and OSD config details.John Wilkins2012-08-301-121/+301
|/ | | | Signed-off-by: John Wilkins <john.wilkins@inktank.com>
* rgw: remove unused block of codeYehuda Sadeh2012-08-291-16/+0
| | | | | | We were reading bucket info, but that wasn't necessary. Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
* rgw_admin.cc: Prevent clobbering the index when linking a bucket.caleb miles2012-08-291-6/+26
| | | | | | | | | Prevent the 'bucket link' command from overwriting the index of an existing bucket. Corrects bug 2935: http://tracker.newdream.net/issues/2935 Signed-off-by: caleb miles <caleb.miles@inktank.com>
* rgw: clear usage map before reading usageYehuda Sadeh2012-08-291-0/+2
| | | | | | | | | | Fixes: #3057 Since we read usage in chunks we need to clear the usage map before reading the next chunk, otherwise we're going to aggregate the old data as well. Backport: argonaut Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
* Merge branch 'next'Sage Weil2012-08-291-5/+8
|\
| * osd: fix waiting_for_disk assertionSage Weil2012-08-291-5/+8
| | | | | | | | | | | | | | | | | | | | If requeue is false, we won't have cleared out waiting_for_ondisk; adjust assert placement as appropriate. Also, make sur we handle the requeue and !op case properly (although I'm not sure offhand if/when it would come up). Signed-off-by: Sage Weil <sage@inktank.com> Reviewed-by: Samuel Just <sam.just@inktank.com>
| * rados_bench: wait for completion callbacks before returningMike Ryan2012-08-281-1/+1
| | | | | | | | | | | | | | | | | | | | If we don't wait for the callback, the finisher may cleanup the callback context before the callback is actually invoked, causing a use-after-free error. This fixes #3048. Signed-off-by: Mike Ryan <mike.ryan@inktank.com>
* | Makefile.am: add missing .hYehuda Sadeh2012-08-281-0/+1
| | | | | | | | | | | | Was missing rgw_html_errors.h Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
* | Merge remote-tracking branch 'origin/wip-multi-delete'Yehuda Sadeh2012-08-2812-78/+487
|\ \ | | | | | | | | | | | | | | | | | | Conflicts: src/Makefile.am Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
| * | Implement multi-object delete.caleb miles2012-08-2812-78/+487
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | An implimentation of multi-object delete described in the latest Amazon S3 API provied at http://docs.amazonwebservices.com/AmazonS3/latest/API This commit is in response to tracker issue 2797 http://tracker.newdream.net/issues/2797 Signed-off-by: caleb miles <caleb.miles@inktank.com>
* | | rados_bench: wait for completion callbacks before returningMike Ryan2012-08-281-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | If we don't wait for the callback, the finisher may cleanup the callback context before the callback is actually invoked, causing a use-after-free error. This fixes #3048. Signed-off-by: Mike Ryan <mike.ryan@inktank.com>
* | | doc: Completed and reviewed RGW config reference.John Wilkins2012-08-281-46/+86
| | | | | | | | | | | | Signed-off-by: John Wilkins <john.wilkins@inktank.com>
* | | doc: added admonishment. Updated header syntax, copy semantics and x-ref.John Wilkins2012-08-281-10/+20
| | | | | | | | | | | | Signed-off-by: John Wilkins <john.wilkins@inktank.com>
* | | rgw: fix usage log readYehuda Sadeh2012-08-282-4/+6
| | | | | | | | | | | | | | | | | | The usage log read got broken in a recent cleanup work. Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
* | | doc: Added internal references. Clarified language in disk prepare.John Wilkins2012-08-281-7/+35
| | | | | | | | | | | | Signed-off-by: John Wilkins <john.wilkins@inktank.com>
* | | doc: added sudo for hdparm command.John Wilkins2012-08-281-1/+1
| | | | | | | | | | | | Signed-off-by: John Wilkins <john.wilkins@inktank.com>
* | | doc: added internal hyperlink targets.John Wilkins2012-08-281-0/+17
| | | | | | | | | | | | Signed-off-by: John Wilkins <john.wilkins@inktank.com>
* | | doc: Clean up quick start to ensure nobody uses "localhost".John Wilkins2012-08-282-11/+19
| | | | | | | | | | | | Signed-off-by: John Wilkins <john.wilkins@inktank.com>
* | | doc: Cleaned up syntax errors, and converted table to list.John Wilkins2012-08-281-14/+23
| | | | | | | | | | | | Signed-off-by: John Wilkins <john.wilkins@inktank.com>