Activity
From 03/03/2016 to 04/01/2016
04/01/2016
- 04:11 PM Bug #15355 (Resolved): tests: qemu_rebuild_object_map.sh needs to wait for image to appear
- It's failing early since it doesn't exist yet when enabling features:...
- 04:06 PM Bug #15354 (Resolved): rbd_mirror: valgrind says the 'impossible' happened - thread limit too low
- http://qa-proxy.ceph.com/teuthology/teuthology-2016-03-30_12:01:01-rbd-jewel-distro-basic-smithi/97384/teuthology.log...
- 04:01 PM Bug #15353 (Rejected): librbd: disable optimizations that result in pipelining guarded writes mix...
- These cause ordering issues, resulting in an osd crash as seen here:
http://qa-proxy.ceph.com/teuthology/teutholog... - 03:55 PM Bug #15352 (Resolved): TestJournalEntries.AioWrite: failed assert(m_watch_in_progress)
- http://qa-proxy.ceph.com/teuthology/teuthology-2016-03-30_12:01:01-rbd-jewel-distro-basic-smithi/97305/teuthology.log...
- 03:52 PM Bug #15097: journal.sh fails when removing image
- http://qa-proxy.ceph.com/teuthology/teuthology-2016-03-30_12:01:01-rbd-jewel-distro-basic-smithi/97276/teuthology.log
- 03:48 PM Bug #15351 (Resolved): librbd: resize timed out
- http://qa-proxy.ceph.com/teuthology/teuthology-2016-03-30_12:01:01-rbd-jewel-distro-basic-smithi/97490/teuthology.log...
03/31/2016
- 03:48 PM Backport #15129 (In Progress): hammer: Protect against excessively large object map sizes
- 01:54 AM Bug #15225: Linking to -lrbd causes process startup times to balloon
- LGTM
03/30/2016
- 10:45 PM Bug #15332 (Fix Under Review): tests: race in unittest_librbd during make check
- *PR*: https://github.com/ceph/ceph/pull/8380
- 10:43 PM Bug #15332: tests: race in unittest_librbd during make check
- Ah of course. Guess my partial recompile wasn't complete enough.
- 10:41 PM Bug #15332: tests: race in unittest_librbd during make check
- D'oh -- librados_test_stub needs the new cls methods.
- 10:36 PM Bug #15332: tests: race in unittest_librbd during make check
- ENOSYS on image open -- must have been an issue opening the cls shared libraries. Notice that it fails on the first ...
- 10:31 PM Bug #15332 (Resolved): tests: race in unittest_librbd during make check
- This doesn't reproduce locally, so I'm assuming it's a race (maybe related to real daemons used by 'make check'?
h... - 03:11 PM Feature #15322 (Resolved): Support asynchronous v2 image deletion
- When the rbd-mirror daemon needs to propagate the deletion of a primary-image to the local non-primary image, this is...
- 03:09 PM Feature #15321 (Resolved): Support asynchronous v2 image creation/cloning
- The rbd-mirror daemon needs to create/clone images from remote peers. Right now this is handled as a blocking operat...
- 03:08 PM Subtask #14421 (In Progress): Propagate image deletes from remote pool to local pool
- 01:52 PM Subtask #14937 (In Progress): Cloned images must only be bootstrapped after parent image successf...
- 12:57 PM Bug #15076 (Won't Fix): client upgrade(osd: firefly, client: jewel) rbd import_export firefly wor...
- 12:56 PM Subtask #15232 (Resolved): Support failover / failback
- 12:55 PM Subtask #15267 (Resolved): Enabling/Disabling image mirroring must respect pool mirroring mode
03/29/2016
- 05:32 PM Subtask #15029: Use watch/notify to alert to specific changes in the rbd_mirroring object
- *librbd PR*: https://github.com/ceph/ceph/pull/8355
- 03:44 PM Subtask #15265 (In Progress): Automatically disable image mirroring when image is removed
- 02:37 PM Cleanup #15306 (Resolved): ImageWatcher should derive from ObjectWatcher
- The new ObjectWatcher will handle the necessary watch, unwatch, and error recovery steps.
- 02:24 PM Subtask #15267 (Fix Under Review): Enabling/Disabling image mirroring must respect pool mirroring...
- 02:23 PM Subtask #15217 (Resolved): Enabling/disabling pool-level mirroring should enable/disable mirrorin...
- 11:50 AM Subtask #15144 (In Progress): rbd CLI to retrieve rbd mirror state for a pool / specific image
- 11:49 AM Subtask #14420 (In Progress): New RBD notification pool object for recording mirroring errors
03/28/2016
- 11:56 PM Subtask #15029 (In Progress): Use watch/notify to alert to specific changes in the rbd_mirroring ...
- 09:13 PM Subtask #14418: rbd-mirror multi-peer: cleanly transition alive peers to new period
- Not required for initial version of mirroring as only a single peer is supported.
- 08:25 PM Subtask #15232 (Fix Under Review): Support failover / failback
- *PR*: https://github.com/ceph/ceph/pull/8287
- 03:18 PM Bug #15290 (Can't reproduce): rbd journal
- I use fio to test rbd-mirror, I do not use two rbd-mirror each run witin cluster.
I just use one rbd-mirror in clus...
03/25/2016
03/24/2016
- 03:10 PM Subtask #15267 (Resolved): Enabling/Disabling image mirroring must respect pool mirroring mode
- The enabling/disabling of image mirroring ("rbd mirror image enable / disable") is only allowed when mirroring pool m...
- 02:58 PM Subtask #15238 (Resolved): Switch fsid over to mirror uuid
- PR: https://github.com/ceph/ceph/pull/8280
- 02:29 PM Subtask #15265 (Resolved): Automatically disable image mirroring when image is removed
- When a user removes an rbd image, if mirroring is enabled for that image, we must disable mirroring before deleting t...
03/23/2016
- 08:19 PM Bug #15233 (Need More Info): Flattening an rbd image with a running Qemu instances causes librbd ...
- 08:08 PM Bug #15259 (Resolved): performance: journaling results in 4X slowdown when writes are not blocked...
- Using bench-write on a non-journaled image:...
- 07:42 PM Bug #15250 (Fix Under Review): librbd is not respecting cache setting
- *PR*: https://github.com/ceph/ceph/pull/8282
- 03:50 PM Bug #15250 (In Progress): librbd is not respecting cache setting
- 03:35 PM Bug #15250 (Resolved): librbd is not respecting cache setting
- Attempting to disable the rbd cache via "rbd cache = false" results in the cache still being enabled. Only affects t...
- 04:33 PM Bug #14984 (Resolved): rbdmap.service should include RBDMAPFILE environment variable
- 01:04 PM Bug #15248 (Rejected): Flag is showing "flags: object map invalid", after enabling object map on ...
- This is expected behavior -- when you enable object map on a pre-existing image, the object map is in fact invalid. ...
- 12:21 PM Bug #15248 (Rejected): Flag is showing "flags: object map invalid", after enabling object map on ...
- 1. Create a Image
sudo rbd create Tanay-RBD/new4 --size 10240G --image-format 2 --image-feature exclusive-lock
2. ...
03/22/2016
- 06:32 PM Subtask #15239 (Resolved): Throttle in-flight image syncs to only a X concurrent
- Otherwise, adding a new peer could result in hundreds of images attempting to be sync'ed at the same time.
- 05:16 PM Subtask #15238 (Resolved): Switch fsid over to mirror uuid
- Each replicated pool has its own unique uuid. This uuid should be used when registering with remote journals instead...
- 12:37 PM Bug #15233: Flattening an rbd image with a running Qemu instances causes librbd worker threads to...
- I assume this is on 0.94.6? Can you please provide the full "debug rbd=20" logs pre/post hang or can you attach to t...
- 08:59 AM Bug #15233 (Duplicate): Flattening an rbd image with a running Qemu instances causes librbd worke...
- I'm sorry if this is noise, but #14483 is not solved for me and it seems responding to the fixed issue doesn't attrac...
- 01:18 AM Subtask #14417: Interlock RBD mirroring daemon and acquiring exclusive lock
- Basic support for interlock is include in branch for #15232
- 01:17 AM Subtask #15232 (Resolved): Support failover / failback
- An image being mirrored from cluster A to B should be able to be promoted in site B and eventually cleanly failback t...
- 01:16 AM Subtask #14981 (Resolved): rbd-mirror daemon systemd / upstart scripts
03/21/2016
- 08:17 PM Bug #15224 (Resolved): EINVAL on test_cls_rbd set_features on infernalis->jewel upgrade
- 01:34 PM Bug #15224 (Fix Under Review): EINVAL on test_cls_rbd set_features on infernalis->jewel upgrade
- *PR*: https://github.com/ceph/ceph/pull/8240
- 01:16 PM Bug #15224 (In Progress): EINVAL on test_cls_rbd set_features on infernalis->jewel upgrade
- 11:34 AM Bug #15224: EINVAL on test_cls_rbd set_features on infernalis->jewel upgrade
- from infernalis test_cls_rbd.cc:...
- 11:25 AM Bug #15224 (Resolved): EINVAL on test_cls_rbd set_features on infernalis->jewel upgrade
- ...
- 03:05 PM Bug #15202 (Resolved): rbd bench-write crashes at end with journalling turned on.
- 02:33 PM Bug #15225: Linking to -lrbd causes process startup times to balloon
- I can't get Ceph to compile at the moment. Seems to break with GCC 6.0. Anyway, I wrote the attached, lightly teste...
- 02:12 PM Bug #15225: Linking to -lrbd causes process startup times to balloon
- Attaching perf output from the original bug report. This shows the perf output of the null program linked to librbd.
- 01:42 PM Bug #15225: Linking to -lrbd causes process startup times to balloon
- @Haomai, it appears that Cycles is only used in a couple test cases. Can we explicitly enable Cycles only within the...
- 01:06 PM Bug #15225: Linking to -lrbd causes process startup times to balloon
- Original source: https://bugzilla.redhat.com/show_bug.cgi?id=1319483
- 01:04 PM Bug #15225 (Resolved): Linking to -lrbd causes process startup times to balloon
- Take a trivial program:
$ cat test.c
#include <stdlib.h>
int main () { exit (0); }
and compare the sta... - 01:56 PM Subtask #15144: rbd CLI to retrieve rbd mirror state for a pool / specific image
- Perhaps the per-image status could just be included within 'rbd status' if mirroring is enabled.
03/20/2016
- 03:13 PM Bug #15220 (Can't reproduce): Deadlock in Objecter::_throttle_op
- This was encountered on an infernalis build:...
03/19/2016
- 10:19 PM Subtask #14415 (Resolved): Pull journal events from remote peer to local journal
- 10:17 PM Subtask #15142 (Resolved): Integrate the rbd mirroring directory within the replay daemon
- 10:03 PM Subtask #15217 (Resolved): Enabling/disabling pool-level mirroring should enable/disable mirrorin...
- When pool-level mirroring is enabled:
1) set mirroring mode to image
2) loop through all images in the pool and... - 10:01 PM Subtask #15143 (Resolved): Enabling/disabling journaling needs to interact with mirroring
- 08:54 PM Documentation #15212 (In Progress): rbdmap manpage is missing
- *PR:* https://github.com/ceph/ceph/pull/8224
- 05:44 AM Documentation #15212 (Resolved): rbdmap manpage is missing
- There does not appear to be any manpage for /usr/bin/rbdmap
- 05:43 AM Bug #14984 (Fix Under Review): rbdmap.service should include RBDMAPFILE environment variable
- 04:44 AM Bug #14984 (In Progress): rbdmap.service should include RBDMAPFILE environment variable
- *PR:* https://github.com/ceph/ceph/pull/8222
03/18/2016
- 11:28 PM Bug #15202 (Fix Under Review): rbd bench-write crashes at end with journalling turned on.
- *PR*: https://github.com/ceph/ceph/pull/8220
Able to reproduce in the presence of socket faults. - 03:46 PM Bug #15202 (Resolved): rbd bench-write crashes at end with journalling turned on.
- Running basic ./vstart.sh -n cluster on laptop. At the end of the ./rbd bench-write test, we hit an assert.
journ... - 07:12 PM Subtask #14981 (Fix Under Review): rbd-mirror daemon systemd / upstart scripts
- *PR*: https://github.com/ceph/ceph/pull/8217
- 12:40 PM Subtask #15143 (Fix Under Review): Enabling/disabling journaling needs to interact with mirroring
- *PR*: https://github.com/ceph/ceph/pull/8204
03/17/2016
- 03:53 PM Bug #14483: Flattening an rbd image with a running Qemu instances causes librbd worker threads to...
- I had a small epiphany about our pool setup today and that might be something that is the cause for this: we're runni...
03/16/2016
- 10:59 PM Documentation #15041 (Resolved): Write RBD image mirroring documentation
- 06:18 PM Documentation #15041: Write RBD image mirroring documentation
- *PR*: https://github.com/ceph/ceph/pull/8169
- 06:11 PM Documentation #15041 (In Progress): Write RBD image mirroring documentation
- 06:50 PM Bug #15140 (Resolved): librbd: TestJournalEntries races
- Fixed by PR 8132: https://github.com/ceph/ceph/pull/8132/commits/921409f721d43f617a27fc1f447eaba08c36e60c
- 05:26 PM Bug #15150: librbd: AioImageRequestWQ::aio_write triggered helgrind assert
- Makes sense, figured it was some kind of use-after-free.
- 03:53 PM Bug #15150: librbd: AioImageRequestWQ::aio_write triggered helgrind assert
- This is that fun issue where if a spin lock isn't properly destroyed and later a rwlock is placed in the same memory ...
- 03:08 PM Subtask #15142 (Fix Under Review): Integrate the rbd mirroring directory within the replay daemon
- *PR*: https://github.com/ceph/ceph/pull/8162
- 02:39 AM Subtask #15141 (Resolved): Mirroring API + rbd CLI updates for image promotion/demotion
03/15/2016
- 11:41 PM Bug #15150 (Duplicate): librbd: AioImageRequestWQ::aio_write triggered helgrind assert
- http://teuthology.ovh.sepia.ceph.com/teuthology/joshd-2016-03-15_20:25:10-rbd-master---basic-openstack/16261/teutholo...
- 08:41 PM Subtask #15141 (Fix Under Review): Mirroring API + rbd CLI updates for image promotion/demotion
- *PR*: https://github.com/ceph/ceph/pull/8138
- 05:05 PM Subtask #15141 (In Progress): Mirroring API + rbd CLI updates for image promotion/demotion
- 04:13 PM Subtask #15141 (Resolved): Mirroring API + rbd CLI updates for image promotion/demotion
- ...
- 05:07 PM Subtask #14420: New RBD notification pool object for recording mirroring errors
- See #15144 for a related task
- 05:06 PM Subtask #14420: New RBD notification pool object for recording mirroring errors
- We should also use this object to report the current status of an image's replication (e.g. is a sync is in-progress,...
- 05:01 PM Subtask #15144 (Resolved): rbd CLI to retrieve rbd mirror state for a pool / specific image
- ...
- 04:36 PM Bug #15127: fsx tests taking too long and possibly stuck
- Jason,
quite a few tests failed in this run, I suspect bad jewel sha as well, As you mentioned this run just ended... - 01:49 PM Bug #15127: fsx tests taking too long and possibly stuck
- @Vasu, I re-ran the test with the same seed value and was unable to reproduce a hang. Can you please re-test and if ...
- 01:20 PM Bug #15127 (Need More Info): fsx tests taking too long and possibly stuck
- @Vasu, do you have any of the node logs? It appears the test was hard-killed.
- 04:14 AM Bug #15127 (Closed): fsx tests taking too long and possibly stuck
- I have noticed in the rbd suite, that fsx tests are taking just too long and they might be stuck, I am seeing
the s... - 04:19 PM Subtask #15143 (Resolved): Enabling/disabling journaling needs to interact with mirroring
- If the pool mirroring state is set to pool-level and the journaling feature is enabled (dynamically or during image c...
- 04:16 PM Subtask #15142 (Resolved): Integrate the rbd mirroring directory within the replay daemon
- The current pool watcher lists all images in a pool and attempts to replicate them. Instead, it should use the RBD m...
- 04:13 PM Subtask #14413 (Resolved): Pull full image from remote peer when out-of-sync
- 04:13 PM Subtask #15109 (Resolved): Integrate image sync process within rbd-mirror image replayer
- 04:12 PM Subtask #13296 (Resolved): Mirroring API + rbd CLI updates for images
- 04:11 PM Subtask #14673 (Resolved): Asynchronously open and close image replayers
- *PR*: https://github.com/ceph/ceph/pull/7944
- 03:29 PM Bug #15140 (Resolved): librbd: TestJournalEntries races
- http://teuthology.ovh.sepia.ceph.com/teuthology/joshd-2016-03-15_06:51:24-rbd-master---basic-openstack/16163/teutholo...
- 06:23 AM Backport #15129 (Resolved): hammer: Protect against excessively large object map sizes
- https://github.com/ceph/ceph/pull/8401
- 06:23 AM Backport #15128 (Rejected): infernalis: Protect against excessively large object map sizes
- 01:05 AM Bug #15101 (Resolved): librbd: remove_snap TimeOut failure
03/14/2016
- 10:46 PM Bug #15121 (Pending Backport): Protect against excessively large object map sizes
- 05:59 PM Bug #15121 (Fix Under Review): Protect against excessively large object map sizes
- *PR*: https://github.com/ceph/ceph/pull/8099
- 05:54 PM Bug #15121 (Resolved): Protect against excessively large object map sizes
- For example, creating a 1 exabyte RBD image w/ object map enabled would require 64GB of RAM to store.
- 09:45 PM Bug #15078 (Resolved): client upgrade(osd/mon: hammer, client: jewel) 1 test failure TestLibRBD.T...
- 09:44 PM Bug #15092 (Resolved): "rbd: image creation failed" in upgrade:client-upgrade-jewel-distro-basic-vps
- 09:44 PM Bug #15101 (Fix Under Review): librbd: remove_snap TimeOut failure
- *PR*: https://github.com/ceph/ceph/pull/8102
- 09:43 PM Bug #15103 (Resolved): librbd: read_flags test fails to find balance_reads flag when exporting sn...
- *PR*: https://github.com/ceph/ceph/pull/8104
- 12:55 PM Bug #15115 (Duplicate): rbd journal reset leaves journal in inconsistent state
- It needs to allocate a tag so that acquiring the exclusive lock will properly function.
- 02:27 AM Subtask #15109 (Fix Under Review): Integrate image sync process within rbd-mirror image replayer
- *PR*: https://github.com/ceph/ceph/pull/8079
- 02:27 AM Subtask #15110 (Resolved): Image sync should sync full snapshot state
- Currently, image sync doesn't handle resized, protected, non-flattened snapshots.
03/13/2016
- 08:33 PM Bug #15078 (Fix Under Review): client upgrade(osd/mon: hammer, client: jewel) 1 test failure Test...
- *PR*: https://github.com/ceph/ceph-qa-suite/pull/871
- 08:20 PM Bug #15076 (Need More Info): client upgrade(osd: firefly, client: jewel) rbd import_export firefl...
- Is this a valid upgrade? EOL Firefly backends with Jewel clients?
- 08:18 PM Bug #15092 (Fix Under Review): "rbd: image creation failed" in upgrade:client-upgrade-jewel-distr...
- *PR*: https://github.com/ceph/ceph-qa-suite/pull/871
- 07:58 PM Subtask #15109 (Resolved): Integrate image sync process within rbd-mirror image replayer
- 07:58 PM Subtask #15108 (Resolved): Periodically update the sync point object number during sync
- This will allow an interrupted image sync to restart from the (near) last synced object within the image.
- 03:49 AM Subtask #14413 (Fix Under Review): Pull full image from remote peer when out-of-sync
- *PR*: https://github.com/ceph/ceph/pull/7979
03/12/2016
- 01:54 AM Bug #15104 (Resolved): qa: verify_pool.sh: syntax error
- 01:09 AM Bug #15104 (Fix Under Review): qa: verify_pool.sh: syntax error
- *jewel PR*: https://github.com/ceph/ceph/pull/8068
- 12:56 AM Bug #15104 (In Progress): qa: verify_pool.sh: syntax error
- https://wiki.ubuntu.com/DashAsBinSh#function
- 12:32 AM Bug #15104: qa: verify_pool.sh: syntax error
- guessing this is a bashism, since /bin/sh is dash where this failed
- 12:29 AM Bug #15104 (Resolved): qa: verify_pool.sh: syntax error
- ...
- 12:26 AM Bug #15103 (Resolved): librbd: read_flags test fails to find balance_reads flag when exporting sn...
- http://qa-proxy.ceph.com/teuthology/joshd-2016-03-11_15:03:28-rbd-wip-josh-testing---basic-multi/54643/teuthology.log
- 12:22 AM Bug #15102 (Resolved): librbd: exclusive lock AcquireRequest failed assert m_image_ctx.journal ==...
- http://qa-proxy.ceph.com/teuthology/joshd-2016-03-11_15:03:28-rbd-wip-josh-testing---basic-multi/54614/teuthology.log...
- 12:18 AM Bug #15101 (Resolved): librbd: remove_snap TimeOut failure
- http://qa-proxy.ceph.com/teuthology/joshd-2016-03-11_15:03:28-rbd-wip-josh-testing---basic-multi/54607/teuthology.log...
03/11/2016
- 11:29 PM Bug #15097: journal.sh fails when removing image
- same issue in the new rbd_mirror_image_replay workunit: http://qa-proxy.ceph.com/teuthology/joshd-2016-03-11_15:03:28...
- 11:23 PM Bug #15097 (Resolved): journal.sh fails when removing image
- Occurs on master as well as wip-josh-testing. From http://qa-proxy.ceph.com/teuthology/joshd-2016-03-11_15:03:28-rbd-...
- 10:09 PM Bug #15092: "rbd: image creation failed" in upgrade:client-upgrade-jewel-distro-basic-vps
- We'll need to adjust the client-upgrade tests to not use new features.
- 10:06 PM Bug #15092 (Resolved): "rbd: image creation failed" in upgrade:client-upgrade-jewel-distro-basic-vps
- Run: http://pulpito.ceph.com/teuthology-2016-03-11_10:42:14-upgrade:client-upgrade-jewel-distro-basic-vps/
Job: 5326... - 03:29 PM Bug #15078 (Resolved): client upgrade(osd/mon: hammer, client: jewel) 1 test failure TestLibRBD.T...
- osd/mon: in hammer, client on jewel
out of 43, 1 test failed: TestLibRBD.TestCreateLsDeletePP
http://magna002.cep... - 03:16 PM Bug #15076 (Won't Fix): client upgrade(osd: firefly, client: jewel) rbd import_export firefly wor...
- OSD is firefly and Client is jewel, seen failures during rbd delete and other areas, workunit is from firefly
http... - 11:04 AM Bug #14483: Flattening an rbd image with a running Qemu instances causes librbd worker threads to...
- Hm. I think this is still an issue. I updated everything to 0.94.6 and this still happens. What's the most helpful th...
- 04:42 AM Backport #14824: hammer: rbd and pool quota do not go well together
- Moving to Ceph for cross reference purposes
03/10/2016
- 11:55 AM Subtask #13296: Mirroring API + rbd CLI updates for images
- Jason Dillaman wrote:
>
> Also add journal details/mirroring status support to 'rbd info' and 'rbd status'
What... - 03:04 AM Documentation #15041 (Resolved): Write RBD image mirroring documentation
- 02:53 AM Bug #14908 (Resolved): Journal replay needs to conditionally refresh the image between events
- 02:48 AM Backport #15032 (Fix Under Review): infernalis: QEMU VM hangs talking to RBD via librbd
- 02:48 AM Backport #15033 (Fix Under Review): hammer: QEMU VM hangs talking to RBD via librbd
- 01:32 AM Subtask #14663 (Resolved): Integrate librbd with journal tag allocation
- 01:32 AM Subtask #14869 (Resolved): journal library should re-use thread pool and timer
03/09/2016
- 11:10 PM Backport #15032 (In Progress): infernalis: QEMU VM hangs talking to RBD via librbd
- 09:52 PM Backport #15032 (Resolved): infernalis: QEMU VM hangs talking to RBD via librbd
- https://github.com/ceph/ceph/pull/8010
- 11:09 PM Backport #15033 (In Progress): hammer: QEMU VM hangs talking to RBD via librbd
- 09:52 PM Backport #15033 (Resolved): hammer: QEMU VM hangs talking to RBD via librbd
- https://github.com/ceph/ceph/pull/8011
- 10:37 PM Bug #14988: QEMU VM hangs talking to RBD via librbd
- *master PR*: https://github.com/ceph/ceph/pull/8009 (reproducer -- confirms not an issue in Jewel)
- 09:52 PM Bug #14988 (Pending Backport): QEMU VM hangs talking to RBD via librbd
- Note that there is no master PR for this issue. Jason is going to do the fix in infernalis and then backport it from ...
- 09:46 PM Bug #14988: QEMU VM hangs talking to RBD via librbd
- Shouldn't be an issue in Jewel due to new asynchronous internals
- 09:26 PM Bug #14988 (In Progress): QEMU VM hangs talking to RBD via librbd
- 09:13 PM Bug #14988: QEMU VM hangs talking to RBD via librbd
- If an AIO request results in an image refresh due to a new snapshot creation, the cache will be flushed. When this o...
- 10:02 PM Bug #14789 (Resolved): Truncate of non-existent object results in object map flagged as exists
- 09:55 PM Bug #15034 (Resolved): Possible inconsistent IO when using configured for multiple op threads
- When 'rbd_op_threads' is set to a value higher than 1 (defaults to 1), it's quite possible for an aio flush op to com...
- 06:11 PM Bug #13122 (Resolved): rbd: stripingv2 feature bit not set when unnecessary for striping params
- This was fixed sometime in the recent rbd cli refactor.
- 04:56 PM Subtask #15029 (Resolved): Use watch/notify to alert to specific changes in the rbd_mirroring object
- This will eliminate to constantly poll the object for updates -- instead, it would only need to pull the object after...
- 04:32 PM Bug #15028 (Resolved): Deep-flatten incorrectly updates fast-diff stats
- Flattening a clone of an empty image with fast-diff and deep-flatten enabled results in all objects being flagged as ...
- 03:24 PM Fix #15026 (New): use derr instead of cerr in rbd cli actions
- ...
- 09:14 AM Bug #15007: Cannot rebuild object map in in-flight IO
- Due to the upgrade to infernalis it would be fine to get the ability for live enabling the object map. Jonas +1
- 08:01 AM Bug #15007: Cannot rebuild object map in in-flight IO
- Jason Dillaman wrote:
> > Object Map Rebuild: 99% complete...failed.
> > rbd: rebuilding object map failed: (16) De... - 02:09 AM Fix #3588 (Resolved): rbd.py's clone should take stripe parms, call rbd_clone2
- Fixed as part of the new image create api use in commit:c3be44ed8f9d99d7257156f2e0bf7ef6ea1b5761
03/08/2016
- 06:21 PM Bug #14908 (Fix Under Review): Journal replay needs to conditionally refresh the image between ev...
- *PR*: https://github.com/ceph/ceph/pull/7978
- 04:52 PM Bug #14908 (In Progress): Journal replay needs to conditionally refresh the image between events
- 04:58 PM Bug #14986 (Closed): rbd export/export-diff with needs to protect against unintended journal replay
- The journal actually won't be replayed since export/export-diff open the image read-only. This prevents the journal ...
- 04:45 PM Bug #14953 (Rejected): can add 'rbd lock' to format 1 images
- 04:43 PM Bug #14953: can add 'rbd lock' to format 1 images
- @Vasu, the "rbd lock"-related commands are to be considered as advisory locks. There is no enforcement within librbd...
- 04:41 PM Bug #14988 (Need More Info): QEMU VM hangs talking to RBD via librbd
- 04:19 PM Bug #14780 (Resolved): librbd: TaskFinisher lifetime no longer matches ImageWatcher
- 02:50 PM Bug #15007 (Resolved): Cannot rebuild object map in in-flight IO
- > Object Map Rebuild: 99% complete...failed.
> rbd: rebuilding object map failed: (16) Device or resource busy
03/07/2016
- 04:52 PM Documentation #15000 (Resolved): Need better documentation to describe RBD image features
- 01:18 PM Bug #14988: QEMU VM hangs talking to RBD via librbd
- @Roy,
From the backtrace, Ceph is waiting for a cache flush to complete. The thread responsible for handling cac...
03/06/2016
- 08:11 PM Bug #14988: QEMU VM hangs talking to RBD via librbd
- ...
- 06:28 PM Bug #14988: QEMU VM hangs talking to RBD via librbd
- @Roy: Upgrading is recommended anyway, but before you take that step you can try setting "rbd_non_blocking_aio" to fa...
- 06:01 PM Bug #14988: QEMU VM hangs talking to RBD via librbd
- I can try with a newer Ceph, but #13726 seems to be dependant upon RBD cache being disabled but it should be enabled ...
03/05/2016
- 10:49 PM Bug #14988: QEMU VM hangs talking to RBD via librbd
- @Roy: Can you reproduce this on 0.94.6? If not, it is probably http://tracker.ceph.com/issues/13726
- 08:44 PM Bug #14988 (Resolved): QEMU VM hangs talking to RBD via librbd
- I'm having a repeatable hang in QEMU (v2.4.1) talking to a Ceph (v0.95.4) RBD via librbd.
I've acquired a core fil... - 12:32 AM Bug #14986 (Closed): rbd export/export-diff with needs to protect against unintended journal replay
- If journaling is enabled on an image, reading from the image HEAD will result in a journal replay. If the image was ...
03/04/2016
- 09:33 PM Bug #14984 (Resolved): rbdmap.service should include RBDMAPFILE environment variable
- /usr/bin/rbdmap requires the RBDMAPFILE variable to be set. I've worked around this on my machines by adding Environm...
- 03:28 PM Subtask #14981 (Resolved): rbd-mirror daemon systemd / upstart scripts
03/03/2016
- 03:48 PM Subtask #14869 (Fix Under Review): journal library should re-use thread pool and timer
- *PR*: https://github.com/ceph/ceph/pull/7906
- 09:17 AM Subtask #13296 (In Progress): Mirroring API + rbd CLI updates for images
- 01:34 AM Subtask #13296: Mirroring API + rbd CLI updates for images
- Correct, the description is from an old design. We are using http://pad.ceph.com/p/rbd_mirror_daemon to track the cu...
Also available in: Atom