Activity
From 06/16/2016 to 07/15/2016
07/15/2016
- 06:10 PM Documentation #16704 (Duplicate): RBD replay needs to document new configuration option
- The "rbd_tracing" configuration option needs to be set to true to enable tracing.
- 09:36 AM Backport #16701 (Resolved): jewel: rbd-mirror: image sync throttle needs to use pool id + image i...
- https://github.com/ceph/ceph/pull/10678
07/14/2016
- 09:38 PM Bug #16689 (Resolved): mkfs.xfs slow performance with discards and object map
- Examples:
object-map enabled:
time mkfs.xfs -s size=4096 -f /dev/sda
real 9m10.882s
user 0m0.000s
sys 0m0.012s... - 02:41 AM Bug #16623: segfault in unittest_rbd_mirror
- Always some problems when on the bleeding edge.
- 01:42 AM Bug #16623 (Resolved): segfault in unittest_rbd_mirror
- Damn, I thought about a problem in the gmock/gtest code but dismissed it as "unlikely"
Sure enough, it works fine ...
07/13/2016
- 04:43 PM Bug #16536 (Pending Backport): rbd-mirror: image sync throttle needs to use pool id + image id to...
- 03:16 PM Bug #16623: segfault in unittest_rbd_mirror
- @Brad: Josh just merged the upgraded googletest/googlemock changes. It works for me now, but can you pull the latest ...
- 03:05 PM Bug #16623: segfault in unittest_rbd_mirror
- Work for switching to the newer googletest framework was already in-progress:
*PR*: https://github.com/ceph/ceph/p... - 02:58 PM Bug #16623: segfault in unittest_rbd_mirror
- Using the latest gmock/gtest environment appears to fix the issue.
- 02:45 PM Bug #16623: segfault in unittest_rbd_mirror
- Yup -- able to instantly reproduce under F24.
- 01:02 PM Bug #16623: segfault in unittest_rbd_mirror
- Turns out that I am on F23 -- I thought I had already upgraded. I found a similar bug report where GCC 6 + F24 resul...
- 10:07 AM Bug #16623: segfault in unittest_rbd_mirror
- I spent a lot of time looking at this today but I couldn't pin it down but I do have some findings.
The following ... - 02:45 AM Bug #16623: segfault in unittest_rbd_mirror
- Hi @Jason,
Following our discussion on IRC I did the following.
# git clone --recursive https://github.com/ceph...
07/12/2016
- 11:01 PM Bug #16623: segfault in unittest_rbd_mirror
- @jason yes, I can
- 01:13 PM Bug #16623 (Need More Info): segfault in unittest_rbd_mirror
- @Brad: are you able to repeat this issue?
- 03:01 PM Bug #16538 (In Progress): rbd-mirror: image deleter should use pool id + global image uuid for key
- 02:33 PM Backport #16658 (Resolved): jewel: rbd-mirror: gracefully handle being blacklisted
- https://github.com/ceph/ceph/pull/10684
- 04:12 AM Bug #16536 (Fix Under Review): rbd-mirror: image sync throttle needs to use pool id + image id to...
- *PR*: https://github.com/ceph/ceph/pull/10254
- 01:16 AM Bug #16536 (In Progress): rbd-mirror: image sync throttle needs to use pool id + image id to form...
- 03:10 AM Bug #16654: the option 'rbd_cache_writethrough_until_flush=true' dosn't work
- Sorry, the correct test data is :
1. Test in the VM with 'rbd_cache_writethrough_until_flush=false' , the randwrit... - 03:04 AM Bug #16654 (Resolved): the option 'rbd_cache_writethrough_until_flush=true' dosn't work
- Env: my ceph cluster with 252 SATA osds. the test VM kernerl version is ' 3.13.0-86-generic'
test cmd: sudo fio -...
07/11/2016
- 08:48 PM Bug #16622 (Fix Under Review): rbd-mirror: snap rename does not correctly replicate
- *PR*: https://github.com/ceph/ceph/pull/10249
07/10/2016
- 05:36 AM Bug #16349: rbd-mirror: gracefully handle being blacklisted
- -Note: same master PR as #16622- nevermind
07/09/2016
- 11:43 PM Bug #15034: Possible inconsistent IO when using configured for multiple op threads
- *PR*: https://github.com/ceph/ceph/pull/9023 -- still requires re-enabling the librbd option.
- 11:40 PM Bug #16349 (Pending Backport): rbd-mirror: gracefully handle being blacklisted
- *PR*: PR: https://github.com/ceph/ceph/pull/9970
- 11:40 PM Bug #16622 (In Progress): rbd-mirror: snap rename does not correctly replicate
- 11:39 PM Bug #16622 (Pending Backport): rbd-mirror: snap rename does not correctly replicate
- 11:37 PM Bug #4446 (Closed): librbd: crash from opensolaris vm
- 2 years since last update -- closing.
07/08/2016
- 04:19 AM Bug #16623: segfault in unittest_rbd_mirror
- jason, mind taking a look?
- 04:12 AM Bug #16623 (Resolved): segfault in unittest_rbd_mirror
- @Core was generated by `/home/brad/working/src/ceph/build/bin/unittest_rbd_mirror'.
Program terminated with signal S...
07/07/2016
- 10:25 PM Bug #16622 (Resolved): rbd-mirror: snap rename does not correctly replicate
- 03:16 AM Bug #16608 (Resolved): bashism in src/rbdmap
- the shebang line reads @#!/bin/sh@@
while we are using array in this script, ...
07/06/2016
- 03:15 PM Bug #15259 (In Progress): performance: journaling results in 4X slowdown when writes are not bloc...
- 09:43 AM Backport #16601 (In Progress): jewel: librbd: fix missing return statement if failed to get mirro...
- 09:39 AM Backport #16601 (Resolved): jewel: librbd: fix missing return statement if failed to get mirror i...
- https://github.com/ceph/ceph/pull/10144
- 09:39 AM Bug #16600 (Resolved): librbd: fix missing return statement if failed to get mirror image state
- https://github.com/ceph/ceph/pull/10136
07/05/2016
- 06:20 PM Backport #16593 (Resolved): jewel: FAILED assert(object_no < m_object_map.size())
- https://github.com/ceph/ceph/pull/10647
- 08:45 AM Bug #16561 (Pending Backport): FAILED assert(object_no < m_object_map.size())
07/04/2016
- 07:16 PM Bug #16449 (Fix Under Review): Prevent the creation of a clone from a non-primary mirrored image
- PR: https://github.com/ceph/ceph/pull/10123
- 10:28 AM Bug #16449 (In Progress): Prevent the creation of a clone from a non-primary mirrored image
- 05:20 PM Bug #16386 (Fix Under Review): Discard hangs when 'rbd_skip_partial_discard' is enabled
- PR: https://github.com/ceph/ceph/pull/10060
07/03/2016
- 11:34 AM Backport #16576 (Resolved): jewel: rbd-mirror: FAILED assert(m_local_image_ctx->object_map != nul...
- https://github.com/ceph/ceph/pull/10646
07/01/2016
- 12:29 PM Cleanup #16539 (Resolved): rbd-mirror: remove ceph_test_rbd_mirror_image_replay test case
- 06:10 AM Cleanup #16539 (Fix Under Review): rbd-mirror: remove ceph_test_rbd_mirror_image_replay test case
- PR: https://github.com/ceph/ceph/pull/10083
QA PR: https://github.com/ceph/ceph-qa-suite/pull/1072 - 06:08 AM Cleanup #16539: rbd-mirror: remove ceph_test_rbd_mirror_image_replay test case
- Nathan, it is not related to #16529
- 12:12 PM Feature #16571 (Resolved): Discard journal event should record state of rbd_skip_partial_discard ...
- When RBD mirroring verification is added, if two clusters have different settings for this option, the images will di...
- 11:19 AM Bug #16558 (Pending Backport): rbd-mirror: FAILED assert(m_local_image_ctx->object_map != nullptr)"
06/30/2016
- 10:17 PM Bug #16563 (Duplicate): rbd-mirror: missing op finish event should be treated as an error
- Issue fixed under #16362
- 07:42 PM Bug #16563 (New): rbd-mirror: missing op finish event should be treated as an error
- 07:29 PM Bug #16563 (Duplicate): rbd-mirror: missing op finish event should be treated as an error
- If an op doesn't successfully complete and record its success in the journal via an OpFinishEvent, treat the non-prim...
- 07:26 PM Bug #16561 (Fix Under Review): FAILED assert(object_no < m_object_map.size())
- *PR*: https://github.com/ceph/ceph/pull/10072
- 05:52 PM Bug #16561 (Resolved): FAILED assert(object_no < m_object_map.size())
- Steps to reproduce:
1. clone a large image
2. create a snapshot on the clone
3. shrink the clone twice
The semi... - 02:45 PM Bug #16558 (Fix Under Review): rbd-mirror: FAILED assert(m_local_image_ctx->object_map != nullptr)"
- *PR*: https://github.com/ceph/ceph/pull/10065
- 02:20 PM Bug #16558 (Resolved): rbd-mirror: FAILED assert(m_local_image_ctx->object_map != nullptr)"
- The exclusive lock for the local image was lost due to cluster starvation during image sync. The daemon should gracef...
- 02:19 PM Feature #16557 (Resolved): Update on-disk exclusive lock tag when image watcher is lost
- Under heavy-cluster loads, it's quite possible that the watcher on the RBD image header will time-out. If the exclusi...
- 12:52 PM Bug #16555 (Resolved): librbd should permit removal of image being bootstrapped by rbd-mirror
- If an image is being bootstrapped, it implies that the rbd-mirror daemon currently has the image open. The removal AP...
- 08:56 AM Bug #16404 (Resolved): Sporadic test failures when image update notification missed
- 08:56 AM Feature #16197 (Resolved): Improve rbd-mirror test case coverage
- 08:55 AM Bug #16289 (Resolved): "rbd: create error: (38) Function not implemented" in upgrade:client
- 08:00 AM Backport #16512: jewel: rbd-mirror: potential race condition when restarting image replayer
- merge conflict at c97f7245a015dbdda25584134840d023fd65cdd1 from https://github.com/ceph/ceph/pull/9958/commits
- 07:58 AM Backport #16511: jewel: rbd-mirror: 'wait_for_scheduled_deletion' callback might deadlock
- merge conflict at c136f443366fe804057a9c1f8c01c3f0a33a4d63 from https://github.com/ceph/ceph/pull/9964/commits
- 07:56 AM Backport #16485 (In Progress): jewel: Whitelist EBUSY error from "snap unprotect" for journal replay
- 07:55 AM Backport #16484 (In Progress): jewel: ExclusiveLock object leaked when switching to snapshot
- 07:54 AM Backport #16483 (In Progress): jewel: Close journal and object map before flagging exclusive lock...
- 07:53 AM Backport #16482 (In Progress): jewel: Timeout sending mirroring notification shouldn't result in ...
- 07:52 AM Backport #16460 (In Progress): jewel: Crash when utilizing advisory locking API functions
- 07:50 AM Backport #16459 (In Progress): jewel: rbd-mirror should disable proxied maintenance ops for non-p...
- 07:49 AM Backport #16232 (Resolved): jewel: Improve rbd-mirror test case coverage
- 07:49 AM Backport #16458: jewel: Potential crash during journal::Replay shut down
- merge conflict at 3112a93b49c24f9ae101a7f252c8e708e0d3e260
- 07:32 AM Backport #16438 (In Progress): jewel: Delete image when a resync is requested
- 07:25 AM Backport #16426 (In Progress): jewel: Possible race condition during journal transition from repl...
- 07:23 AM Backport #16425 (In Progress): jewel: rbd-mirror: potential race condition accessing local image ...
- 07:22 AM Backport #16424 (In Progress): jewel: Journal needs to handle duplicate maintenance op tids
- 07:20 AM Backport #16423 (In Progress): jewel: Journal duplicate op detection can cause lockdep error
- 07:19 AM Backport #16373: jewel: rbd-mirror: gracefully handle missing sync point snapshots
- https://github.com/ceph/ceph/pull/9730/commits/d16698f96c65b9627cc1f64ef80b7f1e39d69d45 conflicts
- 07:16 AM Backport #16371 (In Progress): jewel: rbd-mirror: ensure replay status formatter has completed be...
- 07:16 AM Cleanup #16539: rbd-mirror: remove ceph_test_rbd_mirror_image_replay test case
- Is this related to #16529 ?
- 07:15 AM Backport #16372 (In Progress): jewel: Unable to disable journaling feature if in unexpected mirro...
- 07:13 AM Backport #16315 (In Progress): jewel: When journaling is enabled, a flush request shouldn't flush...
- 06:50 AM Bug #16386 (In Progress): Discard hangs when 'rbd_skip_partial_discard' is enabled
- 12:53 AM Subtask #16545 (New): rbd-mirror multi-peer: register local image as client of remote peer image ...
- If a new peer image is discovered after the ImageReplayer state machine as started the bootstrap stage, the local ima...
06/29/2016
- 11:44 PM Subtask #16544 (New): rbd-mirror multi-peer: image deleter should only schedule deletion if last ...
- The image deleter currently takes a shortcut since it only has to handle a single peer. With multiple peers, the imag...
- 11:42 PM Subtask #16543 (New): rbd-mirror multi-peer: ImageReplayer should restart when a new mirror peer ...
- This condition would indicate a failover to a new peer. By restarting the state machine, it would re-invoke the boots...
- 11:39 PM Subtask #16542 (New): rbd-mirror multi-peer: bootstrap state machine should support multiple remo...
- In the case where the local image doesn't exist or is not primary and its last journal tag isn't linked to a specific...
- 11:37 PM Subtask #16541 (New): rbd-mirror multi-peer: ImageReplayer should support multiple registered rem...
- No longer pass the remote librados connection, remote mirror uuid, remote pool id, and remote image id via the constr...
- 11:32 PM Feature #16540 (New): rbd-mirror: support multiple peers per pool in mesh topology
- Update rbd-mirror to support transitioning the primary status between N peer clusters.
- 10:03 PM Cleanup #16539 (Resolved): rbd-mirror: remove ceph_test_rbd_mirror_image_replay test case
- It is essentially duplicated by ceph_test_rbd_mirror + the rbd-mirror workunits. Its special hooks into ImageReplayer...
- 09:57 PM Bug #16538 (Resolved): rbd-mirror: image deleter should use pool id + global image uuid for key
- Waiting for a deletion or canceling pending waiters should use the pool id + global image uuid as the key for referen...
- 09:50 PM Bug #16536 (Resolved): rbd-mirror: image sync throttle needs to use pool id + image id to form un...
- There is a possibility that the image id will collide between pools, so it should also use the local pool id to ensur...
- 04:52 PM Bug #16529 (Resolved): "[ FAILED ] TestClsRbd.mirror_image" in upgrade:jewel-x-master-distro-ba...
- Run: http://pulpito.ceph.com/teuthology-2016-06-29_04:20:02-upgrade:jewel-x-master-distro-basic-vps/
Jobs: 283220, 2... - 09:05 AM Backport #16486 (In Progress): jewel: Object map/fast-diff invalidated if journal replays the sam...
- 08:59 AM Backport #16513: jewel: rbd-mirror: image-replayer: segfault when removing resync listener
- It does not apply cleanly, probably needs to be clustered with other replay related backports.
- 06:37 AM Backport #16513 (Resolved): jewel: rbd-mirror: image-replayer: segfault when removing resync list...
- https://github.com/ceph/ceph/pull/10678
- 08:55 AM Backport #16514 (In Progress): jewel: Image removal doesn't necessarily clean up all rbd_mirrorin...
- 06:37 AM Backport #16514 (Resolved): jewel: Image removal doesn't necessarily clean up all rbd_mirroring e...
- https://github.com/ceph/ceph/pull/10009
- 08:44 AM Backport #16324 (Resolved): jewel: rbd: create error: (38) Function not implemented in upgrade:cl...
- 07:38 AM Backport #16518 (In Progress): jewel: TaskFinisher: cancel all tasks wait until finisher done
- 07:21 AM Backport #16518 (Resolved): jewel: TaskFinisher: cancel all tasks wait until finisher done
- https://github.com/ceph/ceph/pull/9752
- 07:37 AM Backport #16520 (In Progress): jewel: librbd: potential use after free on refresh error
- 07:35 AM Backport #16520 (Resolved): jewel: librbd: potential use after free on refresh error
- https://github.com/ceph/ceph/pull/9952
- 07:34 AM Bug #16519 (Resolved): librbd: potential use after free on refresh error
- https://github.com/ceph/ceph/pull/9949
- 07:20 AM Bug #16517 (Resolved): TaskFinisher: cancel all tasks wait until finisher done
- https://github.com/ceph/ceph/pull/9682
- 06:37 AM Backport #16512 (Resolved): jewel: rbd-mirror: potential race condition when restarting image rep...
- https://github.com/ceph/ceph/pull/10684
- 06:37 AM Backport #16511 (Resolved): jewel: rbd-mirror: 'wait_for_scheduled_deletion' callback might deadlock
- https://github.com/ceph/ceph/pull/10678
06/28/2016
- 07:54 PM Bug #16269 (Resolved): "AssertionError" in upgrade:client-upgrade-jewel-distro-basic-smithi
- Fix will be included in v10.2.3 (or anything against the current jewel branch HEAD)
- 07:46 PM Bug #16269: "AssertionError" in upgrade:client-upgrade-jewel-distro-basic-smithi
- Run: http://pulpito.ceph.com/teuthology-2016-06-26_02:45:02-upgrade:client-upgrade-jewel-distro-basic-smithi/
Jobs: ... - 07:53 PM Backport #16422 (Resolved): jewel: Sporadic test failures when image update notification missed
- 06:14 PM Bug #16489 (Pending Backport): rbd-mirror: potential race condition when restarting image replayer
- 06:12 PM Bug #16471 (Pending Backport): Image removal doesn't necessarily clean up all rbd_mirroring entries
- 06:11 PM Bug #16491 (Pending Backport): rbd-mirror: 'wait_for_scheduled_deletion' callback might deadlock
- 06:57 AM Bug #16502 (Closed): fio ended up with soft lockup - CPU#1 stuck for 22s!
- *Ceph Client*
_//DISTRO_
Ubuntu 14.04.4 LTS - trusty
_//KERNEL_
4.2.0-36-generic #42~14.04.1-Ubuntu
_//PACKA...
06/27/2016
- 04:24 PM Bug #16491 (Fix Under Review): rbd-mirror: 'wait_for_scheduled_deletion' callback might deadlock
- *PR*: https://github.com/ceph/ceph/pull/9964
- 01:12 PM Bug #16491 (Resolved): rbd-mirror: 'wait_for_scheduled_deletion' callback might deadlock
- If there is a race and there is no scheduled deletion, it's possible for the callback to complete within the caller's...
- 04:14 PM Bug #16488 (Pending Backport): rbd-mirror: image-replayer: segfault when removing resync listener
- 10:22 AM Bug #16488 (Fix Under Review): rbd-mirror: image-replayer: segfault when removing resync listener
- PR: https://github.com/ceph/ceph/pull/9945
- 09:28 AM Bug #16488 (Resolved): rbd-mirror: image-replayer: segfault when removing resync listener
- Transcript from Mykola Golub:...
- 03:51 PM Backport #15360 (Resolved): hammer: Linking to -lrbd causes process startup times to balloon
- 01:09 PM Bug #16489 (Fix Under Review): rbd-mirror: potential race condition when restarting image replayer
- *PR*: https://github.com/ceph/ceph/pull/9958
- 12:31 PM Bug #16489 (Resolved): rbd-mirror: potential race condition when restarting image replayer
- "ImageReplayer::handle_shut_down" advances the state machine before closing the local and remote IoCtxs. If "Replayer...
- 07:56 AM Backport #16486 (Resolved): jewel: Object map/fast-diff invalidated if journal replays the same s...
- https://github.com/ceph/ceph/pull/10010
- 07:55 AM Backport #16485 (Resolved): jewel: Whitelist EBUSY error from "snap unprotect" for journal replay
- https://github.com/ceph/ceph/pull/10055
- 07:55 AM Backport #16484 (Resolved): jewel: ExclusiveLock object leaked when switching to snapshot
- https://github.com/ceph/ceph/pull/10054
- 07:55 AM Backport #16483 (Resolved): jewel: Close journal and object map before flagging exclusive lock as...
- https://github.com/ceph/ceph/pull/10053
- 07:55 AM Backport #16482 (Resolved): jewel: Timeout sending mirroring notification shouldn't result in fai...
- https://github.com/ceph/ceph/pull/10052
06/25/2016
- 05:01 PM Bug #16470 (Pending Backport): Timeout sending mirroring notification shouldn't result in failure
- 12:31 PM Bug #16478 (Resolved): Non-primary image is recording journal events during image sync
- When the snapshot state is being synchronized from the primary to the non-primary, these events are being incorrectly...
- 12:26 PM Bug #16473 (In Progress): Demotion/promotion results in the image syncing again from the beginning
06/24/2016
- 07:25 PM Bug #16450 (Pending Backport): Close journal and object map before flagging exclusive lock as rel...
- 07:24 PM Bug #16350 (Pending Backport): Object map/fast-diff invalidated if journal replays the same snap ...
- 07:23 PM Bug #16446 (Pending Backport): ExclusiveLock object leaked when switching to snapshot
- 07:23 PM Bug #16445 (Pending Backport): Whitelist EBUSY error from "snap unprotect" for journal replay
- 06:13 PM Bug #16473 (Resolved): Demotion/promotion results in the image syncing again from the beginning
- Demote the primary image and promote the original non-primary image. The rbd-mirror for the newly demoted non-primar...
- 02:55 PM Bug #16471 (Fix Under Review): Image removal doesn't necessarily clean up all rbd_mirroring entries
- *PR*: https://github.com/ceph/ceph/pull/9923
- 02:09 PM Bug #16471 (Resolved): Image removal doesn't necessarily clean up all rbd_mirroring entries
- If an image was partially created (due to a failure), attempting to remove the image will not clean up its rbd_mirror...
- 02:12 PM Bug #16470 (Fix Under Review): Timeout sending mirroring notification shouldn't result in failure
- *PR*: https://github.com/ceph/ceph/pull/9922
- 02:00 PM Bug #16470 (Resolved): Timeout sending mirroring notification shouldn't result in failure
- Log and ignore any notification failure when sending mirroring status updates:...
- 03:14 AM Cleanup #16465 (Resolved): rbd discard ret value truncated
- rbd discard use 'int' as return type, but 'len' user passed is 'unit64',
in some case, the ret value will be truncat...
06/23/2016
- 07:09 PM Backport #16460 (Resolved): jewel: Crash when utilizing advisory locking API functions
- https://github.com/ceph/ceph/pull/10051
- 07:09 PM Backport #16459 (Resolved): jewel: rbd-mirror should disable proxied maintenance ops for non-prim...
- https://github.com/ceph/ceph/pull/10050
- 07:09 PM Backport #16458 (Resolved): jewel: Potential crash during journal::Replay shut down
- https://github.com/ceph/ceph/pull/10645
- 05:40 PM Bug #16450 (Fix Under Review): Close journal and object map before flagging exclusive lock as rel...
- *PR*: https://github.com/ceph/ceph/pull/9905
- 02:16 PM Bug #16450 (In Progress): Close journal and object map before flagging exclusive lock as released
- 02:16 PM Bug #16450 (Resolved): Close journal and object map before flagging exclusive lock as released
- The journal might have in-flight IO which will check if the image is the exclusive lock owner. Therefore, ensure that...
- 05:28 PM Bug #16364 (Pending Backport): Crash when utilizing advisory locking API functions
- 05:27 PM Bug #16433 (Pending Backport): Potential crash during journal::Replay shut down
- 05:26 PM Bug #16411 (Pending Backport): rbd-mirror should disable proxied maintenance ops for non-primary ...
- 02:28 PM Bug #16350 (Fix Under Review): Object map/fast-diff invalidated if journal replays the same snap ...
- *PR*: https://github.com/ceph/ceph/pull/9899
- 02:25 PM Bug #16350 (In Progress): Object map/fast-diff invalidated if journal replays the same snap remov...
- 02:14 PM Bug #14059 (Resolved): Can't build Ceph with --with-rbd (Cython)
- Jewel doesn't officially support stock CentOS 6 and no known issues with CentOS 7.
- 01:57 PM Bug #16449 (Resolved): Prevent the creation of a clone from a non-primary mirrored image
- 01:30 PM Bug #16446 (Fix Under Review): ExclusiveLock object leaked when switching to snapshot
- *PR*: https://github.com/ceph/ceph/pull/9896
- 01:21 PM Bug #16446 (Resolved): ExclusiveLock object leaked when switching to snapshot
- The exclusive lock is properly shut down but its object is not deleted when switching from image HEAD to a snapshot.
- 12:49 PM Bug #16445 (Fix Under Review): Whitelist EBUSY error from "snap unprotect" for journal replay
- *PR*: https://github.com/ceph/ceph/pull/9895
- 12:26 PM Bug #16445 (Resolved): Whitelist EBUSY error from "snap unprotect" for journal replay
- If the OpFinishEvent's return code is "-EBUSY" for a snap unprotect event, do not attempt to replay the snap unprotec...
- 07:43 AM Backport #16438 (Resolved): jewel: Delete image when a resync is requested
- https://github.com/ceph/ceph/pull/10678
- 12:42 AM Bug #16269 (Fix Under Review): "AssertionError" in upgrade:client-upgrade-jewel-distro-basic-smithi
- 12:40 AM Bug #16269 (In Progress): "AssertionError" in upgrade:client-upgrade-jewel-distro-basic-smithi
- Inadvertently fixed by tracker ticket #16422
- 12:39 AM Backport #16422 (In Progress): jewel: Sporadic test failures when image update notification missed
06/22/2016
- 11:02 PM Bug #15561: RBD image can be listed but not opened
- @Ke Ke: any update or can this be closed?
- 10:31 PM Bug #15220 (Can't reproduce): Deadlock in Objecter::_throttle_op
- Haven't seen this reproduce in several months -- closing for now.
- 10:30 PM Bug #14059 (Need More Info): Can't build Ceph with --with-rbd (Cython)
- @Piotr: is this still an issue for you and the Jewel release?
- 10:27 PM Bug #8385 (Closed): RBD / QEMU Crash: Invalid fastbin entry (free)
- Closing ticket as there have been no similar issues noted against Hammer or later releases.
- 10:22 PM Bug #16364 (Fix Under Review): Crash when utilizing advisory locking API functions
- *PR*: https://github.com/ceph/ceph/pull/9882
- 10:13 PM Bug #16364 (In Progress): Crash when utilizing advisory locking API functions
- 10:12 PM Bug #16433 (Fix Under Review): Potential crash during journal::Replay shut down
- *PR*: https://github.com/ceph/ceph/pull/9881
- 10:02 PM Bug #16433 (Resolved): Potential crash during journal::Replay shut down
- Replay<I>::handle_op_complete shouldn't be holding the mutex when invoking the callback:...
- 10:03 PM Subtask #15670 (Pending Backport): Delete image when a resync is requested
- 09:30 PM Bug #16394 (Need More Info): Ceph RBD
- @Junming: unfortunately, this isn't enough information to be acted upon. What were you doing when this occurred? Can...
- 09:08 PM Backport #16426 (Resolved): jewel: Possible race condition during journal transition from replay ...
- https://github.com/ceph/ceph/pull/10047
- 09:08 PM Backport #16425 (Resolved): jewel: rbd-mirror: potential race condition accessing local image jou...
- https://github.com/ceph/ceph/pull/10046
- 09:08 PM Backport #16424 (Resolved): jewel: Journal needs to handle duplicate maintenance op tids
- https://github.com/ceph/ceph/pull/10045
- 09:08 PM Backport #16423 (Resolved): jewel: Journal duplicate op detection can cause lockdep error
- https://github.com/ceph/ceph/pull/10044
- 09:08 PM Backport #16422 (Resolved): jewel: Sporadic test failures when image update notification missed
- https://github.com/ceph/ceph/pull/9883
- 05:13 PM Bug #16404 (Pending Backport): Sporadic test failures when image update notification missed
- 02:20 PM Bug #16411 (Fix Under Review): rbd-mirror should disable proxied maintenance ops for non-primary ...
- *PR*: https://github.com/ceph/ceph/pull/9867
- 12:43 PM Bug #16411 (In Progress): rbd-mirror should disable proxied maintenance ops for non-primary image
- 12:29 PM Bug #16411 (Resolved): rbd-mirror should disable proxied maintenance ops for non-primary image
- When rbd-mirror is replaying updates into a local image, it owns the exclusive lock and currently is accepting mainte...
- 06:51 AM Bug #16362 (Pending Backport): Journal needs to handle duplicate maintenance op tids
06/21/2016
- 07:19 PM Bug #15150 (Duplicate): librbd: AioImageRequestWQ::aio_write triggered helgrind assert
- Tracking helgrind issues under tracker #14846
- 07:18 PM Bug #15007 (Resolved): Cannot rebuild object map in in-flight IO
- This issue is resolved in Jewel and we have stress-test IO cases to verify it properly functions. Infernalis is effec...
- 06:59 PM Bug #16404 (Fix Under Review): Sporadic test failures when image update notification missed
- *PR*: https://github.com/ceph/ceph/pull/9850
- 06:58 PM Bug #16404 (In Progress): Sporadic test failures when image update notification missed
- 06:34 PM Bug #16404 (Resolved): Sporadic test failures when image update notification missed
- Hammer and Infernalis automatically mark the image as updated when proxying requests to the exclusive lock holder to ...
- 04:52 PM Bug #16363 (Pending Backport): Journal duplicate op detection can cause lockdep error
- 04:51 PM Bug #16198 (Pending Backport): Possible race condition during journal transition from replay to r...
- 04:51 PM Bug #16230 (Pending Backport): rbd-mirror: potential race condition accessing local image journal
- 02:07 AM Bug #16394: Ceph RBD
- ./log/SubsystemMap.h: In function 'bool ceph::log::SubsystemMap::should_gather(unsigned int, int)' thread 2abc8630270...
- 02:03 AM Bug #16394 (Rejected): Ceph RBD
06/20/2016
- 04:04 PM Bug #16349 (In Progress): rbd-mirror: gracefully handle being blacklisted
- 04:03 PM Bug #16362 (Fix Under Review): Journal needs to handle duplicate maintenance op tids
- *PR*: https://github.com/ceph/ceph/pull/9823
- 02:36 PM Bug #16362 (In Progress): Journal needs to handle duplicate maintenance op tids
- 02:34 PM Bug #16363 (Fix Under Review): Journal duplicate op detection can cause lockdep error
- *PR*: https://github.com/ceph/ceph/pull/9819
- 02:26 PM Bug #16363 (In Progress): Journal duplicate op detection can cause lockdep error
- 01:42 PM Bug #16198 (Fix Under Review): Possible race condition during journal transition from replay to r...
- *PR*: https://github.com/ceph/ceph/pull/9816
06/18/2016
06/17/2016
- 08:01 PM Bug #16230 (Fix Under Review): rbd-mirror: potential race condition accessing local image journal
- *PR*: https://github.com/ceph/ceph/pull/9788
- 05:59 PM Backport #16373 (Resolved): jewel: rbd-mirror: gracefully handle missing sync point snapshots
- https://github.com/ceph/ceph/pull/10678
- 05:59 PM Backport #16372 (Resolved): jewel: Unable to disable journaling feature if in unexpected mirror s...
- https://github.com/ceph/ceph/pull/10042
- 05:59 PM Backport #16371 (Resolved): jewel: rbd-mirror: ensure replay status formatter has completed befor...
- https://github.com/ceph/ceph/pull/10043
- 01:44 PM Bug #16362: Journal needs to handle duplicate maintenance op tids
- rbd::mirror::ImageReplayer::replay_flush should be modified to invoke a new method in librbd::journal::Replay to flus...
- 12:49 PM Bug #16362 (Resolved): Journal needs to handle duplicate maintenance op tids
- The ops can be re-used over new instantiations of librbd since they should have a unique journal tag each time the ex...
- 01:33 PM Bug #16364 (Resolved): Crash when utilizing advisory locking API functions
- The advisory locking functions permit the image to be opened in R/O mode but also send header update notifications. ...
- 01:23 PM Bug #16329 (Pending Backport): rbd-mirror: gracefully handle missing sync point snapshots
- 12:50 PM Bug #16363 (Resolved): Journal duplicate op detection can cause lockdep error
- ...
- 11:16 AM Bug #16348 (Pending Backport): Unable to disable journaling feature if in unexpected mirror state
- 11:16 AM Bug #16352 (Pending Backport): rbd-mirror: ensure replay status formatter has completed before st...
06/16/2016
- 09:35 PM Bug #16352 (Fix Under Review): rbd-mirror: ensure replay status formatter has completed before st...
- *PR*: https://github.com/ceph/ceph/pull/9759
- 08:29 PM Bug #16352 (In Progress): rbd-mirror: ensure replay status formatter has completed before stoppin...
- 07:46 PM Bug #16352 (Resolved): rbd-mirror: ensure replay status formatter has completed before stopping r...
- *Relevant Logs*...
- 09:14 PM Bug #16348 (Fix Under Review): Unable to disable journaling feature if in unexpected mirror state
- *PR*: https://github.com/ceph/ceph/pull/9751
- 01:31 PM Bug #16348 (Resolved): Unable to disable journaling feature if in unexpected mirror state
- ...
- 01:58 PM Bug #16350 (Resolved): Object map/fast-diff invalidated if journal replays the same snap remove e...
- When fast-diff is enabled, object-map needs to merge the current object map with the next object map to track the dir...
- 01:54 PM Bug #16349 (Resolved): rbd-mirror: gracefully handle being blacklisted
- rbd-mirror has a dedicated connection to the remote peer on a per-pool basis. It should also use a dedicated connect...
- 09:53 AM Bug #16202 (Resolved): teuthology: mon/rbd_snaps_ops.sh needs update for cppool command
- 05:26 AM Backport #16325 (Resolved): hammer: "rbd: create error: (38) Function not implemented" in upgrade...
- 05:16 AM Bug #16321 (Fix Under Review): Renaming old format image results in "Transport endpoint is not co...
- PR: https://github.com/ceph/ceph/pull/9715
- 02:21 AM Bug #16198 (In Progress): Possible race condition during journal transition from replay to ready
Also available in: Atom