Project

General

Profile

Activity

From 11/13/2019 to 12/12/2019

12/12/2019

12:59 AM Bug #43183: Segmentation fault in tcmalloc when create osd
Yes, dpdk is enabled, the error probability is 10%, and retry will succeed chunsong feng

12/11/2019

10:26 PM Bug #43183: Segmentation fault in tcmalloc when create osd
Looks like SPDK/DPDK mode is enabled. Suggest to turn this off as a workaround. Igor Fedotov

12/10/2019

04:04 AM Bug #43147: segv in LruOnodeCacheShard::_pin
... Sage Weil
03:43 AM Bug #43147: segv in LruOnodeCacheShard::_pin
/a/sage-2019-12-09_20:35:48-rados:thrash-erasure-code-wip-sage3-testing-2019-12-09-1226-distro-basic-smithi/4585860
...
Sage Weil
03:40 AM Bug #43217 (Duplicate): segv in BlueStore::OnodeSpace::map_any
... Sage Weil

12/09/2019

05:59 PM Bug #43211 (Duplicate): Bluestore OSDs don't start after upgrade to 14.2.4
Igor Fedotov
05:58 PM Bug #43211: Bluestore OSDs don't start after upgrade to 14.2.4
This is a known bug, you should switch to 14.2.5 once it's out Igor Fedotov
04:24 PM Bug #43211 (Duplicate): Bluestore OSDs don't start after upgrade to 14.2.4
After an upgrade from 13.2.7 to 14.2.4 the OSDs were no longer able to start. Restarting ceph resulted in losing all ... Dino Godor

12/07/2019

06:32 PM Bug #43131: segfault in BlueStore::Collection::split_cache()
I haven't been able to reproduce it with that pr. see e.g. http://pulpito.ceph.com/sage-2019-12-05_22:59:50-rados-wi... Sage Weil
08:20 AM Bug #43183 (Can't reproduce): Segmentation fault in tcmalloc when create osd
[ceph_deploy.conf][DEBUG ] found configuration file at: /root/.cephdeploy.conf
[ceph_deploy.cli][INFO ] Invoked (2....
chunsong feng

12/06/2019

11:07 AM Backport #41810 (In Progress): nautilus: osd_memory_target isn't applied in runtime.
Sridhar Seshasayee
09:45 AM Backport #41810 (Need More Info): nautilus: osd_memory_target isn't applied in runtime.
Sridhar Seshasayee

12/05/2019

09:40 PM Bug #39318 (New): w_await high when rockdb compacting
Patrick Donnelly
09:40 PM Support #23433 (New): Ceph cluster doesn't start - ERROR: error creating empty object store in /d...
Patrick Donnelly
09:37 PM Bug #43147 (New): segv in LruOnodeCacheShard::_pin
Patrick Donnelly
01:17 PM Bug #43147 (Resolved): segv in LruOnodeCacheShard::_pin
... Sage Weil
09:37 PM Bug #42010 (New): segv in BlueStore::OnodeSpace::lookup during deletions
Patrick Donnelly
09:37 PM Bug #40741 (New): Mass OSD failure, unable to restart
Patrick Donnelly
09:37 PM Bug #40434 (New): ceph-bluestore-tool:bluefs-bdev-migrate might result in broken OSD
Patrick Donnelly
09:36 PM Bug #38637 (New): BlueStore::ExtentMap::fault_range() assert
Patrick Donnelly
09:35 PM Bug #20847 (New): low performance for bluestore rbd block creation vs filestore
Patrick Donnelly
09:35 PM Bug #20236 (New): bluestore: ObjectStore/StoreTestSpecificAUSize.Many4KWritesNoCSumTest/2 failure
Patrick Donnelly
07:49 AM Bug #43131: segfault in BlueStore::Collection::split_cache()
might be a regression introduced by https://github.com/ceph/ceph/pull/29687. need to rerun the test without it. Kefu Chai
04:57 AM Bug #43131 (Resolved): segfault in BlueStore::Collection::split_cache()
... Kefu Chai

12/02/2019

12:42 PM Backport #43087 (Resolved): nautilus: bluefs: sync_metadata leaks dirty files if log_t is empty
https://github.com/ceph/ceph/pull/34515 Nathan Cutler
12:41 PM Backport #43086 (Rejected): mimic: bluefs: sync_metadata leaks dirty files if log_t is empty
https://github.com/ceph/ceph/pull/34792 Nathan Cutler
08:40 AM Bug #42091 (Pending Backport): bluefs: sync_metadata leaks dirty files if log_t is empty
Kefu Chai

12/01/2019

04:28 PM Bug #43068: on disk size (81292) does not match object info size (81237)
I dump the on-disk object via objectstore tool , seems the last 55 bytes are all zero...
This file is a bash_hist...
Xiaoxi Chen
01:37 AM Bug #43068 (New): on disk size (81292) does not match object info size (81237)
... Xiaoxi Chen

11/25/2019

01:53 PM Backport #41810 (In Progress): nautilus: osd_memory_target isn't applied in runtime.
Sridhar Seshasayee

11/23/2019

07:12 PM Bug #20236: bluestore: ObjectStore/StoreTestSpecificAUSize.Many4KWritesNoCSumTest/2 failure
/a/nojha-2019-11-22_22:10:13-rados-wip-31657-nautilus-distro-basic-smithi/4534580/ Neha Ojha

11/22/2019

04:15 PM Bug #42823: crash in BlueStore::Onode destructor
New crash today. Looks somewhat similar to the old one. This one is based on e4b3036422df70e3 with some cephfs patche... Jeff Layton
08:32 AM Bug #41301 (Resolved): os/bluestore/BlueFS: use 64K alloc_size on the shared device
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Nathan Cutler

11/21/2019

01:42 PM Bug #42928 (Closed): ceph-bluestore-tool bluefs-bdev-new-db does not update lv tags
Adding a DB Device to an existing OSD with ceph-bluestore-tool bluefs-bdev-new-db does not update the lv tags of the ... Arthur van Kleef
05:52 AM Bug #42223: ceph-14.2.4/src/os/bluestore/fastbmap_allocator_impl.h: 750: FAILED ceph_assert(avail...
After 24h of testing, we can confirm, that fix is helping.
Good job Igor!
Rafal Wadolowski
01:58 AM Backport #41340 (Resolved): nautilus: os/bluestore/BlueFS: use 64K alloc_size on the shared device
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/30229
m...
Nathan Cutler

11/20/2019

08:07 PM Backport #41340: nautilus: os/bluestore/BlueFS: use 64K alloc_size on the shared device
Nathan Cutler wrote:
> https://github.com/ceph/ceph/pull/30229
merged
Yuri Weinstein
06:24 PM Bug #42913 (Resolved): nautilus: cram test fails with _do_alloc_write failed with (28) No space l...
... Neha Ojha

11/19/2019

07:26 PM Backport #42834 (Resolved): luminous: STATE_KV_SUBMITTED is set too early.
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/31674
m...
Nathan Cutler
05:02 PM Backport #42834: luminous: STATE_KV_SUBMITTED is set too early.
Nathan Cutler wrote:
> https://github.com/ceph/ceph/pull/31674
merged
Yuri Weinstein

11/18/2019

02:50 PM Bug #42223: ceph-14.2.4/src/os/bluestore/fastbmap_allocator_impl.h: 750: FAILED ceph_assert(avail...
TObias, thanks for the info. Hopefully we wouldn't need it any more.
Please let us know if the fix helps...
Igor Fedotov
07:05 AM Bug #42223: ceph-14.2.4/src/os/bluestore/fastbmap_allocator_impl.h: 750: FAILED ceph_assert(avail...
Hi Igor,
looks like you fixed the issue :) nevertheless, i got logs and sst of 2 new OSDs if you need further confir...
Tobias Fischer

11/17/2019

09:02 AM Backport #40449 (Resolved): nautilus: "no available blob id" assertion might occur
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/30144
m...
Nathan Cutler
09:01 AM Backport #40449 (In Progress): nautilus: "no available blob id" assertion might occur
Nathan Cutler
09:00 AM Backport #41460 (Resolved): nautilus: incorrect RW_IO_MAX
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/31397
m...
Nathan Cutler

11/16/2019

09:38 PM Backport #41282 (Resolved): nautilus: BlueStore tool to check fragmentation
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/29949
m...
Nathan Cutler
03:52 PM Backport #41282: nautilus: BlueStore tool to check fragmentation
Nathan Cutler wrote:
> https://github.com/ceph/ceph/pull/29949
merged
Yuri Weinstein
04:13 PM Bug #38272 (Resolved): "no available blob id" assertion might occur
Igor Fedotov
04:12 PM Backport #40449 (Resolved): nautilus: "no available blob id" assertion might occur
Igor Fedotov
04:07 PM Backport #40449: nautilus: "no available blob id" assertion might occur
Igor Fedotov wrote:
> https://github.com/ceph/ceph/pull/30144
merged
Yuri Weinstein
04:06 PM Backport #41460: nautilus: incorrect RW_IO_MAX
Nathan Cutler wrote:
> https://github.com/ceph/ceph/pull/31397
merged
Yuri Weinstein
06:34 AM Backport #42041: nautilus: bluestore objectstore_blackhole=true violates read-after-write
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/31019
m...
Nathan Cutler

11/15/2019

11:22 PM Bug #40684 (Resolved): bluestore objectstore_blackhole=true violates read-after-write
Igor Fedotov
11:21 PM Backport #42041 (Resolved): nautilus: bluestore objectstore_blackhole=true violates read-after-write
Igor Fedotov
10:39 PM Backport #42041: nautilus: bluestore objectstore_blackhole=true violates read-after-write
Nathan Cutler wrote:
> https://github.com/ceph/ceph/pull/31019
merged
Yuri Weinstein
02:33 PM Backport #42834 (In Progress): luminous: STATE_KV_SUBMITTED is set too early.
Nathan Cutler
02:29 PM Backport #42834 (Resolved): luminous: STATE_KV_SUBMITTED is set too early.
https://github.com/ceph/ceph/pull/31674 Nathan Cutler
02:30 PM Backport #42833 (In Progress): mimic: STATE_KV_SUBMITTED is set too early.
Nathan Cutler
02:29 PM Backport #42833 (Resolved): mimic: STATE_KV_SUBMITTED is set too early.
https://github.com/ceph/ceph/pull/31673 Nathan Cutler
01:12 PM Bug #42209 (Pending Backport): STATE_KV_SUBMITTED is set too early.
nautilus fix merged in https://github.com/ceph/ceph/pull/30755 Sage Weil
01:09 PM Bug #42223 (Resolved): ceph-14.2.4/src/os/bluestore/fastbmap_allocator_impl.h: 750: FAILED ceph_a...
Sage Weil

11/14/2019

09:07 PM Bug #42823 (Duplicate): crash in BlueStore::Onode destructor
Testing xfstests on cephfs in vstart cluster, and OSD crashed:... Jeff Layton
04:32 PM Bug #42223 (Pending Backport): ceph-14.2.4/src/os/bluestore/fastbmap_allocator_impl.h: 750: FAILE...
backport pr: https://github.com/ceph/ceph/pull/31644 Sage Weil

11/13/2019

11:47 PM Bug #42284 (Duplicate): fastbmap_allocator_impl.h: FAILED ceph_assert(available >= allocated) in ...
haha - we've finally got it locally...
https://tracker.ceph.com/issues/42223
Igor Fedotov
09:11 PM Bug #42223: ceph-14.2.4/src/os/bluestore/fastbmap_allocator_impl.h: 750: FAILED ceph_assert(avail...
@Marcin,
003808.sst has the same bluefs log pattern inside at e.g. offset 5687664. So it seems it has been overwritt...
Igor Fedotov
08:27 PM Bug #42223: ceph-14.2.4/src/os/bluestore/fastbmap_allocator_impl.h: 750: FAILED ceph_assert(avail...
@Igor,
Well done!
Would it also explain problem I had with 003808.sst(30MB) where all others were 16MB as they w...
Marcin W
07:48 PM Bug #42223: ceph-14.2.4/src/os/bluestore/fastbmap_allocator_impl.h: 750: FAILED ceph_assert(avail...
Hopefully here is the final analysis for the root cause.
a) analysis for 002375.sst dump from comment #94 reveals ...
Igor Fedotov
05:39 PM Bug #42223: ceph-14.2.4/src/os/bluestore/fastbmap_allocator_impl.h: 750: FAILED ceph_assert(avail...
@Rafal - great, thank you. Now I can tell that data extents in this file which are supposed to be RocksDB data belong... Igor Fedotov
11:25 AM Bug #42223: ceph-14.2.4/src/os/bluestore/fastbmap_allocator_impl.h: 750: FAILED ceph_assert(avail...
Yes it is available, I didn't redeployed failed OSDs... Rafal Wadolowski
07:12 PM Bug #20236: bluestore: ObjectStore/StoreTestSpecificAUSize.Many4KWritesNoCSumTest/2 failure
/a/yuriw-2019-11-08_20:50:44-rados-wip-yuri3-testing-2019-11-08-1221-nautilus-distro-basic-smithi/4485359/ Neha Ojha
06:17 PM Bug #20236: bluestore: ObjectStore/StoreTestSpecificAUSize.Many4KWritesNoCSumTest/2 failure
This appeared in nautilus
/a/yuriw-2019-11-12_15:30:19-rados-wip-yuri5-testing-2019-11-11-1520-nautilus-distro-bas...
Neha Ojha
05:25 PM Bug #42683: OSD Segmentation fault
@Antonio - yes, please go head. Igor Fedotov
04:17 PM Bug #42683: OSD Segmentation fault
@Igor if you don't object I would scratch the OSD to keep testing the system. Antonio Falabella
 

Also available in: Atom