Activity
From 02/20/2019 to 03/21/2019
03/21/2019
- 11:28 AM Bug #38824: kclient: ceph: remove duplicated filelock ref increase
- should remove code in ceph_lock().
- 08:36 AM Bug #37713: Centos 7 kernel client overwriting files
- It's an append write bug...
03/20/2019
- 07:00 AM Bug #38824: kclient: ceph: remove duplicated filelock ref increase
- ...
- 06:58 AM Bug #38824 (Resolved): kclient: ceph: remove duplicated filelock ref increase
- In kernel client, inode i_filelock_ref is increased in ceph_lock or ceph_flock, but it is increased again in ceph_loc...
03/19/2019
- 10:32 AM Bug #37713: Centos 7 kernel client overwriting files
- Ilya Dryomov wrote:
> Hi Jozef,
>
> Jozef Kováč wrote:
> > This happen only with ceph kernel client on Centos 7....
03/15/2019
- 08:00 PM Bug #147 (Resolved): lockdep: possible irq lock inversion dependency w/ osdc->request_mutex and c...
- Sage Weil wrote:
> iirc the fundamental problem is that we create sockets, which allocate an inode via create_inode(... - 07:47 PM Bug #13189 (Closed): Reboot systerm can not set up.
- 07:44 PM Bug #13189: Reboot systerm can not set up.
- It hangs because the network is getting shut down before the filesystems on rbd devices are unmounted.
Getting thi... - 06:47 PM Feature #21944 (Resolved): kclient: implement copy_file_range
- In 4.20, but the copyfrom optimization was subsequently disabled due to https://tracker.ceph.com/issues/37378.
- 06:41 PM Bug #15694 (Closed): process enter D status when running on rbd
- 06:33 PM Bug #10208 (Resolved): libceph: intermittent hangs under memory pressure
- 06:32 PM Bug #12691 (Resolved): ffsb osd thrash test - osd/ReplicatedPG.cc: 2348: FAILED assert(0 == "out ...
- Haven't seen out of order ops on 4.7 and later kernels.
- 06:31 PM Bug #10889 (Resolved): krbd: sent out of order write
- Haven't seen out of order ops on 4.7 and later kernels.
- 06:25 PM Bug #14022 (Resolved): map_sem for read + request_mutex are held indefinitely
- No new occurrences, request_mutex is gone, closing.
- 06:24 PM Bug #15891 (Resolved): [rbd] i/o to rbd block device stopped constantly
- No new occurrences, request_mutex is gone, closing.
- 06:15 PM Bug #36747 (Resolved): RBD Unmap Hang
- 06:12 PM Bug #37713: Centos 7 kernel client overwriting files
- Hi Jozef,
Jozef Kováč wrote:
> This happen only with ceph kernel client on Centos 7.3~7.6 ...
Are you saying t... - 05:59 PM Feature #9345 (Resolved): look into using MSG_MORE and MSG_SENDPAGE_NOTLAST more
- https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=1f6b821aef78e3d79e8d598ae59fc7e23fb6c56...
- 05:53 PM Bug #15946 (Need More Info): xfs layering on rbd block device was corrupted
- Shinobu, IIRC from our IRC conversation, there weren't any additional details available beyond what's in this ticket....
- 05:43 PM Feature #26936 (Resolved): Update Kernel Client to support versioned reply
- https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=b37fe1f923fb4b17dc7d63406ec8dc67f13c279...
- 05:41 PM Feature #37576 (Resolved): support getting ceph.dir.pin attribute
- https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=08796873a5183bfaab52a3bd899fe82f9e64be9...
- 05:39 PM Bug #37278 (Resolved): filefrag receives SIGFPE when run on any file on CephFS (kernel mount)
- https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=75c9627efb7288e1725e9903ea275cc6b5992f1...
03/12/2019
- 06:06 PM Bug #23112 (Resolved): rbd kernel client might hang when write to a quota-full pool
- 06:06 PM Bug #23112: rbd kernel client might hang when write to a quota-full pool
- There is a new libceph option for this in 5.0:
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/...
03/08/2019
- 02:17 AM Bug #37278: filefrag receives SIGFPE when run on any file on CephFS (kernel mount)
- patch hasn't been merged into upstream
03/07/2019
- 11:35 PM Bug #37278: filefrag receives SIGFPE when run on any file on CephFS (kernel mount)
- Zheng, should close this?
03/06/2019
- 07:25 PM Bug #15887: client reboot stuck if the ceph node is not reachable or shutdown
- For kcephfs, I believe umount -f is now more aggressive and aborts OSD requests in addition to MDS requests, but that...
03/05/2019
- 01:23 PM Bug #19127 (Resolved): NULL pointer dereference in ceph_readdir
- I haven't heard of this cropping up in quite some time, so I'm going to assume that the original oops here has been f...
- 01:15 PM Bug #15255 (Resolved): kclient: lost filesystem operations (on mds disconnect?)
- Jeff Layton wrote:
> So it looks like when the session ends up stale, that we try to regain our caps and soldier o...
03/01/2019
- 06:05 PM Bug #38482: Quotas: mounting quotas subdir doesn't respect quotas in kernel client
- You're absolutely right, Yanhu. But the *quotarealms_count* is just part of the story, because we actually need to b...
- 03:18 AM Bug #38482: Quotas: mounting quotas subdir doesn't respect quotas in kernel client
- ...
02/28/2019
- 12:09 PM Bug #38482: Quotas: mounting quotas subdir doesn't respect quotas in kernel client
- After an initial analysis, it looks like this _could_ be solved without any major drawbacks. The relevant code is in...
02/27/2019
- 02:35 PM Bug #20164: libceph: got bad padding
- In 4.9.161, 4.14.104, 4.19.26, 4.20.13.
02/26/2019
- 12:07 PM Bug #38482 (Resolved): Quotas: mounting quotas subdir doesn't respect quotas in kernel client
- The kernel client doesn't respect quotas that are set in directories it doesn't see in the mount point. Here's a rep...
02/25/2019
- 01:31 PM Bug #20164: libceph: got bad padding
- https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=0fd3fd0a9bb0b02b6435bb7070e9f7b82a23f06...
- 01:29 PM Bug #20164 (Pending Backport): libceph: got bad padding
02/23/2019
- 07:42 PM Bug #15887: client reboot stuck if the ceph node is not reachable or shutdown
- This is still an issue today with RHEL 7.2, any recommendations on workarounds?
Also available in: Atom