Hi,
Regarding two recent messages I sent to the list [1][2], yesterday it
happened again: there were slow requests in one OSD, until it committed
suicide, and many virtual machines crashed with disk errors. I'm
attaching the log for the OSD that failed. The logs of the virtual
machines don't show anything. There were on-screen messages informing
that they were remounting read-only. I'll transcribe the screen of one
of those:
ata1.01: failed command: FLUSH CACHE
ata1.01: cmd e7/00:00:00:00:00/00:00:00:00:00/b0 tag 0
res 40/00:01:00:00:00/00:00:00:00:00/b0 Emask 0x4 (timeout)
ata1.01: status: { DRDY }
end_request: I/O error, dev sda, sector 1596912
end_request: I/O error, dev sda, sector 1596912
Buffer I/O error on device sda1, logical block 199358
.
.
Aborting journal on device sda1.
EXT3-fs (sda1): error: ext3_journal_start_sb: Detected aborted journal
EXT3-fs (sda1): error: remounting filesystem read-only
Buffer I/O error on device sda1
JBD: I/O error detected when updating journal superblock for sda1.
sd 0:0:1:0: [sda] Asking for cache data failed
sd 0:0:1:0: [sda] Assuming drive cache: write through
[1]http://article.gmane.org/gmane.comp.file-systems.ceph.user/15642/
[2]http://lists.ceph.com/pipermail/ceph-users-ceph.com/2014-November/044887.html
Thanks,
Paulo
Attachment:
ceph-osd.18.log.1.gz
Description: GNU Zip compressed data
_______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
