[DRBD-user] Device crash of unknown reason

Lars Ellenberg Lars.Ellenberg at linbit.com
Mon Oct 16 13:30:01 CEST 2006


/ 2006-10-14 20:09:25 +0200
\ Axel.Weber at rtl.de:
> Hello,
> 
> We are running a gentoo server cluster each of them has an external
> raid, having this setup
> Infotrend Raid5 ->LSI Raid Controller (mptscsih) -> drbd -> lvm -> xfs.
> 
> What happend: one drive of one node's Raid set failed, strange enough
> since nothing should have happend here. In the raid's log was a timeout
> message.
> The syslog came up with these messages:
> Oct 11 17:01:41 sowe1 kernel: xfs_force_shutdown(dm-0,0x8) called from
> line 1091 of file fs/xfs/xfs_trans.c.  Return address = 0xc01ffc6b
> Oct 11 17:01:41 sowe1 nfsd[9447]: non-standard errno: 990 (Unknown error
> 990)
> Oct 11 17:01:41 sowe1 kernel: Filesystem "dm-0": Corruption of in-memory
> data detected.  Shutting down filesystem: dm-0
> Oct 11 17:01:41 sowe1 kernel: Please umount the filesystem, and rectify
> the problem(s)
> 
> Due to heartbeat the other node took over but there happend the same.
> After the disk was replaced everything was fine again.

> Unfortunaltely there are no more error messages since the lower layer
> don't come up in the syslog.

I don't really understand this last sentence?

> Has somebody any idea?

how does this problem relate to drbd?
if you feed drbd with invalid data, invalid data will get replicated.

what did I miss?

-- 
: Lars Ellenberg                                  Tel +43-1-8178292-0  :
: LINBIT Information Technologies GmbH            Fax +43-1-8178292-82 :
: Schoenbrunner Str. 244, A-1120 Vienna/Europe   http://www.linbit.com :
__
please use the "List-Reply" function of your email client.



More information about the drbd-user mailing list