After change mount option to sync shutdown still happens, and I got a trace again, the inode 0x1c57d is abnormal.
https://docs.google.com/file/d/0B7n2C4T5tfNCYW1jNWhBbXBYakE/edit?usp=sharing
2013/4/20 符永涛 <yongtaofu@xxxxxxxxx>
Dear xfs experts,Does mount with sync option helps to isolate this problem?--2013/4/20 符永涛 <yongtaofu@xxxxxxxxx>
Thank you very much!Dear Eric and xfs experts,Updated progress is after more than one day glusterfs rebalance 3 of our servers xfs shutdown(8 servers in the test cluster). The errors are identical. Actually one of the most serious accident for us is 8 of our servers xfs shutdown at the same time during glusterfs rebalance.
--2013/4/20 符永涛 <yongtaofu@xxxxxxxxx>
Dear Eric,I noticed some functions call the xfs_lock_two_inodes(dp, ip, XFS_ILOCK_EXCL); twince but not in xfs_remove.--2013/4/20 符永涛 <yongtaofu@xxxxxxxxx>
There it is, I use latest 279.19.1 and only apply xfs trace path.--2013/4/20 Eric Sandeen <sandeen@xxxxxxxxxxx>
On 4/19/13 10:00 AM, 符永涛 wrote:
> Dear Eric,
>
> I checked rh srpm https://content-web.rhn.redhat.com/rhn/public/NULL/kernel/2.6.32-279.19.1.el6/SRPMS/kernel-2.6.32-279.19.1.el6.src.rpm?__gda__=1366390847_8550b8568c50ea46b3180266b476353d&ext=.rpmneed to look in lib/rwsem.c not lib/rwsem-spinlock.c
> And the code is same, as following:
>
> __rwsem_do_wake(struct rw_semaphore *sem, int wakewrite)
> {
Thanks,
-Eric
符永涛
符永涛
符永涛
符永涛
--
符永涛
_______________________________________________ xfs mailing list xfs@xxxxxxxxxxx http://oss.sgi.com/mailman/listinfo/xfs
