[Ocfs2-users] Process hangs when accessing OCFS2 filesystem

[Welsh, Jeff D]

I have a 7 node ocfs2 cluster and access to the ocfs file system is hanging from one of the nodes.  Whether it's an rm command, ls command, find command, etc, any process that attempts to access the filesystem on the node in question goes into a deep sleep state and hangs indefinitely.  Access to the filesystem from all the other nodes is ok.

The o2net kernel thread on the problem node is at 100% and it has over 12.5 hours of cpu time at this point.  o2net cpu time on the other nodes is around 1-2 hours .  There are no ocfs messages on the console.  The only thing that fixes the problem is a re-boot.

Any ideas on what's going on and how to fix it?

My environment: 2.6.9-89.0.3.Elsmp kernel, 1.2.9-1 ocfs2

~Jeff

-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://oss.oracle.com/pipermail/ocfs2-users/attachments/20100827/fd4dc46f/attachment.html