Hi Marcin, Can you share the Free blocks for the disk at the time of this issue(df -k)? It seems that the disk do not have enough free space to reserve a transaction. Also, the logs also seems to be mixed. The stucked position really seems to be : Function: xlog_grant_log_space() /* Is there space or do we need to sleep? */ spin_lock(&log->l_grant_lock); Is there any other activity which was done on the disk before you observed these hang traces?At first it does seems to hang XFS, next if you issue a 'sync' you will observe that sync will also turn to TASK_UNINTERRUPTIBLE 'D' state. Thanks & Regards, Amit Sahrawat On Sat, Oct 15, 2011 at 5:58 PM, Marcin M <gmane@xxxxxxxx> wrote: > One more thing, probably doesn't have matter, this is Xen HVM. > > _______________________________________________ > xfs mailing list > xfs@xxxxxxxxxxx > http://oss.sgi.com/mailman/listinfo/xfs > _______________________________________________ xfs mailing list xfs@xxxxxxxxxxx http://oss.sgi.com/mailman/listinfo/xfs
