On Fri, 7 Nov 2008, Sage Weil wrote: > Ah, ok, makes sense. Can you describe the workload leading up to the rm a > bit? Is it this something you can reproduce? I can see where it bugged, > but that's unfortuantely a long way off from the root of the problem > (which looks like a missing ref count on the dentry).
This should be the relevant workload. I run this on all nodes and with wrappers around to get the bandwidth. cd /ceph/tmp rm -f `hostname`.tmp `hostname`.done dd if=/hda/tmp/knoppix.iso of=`hostname`.tmp bs=1M mv `hostname`.tmp `hostname`.done --jerker ------------------------------------------------------------------------- This SF.Net email is sponsored by the Moblin Your Move Developer's challenge Build the coolest Linux based applications with Moblin SDK & win great prizes Grand prize is a trip for two to an Open Source event anywhere in the world http://moblin-contest.org/redirect.php?banner_id=100&url=/ _______________________________________________ Ceph-devel mailing list Ceph-devel@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/ceph-devel
