On 07/09/2009, at 12:53 AM, Ross Walker wrote:
That behavior sounds a lot like a process has a memory leak and is filling the VM. On Linux there is an OOM killer for these, but on OpenSolaris, your the OOM killer.
If it was this type of behaviour, where would it be logged when the process was killed/restarted? If it’s not logged by default, can that be enabled?
I have not seen any evidence of this in /var/adm/messages, /var/log/ syslog, or my /var/log/debug (*.debug), but perhaps I’m not looking for the right clues.
You have iSCSI, NFS, CIFS to choose from (most obvious), try restarting them one at a time during down time and see if performance improves after each restart to find the culprit.
The downtime is being reported by users, and I have only seen it once (while in their office) so this method of debugging isn’t going to help, I’m afraid. (this is why I asked about alternate root cause analysis methods)
cheers, James _______________________________________________ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
