[Gluster-users] hanging "df" (3.1, infiniband)

[Lana Deere]

For the last little while I've been using storage0 as both client and
server, so those files are both client and server files at the same
time.  If it would be helpful, I could go back to using a different
host as client (but then 'df' will hang instead of reporting the
Transport message).

[root at storage0 ~]# cat /etc/glusterd/.cmd_log_history
[2010-10-19 07:54:36.244333] peer probe :  on host storage1:24007
[2010-10-19 07:54:36.249891] peer probe : on host storage1:24007 FAILED
[2010-10-19 07:54:43.745558] peer probe :  on host storage2:24007
[2010-10-19 07:54:43.750752] peer probe : on host storage2:24007 FAILED
[2010-10-19 07:54:48.915378] peer probe :  on host storage3:24007
[2010-10-19 07:54:48.920595] peer probe : on host storage3:24007 FAILED
[2010-10-19 07:59:49.737251] Volume create : on volname: RaidData attempted
[2010-10-19 07:59:49.737314] Volume create : on volname: RaidData
type:DEFAULT count:4 bricks: storage0:/data storage1:/data
storage2:/data storage3:/data
[2010-10-19 07:59:49.737631] Volume create : on volname: RaidData SUCCESS
[2010-10-19 08:01:36.909963] volume start : on volname: RaidData SUCCESS

The /var/log file was pretty big, so I put it on pastebin:
    http://pastebin.com/m6WbHPUp


.. Lana (lana.deere at gmail.com)






On Tue, Oct 19, 2010 at 6:10 PM, Craig Carl <craig at gluster.com> wrote:
> Lana -
>    Can you also post the contents of
>
> /var/log/glusterfs/etc-glusterfs-glusterd.vol.log
> and
> /etc/glusterd/.cmd_log_history
>
> on both the client and server to the list?