To close out this thread I rebuilt the entire volume with ZFS instead of ext4 and it now appears to work well. I have not loaded it up yet but the ls / ll hanging problem is gone and I can move data to and from the mounted filesystem via a glusterfs mount. Thanks, ~Mike C. -----Original Message----- From: gluster-users-bounces at gluster.org [mailto:gluster-users-bounces at gluster.org] On Behalf Of Robert Hajime Lanning Sent: Thursday, January 31, 2013 7:12 PM To: gluster-users at gluster.org Subject: Re: hanging of mounted filesystem (3.3.1) On 01/31/13 19:01, Robert Hajime Lanning wrote: > On 01/31/13 17:58, Michael Colonno wrote: >> Doing more searching, it appears there are several posts on various >> forums describing the same issue with Gluster deployments of 4+ nodes >> (e.g. >> http://serverfault.com/questions/453345/certain-operations-like-ls-ha >> ng-in-4 >> >> -node-gluster-setup). None of these posts are answered which doesn't >> fill me with confidence. Can anyone confirm a 4+ node cluster with >> replication that does not show this (indefinite hang on ls or ll) >> behavior? >> > > Volume Name: vol01 > Type: Distributed-Replicate > Volume ID: 3d5d1791-044e-4cf3-b17b-79c74578e590 > Status: Started > Number of Bricks: 24 x 2 = 48 > Transport-type: tcp > > 4 bricks per server * 12 servers > All bricks are 37TB logical volumes formated with XFS. > > Filesystem Size Used Avail Use% Mounted on > gfs-vol:/vol01 888T 119G 888T 1% /glusterfs/vol01 > > No issues. > Sorry, should have included: CentOS 6.3 GlusterFS 3.3.1 -- Mr. Flibble King of the Potato People _______________________________________________ Gluster-users mailing list Gluster-users at gluster.org http://supercolony.gluster.org/mailman/listinfo/gluster-users