I ended up using the 'nolock' option with NFS - Even with only one client mounted, I had issues with locking. On 3/14/12 5:26 PM, Sean Fulton wrote: > We have a four-node, replicated cluster. When using the native gluster > client, we use the local server as the mount point (ie., mount > localhost:/glustervolume /dir). For NFS, can we do the same, or should > all of the clients mount from the same server to ensure proper > locking?? I've tried using the localhost for NFS but we seemed to have > lock contention. > > Recommendations would be appreciated. > > sean >
