My server and clients are both using glusterfs v3.0.4-1 in this environment, and it looks like on some hosts, the client is restarting itself at regular intervals. I've found these occasional log lines in the client log. It looks like the client is hitting an error and restarting. It's causing a problem, because after this occurs, there is one more client process running. The previous client process doesn't exit, and a new client process gets started. At this point, it doesn't look like it causes a real production problem, but it's setting off my nagios alerts, because they monitor the # of procs that should be running. [2011-04-06 01:22:23] N [fuse-bridge.c:3140:fuse_thread_proc] glusterfs-fuse: terminating upon getting ENODEV when reading /dev/fuse [2011-04-11 01:18:33] N [fuse-bridge.c:3140:fuse_thread_proc] glusterfs-fuse: terminating upon getting EBADF when reading /dev/fuse However, these lines don't always accompany a client restart. Does anyone know if this has been fixed in the current version of gluster? Is it even a bug? I've done some searching, but I haven't found anything conclusive. Alternately, is it something that can be fixed via configuration? I've included my client config file in case it helps. # Gluster Client configuration /etc/glusterfs/glusterfs-client.vol volume remote1 type protocol/client option transport-type tcp option transport.socket.nodelay on option remote-host host1 option remote-subvolume brick end-volume volume remote2 type protocol/client option transport-type tcp option transport.socket.nodelay on option remote-host host2 option remote-subvolume brick end-volume volume remote3 type protocol/client option transport-type tcp option transport.socket.nodelay on option remote-host host3 option remote-subvolume brick end-volume volume remote4 type protocol/client option transport-type tcp option transport.socket.nodelay on option remote-host host4 option remote-subvolume brick end-volume volume remote5 type protocol/client option transport-type tcp option transport.socket.nodelay on option remote-host host5 option remote-subvolume brick end-volume volume remote6 type protocol/client option transport-type tcp option transport.socket.nodelay on option remote-host host6 option remote-subvolume brick end-volume volume remote7 type protocol/client option transport-type tcp option transport.socket.nodelay on option remote-host host7 option remote-subvolume brick end-volume volume remote8 type protocol/client option transport-type tcp option transport.socket.nodelay on option remote-host host8 option remote-subvolume brick end-volume volume replicate1 type cluster/replicate subvolumes remote1 remote2 end-volume volume replicate2 type cluster/replicate subvolumes remote3 remote4 end-volume volume replicate3 type cluster/replicate subvolumes remote5 remote6 end-volume volume replicate4 type cluster/replicate subvolumes remote7 remote8 end-volume volume distribute type cluster/distribute subvolumes replicate1 replicate2 replicate3 replicate4 end-volume volume writebehind type performance/write-behind #option aggregate-size 128KB #option window-size 1MB option cache-size 512MB subvolumes distribute end-volume volume cache type performance/io-cache option cache-size 512MB subvolumes writebehind end-volume volume stat-prefetch type performance/stat-prefetch subvolumes cache end-volume volume readahead type performance/read-ahead option page-count 8 subvolumes stat-prefetch end-volume Thanks, -elb-
