Hi, I am running glusterfs on two nodes acting as a mirror via afr and am experiencing some problems with too many open file descriptors. When I list the /proc/<pid>/fd of one glusterfs process it has 1024 descriptors still open. This is glusterfs version 1.3.8pre3 and fuse 2.7.2glfs8. Configuration is attached. Best regards, Jernej Kos. -- Jernej Kos <kostko@xxxxxxxxxxxxxxxxx> Unimatrix-One
### file: client-volume.spec.sample volume drone02 type protocol/client option transport-type tcp/client option remote-host 192.168.3.1 option remote-port 6996 option remote-subvolume storage0 end-volume volume drone03 type protocol/client option transport-type tcp/client option remote-host 192.168.5.1 option remote-port 6996 option remote-subvolume storage0 end-volume volume mirror0 type cluster/afr subvolumes drone02 drone03 option read-subvolume drone03 end-volume volume writebehind type performance/write-behind option aggregate-size 128KB option flush-behind on subvolumes mirror0 end-volume volume iothreads type performance/io-threads option thread-count 4 option cache-size 32MB subvolumes writebehind end-volume volume iocache type performance/io-cache option cache-size 64MB option page-size 1MB option force-revalidate-timeout 2 subvolumes iothreads end-volume
### file: server-volume.spec.sample volume storage0 type storage/posix option directory /mnt/raid/gluster end-volume volume server type protocol/server option transport-type tcp/server option bind-address 192.168.5.1 option listen-port 6996 subvolumes storage0 option auth.ip.storage0.allow 192.168.* end-volume