[Gluster-devel] Too many open files

[Jernej Kos]

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 at unimatrix-one.org>
Unimatrix-One
-------------- next part --------------
### 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

-------------- next part --------------
### 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