[Gluster-devel] Problems with self-heal

[E-Comm Factory]

Hello,

I have 2 boxes with 4 unified disks (so i have 2 volumes). Then, in client
side, i have set afr with this 2 virtual volumes.

For testing purposes I've deleted one file on the second afr volume and then
tried to self-heal the global afr but it crashes with this error:

[afr.c:2754:afr_open] disk: self heal failed, returning EIOç
[fuse-bridge.c:675:fuse_fd_cbk] glusterfs-fuse: 98: /fichero4.img => -1 (5)

An strace to the pid of the glusterfs-server running on the first afr volume
crashes too when selfhealing:

epoll_wait(6, {{EPOLLIN, {u32=6304624, u64=6304624}}}, 2, 4294967295) = 1
read(4, out of memory
0x7fff9a3b1d90, 113)            = 113
read(4, Segmentation fault

My server config file (same on both server boxes):

# datastores
volume disk1
  type storage/posix
  option directory /mnt/disk1
end-volume
volume disk2
  type storage/posix
  option directory /mnt/disk2
end-volume
volume disk3
  type storage/posix
  option directory /mnt/disk3
end-volume
volume disk4
  type storage/posix
  option directory /mnt/disk4
end-volume

# namespaces
volume disk1-ns
  type storage/posix
  option directory /mnt/disk1-ns
end-volume
volume disk2-ns
  type storage/posix
  option directory /mnt/disk2-ns
end-volume
#volume disk3-ns
#  type storage/posix
#  option directory /mnt/disk3-ns
#end-volume
#volume disk4-ns
#  type storage/posix
#  option directory /mnt/disk4-ns
#end-volume

# afr de namespaces
volume disk-ns-afr
  type cluster/afr
  subvolumes disk1-ns disk2-ns
  option scheduler random
end-volume

# unify de datastores
volume disk-unify
  type cluster/unify
  subvolumes disk1 disk2 disk3 disk4
  option namespace disk-ns-afr
  option scheduler rr
end-volume

# performace para el disco
volume disk-fs11
  type performance/io-threads
  option thread-count 8
  option cache-size 64MB
  subvolumes disk-unify
end-volume

# permitimos acceso a cualquier cliente
volume server
  type protocol/server
  option transport-type tcp/server
  subvolumes disk-fs11
  option auth.ip.disk-fs11.allow *
end-volume

My client config file:

volume disk-fs11
  type protocol/client
  option transport-type tcp/client
  option remote-host 192.168.1.34
  option remote-subvolume disk-fs11
end-volume

volume disk-fs12
  type protocol/client
  option transport-type tcp/client
  option remote-host 192.168.1.35
  option remote-subvolume disk-fs12
end-volume

volume disk
  type cluster/afr
  subvolumes disk-fs11 disk-fs12
end-volume

volume trace
  type debug/trace
  subvolumes disk
#  option includes open,close,create,readdir,opendir,closedir
#  option excludes lookup,read,write
end-volume

Anyone could help me?

Thanks in advance.

-- 
ecomm
sistemas at e-commfactory.com