[Gluster-devel] get error while write for stripe

徐肇駿 jackhsu at e-fun.cc
Mon Apr 30 10:40:28 UTC 2007


Before I ask for help,  I have read the thread below,
http://www.mail-archive.com/gluster-devel@nongnu.org/msg00455.html

I'm using the latest glusterfs-1.3.0-pre2.3 code on centos with
fuse-2.6.3 ( and fuse-2.6.3-rhel-build.patch ) and the OS is Cent-4.4.

I use the "stripe"  translator , but when I copy a testfile i get an
error below, and lost mount point.

the log ( at  server side ) is
[Apr 30 17:38:53] [ERROR/common-utils.c:54/full_rw()]
libglusterfs:full_rw: 0 bytes r/w instead of 113

Here are my configurations.

# server 1
volume brick
        type storage/posix
        option directory /zoo/gfs1
end-volume

volume server
        type protocol/server
        option transport-type tcp/server
        option listen-port 20000
        option bind-address 192.168.1.211
        subvolumes brick
        option auth.ip.brick.allow *
end-volume

volume trace
  type debug/trace
  subvolumes server
  option debug on
end-volume

# server2
volume brick
        type storage/posix
        option directory /zoo/gfs2
end-volume

volume server
        type protocol/server
        option transport-type tcp/server
        option listen-port 20000
        option bind-address 192.168.1.212
        subvolumes brick
        option auth.ip.brick.allow *
end-volume

volume trace
  type debug/trace
  subvolumes server
  option debug on
end-volume

[client]
volume server1
 type protocol/client
 option transport-type tcp/client
 option remote-host 192.168.1.211
 option remote-port 20000
 option remote-subvolume brick
end-volume

volume server2
 type protocol/client
 option transport-type tcp/client
 option remote-host 192.168.1.212
 option remote-port 20000
 option remote-subvolume brick
end-volume

volume stripe
   type cluster/stripe
   subvolumes client1 client2
   option stripe-size 131072 # 128k
end-volume

volume trace
  type debug/trace
  subvolumes stripe
  option debug on
end-volume

# to start glusterfsd server
[root at s01 zoo]# ./sbin/glusterfsd -f /zoo/server1
[root at s02 zoo]# ./sbin/glusterfsd -f /zoo/server2

# to start glusterfs client
[root at c01 zoo]# ./sbin/glusterfs -f /zoo/test.vol /zoo/qoo

[root at c01 zoo]# cp testfile ./qoo/
cp: writing `./qoo/testfile': Software caused connection abort
cp: closing `./qoo/testfile': Transport endpoint is not connected

Thanks for your help.

Jack Hsu





More information about the Gluster-devel mailing list