[Gluster-devel] get error while write for stripe

[Anand Avati]

Jack,
 can you use the latest TLA and give the log from the client side as
well as a backtrace of the core dump (if any) ?

regards,
avati

On Mon, Apr 30, 2007 at 06:40:28PM +0800, ????????? wrote:
> 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
> 
> 
> _______________________________________________
> Gluster-devel mailing list
> Gluster-devel at nongnu.org
> http://lists.nongnu.org/mailman/listinfo/gluster-devel
> 

-- 
ultimate_answer_t
deep_thought (void)
{ 
  sleep (years2secs (7500000)); 
  return 42;
}