[Gluster-devel] rsync failures with 1.3.1

[Paul Jochum]

Hi All:

    Ok, now that I have glusterfs up and running, first test is an rsync 
(well, actually, the second test, because the first test was a simple cp 
and that worked).
This is what I get:

*rsync -avHP /usr/local/ /mnt/point*
building file list ...
188 files to consider
lib/
lib/libfuse.a
      156462 100%    5.90MB/s    0:00:00 (xfer#1, to-check=169/188)
lib/libfuse.la
         986 100%   45.85kB/s    0:00:00 (xfer#2, to-check=168/188)
lib/libfuse.so.2.7.0
rsync: writefd_unbuffered failed to write 4 bytes [sender]: Broken pipe (32)
rsync: write failed on "/mnt/point/lib/libfuse.a": Input/output error (5)
rsync error: error in file IO (code 11) at receiver.c(253) [receiver=2.6.8]
rsync: connection unexpectedly closed (3963 bytes received so far) 
[generator]
rsync error: error in rsync protocol data stream (code 12) at io.c(463) 
[generator=2.6.8]
rsync: connection unexpectedly closed (80 bytes received so far) [sender]
rsync error: error in rsync protocol data stream (code 12) at io.c(463) 
[sender=2.6.8]

Here is some background information:
*Client Side:*
No messages in the log files (either gluster's log file or 
/var/log/messages)

glusterfs -V
glusterfs 1.3.1

fuse version is fuse-2.7.0-glfs1

spec file:
volume client
  type protocol/client
  option transport-type tcp/client     # for TCP/IP transport
  option remote-host 192.168.1.225     # IP address of the remote brick
  option remote-subvolume brick        # name of the remote volume
end-volume

machine's OS = CentOS release 5 (Final)
 2.6.18-8.1.8.el5 #1 SMP Tue Jul 10 06:50:22 EDT 2007 i686 i686 i386 
GNU/Linux


*Server Side:*
No messages in the log files (either gluster's log file or 
/var/log/messages)

glusterfsd -V
glusterfs 1.3.1

spec file:
volume brick
  type storage/posix                   # POSIX FS translator
  option directory /home/export        # Export this directory
end-volume

volume server
  type protocol/server
  option transport-type tcp/server     # For TCP/IP transport
  subvolumes brick
  option auth.ip.brick.allow * # Allow access to "brick" volume
end-volume

machine's OS = Scientific Linux SL release 5.0 (Boron)
2.6.18-8.1.6.el5 #1 SMP Thu Jun 14 11:57:17 EDT 2007 i686

The server and client are connected through a wireless connection (I am 
testing for usability, not for performance).  I can perform an rsync 
using an SSH connection between the two computers without a problem, but 
over glusterfs I keep hitting the same errors.  If I perform an rsync of 
only the file that caused the initial error, that works fine.  However, 
starting a new rsync will then fail on another file.

So, any suggestions?

thanks,

Paul Jochum