[Gluster-devel] glusterfs 3.0.0 crash

[elsif]

Hello.  I am experiencing client crashes under fairly low load
conditions using the source from
http://ftp.gluster.com/pub/gluster/glusterfs/3.0/LATEST/glusterfs-3.0.0.tar.gz.

Any suggestions on further steps for investigation would be greatly
appreciated.

Here are the messages from the log file:

pending frames:
frame : type(1) op(LOOKUP)
frame : type(1) op(LK)
frame : type(1) op(LK)
frame : type(1) op(LK)
frame : type(1) op(LK)

patchset: 2.0.1-886-g8379edd
signal received: 11
time of crash: 2009-12-16 14:42:18
configuration details:
argp 1
backtrace 1
dlfcn 1
fdatasync 1
libpthread 1
llistxattr 1
setfsid 1
spinlock 1
epoll.h 1
xattr.h 1
st_atim.tv_nsec 1
package-string: glusterfs 3.0.0
[0xffffe400]
/opt/gluster/lib/libglusterfs.so.0(data_destroy+0x3f)[0xf7f3c23f]
/opt/gluster/lib/libglusterfs.so.0(data_unref+0x60)[0xf7f3c2e0]
/opt/gluster/lib/libglusterfs.so.0(dict_destroy+0x46)[0xf7f3cb46]
/opt/gluster/lib/libglusterfs.so.0(dict_unref+0x60)[0xf7f3cc80]
/opt/gluster/lib/glusterfs/3.0.0/xlator/cluster/replicate.so(afr_local_cleanup+0x86)[0xf751ec76]
/opt/gluster/lib/glusterfs/3.0.0/xlator/cluster/replicate.so(afr_self_heal_completion_cbk+0x151)[0xf75400f1]
/opt/gluster/lib/glusterfs/3.0.0/xlator/cluster/replicate.so(afr_sh_entry_done+0xc1)[0xf7544de1]
/opt/gluster/lib/glusterfs/3.0.0/xlator/cluster/replicate.so(afr_self_heal_entry+0x4e)[0xf7544e3e]
/opt/gluster/lib/glusterfs/3.0.0/xlator/cluster/replicate.so(afr_sh_metadata_done+0x2e2)[0xf7540dd2]
/opt/gluster/lib/glusterfs/3.0.0/xlator/cluster/replicate.so(afr_self_heal_metadata+0x40)[0xf7540e20]
/opt/gluster/lib/glusterfs/3.0.0/xlator/cluster/replicate.so(afr_sh_missing_entries_done+0x11d)[0xf753d9bd]
/opt/gluster/lib/glusterfs/3.0.0/xlator/cluster/replicate.so(afr_self_heal+0x347)[0xf753fc87]
/opt/gluster/lib/glusterfs/3.0.0/xlator/cluster/replicate.so[0xf7521312]
/opt/gluster/lib/glusterfs/3.0.0/xlator/cluster/replicate.so(afr_revalidate_lookup_cbk+0x1f3)[0xf75215d3]
/opt/gluster/lib/glusterfs/3.0.0/xlator/protocol/client.so(client_lookup_cbk+0x687)[0xf756ce37]
/opt/gluster/lib/glusterfs/3.0.0/xlator/protocol/client.so(protocol_client_interpret+0x245)[0xf7558b75]
/opt/gluster/lib/glusterfs/3.0.0/xlator/protocol/client.so(protocol_client_pollin+0xcf)[0xf7558d1f]
/opt/gluster/lib/glusterfs/3.0.0/xlator/protocol/client.so(notify+0xd2)[0xf755e832]
/opt/gluster/lib/libglusterfs.so.0(xlator_notify+0x3f)[0xf7f4272f]
/opt/gluster/lib/glusterfs/3.0.0/transport/socket.so(socket_event_poll_in+0x3d)[0xf7f2bafd]
/opt/gluster/lib/glusterfs/3.0.0/transport/socket.so(socket_event_handler+0xab)[0xf7f2bbbb]
/opt/gluster/lib/libglusterfs.so.0[0xf7f5d78a]
/opt/gluster/lib/libglusterfs.so.0(event_dispatch+0x21)[0xf7f5c571]
/opt/gluster/sbin/glusterfs(main+0xb53)[0x804b9b3]
/lib/libc.so.6(__libc_start_main+0xe5)[0xf7dcf6a5]
/opt/gluster/sbin/glusterfs[0x8049b61]
---------


Here is the tail end of my config file:

volume dist
  type cluster/distribute
  subvolumes replicate1 replicate2 replicate3 replicate4 replicate5
replicate6 replicate7 replicate8 replicate9 replicate10 replicate11
replicate12 replicate13 replicate14 replicate15 replicate16 replicate17
replicate18
end-volume

volume iothreads
  type performance/io-threads
  option thread-count 16
  subvolumes dist
end-volume

The replicate volumes are made up of three subvolume clients.