Re: [Gluster-devel] Сrash - 2.0.git-2009.06.16

[NovA]

Hi!

It seems that my crashes not connected with DHT and write-behind. One
of the servers crashed yesterday with the following backtrace:
SERVER n54 (Jun 29 15:51)
------------------------
Core was generated by `/usr/sbin/glusterfsd -f
/etc/glusterfs/server.vol -l /var/log/glusterfs/server.'.
Program terminated with signal 6, Aborted.
#0  0x00002b600b19db45 in raise () from /lib64/libc.so.6
(gdb) bt
#0  0x00002b600b19db45 in raise () from /lib64/libc.so.6
#1  0x00002b600b19f0e0 in abort () from /lib64/libc.so.6
#2  0x00002b600b1d5fbb in ?? () from /lib64/libc.so.6
#3  0x00002b600b1db21d in ?? () from /lib64/libc.so.6
#4  0x00002b600b1dcf76 in free () from /lib64/libc.so.6
#5  0x00002b600ab3cefd in mem_put (pool=0x612760, ptr=0x637340) at
mem-pool.c:191
#6  0x00002b600c1422ce in iot_dequeue_ordered (worker=0x6126f0) at
io-threads.c:2407
#7  0x00002b600c142326 in iot_worker_ordered (arg=<value optimized
out>) at io-threads.c:2421
#8  0x00002b600af57020 in start_thread () from /lib64/libpthread.so.0
#9  0x00002b600b231f8d in clone () from /lib64/libc.so.6
#10 0x0000000000000000 in ?? ()
-------------------------

Also glusterFS servers continue crashing with other backtrace, which
I've already reported:
SERVER n45 (Jun 29 19:54)
----------------------
Core was generated by `/usr/sbin/glusterfsd -f
/etc/glusterfs/server.vol -l /var/log/glusterfs/server.'.
Program terminated with signal 11, Segmentation fault.
#0  0x00002b1395813860 in ?? () from /lib64/libc.so.6
(gdb) bt
#0  0x00002b1395813860 in ?? () from /lib64/libc.so.6
#1  0x00002b139581492b in calloc () from /lib64/libc.so.6
#2  0x00002b13969841b3 in get_frame_for_call (trans=0x61ea70,
hdr=0x2aaaac01cde0)
    at server-protocol.c:7315
#3  0x00002b1396984496 in protocol_server_interpret (this=0x60f8c0,
trans=0x61ea70,
    hdr_p=0x2aaaac01cde0 "", hdrlen=60, iobuf=0x2aaaac03dea8) at
server-protocol.c:7481
#4  0x00002b1396984720 in protocol_server_pollin (this=0x60f8c0, trans=0x61ea70)
    at server-protocol.c:7763
#5  0x00002b13969847b2 in notify (this=0x60f8c0, event=<value
optimized out>, data=0x6124b9)
    at server-protocol.c:7819
#6  0x00002b139515a183 in xlator_notify (xl=0x60f8c0, event=2,
data=0x61ea70) at xlator.c:820
#7  0x00002aaaaaaaff0b in socket_event_handler (fd=<value optimized
out>, idx=41, data=0x61ea70,
    poll_in=1, poll_out=0, poll_err=0) at socket.c:813
#8  0x00002b13951722aa in event_dispatch_epoll (event_pool=0x6094f0)
at event.c:804
#9  0x0000000000403f34 in main (argc=5, argv=0x7fff15b7f878) at
glusterfsd.c:1223
------------------
Probably this bug is not connected with the first one. But it's very
annoying, as it's triggered more frequently.

Best wishes,
  Andrey


Shehjar Tikoo (shehjart at gluster.com) wrote:
> Hi
>
> You can keep track of the progress of this crash at the
> following URL:
>
> http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=102
>
> Thanks
> Shehjar
>
>
> NovA wrote:
>>
>> Hi everybody!