[Gluster-devel] Gluster causes fuse to kernel panic

Bruce bruce at webfarm.co.nz
Fri Aug 17 05:00:30 UTC 2007


Hi,

I have been running glusterfs on a server for about 3 days now, and all
of a sudden it has started causing FUSE to kenel panic,

The only information I have is the following stack dump sent via syslog
just before it crashed, It doesn't write this to any of the kernel logs
or anything.

-- 8<--
Message from syslogd at andre at Fri Aug 17 16:40:30 2007 ...
andre kernel: Oops: 0002 [#1]

Message from syslogd at andre at Fri Aug 17 16:40:30 2007 ...
andre kernel: SMP

Message from syslogd at andre at Fri Aug 17 16:40:30 2007 ...
andre kernel: CPU:    0

Message from syslogd at andre at Fri Aug 17 16:40:30 2007 ...
andre kernel: EIP is at request_end+0x37/0xdf [fuse]

Message from syslogd at andre at Fri Aug 17 16:40:30 2007 ...
andre kernel: eax: 00200200   ebx: ceb55320   ecx: ceb55328   edx:
00100100

Message from syslogd at andre at Fri Aug 17 16:40:30 2007 ...
andre kernel: esi: ee3cd980   edi: 00000000   ebp: 00000000   esp:
ee54beac

Message from syslogd at andre at Fri Aug 17 16:40:30 2007 ...
andre kernel: ds: 007b   es: 007b   ss: 0068

Message from syslogd at andre at Fri Aug 17 16:40:30 2007 ...
andre kernel: Process glusterfs (pid: 3384, ti=ee54a000 task=f7bb4aa0
task.ti=ee54a000)

Message from syslogd at andre at Fri Aug 17 16:40:30 2007 ...
andre kernel: Stack: fffffffe ee3cd980 ceb55320 f8b0de71 ee54bf50
00000001 ee54bf7c ee285240

Message from syslogd at andre at Fri Aug 17 16:40:30 2007 ...
andre kernel:        00000030 ceb55320 ee54bf48 00000000 00000000
00000000 00000000 00000000

Message from syslogd at andre at Fri Aug 17 16:40:30 2007 ...
andre kernel:        00000002 00000000 00000088 dfae970c ee3cd980
00000001 ceb55320 ee54bf84

Message from syslogd at andre at Fri Aug 17 16:40:30 2007 ...
andre kernel: Call Trace:

Message from syslogd at andre at Fri Aug 17 16:40:30 2007 ...
andre kernel: Code: 00 8d 4b 08 c7 82 64 01 00 00 00 00 00 00 8b 12 8b
43 04 89 42 04 89 10 c7 43 04 00 02 20 00 8b 53 08 8b 41 04 c7 03 00 01
10 00 <89> 42 04 89 10 c7 41 04 00 02 20 00 f6 43 1c 08 c7 43 08 00 01

Message from syslogd at andre at Fri Aug 17 16:40:30 2007 ...
andre kernel: EIP: [<f8b0d74f>] request_end+0x37/0xdf [fuse] SS:ESP
0068:ee54beac
-- 8<--

As this causes the system to freeze at the kernel level, I would call it
rather a large bug. If there are any more information I can send which
may help please let me know, however most of the time the system doesnt
get to the point of writing log files.

This occurs on both
gluster at sv.gnu.org/glusterfs--mainline--2.5--patch-459 and a previous
revision I rolled back (unfortunately I cannot find how to get this)
There are also no stale libs or files in the usr/local directory where
the files are installed.

Those who have been in IRC should also know where to get my config files
(look for posts by nzhook)


System information:
Debian sarge/etch running 
ii  fuse-utils                 2.6.5-1
Filesystem in USErspace (utilities)
ii  libfuse2                   2.6.5-1
Filesystem in USErspace library

Kernel:
Linux andre.hosts.net.nz 2.6.18-3-686 #1 SMP Mon Dec 4 16:41:14 UTC 2006
i686 GNU/Linux
(stock Debian kernel)


Any help appreciated,
-- 
Bruce Parker
Engineering Team Leader

DDI  +64 6 757 2881

WebFarm Limited  I  Level 2, 2 Devon Street East, New Plymouth, New
Zealand  I  Telephone +64 6 757 2881  I  Facsimile +64 6 757 2883
ICONZ  I WebFarm I  Freeparking I  2day.com I Worldpay
Specializing in Domain Name Registration, Web Hosting, Internet &
E-Commerce Solutions





More information about the Gluster-devel mailing list