[Gluster-devel] glusterfs client crash

[Matthias Albert]

Wow :-) what a great reaction and implementation time. Thanks a lot for
this fast fix.

  Matthias

Amar S. Tumballi schrieb:
> Hi Matthias,
>  Bug fixed in patch-505. Thanks.
>
> Regards,
> Amar
>
> On 10/2/07, *Anand Avati* <avati at zresearch.com
> <mailto:avati at zresearch.com>> wrote:
>
>     Matthias,
>     do you have a core dump on the client side from which you can get
>     us a 'bt'
>     output? that will help us a lot.
>
>     thanks,
>     avati
>
>     On 10/2/07, Matthias Albert <gluster at linux4experts.de
>     <mailto:gluster at linux4experts.de>> wrote:
>     >
>     > Hi,
>     >
>     > 5 minutes ago, I began to delete a huge file (147 Gig) from my
>     glusterfs
>     > storage client. This file was written over the last night from
>     bacula.
>     > While looking for the "rm command"  I got this
>     >
>     > "rm: Entfernen von „Full-Linux-Server-bacula-0003" nicht
>     möglich: Der
>     > Socket ist nicht verbunden"
>     > "rm: Removing from „Full-Linux-Server-bacula-0003" isn't possible:
>     > socket is not connected.
>     >
>     > After looking in my glusterfs client log I saw this.
>     >
>     >
>     > ---------
>     > got signal (11), printing backtrace
>     > ---------
>     > [0xb7ef5420]
>     >
>     >
>     /usr/local/lib/glusterfs/1.3.1/xlator/cluster/unify.so(unify_lookup_cbk+0x1a6)[0xb75412e6]
>
>     > /usr/local/lib/glusterfs/1.3.1/xlator/cluster/afr.so[0xb754eb3e]
>     > /usr/local/lib/glusterfs/1.3.1/xlator/protocol/client.so[0xb75659d2]
>     >
>     >
>     /usr/local/lib/glusterfs/1.3.1/xlator/protocol/client.so(notify+0x3ec)[0xb7560e6c]
>
>     > /usr/local/lib/libglusterfs.so.0(transport_notify+0x37)[0xb7ee3c37]
>     >
>     /usr/local/lib/libglusterfs.so.0(sys_epoll_iteration+0xd9)[0xb7ee48e9]
>     > /usr/local/lib/libglusterfs.so.0(poll_iteration+0x78)[0xb7ee3d68]
>     > [glusterfs](main+0x3fb)[0x804a82b]
>     > /lib/tls/i686/cmov/libc.so.6(__libc_start_main+0xc8)[0xb7d88ea8]
>     > [glusterfs][0x804a3a1]
>     > ---------
>     >
>     > # Client side
>     > fuse: fuse-2.7.0-glfs4
>     > glusterfs: tla 502
>     > AFR enabled with extended attributes
>     >
>     >
>     > glusterfs server Setup with  4 servers
>     >
>     > gluster1   - gluster2 = AFR1, 2 (300 Gig)
>     > 150 Gig       150 Gig (AFR1)
>     > 150 Gig       150 Gig (AFR2)
>     >
>     > gluster3    - gluster4 = AFR 3,4,5 (550 Gig)
>     > 250 Gig       250 Gig (AFR3)
>     > 150 Gig       150 Gig (AFR4)
>     > 150 Gig       150 Gig (AFR5)
>     >
>     > total afr storage: ~ 850 Gig (brutto 1700 Gig -> AFR :2)
>     >
>     > glusterfs-client: unify over afr1-5; namespace over seperate volumes
>     > from gluster1-4
>     >
>     >
>     > Regards,
>     >
>     >   Matthias
>     >
>     >
>     > _______________________________________________
>     > Gluster-devel mailing list
>     > Gluster-devel at nongnu.org <mailto:Gluster-devel at nongnu.org>
>     > http://lists.nongnu.org/mailman/listinfo/gluster-devel
>     >
>
>
>
>     --
>     It always takes longer than you expect, even when you take into
>     account
>     Hofstadter's Law.
>
>     -- Hofstadter's Law
>     _______________________________________________
>     Gluster-devel mailing list
>     Gluster-devel at nongnu.org <mailto:Gluster-devel at nongnu.org>
>     http://lists.nongnu.org/mailman/listinfo/gluster-devel
>     <http://lists.nongnu.org/mailman/listinfo/gluster-devel>
>
>
>
>
> -- 
> Amar Tumballi
> Gluster/GlusterFS Hacker
> [bulde on #gluster/irc.gnu.org]
> http://www.zresearch.com - Commoditizing Supercomputing and Superstorage!