[Gluster-devel] Problem with little write/read files in Gluster 3.0.0

[nicolas prochazka]

no dmesg information
no gluster log
and i'm trying with kernel 2.6.32.x ( 3 4 ) to 2.6.33.x ( rc1 to rc5 )
same result.
I've also test all this configurations with gluster 2.x ( lastest git ) , in
all tests case, servers does not reboot.
i've test without translator, same result .

Regards,
Nicolas

2010/1/28 Vijay Bellur <vijay at gluster.com>

> nicolas prochazka wrote:
>
>> Hi, client replicate ( see my precedent email )
>> server 1 : glusterfsd and glusterfs  (replicate s1 s2 )
>> server 2 : glusterfsd and glustefs ( replicate s1 s2 )
>> cut the cable between server1 and server2
>> waiting for Five minutes
>> two servers reboots.
>>
>> I think is fuse impact, because only fuse can panic the kernel .
>>
> Have you salvaged something from dmesg or /var/log/messages that can point
> to a kernel panic?
> From your previous mail, it looks like you are running 2.6.33-rc5 which is
> not stable as yet.
> Could it be related to that?
>
> Also, what filesystem are you using for the backend?
>
> Thanks,
> Vijay
>
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://supercolony.gluster.org/pipermail/gluster-devel/attachments/20100128/eae7f25f/attachment-0003.html>