Re: machine oops under heavy I/O or network access ???

[Eric Kamm]

Eric Kamm wrote:
> Hello,
>
> I apologize for the long post.   I tried to include as much
> relevant information as possible.
>
> Thank you,
> Eric
>
>
> [1.] One line summary of the problem:
> machine oops under heavy I/O or network access ???
>
> [2.] Full description of the problem/report:
>
> I have a Supermicro X6DHE-XG2 (Intel E7520 chipset) with dual Xeon with 
> 4GB RAM.
> I am using one 3ware 8005 controller, three 3ware 9550sx controllers, and
> reiserfs.  This machine is acting primarily to serve NFS.
>
> The oops below are from my original machine configuration, but I have 
> tried other some variations and have other oops:
>
>     - I have tried Suse 10.1 kernels 2.6.16.13-4-smp and 2.6.16.13-4-default.
>     - I have rebuilt the system onto an identical spare hardware configuration.
>     - I have used 64-bit and 32-bit kernel versions.
>     - I have replaced all the shared reiserfs filesytems with ext3.
>
> In all cases under load, disk IO alone (NFS server off) or disk IO+NFS 
> operations, the system has oops and "general protection fault" errors.
>
> The process is usually nfds or rpc.mountd, but (with the NFS server turned off) I
> also have errors from, for example, cp and rsync.  The system has been 
> up for as much as 16 hours with no problems, and sometimes as little as five minutes.
(~1000 lines snipped)

Any help/pointers will be greatly appreciated.

    - Did I post this to an appropriate place?  If not, could you
      recommend a place to report this problem?

    - Is there something else you can suggest I do to further understand
      the problem?

Thank you,
Eric





-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/