[mvapich-discuss] Anyone saw soft lockup on mvapich1.0 before?

[Dhabaleswar Panda]

Hi Terrence,

The latest MVAPICH version is 1.1 (not 1.0). MVAPICH 1.0 is already more
than one and half years old. We have not seen or received any report on
`soft lockup'. This could be an issue independent of the MPI library.
Anyway, you can use the latest MVAPICH 1.1 branch version from the
following URL:

 http://mvapich.cse.ohio-state.edu/nightly/mvapich/branches/1.1/

Thanks,

DK

> Our AMD DDR IB cluster running mvapich1.0 (latest version I believe),
> starts to show this "soft lockup", see below,  and kill the mpi job.  Any
> advice how to fix this?
>
> Dec  8 08:47:41 s_local at nod230/nod230 kernel:BUG: soft lockup - CPU#6
> stuck for 10s! [pbs_mom:4484]
>
> Thank you very much.
>
> -- Terrence
> --------------------------------------------------------
> Terrence Liao, Ph.D.
> Sr. HPC Research Scientist
> TOTAL E&P RESEARCH & TECHNOLOGY USA, LLC
> 1201 Louisiana, Suite 1800, Houston, TX 77002
> Tel: 713.647.3498  Fax: 713.647.3638
> Email: terrence.liao at total.com
>
>