Open MPI logo

Open MPI User's Mailing List Archives

  |   Home   |   Support   |   FAQ   |   all Open MPI User's mailing list

From: Timothy S. Woodall (twoodall_at_[hidden])
Date: 2005-11-11 21:26:15


Hello Troy,

We have very limited openib resources for testing at the moment. Can
you provide details on how to reproduce?

Thanks,
Tim

> On Fri, 11 Nov 2005 13:12:13 -0700, Jeff Squyres <jsquyres_at_[hidden]>
> wrote:
>
>> At long last, 1.0rc5 is available for download. It fixes all known
>> issues reported here on the mailing list. We still have a few minor
>> issues to work out, but things appear to generally be working now.
>> Please try to break it:
>>
>> http://www.open-mpi.org/software/v1.0/
>
> OK. All tests were also recompiled against RC5.
>
> Notes:
> I haven't tested with the MVAPI or TCP interfaces yet; only GM, MX, and
> OpenIB.
>
> The good: I don't have to use HPL_NO_MPI_DATATYPE to compile HPL or HPCC.
>
> The bad:
> OpenIB frequently crashes with the error:
> ***************
> [0,1,2][btl_openib_endpoint.c:135:mca_btl_openib_endpoint_post_send] error
> posting send request errno says Operation now in progress[0,1,2d
> [0,1,3][btl_openib_endpoint.c:135:mca_btl_openib_endpoint_post_send] error
> posting send request errno says Operation now in progress
> [0,1,3][btl_openib_component.c:655:mca_btl_openib_component_progress]
> error in posting pending send
> [0,1,2][btl_openib_endpoint.c:135:mca_btl_openib_endpoint_post_send] error
> posting send request errno says Operation now in progress
> [0,1,2][btl_openib_component.c:655:mca_btl_openib_component_progress]
> error in posting pending send
> ***************
> This is a new issue; the last SVN build I made (around 8058) didn't have
> this problem.
>
> MX still quits HPL code (as well as IMB) with errors to the tune of:
> ***************
> MX: assertion: <<not yet implemented>> failed at line 281, file
> ./mx__shmem.c
> ***************
>
> GM Still wedges itself when executing HPL code, as well as during the
> 'com' test of presta. Although it is able to get one iteration further
> in..._______________________________________________
> users mailing list
> users_at_[hidden]
> http://www.open-mpi.org/mailman/listinfo.cgi/users