Open MPI logo

Open MPI User's Mailing List Archives

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

Subject: Re: [OMPI users] MPI_Alltoallv function crashes when np > 100
From: ÃÏÏܾü (xjun.meng_at_[hidden])
Date: 2011-05-21 06:51:45


hi,

I have found the reason that cause the problem, when call MPI_Alltoall(v)
with many processes(300 for instanse), it will build lots of connections in
a very short space of time. This situation causes my network card drops lots
of packages including the 'syn' packages, as the result, the connection
building failed. After I figure this porblem out, my program works well.

By the way, I think the error infomation is not reasonable, which takes me
lots of time to fix this bug : )

Thanks
Xianjun

ÔÚ 2011Äê5ÔÂ20ÈÕ ÏÂÎç7:26£¬Jeff Squyres <jsquyres_at_[hidden]>дµÀ£º

> I missed this email in my INBOX, sorry.
>
> Can you be more specific about what exact error is occurring? You just say
> that the application crashes...? Please send all the information listed
> here:
>
> http://www.open-mpi.org/community/help/
>
>
> On Apr 26, 2011, at 10:51 PM, ÃÏÏܾü wrote:
>
> > It seems that the const variable SOMAXCONN who used by listen() system
> call causes this problem. Can anybody help me resolve this question?
> >
> > 2011/4/25 ÃÏÏܾü <xjun.meng_at_[hidden]>
> > Dear all,
> >
> > As I mentioned, when I mpiruned an application with the parameter "np =
> 150(or bigger)", the application who used the MPI_Alltoallv function would
> carsh. The problem would recur no matter how many nodes we used.
> >
> > The edition of OpenMPI: 1.4.1 or 1.4.3
> > The OS: linux redhat 2.6.32
> >
> > BTW, my nodes had enough memory to run the application, and the
> MPI_Alltoall function worked well at my environment.
> > Did anybody meet the same problem? Thanks.
> >
> >
> > Best Regards
> >
> >
> >
> >
> > _______________________________________________
> > users mailing list
> > users_at_[hidden]
> > http://www.open-mpi.org/mailman/listinfo.cgi/users
>
>
> --
> Jeff Squyres
> jsquyres_at_[hidden]
> For corporate legal information go to:
> http://www.cisco.com/web/about/doing_business/legal/cri/
>
>
>
> _______________________________________________
> users mailing list
> users_at_[hidden]
> http://www.open-mpi.org/mailman/listinfo.cgi/users
>