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 : )
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:
On Apr 26, 2011, at 10:51 PM, 孟宪军 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 孟宪军 <email@example.com>
> 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
For corporate legal information go to:
users mailing list