With openmpi-1.3, new mca feature is introduced namely --mca routed binomial. This ensures out of band communication to happen in binomial fashion and reduces the net socket opening and hence solves file open issues.
On Thu, 18 Sep 2008 16:46:23 -0700 Open MPI Users wrote
I'm just running it using mpirun from the command line. Thanks for the reply.
On Thu, Sep 18, 2008 at 4:35 PM, John Hearns
2008/9/18 Alex Wolfe
I am trying to run the HPL benchmarking software on a new 1024 core cluster that we have set up. Unfortunately I'm hitting the "mca_oob_tcp_accept: accept() failed: Too many open files (24)" error known in verson 1.2 of openmpi. No matter what I set the file-descriptor limit for my account to, I am still limited to only 808 or so processes. Does anyone have any suggestions?
Are you running the Linpack via a batch system or just using mpirun from the command line?
If via a batch system, looks for FAQs on how to set the resource limits for that batch system.
users mailing list