Re: [OMPI users] Problems with Mpi Accept - ORTE_ERROR_LOG

2011-06-28 Thread Ralph Castain
Looking deeper, I believe we may have a race condition in the code. Sadly, that error message is actually irrelevant, but causes the code to abort. It can be triggered by race conditions in the app as well, but ultimately is something we need to clean up. On Jun 27, 2011, at 9:29 AM, Rodrigo O

Re: [OMPI users] mpirun does not propagate environment from master node to slave nodes

2011-06-28 Thread Ralph Castain
On Jun 28, 2011, at 3:52 PM, ya...@adina.com wrote: > Thanks, Ralph! > > a) Yes, I know I could use only IB by "--mca btl openib", but just > want to make sure I am using IB interfaces. I am seeking an option > to mpirun to print out the actual interconnect protocol, like --prot to > mpirun i

Re: [OMPI users] mpirun does not propagate environment from master node to slave nodes

2011-06-28 Thread Ralph Castain
On Jun 28, 2011, at 3:52 PM, ya...@adina.com wrote: > Thanks, Ralph! > > a) Yes, I know I could use only IB by "--mca btl openib", but just > want to make sure I am using IB interfaces. I am seeking an option > to mpirun to print out the actual interconnect protocol, like --prot to > mpirun i

Re: [OMPI users] mpirun does not propagate environment from master node to slave nodes

2011-06-28 Thread yanyg
Thanks, Ralph! a) Yes, I know I could use only IB by "--mca btl openib", but just want to make sure I am using IB interfaces. I am seeking an option to mpirun to print out the actual interconnect protocol, like --prot to mpirun in MPICH2. b) Yes, my default shell is bash, but I run a c-shell s

Re: [OMPI users] Problems with Mpi Accept - ORTE_ERROR_LOG

2011-06-28 Thread Ralph Castain
How are you passing the port info between the server and client? You're hitting a race condition between the two sides. On Jun 27, 2011, at 9:29 AM, Rodrigo Oliveira wrote: > Hi there. > I am developing a server/client application using Open MPI 1.5.3. In a point > of the server code I open a p

Re: [OMPI users] mpirun does not propagate environment from master node to slave nodes

2011-06-28 Thread Ralph Castain
On Jun 28, 2011, at 9:05 AM, ya...@adina.com wrote: > Hello All, > > I installed Open MPI 1.4.3 on our new HPC blades, with Infiniband > interconnection. > > My system environments are as: > > 1)uname -a output: > Linux gulftown 2.6.18-194.el5 #1 SMP Tue Mar 16 21:52:39 EDT > 2010 x86_64 x

[OMPI users] InfiniBand, different OpenFabrics transport types

2011-06-28 Thread Bill Johnstone
Hello all. I have a heterogeneous network of InfiniBand-equipped hosts which are all connected to the same backbone switch, an older SDR 10 Gb/s unit. One set of nodes uses the Mellanox "ib_mthca" driver, while the other uses the "mlx4" driver. This is on Linux 2.6.32, with Open MPI 1.5.3 .

[OMPI users] mpirun does not propagate environment from master node to slave nodes

2011-06-28 Thread yanyg
Hello All, I installed Open MPI 1.4.3 on our new HPC blades, with Infiniband interconnection. My system environments are as: 1)uname -a output: Linux gulftown 2.6.18-194.el5 #1 SMP Tue Mar 16 21:52:39 EDT 2010 x86_64 x86_64 x86_64 GNU/Linux 2) /home is mounted over all nodes, and mpirun is