Re: [O-MPI devel] TCP performance

2005-11-29 Thread Tim S. Woodall
George Bosilca wrote: Tim, It looks a little bit better. Here are the latencies for 1 to 4 bytes messages as well as for the maximum length in Netpipe (8 MB). old ob1: 0: 1 bytes694 times --> 0.06 Mbps in 137.54 usec 1: 2 bytes727 times --> 0.11 Mbps

Re: [O-MPI devel] TCP performance

2005-11-29 Thread George Bosilca
Tim, It looks a little bit better. Here are the latencies for 1 to 4 bytes messages as well as for the maximum length in Netpipe (8 MB). old ob1: 0: 1 bytes694 times --> 0.06 Mbps in 137.54 usec 1: 2 bytes727 times --> 0.11 Mbps in 140.54 usec 2:

Re: [O-MPI devel] TCP performance

2005-11-29 Thread Tim S. Woodall
George, Can you try out the changes I just commited on the trunk? We were doing more select/recvs then necessary. Thanks, Tim George Bosilca wrote: I run Netpipe on 4 different clusters with differents OSes and Eternet devices. The results is that nearly the same behaviour happens all the