[Beowulf] Re: typical latencies for gigabit ethernet
Many of your questions may have already been answered in earlier discussions or in the FAQ. The search results page will indicate current discussions as well as past list serves, articles, and papers.
Dave Love d.love at liverpool.ac.ukMon Jun 29 15:43:53 PDT 2009
- Previous message: [Beowulf] typical latencies for gigabit ethernet
- Next message: [Beowulf] Re: typical latencies for gigabit ethernet
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
Rahul Nabar <rpnabar at gmail.com> writes: > I thought so! :) Lazy person's first shot. Now I will try ethtool. It's not relevant with all NICs. Some use driver module parameters. > Any way to verify if I do? Consult the NIC's documentation. > Ah! So my "real" latencies are 140/2 = 70 microsecs. I see ping times of ~70μs between the nVidias I posted data on, and they have an MPI latency of ~12μs. If you want a measurement/benchmark for MPI performance use IMB, like for the results I posted. Otherwise people sometimes use netpipe. If you want basic Ethernet (Layer 2) figures, look for Hughes-Jones' ethmon, somewhere under http://www.hep.man.ac.uk/.
- Previous message: [Beowulf] typical latencies for gigabit ethernet
- Next message: [Beowulf] Re: typical latencies for gigabit ethernet
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
More information about the Beowulf mailing list
