gige benchmark performance
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.
Tim Carlson tim.carlson at pnl.govFri Mar 15 16:51:02 PST 2002
- Previous message: gige benchmark performance
- Next message: gige benchmark performance
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
On Thu, 14 Mar 2002, Mark Hartner wrote: > We are working on putting together a 32 node cluster at the University of > Utah. I have benchmarked several Gigabit cards over cat5, > Netgear GA620T > Netgear GA622T > Intel Pro/1000T Server I put together some similar numbers at have posted them here: http://www.santafe.edu/~tim/netpipe.html One thing that we are seeing is a falloff in perfomance on the Intel cards with bigger packets. Not sure what to think on that. The odd thing is that the netperf numbers typically are better than the syskonnect and every once in a while you see a really big netperf number. The standard deviation is something like 20Mb/s. That's only 5 data points.. I know.. I need more data.. Hey, I have a PhD in Math so I can say crap like that and get away with it. :) The Syskonnects are solid as a rock with netpipe. I threw in the Giganet cLAN numbers just for fun. Tim Tim Carlson Voice: (509) 376 3423 Email: Tim.Carlson at pnl.gov EMSL UNIX System Support
- Previous message: gige benchmark performance
- Next message: gige benchmark performance
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
More information about the Beowulf mailing list
