BEOWULF cluster hangs
Jeffrey B. Layton
laytonjb at bellsouth.net
Thu Sep 26 14:20:57 PDT 2002
John Hearns wrote:
>On Thu, 26 Sep 2002, G.de-With wrote:
>>Since a month we have a LINUX BEOWULF cluster, the clusters contains 7 P4
>>dual processor 2GHz computers, with 8Gb of RAM per machine. For our network
>>we have used Gigabit ethernet.
>>2) To my understanding the most important indicators to indicate the
>>computer usage are:
>>- memory usage
>>- cpu usage
>I'm sure someone on the list knows the exact answer.
>I would start by looking at the network, using ifconfig and
>netstat to look at the network status.
>You are using top and ps to get the process status, right?
>Me, I'm no expert, but for CFD why not use e.g. Myrinet?
>Network performance isn't all about bandwidth - and gig E may
>not be the best choice here.
It depends on the CFD code. The code we use scales very well
with just plain FastE. At 200 processors on FastE we get about 90%
of the theoretical scaling. Oh, it's an external aerodynamics CFD
code (unstructured inviscid/viscous). The above scaling number
is for a viscous run.
When we tested Myrinet we got less than a 1% improvement
in speed (wall clock time for an entire run).
>Beowulf mailing list, Beowulf at beowulf.org
>To change your subscription (digest mode or unsubscribe) visit http://www.beowulf.org/mailman/listinfo/beowulf
More information about the Beowulf