BEOWULF cluster hangs
becker at scyld.com
Thu Sep 26 10:20:25 PDT 2002
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.
First data point: 8GB memory.
> When running large computational fluid simulations the simulation starts to
> slow down. At some point the response of the computer is so poor that we
The symptom. Right away I suspect that you are using a 2.4 kernel
> On our cluster we are running RH7.2 with the LINUX kernel version 2.4.7-10.
No _unmodified_ kernel before 2.4.17 was usable with long-term or
repeated large memory jobs.
Now that the kernel VM problems are largely fixed, I think you will finally
find acknowledgment/consensus about this point.
Donald Becker becker at scyld.com
Scyld Computing Corporation http://www.scyld.com
410 Severn Ave. Suite 210 Second Generation Beowulf Clusters
Annapolis MD 21403 410-990-9993
More information about the Beowulf