Help!

We have several dual pII 500's (Micron, 256MB mem) and they all do the
same thing under 2.0.36 SMP.  We try to run a pair of large (100+MB)
jobs simultaneously - it works file.  One of them ends and we try to
start another similar job (after, say 30 seconds) and it fails
immediately with a Seg Fault SOME of the time.  Retry - still fail.
After BOTH jobs have ended, now we can start another PAIR.

Could this be a problem with linux giving too much mem to the greedy 1st
job during that 30 seconds, so the 2nd can't start?  Plenty of swap
space left - why doesn't it just swap it out?  Any reason to suspect a
later kernel would handle it better?

Thanks
Drew


-
Linux SMP list: FIRST see FAQ at http://www.irisa.fr/prive/dmentre/smp-howto/
To Unsubscribe: send "unsubscribe linux-smp" to [EMAIL PROTECTED]

Reply via email to