Re: use or misuse ofLSF queues ??

From: Flemming Videbaek (videbaek@sgs1.hirg.bnl.gov)
Date: Tue Apr 02 2002 - 09:05:32 EST

  • Next message: Djamel Ouerdane: "DC and BFS tracking" 

    Just a short comment;
and thaks for yours.


>
> Are you sure this had anything to do with jobs running in LSF?
> Saturday afternoon (CET)  Mads and I was checkin out BRAT which took
> something like 1hour!, compiled it, again 1hour+, and no jobs was
> running in LSF - my feeling is that AFS and NFS was hanging. `uptime'
> on rcas0022 gave a load of `0.0, 0.0, 0.0' :-!

Agree this can happen - but not this time around jusrt before the 50 or so
jobs were submitted it was fines;
and as soon as the load was done to < 6 jobs it was fine.

Rmine001 was 60% in  kernel mode and 40% in io/wait !!
None of the jobs in rcas were running at max cpu the sumof two jobs was
~150% showing waiting for
i/o

I have started to read the LSF doc to better understand what kind of
'reasonable' queues one can implemet
to maximize the throughput.

    This archive was generated by hypermail 2b30 : Tue Apr 02 2002 - 09:05:13 EST