[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [HTCondor-users] kill vs. load avg (was: scheduling delay)



What does condor_status -af Name TotalLoadAvg say?

TotalLoadAvg is as measured by the condor classad


Steve



From: HTCondor-users <htcondor-users-bounces@xxxxxxxxxxx> on behalf of Dimitri Maziuk via HTCondor-users <htcondor-users@xxxxxxxxxxx>
Sent: Friday, November 2, 2018 4:25:56 PM
To: htcondor-users@xxxxxxxxxxx
Cc: Dimitri Maziuk
Subject: [HTCondor-users] kill vs. load avg (was: scheduling delay)
 
Hi everyone,

I put

KILL = ( TotalLoadAvg > 4.5 )

on a host, and I am now watching top on it, w/ 32 condor jobs keeping
load average in the 30s for the last 5 minutes or so.

So, what's wrong with my KILL _expression_? Hopefully I'm missing
something glaringly obvious...

TIA
--
Dimitri Maziuk
Programmer/sysadmin
BioMagResBank, UW-Madison -- http://www.bmrb.wisc.edu