Re: [HTCondor-devel] Scheduler reports MAX_JOBS_RUNNING reached when it hasn't been


Date: Thu, 14 Nov 2013 12:22:06 -0600
From: "John (TJ) Knoeller" <johnkn@xxxxxxxxxxx>
Subject: Re: [HTCondor-devel] Scheduler reports MAX_JOBS_RUNNING reached when it hasn't been
try
 condor_status -schedd -af:h ShadowsRunning ShadowsRunningPeak

does the peak ever hit 2000?
-tj


On 11/13/2013 2:48 PM, Ben Cotton wrote:
On Wed, Nov 13, 2013 at 3:35 PM, Todd Tannenbaum <tannenba@xxxxxxxxxxx> wrote:

Another thought: Could it just be observation skew?  I.e. many shadows are
exiting at the same time jobs are starting, and/or jobs are switching
between running and idle very quickly?

It's a good thought, but no. There were 1901 jobs in the submission
and it was the only one active. The running job count ramped up to
1899 pretty quickly and stayed there. Job run times average about an
hour.


Thanks,
BC


[← Prev in Thread] Current Thread [Next in Thread→]