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

Re: [HTCondor-users] PERIODIC_HOLD is applied extremely infrequently



I assume that's an OSG metapackage version. What's the output of
`condor_version`?
$CondorVersion: 8.3.5 Apr 16 2015 BuildID: 315103 $
$CondorPlatform: X86_64-RedHat_6.6 $


Well that's fun. Do you happen to have any sort of performance
monitoring on that server, and if so do you see any common patterns
CPU, memory, etc usage when it works versus doesn't?
The servers are pretty much idle. Most of the time there are at most a few hundred jobs running and a few thousand in the queue. Load average rarely goes above 0.2.


Vlad



On 05/11/15 15:15, Ben Cotton wrote:
Vlad,

First, what version of HTCondor are you running?
3.3.5

I assume that's an OSG metapackage version. What's the output of
`condor_version`?

Is the value of "some" consistent (either in raw terms or as a
percentage) across multiple tests?

No. Sometimes the right thing happens and all jobs go on hold, sometimes
none do.

Well that's fun. Do you happen to have any sort of performance
monitoring on that server, and if so do you see any common patterns
CPU, memory, etc usage when it works versus doesn't?


Thanks,
BC