Mailing List Archives
Authenticated access
|
|
|
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[Condor-users] One node doesn't execute jobs
- Date: Fri, 11 May 2012 14:04:39 -0500
- From: "Smith, Herb" <herb.smith@xxxxxxxxxx>
- Subject: [Condor-users] One node doesn't execute jobs
All,
I have a very simple pool consisting of 3 nodes. The master node is a Windows7 machine and the other two are Windows XP. Each machine has a dual core processor and Condor correctly sees all 6 processors available. I included the logic to ensure that both types of operating systems would be used:
Requirements = (OpSys == "WINNT51" && Arch == "INTEL") || (OpSys == "WINDOWS" && Arch == "X86_64")
Which seems to work fine, with one exception. The master node and one of the two pool members accept jobs, the remaining pool member shows a status of "Matched" but it never shows that it was "Claimed" nor does it run any jobs.
Here is a typical inquiry:
condor_status
Name OpSys Arch State Activity LoadAv Mem ActvtyTime
slot1@xxxxxxxxxxxx WINDOWS X86_64 Claimed Busy 1.000 2014 0+00:00:01
slot2@xxxxxxxxxxxx WINDOWS X86_64 Claimed Busy 1.010 2014 0+00:00:01
slot1@xxxxxxxxxxxx WINNT51 INTEL Matched Idle 0.000 1018 0+00:00:04
slot2@xxxxxxxxxxxx WINNT51 INTEL Matched Idle 0.020 1018 0+00:00:05
slot1@xxxxxxxxxxxx WINNT51 INTEL Claimed Busy 0.000 1002 0+00:00:01
slot2@xxxxxxxxxxxx WINNT51 INTEL Claimed Busy 0.000 1002 0+00:00:02
Total Owner Claimed Unclaimed Matched Preempting Backfill
INTEL/WINNT51 4 0 2 0 2 0 0
X86_64/WINDOWS 2 0 2 0 0 0 0
Total 6 0 4 0 2 0 0
Both of the pool machines have the same operating system setup as all the machines in the company receive the same software load. Is there some way to determine why this machine is not picking up any of the work load?
Thanks,
Herb Smith