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

Re: [HTCondor-users] New to ht condor and have basic questions



Hello,

I've been displaying the other users process in the task manager and
indeed all condor daemons runs under System account as expected and
tolds in the user manual.

When checking the priorities of thoses process (still through
taskmanager), it displayed as "Normal"

Before submitting anything, the following daemons are running :

condor_collector.exe
condor_master.exe
condor_negociator.exe
condor_procd.exe
condor_schedd.exe
condor_stard.exe

All under SYSTEM accound and normal windows process priority.

When submitting the jobs

C:\Data\test_condor>condor_submit test_condor.sub
Submitting job(s)......................................
38 job(s) submitted to cluster 28.

seems ok

condor_q calls also seems ok :

C:\Data\test_condor>condor_q


-- Schedd: LUTECE : <192.168.1.181:49489?...
 ID      OWNER            SUBMITTED     RUN_TIME ST PRI SIZE CMD
  28.14  Mathieu         1/13 10:30   0+00:01:25 R  0   1.0  laszip.exe
-i C:\D
  28.18  Mathieu         1/13 10:30   0+00:01:00 R  0   1.0  laszip.exe
-i C:\D
  28.22  Mathieu         1/13 10:30   0+00:00:31 R  0   1.0  laszip.exe
-i C:\D
  28.23  Mathieu         1/13 10:30   0+00:00:27 I  0   1.0  laszip.exe
-i C:\D
  28.25  Mathieu         1/13 10:30   0+00:00:25 R  0   1.0  laszip.exe
-i C:\D
  28.26  Mathieu         1/13 10:30   0+00:00:00 I  0   1.0  laszip.exe
-i C:\D
  28.27  Mathieu         1/13 10:30   0+00:00:00 I  0   1.0  laszip.exe
-i C:\D
  28.28  Mathieu         1/13 10:30   0+00:00:00 I  0   1.0  laszip.exe
-i C:\D
  28.29  Mathieu         1/13 10:30   0+00:00:00 I  0   1.0  laszip.exe
-i C:\D
  28.30  Mathieu         1/13 10:30   0+00:00:00 I  0   1.0  laszip.exe
-i C:\D
  28.31  Mathieu         1/13 10:30   0+00:00:00 I  0   1.0  laszip.exe
-i C:\D
  28.32  Mathieu         1/13 10:30   0+00:00:00 I  0   1.0  laszip.exe
-i C:\D
  28.33  Mathieu         1/13 10:30   0+00:00:00 I  0   1.0  laszip.exe
-i C:\D
  28.34  Mathieu         1/13 10:30   0+00:00:00 I  0   1.0  laszip.exe
-i C:\D
  28.35  Mathieu         1/13 10:30   0+00:00:00 I  0   1.0  laszip.exe
-i C:\D
  28.36  Mathieu         1/13 10:30   0+00:00:00 I  0   1.0  laszip.exe
-i C:\D
  28.37  Mathieu         1/13 10:30   0+00:00:00 I  0   1.0  laszip.exe
-i C:\D

17 jobs; 0 completed, 0 removed, 13 idle, 4 running, 0 held, 0 suspended

And while watching carrefully taskmanager, I can see from time to time
that a real computation process is started (cf screenshot.jpg in
attachment) which priority is actually the lowest possible one, running
under some condor-slot user account (this seems conform to the
description of the user manual as i'm not using the run_as_owner feature
for now)

However, those computation process are started in a very sparsed manner
and the global cpu load displayed in the taskmanager remains very low
(close to 0 with some short spikes when a process is actually started)

When using the software without HTCondor, CPU load get to 100% for the
whole time and this of course gives (I hope this will get solved) much
shorted computation times...

Best regards,

Mathieu







Le 12/01/2016 16:22, John M Knoeller a écrit :
> The condor_shadow processes do not run the job.  They exist to act as a proxy for the user on the submit machine while the job is running (usually on another machine).     The condor_shadow handles the submit side of the file transfer (if there is any) and writes events into the userlog when the job changes state.   You should expect it to be mostly idle when the job is actually running. 
> 
> The job itself will run on a HTCondor execute node (which can be the same machine as the submit node).   On Windows the jobs will run under the services desktop, so the job will not be visible in task manager unless showing processes from all users.   
> 
> If you show processes from all users, you should expect to see some processes called condor_exec that are your actual  job. 
> 
> So I guess the question I have is  "how are you determining that the cpu is not busy?"


-- 
tel : +33 (0)6 87 30 83 59

Attachment: screenshot.jpg
Description: JPEG image