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

RE: [Condor-users] Slow response



Are there any jobs queued that are trying to run somewhere and keep failing?
condor_q -global might give a hint to this.

That condor_status is impressively slow. I occasionally get condor_q 
failing to return for a while, but only when in the siuation where jobs
have been matched but cannot go there because of firewalls. I don't recall
seeing a problem with condor_status.

JK

> -----Original Message-----
> From: condor-users-bounces@xxxxxxxxxxx
> [mailto:condor-users-bounces@xxxxxxxxxxx]On Behalf Of Sandy Spence
> Sent: 12 May 2005 15:22
> To: 'Rob Fletcher'; 'Condor-Users Mail List'
> Subject: RE: [Condor-users] Slow response
> 
> 
> Hi Rob,
> here is the output from time condor_status
> 
> [axs@wig-01 ~]$ time condor_status
> 
> Name          OpSys       Arch   State      Activity   LoadAv Mem
> ActvtyTime
> 
> wig-01.cluste LINUX       INTEL  Owner      Idle       0.030  1024
> 22+15:25:16
> wig-02.cluste LINUX       INTEL  Unclaimed  Idle       0.000  1024
> 0+00:50:04
> wig-03.cluste LINUX       INTEL  Unclaimed  Idle       0.000  1024
> 0+00:35:04
> wig-04.cluste LINUX       INTEL  Unclaimed  Idle       0.000  1024
> 0+00:35:04
> wig-05.cluste LINUX       INTEL  Unclaimed  Idle       0.000  1024
> 0+00:35:04
> wig-06.cluste LINUX       INTEL  Unclaimed  Idle       0.000  1024
> 0+02:05:08
> wig-07.cluste LINUX       INTEL  Unclaimed  Idle       0.000  1024
> 0+02:05:21
> wig-08.cluste LINUX       INTEL  Unclaimed  Idle       0.000  1024
> 0+02:05:17
> wig-09.cluste LINUX       INTEL  Unclaimed  Idle       0.000  1024
> 0+02:05:16
> wig-10.cluste LINUX       INTEL  Unclaimed  Idle       0.000  1024
> 0+02:05:28
> wig-11.cluste LINUX       INTEL  Unclaimed  Idle       0.000  1024
> 0+02:04:59
> wig-12.cluste LINUX       INTEL  Unclaimed  Idle       0.000  1024
> 0+01:00:04
> wig-13.cluste LINUX       INTEL  Unclaimed  Idle       0.000  1024
> 0+02:05:51
> wig-14.cluste LINUX       INTEL  Unclaimed  Idle       0.000  1024
> 0+02:06:46
> wig-15.cluste LINUX       INTEL  Unclaimed  Idle       0.000  1024
> 0+02:06:32
> wig-16.cluste LINUX       INTEL  Unclaimed  Idle       0.000  1024
> 0+02:06:26
> wig-17.cluste LINUX       INTEL  Unclaimed  Idle       0.000  1024
> 0+02:05:23
> wig-18.cluste LINUX       INTEL  Unclaimed  Idle       0.000  1024
> 0+02:06:29
> wig-19.cluste LINUX       INTEL  Unclaimed  Idle       0.000  1024
> 0+02:06:18
> wig-20.cluste LINUX       INTEL  Unclaimed  Idle       0.000  1024
> 0+02:05:20
> wig-21.cluste LINUX       INTEL  Unclaimed  Idle       0.000  1024
> 0+02:05:39
> wig-22.cluste LINUX       INTEL  Unclaimed  Idle       0.000  1024
> 0+02:07:16
> wig-23.cluste LINUX       INTEL  Unclaimed  Idle       0.000  1024
> 0+02:05:47
> wig-24.cluste LINUX       INTEL  Unclaimed  Idle       0.000  1024
> 0+02:07:10
> wig-25.cluste LINUX       INTEL  Unclaimed  Idle       0.000  1024
> 0+02:08:03
> wig-26.cluste LINUX       INTEL  Unclaimed  Idle       0.000  1024
> 0+02:03:56
> wig-27.cluste LINUX       INTEL  Unclaimed  Idle       0.000  1024
> 0+02:05:23
> wig-28.cluste LINUX       INTEL  Unclaimed  Idle       0.000  1024
> 0+02:04:28
> wig-29.cluste LINUX       INTEL  Unclaimed  Idle       0.040  1024
> 0+02:06:32
> wig-30.cluste LINUX       INTEL  Unclaimed  Idle       0.000  1024
> 0+02:03:13
> wig-31.cluste LINUX       INTEL  Unclaimed  Idle       0.000  1024
> 0+01:30:04
> wig-32.cluste LINUX       INTEL  Unclaimed  Idle       0.000  1024
> 0+00:50:04
> wig-33.cluste LINUX       INTEL  Unclaimed  Idle       0.000  1024
> 0+02:06:48
> wig-34.cluste LINUX       INTEL  Unclaimed  Idle       0.000  1024
> 0+00:50:04
> wig-35.cluste LINUX       INTEL  Unclaimed  Idle       0.000  1024
> 0+02:05:23
> wig-36.cluste LINUX       INTEL  Unclaimed  Idle       0.000  1024
> 0+02:08:09
> wig-37.cluste LINUX       INTEL  Unclaimed  Idle       0.000  1024
> 0+02:03:58
> wig-38.cluste LINUX       INTEL  Unclaimed  Idle       0.000  1024
> 0+02:03:21
> wig-39.cluste LINUX       INTEL  Unclaimed  Idle       0.000  1024
> 0+02:03:24
> wig-40.cluste LINUX       INTEL  Unclaimed  Idle       0.000  1024
> 0+02:06:59
> 
>                      Machines Owner Claimed Unclaimed Matched 
> Preempting
> 
>          INTEL/LINUX       40     1       0        39       0 
>          0
> 
>                Total       40     1       0        39       0 
>          0
> 
> real    3m4.741s
> user    0m0.028s
> sys     0m0.011s
> 
> As you can see it is a little bit longer, this is not always the case
> though.
> 
> Cheers,
> 
> Sandy 
> 
> 
> Computer Officer, RA Certification Manager
> Department of Computer Science - UWA
> Llandinam Building
> Penglais Campus
> Aberystwyth
> Ceredigion
> Wales - UK
> SY23 3DB
> Tel: (01970)-622433
> Fax: (01970)-628536
> 
> 
> -----Original Message-----
> From: Rob Fletcher [mailto:rpf1@xxxxxxxxxx] 
> Sent: 12 May 2005 13:57
> To: Sandy Spence
> Subject: Re: [Condor-users] Slow response
> 
> On Thu, 12 May 2005, Sandy Spence wrote:
> 
> > Hi,
> >
> > I have a private condor pool, 1 master with 2 NICs and 39 slaves, 
> > there are times when entering condor_status takes a long 
> time to show 
> > any output and if running a test job the job takes a long time to 
> > start, are there any tweeks I can perform that would speed up these 
> > processes, I am running Condor 6.6.8.  Which logs are best 
> to view to 
> > get a better feel for what might be happening.
> >
> Hi,
> 
> I am running with master with 2 nics, and 4 slaves (master 
> WBEL, slaves
> WinXP), and I find condor_status takes and age! Or am I simply just
> expecting too much?
> 
> Using a new HP switch too, but the boxes are old PIII 700's 
> with 384 Mb RAM
> (so I sort of expect a slow response).
> 
> Also, condor_submit seems to take age too.
> 
> Running 6.6.9
> 
> 
> e.g.
> 
> [root@WEREWOLF transit]# time condor_status
> 
> Name          OpSys       Arch   State      Activity   LoadAv Mem
> ActvtyTime
> 
> localhost.loc LINUX       INTEL  Unclaimed  Idle       0.000   373
> 0+00:45:36
> xpnode0       WINNT51     INTEL  Unclaimed  Idle       0.000   384
> 0+03:09:30
> xpnode1       WINNT51     INTEL  Unclaimed  Idle       0.010   384
> 0+02:19:47
> xpnode2       WINNT51     INTEL  Unclaimed  Idle       0.020   384
> 0+02:19:59
> xpnode3       WINNT51     INTEL  Unclaimed  Idle       0.010   384
> 0+02:24:57
> 
>                      Machines Owner Claimed Unclaimed Matched 
> Preempting
> 
>          INTEL/LINUX        1     0       0         1       0 
>          0
>        INTEL/WINNT51        4     0       0         4       0 
>          0
> 
>                Total        5     0       0         5       0 
>          0
> 
> real    0m39.773s
> user    0m0.010s
> sys     0m0.010s
> 
> 
> 
> Cheers,
> 
> Rob
> 
> 
> 
> +==========================+=======================================+
> | Dr R P Fletcher    (Rob) | e  R.Fletcher@xxxxxxxxxx              |
> | Graphics Coordinator     | t  +44 (0)1904 433816                 |
> | Computing Service        | f  +44 (0)1904 433740                 |
> | University of York       | w  http://www-users.york.ac.uk/~rpf1/ |
> | YORK YO10 5DD, UK        |                                       |
> +==================================================================+
> 
> _______________________________________________
> Condor-users mailing list
> Condor-users@xxxxxxxxxxx
> https://lists.cs.wisc.edu/mailman/listinfo/condor-users
>