Re: [Condor-users] Tracing why nodes reject jobs?

[David Kotz <dkotz@xxxxxxxxxxxxx>]

Jon,

Have you tried using -better-analyze, rather than -analyze?  It will
give more details.  It certainly doesn't always answer my questions, but
it often does.

- dave



On Thu, 2010-07-15 at 11:52 -0400, Jonathan D. Proulx wrote:
> Hi All,
> 
> I have a user who queued a couple hundred identical Standard Universe
> jobs (well the parameters were a little different but the class ads
> were the same), most completed but 15 are hanging aroundin idle state
> after having accumulated some runtime, but will no longer match any
> execute nodes:
> 
>  ID      OWNER            SUBMITTED     RUN_TIME ST PRI SIZE CMD      
>  ---
>  78745.005:  Run analysis summary.  Of 429 machines,
>        19 are rejected by your job's requirements
>       410 reject your job because of their own requirements
> 	0 match but are serving users with a better priority
> in the pool
>         0 match but reject the job for unknown reasons
>         0 match but will not currently preempt their existing job
> 	0 match but are currently offline
> 	) are available to run your job
> 	Last successful match: Tue Jul  617:33:30 2010
>         Last failed match: Thu Jul 15 11:46:30 2010
> 	Reason for last match failure: no match found
> 		
> The 19 rejected for Job requirements are clear (wrong ARCH), the 410
> for node rrequirements is odd in several ways:
> 
> 1) there are 410 total systems available and 344 are currently claimed
> so I'd expect those to be either "match but are serving users with a
> better priority in the pool" or "match but will not currently preempt
> their existing job" 
> 
> 2) clearly they used to match some or the job wouldn't have had runtime
> 
> Where/how can I see why a specific node rejects a given job?
> 
> -Jon
> _______________________________________________
> Condor-users mailing list
> To unsubscribe, send a message to condor-users-request@xxxxxxxxxxx with a
> subject: Unsubscribe
> You can also unsubscribe by visiting
> https://lists.cs.wisc.edu/mailman/listinfo/condor-users
> 
> The archives can be found at:
> https://lists.cs.wisc.edu/archive/condor-users/