[GE users] PE Accounting

templedf dan.templeton at sun.com
Fri Nov 13 15:40:43 GMT 2009


OK.  I tested the issue on u4 and u3.  u4 has it and u3 doesn't.  I'll 
file a bug report.

Daniel

templedf wrote:
> Good tip on the accounting summary.  I had forgotten about that field.  
> I set it to FALSE and tried again.  This time I got an accounting record 
> for each slave, and the sum of the cpu fields matched the CPU time 
> reported by qstat -j.  I'll test this issue on u4 and file a bug report 
> if I find it there, too.
>
> Daniel
>
> templedf wrote:
>   
>> reuti wrote:
>>   
>>     
>>> Am 13.11.2009 um 15:48 schrieb templedf:
>>>
>>>   
>>>     
>>>       
>>>> Can someone point out what I'm missing here?  I have a tightly
>>>> integrated parallel job.  It runs for about 11 minutes.  Just  
>>>> before it
>>>> ends, I run a qstat -j, and I get the following usage line:
>>>>
>>>> usage    1:               cpu=00:40:53, mem=652.32980 GBs, io=0.00000,
>>>> vmem=23.023M, maxvmem=50.125M
>>>>
>>>> As far as I can tell, it's working as intended.  I have 40 CPU-minutes
>>>> in 11 minutes of execution, which corresponds to the 4 slots on which
>>>> the job is running.  BUT, after the job ends, I run qacct -j, and it
>>>> shows me:
>>>>
>>>> cpu          9.040
>>>> mem          0.369
>>>> io           0.000
>>>> iow          0.000
>>>> maxvmem      50.125M
>>>>
>>>> It got the maxvmem right, but the CPU time is clearly only for the
>>>> master task.  Even better, a little further up in the qacct output  
>>>> we see:
>>>>
>>>> ru_wallclock 726
>>>> ru_utime     1356.589
>>>> ru_stime     104.770
>>>>
>>>> which says that the job consumed twice as much CPU time as wallclock
>>>> time.  Huh?
>>>>     
>>>>       
>>>>         
>>> Is it a job with 2 threads on the master node of the job? This is  
>>> what the kernel sees on it's own, while "cpu" is accounted by the  
>>> additional GID.
>>>   
>>>     
>>>       
>> There's a slave task on the master node, and it's trying to use two 
>> threads, yes.  There's only one CPU, though.
>>
>>   
>>     
>>>   
>>>     
>>>       
>>>> Why do I have three different CPU time values that don't agree with  
>>>> each
>>>> other?  Am I just misunderstanding the numbers?
>>>>     
>>>>       
>>>>         
>>> Which version of SGE and which startup-method (builtin or traditional  
>>> rsh).
>>>   
>>>     
>>>       
>> It's 6.2u5alpha2 with builtin interactive support.  It's actually a 
>> completely default installation with my PE added in.
>>
>>   
>>     
>>> How many records do you have in the qaact output for the job - one or  
>>> more?
>>>   
>>>     
>>>       
>> For each of the jobs in both the emails I wrote there is only one entry 
>> in accounting:
>>
>>   
>>     
>>> What is the setting of "accounting_summary" in the PE?
>>>   
>>>     
>>>       
>> In both PEs, the accounting_summary is TRUE.  And control_slave is TRUE, 
>> and job_is_first_task is FALSE.
>>
>> Thanks,
>> Daniel
>>
>>   
>>     
>>> -- Reuti
>>>
>>> ------------------------------------------------------
>>> http://gridengine.sunsource.net/ds/viewMessage.do?dsForumId=38&dsMessageId=226688
>>>
>>> To unsubscribe from this discussion, e-mail: [users-unsubscribe at gridengine.sunsource.net].
>>>
>>>     
>>>       
>> ------------------------------------------------------
>> http://gridengine.sunsource.net/ds/viewMessage.do?dsForumId=38&dsMessageId=226692
>>
>> To unsubscribe from this discussion, e-mail: [users-unsubscribe at gridengine.sunsource.net].
>>
>>     
>
> ------------------------------------------------------
> http://gridengine.sunsource.net/ds/viewMessage.do?dsForumId=38&dsMessageId=226694
>
> To unsubscribe from this discussion, e-mail: [users-unsubscribe at gridengine.sunsource.net].
>

------------------------------------------------------
http://gridengine.sunsource.net/ds/viewMessage.do?dsForumId=38&dsMessageId=226696

To unsubscribe from this discussion, e-mail: [users-unsubscribe at gridengine.sunsource.net].



More information about the gridengine-users mailing list