[GE users] Accounting

Ron Chen ron_chen_123 at yahoo.com
Tue Apr 19 07:01:52 BST 2005


Richard,

(Got your mail while writing a reply to Shaila's
original message)

Does ARCo report why the job isn't scheduled
immediately (answers can be: large number of queued
jobs ahead of the job, and/or resource requirements
not satisfied. May be giving the users the % of wait
time contributed by each of the reasons is useful!)

Anyway, here's my original mail:

I guess you can get the number of CPUs used by looking
at the accounting file, and find out when the jobs are
running, and how many CPUs are used by each one. This
requires some sort of data mining.

I think it may be easier to run qstat/qhost
periodically and store the output to a file/database.
Doing this would then allow us to find out the license
usage (or any kind of resources that change
dynamically), and why the job isn't dispatched
(because of many jobs ahead of it, or because the job
requests for a resource that can't be obtained).

BTW, did you look at ARCo?

 -Ron


--- Richard Hierlmeier wrote:
> Shaila,
> 
> the commercial version of the gridengine includes
> the Accounting and Reporting
> Console. It also includes a daemon which imports the
> reporting and accounting data
> into a realation database (postgresql an oracle is
> supported).
> This tools uses the reporting file
> ($SGE_ROOT/$SGE_CELL/common/reporting) not the
> accounting file. All information you need should be
> included in this file.
> 
> Regards
> 
>    Richard
> 
> Shaila Parashar wrote:
> > Hi
> > 
> > We have a cluster consisting of 4 nodes  running
> SGE 6.0u3 .  The number 
> > of CPUs on these nodes are 24, 12, 8 and 4 . We
> have been running this 
> > cluster since Aug 2004 and are now in need of some
> statistics. I read 
> > the mailing lists and did get some ideas about the
> statistics. I also 
> > imported the accounting file into MySQL . I did
> manage to get statistics 
> > on the jobs - as average CPU time used, average
> waiting time, etc. But 
> > we need statistics similar to the following :-
> > 
> > Number of CPU's used versus time. Also number oc
> CPUs used on each of 
> > the hosts vs time.
> > 
> > Basically we need plots vs time.
> > 
> > I wanted to know if this is possible from the SGE
> accounting files and 
> > if so how ?
> > 
> > I would appreciate it if  you can suggest of any
> other values that we 
> > can plot against time.
> > 
> > Any ideas/suggestions on how to get these values (
> if possible ) will be 
> > really appreciated.
> > 
> > Thanks
> > 
> > Shaila
> > 
> 
> 
> -- 
> - - - - - - - - - - - - - - - - - - - - - - - - - -
> - - - - - - - - - - - -
> Richard Hierlmeier           Phone: ++49 (0)941
> 3075-223
> Software Engineering         Fax:   ++49 (0)941
> 3075-222
> Sun Microsystems GmbH
> Dr.-Leo-Ritter-Str. 7	     mailto:
> richard.hierlmeier at sun.com
> D-93049 Regensburg           http://www.sun.com/grid
> 
>
---------------------------------------------------------------------
> To unsubscribe, e-mail:
> users-unsubscribe at gridengine.sunsource.net
> For additional commands, e-mail:
> users-help at gridengine.sunsource.net
> 
> 


		
__________________________________ 
Do you Yahoo!? 
Yahoo! Mail - Find what you need with new enhanced search. 
http://info.mail.yahoo.com/mail_250

---------------------------------------------------------------------
To unsubscribe, e-mail: users-unsubscribe at gridengine.sunsource.net
For additional commands, e-mail: users-help at gridengine.sunsource.net




More information about the gridengine-users mailing list