[GE users] SGE6 does not backfill

Stephan Grell - Sun Germany - SSG - Software Engineer stephan.grell at sun.com
Sun Apr 17 18:40:05 BST 2005


    [ The following text is in the "ISO-8859-15" character set. ]
    [ Your display is set for the "ISO-8859-10" character set.  ]
    [ Some special characters may be displayed incorrectly. ]

Juha Jäykkä wrote:

>>Due to the speed up in the pe startup process, this should happen only 
>>very, very seldom now. Based
>>on my data, a misplaced qmod -s and qmod -us is the only way to kill a 
>>pe job. The scheduler should
>>be too slow for it.
>>    
>>
>
>It seems to really work now: schedule_interval = 15 s and reprioritize
>totally turned off (the previous worst case) and no jobs lost in 110
>instances. Thank you very much. Oh, and the version I used is CVS version
>from ~20:00 EET DST 16.4.2005.
>  
>

That is good news. Thank you very much. We expected it. However, the bug 
is not fixed. We will
need the fix real bug behind it. It is just very, very unlikely now.

Is everything else in the 6.0u4beta working for you?

Anything you noticed?

Pe jobs should start almost immediately. Can you confirm that?

Again, thanks for you cooperation.

Kind Regards,
Stephan

>For Christian:
>
>I have about 2500 open files, but it should not matter since ulimit -n is
>a per-process (including children?) limit and not a per-system. The
>qmaster, execd or scheduler do not have that many files open, ever. And
>ulimit -Hn is the same as ulimit -n, equal to 1024.
>
>I hope this is settled. :) Thanks one more time!
>
>  
>


---------------------------------------------------------------------
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