[GE users] qacct and ARCO accounting for multithreaded jobs

cwchan c-chan at uchicago.edu
Thu Aug 20 17:18:58 BST 2009


I've been going through the mailing list archives for posts about
ARCO and qacct.  In comparing qacct statistics vs. the ARCO output
they are usually of the same order of magnitude, but are almost
always different, typically by 20-40%, sometimes by a factor of 2-4.
I'm using simple queries, user or Project CPU and mem usage over
the period of a month.

For simple queries, is qacct or ARCO usually more accurate?

Also, do qacct or ARCO properly account CPU time used by multithreaded
jobs on the Linux x86_64 platform, even in the case when they only consume
1 job slot?

-- 
C. Chan <c-chan at uchicago.edu>
GPG Public Key registered at pgp.mit.edu

------------------------------------------------------
http://gridengine.sunsource.net/ds/viewMessage.do?dsForumId=38&dsMessageId=213298

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



More information about the gridengine-users mailing list