[GE users] qmaster using HUGE memory

fx d.love at liverpool.ac.uk
Tue Aug 31 12:25:49 BST 2010


seandavi <seandavi at gmail.com> writes:

> This post is a bit dated, but I wanted to follow up.  Turning off
> schedd_job_info did fix this issue (6.2u5).  However, users miss the
> job scheduling information.  Any other hints that we could try that
> would get us the scheduling info back?  This is not a big system and I
> wouldn't expect scheduling for a few dozen jobs to require more than
> 32GB of RAM (what our qmaster has).

For what it's worth, I have schedd_job_info on, and qmaster is running
at ~700MB virtual and 24MB resident with 32 jobs on ~100 nodes.  I've
noticed a problem with memory consumption on one or two occasions, but
that was before applying the fix for crashes due to tightly-integrated
jobs, which I could believe could cause it to go wild.  It's on an 8GB
head which is doing Nagios, Ganglia, and stuff too.

-- 
Dave Love
Advanced Research Computing, Computing Services, University of Liverpool
AKA fx at gnu.org

------------------------------------------------------
http://gridengine.sunsource.net/ds/viewMessage.do?dsForumId=38&dsMessageId=278458

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



More information about the gridengine-users mailing list