[gridengine users] RQS and scheduler performance (max-slots-on-all-hosts)
jlb at salilab.org
Thu Apr 26 17:33:43 UTC 2012
On Thu, 26 Apr 2012 at 1:24pm, Stuart Barkley wrote
> On Thu, 26 Apr 2012 at 12:57 -0000, Reuti wrote:
>> What was your "schedule_interval" set to?
>> Was "schedd_job_info true" set by accident?
> I've played with various values. My current setting are:
> % qconf -ssconf
> schedule_interval 0:01:00
> schedd_job_info true
> flush_submit_sec 5
> flush_finish_sec 5
> report_pjob_tickets TRUE
> Previously the scheduler seemed to be taking ~5 minutes to do one pass
> and appeared to be doing scheduling passes back-to-back. I think I
> tried setting schedule_interval to 10 minutes once and then there was
> some idle time between scheduler runs.
Well, this is disappointing. I noticed something similar with our rather
ancient 6.1u3 install -- scheduling runs were taking a long, long time
whenever anybody submitted jobs to our PEs, and setting "max_reservation
0" made them run much more quickly. We do have 4 RQSs, but I haven't
tried disabling them as they are rather essential to our setup. In all
cases, schedd_job_info was set to false.
I'm in the midst of installing hardware for a new server on which I'll be
running a much newer SGE version. I was rather hoping that this would
allow me to get reservations, RQSs, and "schedd_job_info true" (since it
is rather handy) all working together. Apparently not...
QB3 Shared Cluster Sysadmin
More information about the users