Hello:
I'm doing the initial configuration for maui (maui-3.2.6p20) on a
university-based cluster. I've configured a very basic configuration file
which I've hacked to death trying to solve this issue. Two key lines:
NODECFG[argo17-1] MAXJOB=10
CLASSCFG[dedicated] MAXPROC=12
In order to test, I wrote a simple hello_world program in C. When I submit
the program for execution, I see that the number of tasks is 6:
Job ID Username Queue Jobname SessID NDS TSK Memory Time S Time
317 mhoma dedicate hello_worl -- 1 6 --- 00:30 Q --
and the job remains queued because:
"job cannot run in partition DEFAULT (idle procs do not meet requirements
: 0 of 6 procs found)"
The dedicated queue has three dual CPU, dual cores and was established in
torque:
argo17-1 np=4 Linux2.i86pc dualcore amd smp dedicated
argo18-2 np=4 Linux2.i86pc dualcore amd smp dedicated
argo18-3 np=4 Linux2.i86pc dualcore amd smp dedicated
According to the admin manual, "by default, a task maps directly to a
single processor within a job."
A few questions:
1) What configuration variable controls this setting? In other words,
how does one change maui so that a single processor can handle
multiple tasks from the same job. By its very nature, a hello_world
stub should not require six processors. Of course, my job will
queue; it's asking for six processors and there are only four
available. But, I'm surprised that the message says "0 of 6 found".
2) I'm unclear as to how the "task" number is derived? I noticed that
my hello_world has a PE of 6. Is that a coincidence or does the
resulting PE become the number of tasks? Why six processors for
hello_world?
I'm new to Maui so if I'm asking dumb questions, chalk it up to being an
idiot.
Michael Homa
Operating Systems Support and Database Group
Academic Computing and Communication Center
University of Illinois at Chicago
email: [EMAIL PROTECTED]
_______________________________________________
mauiusers mailing list
[email protected]
http://www.supercluster.org/mailman/listinfo/mauiusers
