[Mauiusers] parallel job was queued

wzlu wzlu at gate.sinica.edu.tw
Tue Jan 23 01:59:01 MST 2007


Dear All,

I am using torque-2.0.0p8 and maui-3.2.6p14 on RHEL 4 WS.
I submit a parallel job to using 4 nodes, the job can be execution.
But I submit a parallel job to using 8 nodes, the job was queued.
maui had allocate 8 nodes for my job, but it do not run.
qstat show as following:
$ qstat -n -u userA

my.queue.server:
Req'd Req'd Elap
Job ID Username Queue Jobname SessID NDS TSK Memory Time S Time
-------------------- -------- -------- ---------- ------ ----- ---
------ ----- - -----
4276.my.queue.server userA parallel cpi -- 8 -- -- --:-- Q --
host008+host007+host006+host005+host004+host003+host002+host001

>From torque log, torque server try to start the job every second.
But the job still queued. Have any idea? Thanks.


The maui configuration as following:
CLASSCFG[parallel] MAXJOBPERUSER=2
CLASSCFG[parallel] MAXPROCPERUSER=10

SRPARTITION[parallel] PARALLEL
SRTASKCOUNT[parallel] 24
SRRESOURCES[parallel] PROCS=-1
SRCLASSLIST[parallel] parallel
SRPERIOD[parallel] INFINITY

The torque configuration as following:
#
# Create and define queue parallel
#
create queue parallel
set queue parallel queue_type = Execution
set queue parallel resources_max.nodect = 64
set queue parallel resources_min.nodect = 2
set queue parallel resources_default.neednodes = parallel
set queue parallel resources_default.nodect = 2
set queue parallel resources_default.nodes = 2:ppn=1
set queue parallel enabled = True
set queue parallel started = True



More information about the mauiusers mailing list