Some limits are set in the job's environment, and there is no way to change it
once the job has started running already.
-Ron
________________________________
From: Schmidt U. <[email protected]>
To: [email protected]
Sent: Wednesday, January 11, 2012 1:42 AM
Subject: [gridengine users] qalter not successful
Dear all,
I used in sge6.2u5 the qalter command to extend the run time of
already running jobs:
qalter -l h_rt=259200,virtual_free=4.0G 540165
Unfortunately the job exited according to the h_rt=172800 defined in
the job script:
root@frontend01:~>qacct -j 540165
==============================================================
qname all.q
hostname node166.cruncher
group alinsch
owner alinsch
project NONE
department defaultdepartment
jobname CuPb.ph.q1.irrep110to110.5oyaELRwZd
jobnumber 540165
taskid undefined
account sge
priority 0
qsub_time Sun Jan 8 15:18:25 2012
start_time Sun Jan 8 15:18:27 2012
end_time Tue Jan 10 15:18:28 2012
granted_pe openmpi_a
slots 5
failed 100 : assumedly after job
exit_status 137
ru_wallclock 172801
ru_utime 21.570
ru_stime 2.349
ru_maxrss 0
ru_ixrss 0
ru_ismrss 0
ru_idrss 0
ru_isrss 0
ru_minflt 7337
ru_majflt 0
ru_nswap 0
ru_inblock 0
ru_oublock 0
ru_msgsnd 0
ru_msgrcv 0
ru_nsignals 0
ru_nvcsw 338428
ru_nivcsw 1594
cpu 862358.530
mem 2575536.313
io 497.175
iow 0.000
maxvmem 15.582G
arid undefined
Is this a bug or was my qalter command incomplete ?
Any ideas are welcome.
Udo
_______________________________________________
users mailing list
[email protected]
https://gridengine.org/mailman/listinfo/users_______________________________________________
users mailing list
[email protected]
https://gridengine.org/mailman/listinfo/users
