[gridengine users] Strange Errors requesting advance reservation

[Mauro Donadello]

Thank you Reuti.
> This is indeed strange. h_vmem is still included in `qconf -sc` I assume?
Yes is included. This is a real strange issue. 
Anyway, thanks.


On Oct 13, 2011, at 6:09 PM, Reuti wrote:

> Hi,
> 
> Am 13.10.2011 um 17:42 schrieb Mauro Donadello:
> 
>> Hi List, 
>> I need your help, if is possible. 
>> I would like to reserve some resources for an incoming event. 
>> I proceed with this row :
>> qrsub -w v -q "*@puffo.ifom-ieo-campus.it" -l "num_proc=10,h_vmem=50G" -a 10131740 -d 3:00:00  -u semmuser
> 
> num_proc is like a feature of an exechost and should be treated like that. I.e. you request a machine which has 10 cores built in. But the machine in question has 24. If you want to reserve 10 slots out of the 24, it's better to request a PE (parallel environment) with 10 slots on this machine.
> 
> 
>> Your job (-l h_vmem=50G,num_proc=10) cannot run at host "puffo.bioinfo.ifom-ieo-campus.it" because it offers only hl:num_proc=24.000000
>> verification: no suitable queues
>> 
>> Ok, then I try without processors:
>> qrsub -w v -q "*@puffo.ifom-ieo-campus.it" -u semmuser -l h_vmem=50G -a 10131740 -d 3:00:00 
>> Your job (-l h_vmem=50G) cannot run in queue "all.q at puffo.ifom-ieo-campus.it" because job requests unknown resource (h_vmem)
> 
> This is indeed strange. h_vmem is still included in `qconf -sc` I assume?
> 
> -- Reuti
> 
> 
>> I do not understand why such errors . 
>> Could you help me to find the issue