[gridengine users] qw job state when requesting all slots

Guillermo Marco Puche guillermo.marco at sistemasgenomicos.com
Tue Nov 13 09:01:31 UTC 2012


Hello,

Since today and I really don't know why when i request 16 slots in my 
cluster i'm getting job queued in qw status forever.
I've 2 compute nodes each one has 8 cpus (8 slots).

When I request 8 sloths with '-pe mpi 8' or '-pe orte 8', it works 
perfect and allocates task in compute-0-0.
When that job is running if i request 8 more slots with another job, it 
never gets queued to compute-0-1 slots.
Job isn't showing any error or even typical "queue instances are full" 
message.
If i request 16 slots at one it also gets queued forever.

Seems like compute-0-1 slots aren't provided or availabe.


Best regards,
Guillermo.



More information about the users mailing list