Re: [HTCondor-users] Problem in running parallel program

[Carsten Aulbert <carsten.aulbert@xxxxxxxxxx>]

Hi

On 23.09.21 07:42, Rajagopala Reddy Seelam wrote:
> Try using a single partition-able slot, e.g.
> NUM_SLOTS_TYPE_1Â Â Â Â Â Â Â Â Â= 1
> SLOT_TYPE_1Â Â Â Â Â Â Â Â Â Â Â = cpus=100%, ram=100%, swap=0%
> SLOT_TYPE_1_PARTITIONABLEÂ Â Â Â = True
>
> If you dont mind, I need further assistance here. When I include these 
> instructions in the submission script, condor returns
>
> WARNING: the line 'SLOT_TYPE_1_PARTITIONABLE = True' was unused by 
> condor_submit. Is it a typo?
> WARNING: the line 'SLOT_TYPE_1 = cpus=100%, ram=100%, swap=0%' was 
> unused by condor_submit. Is it a typo?
> WARNING: the line 'NUM_SLOTS_TYPE_1 = 1' was unused by condor_submit. Is 
> it a typo?
>
> It seems I need to use these instructions at the time of installation. I 
> request you to help me.

You need to place those instructions to the configuration file for the 
startd, e.g. on the machine where the jobs should run on in 
/etc/condor/config.d/01_startd.config

In other words, you first need to configure the starter "correctly", run 
condor_reconfig and verify that you only have one slot with all the 
resources in it, e.g.

condor_status -constraint PartitionableSlot -af Name TotalCpus TotalMemory

should show something like (final number depends how much memory the 
machine has)

slot1@machinename 20.0 16000

When this is set, you should be able to submit your jobs and it should 
not overwhelm the machine anymore.

HTH

Carsten

Attachment: smime.p7s
Description: S/MIME Cryptographic Signature