Re: [HTCondor-users] DEBUG CONSUMPTION POLICY

[Alessandro Italiano <alessandro.italiano@xxxxxxxxxx>]

Hi all,

switching from D_ALL to D_FULLDEBUG I’ve found a meaningful log message

06/04/15 16:27:41 Attempting to use cached MatchList: Failed (MatchList length: 0, Autocluster: 1, Schedd Nam

which has pointed me out to 

[root@collector-01 ~]# condor_config_val -dump | grep -i NEGOTIATOR_MATCHLIST_CACHING

NEGOTIATOR_MATCHLIST_CACHING = true

changing it to false has fixed the issue so a p-slot is matched  multiple time over the same negotiator cycle.

Ale

On 03 Jun 2015, at 16:23, Alessandro Italiano <alessandro.italiano@xxxxxxxxxx> wrote:

Hi all,

I’ve configured a partitionable slot with consumption policy but I can't get it filled in one negotiator cycle.

Actually only a dynamic slot is instantiated per negotiator cycle

I’ve enable SCHEDD_DEBUG, NEGOTIATOR_DEBUG = D_ALL

[root@schedd-01 ~]# tail -f /var/log/condor/SchedLog

..

06/03/15 16:14:35 (fd:14) (pid:20560) (D_ALWAYS) Finished negotiating for italiano in local pool: 2 matched, 1 rejected

..

I have found this entry but nothing  about the reason for the rejected job

STARTD conf:

NUM_SLOTS = 1

NUM_SLOTS_TYPE_1 = 1

SLOT_TYPE_1 = cpus=100%,mem=100%,auto

SLOT_TYPE_1_PARTITIONABLE = True

CONSUMPTION_POLICY = True

CONSUMPTION_CPUS = TARGET.RequestCpus

SLOT_WEIGHT = Cpus

which is the right way to debug the consumption policy ?

thanks 

Ale

_______________________________________________
HTCondor-users mailing list
To unsubscribe, send a message to htcondor-users-request@xxxxxxxxxxx with a
subject: Unsubscribe
You can also unsubscribe by visiting
https://lists.cs.wisc.edu/mailman/listinfo/htcondor-users

The archives can be found at:
https://lists.cs.wisc.edu/archive/htcondor-users/