[slurm-users] Slurm configuration, Weight Parameter

Goetz, Patrick G pgoetz at math.utexas.edu
Fri Nov 22 17:29:13 UTC 2019


Can't you just set the usage priority to be higher for the 2GB machines? 
  This way, if the requested memory is less than 2GB those machines will 
be used first, and larger jobs skip to the higher memory machines. 
 


On 11/21/19 9:44 AM, Jim Prewett wrote:
> 
> Hi Sistemas,
> 
> I could be mistaken, but I don't think there is a way to require jobs on 
> the 3GB nodes to request more than 2GB!
> 
> https://slurm.schedmd.com/slurm.conf.html states this: "Note that if a 
> job allocation request can not be satisfied using the nodes with the 
> lowest weight, the set of nodes with the next lowest weight is added to 
> the set of nodes under consideration for use (repeat as needed for 
> higher weight values)."
> 
> I read that to mean "if there are only 3GB nodes available, jobs will be 
> run there reguardless of the memory needed."  We had a similar request 
> but were unable to find a solution (and, ultimately the particular user 
> is happier to not have idle machines when there's work to be done!).
> 
> If I'm misunderstanding, I'd love to know!
> 
> HTH,
> Jim
> 
> On Thu, 21 Nov 2019, Sistemas NLHPC wrote:
> 
>> Hi all,
>>
>> Currently we have two types of nodes, one with 3GB and another with 
>> 2GB of
>> RAM, it is required that in nodes of 3 GB it is not allowed to execute
>> tasks with less than 2GB, to avoid underutilization of resources.
>>
>> This, because we have nodes that can fulfill the condition of executing
>> tasks with 2GB or less.
>>
>> I try in the nodes configuration with the option "Weight".I send 
>> multiples
>> jobs but slurm not asigned by "Weight", it's arbitrary in the order how
>> send jobs. Some configuration and logs:
>>
>> slurm.conf
>>
>> NodeName=DEFAULT RealMemory=3007 Features=3007MB Weight=500 State=idle
>> Sockets=2 CoresPerSocket=1
>> NodeName=devcn050
>>
>> NodeName=DEFAULT RealMemory=3007 Features=3007MB Weight=100 State=idle
>> Sockets=2 CoresPerSocket=1
>> NodeName=devcn002
>>
>> NodeName=DEFAULT RealMemory=2000 Features=2000MB Weight=1 State=idle
>> Sockets=2 CoresPerSocket=1
>> NodeName=devcn001
>>
>> Extra information, I see that slurm assing Weight in the node.
>>
>> # sinfo -N -l
>>
>> NODELIST   NODES PARTITION       STATE CPUS    S:C:T MEMORY TMP_DISK 
>> WEIGHT
>> AVAIL_FE REASON
>> devcn001       1              slims*               idle       2
>> 2:1:1   2000           0                1             2000MB    none
>>
>> devcn002       1              slims*               idle       2
>> 2:1:1   3007           0             100            3007MB    none
>>
>> devcn050       1              slims*               idle       2
>> 2:1:1   3007           0             500            3007MB    none
>>
>> I test other settings, such as the TRESWeigths parameter with no results,
>> for example:
>>
>> NodeName=devcn001 TRESWeights="CPU=2.0,Mem=2000MB"
>>
>> Too PriorityType=priority/multifactor plugin is also activated and
>> deactivated to test, but in all these cases it does not work.
>>
>> Thanks in advance.
>>
>> Regards.
>>
> 
> James E. Prewett                    Jim at Prewett.org download at hpc.unm.edu
> Systems Team Leader           LoGS: http://www.hpc.unm.edu/~download/LoGS/
> Designated Security Officer         OpenPGP key: pub 1024D/31816D93
> HPC Systems Engineer III   UNM HPC  505.277.8210
> 
>>> This message is from an external sender. Learn more about why this <<
>>> matters at https://links.utexas.edu/rtyclf.                        <<
> 


More information about the slurm-users mailing list