I fixed my problem, I have to remove already running jobs , since they took all 
the memory other jobs will not be able to run. once I removed already running 
jobs, new jobs just landed where they suppose to run.

Saerda Halifu
Overingeniør,VD@IT-avd., UiB

> On 17 Jun 2015, at 11:02, Saerda Halifu <[email protected]> wrote:
> 
> Here is what I have :
> 
> scontrol show config |grep SelectType
> SelectType              = select/cons_res
> SelectTypeParameters    = CR_CORE_MEMORY
> 
> scontrol show config |grep DefMemPerCPU
> DefMemPerCPU            = 2000
> 
> 
> 
> Saerda Halifu
> Overingeniør,VD@IT-avd., UiB
> 
>> On 17 Jun 2015, at 10:55, Saerda Halifu <[email protected] 
>> <mailto:[email protected]>> wrote:
>> 
>> Hi,
>> 
>> Thanks.
>> I have configured DefMemPerCPU, but still the same.
>> This was not problem when I was running slurm-14.03.3-2, now I updated to 
>> 14.11.7-1 and started slurmdbd (I was using flat file before).
>> as I asked how can I check which resources are limited ? 
>> 
>> 
>> Saerda Halifu
>> Overingeniør,VD@IT-avd., UiB
>> 
>>> On 17 Jun 2015, at 10:30, Carlos Fenoy <[email protected] 
>>> <mailto:[email protected]>> wrote:
>>> 
>>> As already commented on several threads, you have to specify DefMemPerCPU 
>>> or DefMemPerNode. The default behavior of slurm is to allocate all the 
>>> memory.
>>> 
>>> On Wed, Jun 17, 2015 at 10:19 AM, Saerda Halifu <[email protected] 
>>> <mailto:[email protected]>> wrote:
>>> 
>>> Hi,
>>> 
>>> Thanks for your answer, SelectType is set to select/cons_res.
>>> 
>>>  scontrol show config | grep SelectType
>>> SelectType              = select/cons_res
>>> 
>>> if I check pending jobs , it says jobs are pending because of “ resources”
>>> 
>>> How can I check which “resources “ actually is limiting jobs?
>>> 
>>> Saerda Halifu
>>> Overingeniør,VD@IT-avd., UiB
>>> 
>>> > On 17 Jun 2015, at 09:57, Daniel Letai <[email protected] 
>>> > <mailto:[email protected]>> wrote:
>>> >
>>> >
>>> > Are you sure you set SelectType=select/cons_res?
>>> > It seems from your description that slurm allocates entire nodes for jobs.
>>> >
>>> > On 06/17/2015 10:28 AM, Saerda Halifu wrote:
>>> >> Hi,
>>> >>
>>> >> I just updated to slurm 14.11.7 , and having following issue.
>>> >> I have nodes with 32 cores, they all have 1 core job allocated(running) 
>>> >> and slurm tells me that they are in mixed state.
>>> >> I have plenty of jobs(all single core jobs) queueing and they are not 
>>> >> able to run because of no resources.
>>> >> I can’t find anything obvious in the log message, any suggestion  about 
>>> >> what to check ?
>>> >>
>>> >> Best Regards
>>> >>
>>> >> Saerda Halifu
>>> >> Overingeniør,VD@IT-avd., UiB
>>> 
>>> 
>>> 
>>> -- 
>>> --
>>> Carles Fenoy
>> 
> 

Reply via email to