Valgrind will slow slurm down by a lot. You'll probably want to run  
this on some test system or during a test time.

There are too many factors to say how large slurmctld should be, but  
1+ GB is probably too large.

Quoting Mario Kadastik <[email protected]>:

>
>> We use the valgrind tool to test all slurm daemons for memory leaks
>> with a variety of configurations. See if you can identify the source
>> of leaks.Iinstructions in src/slurmctld/controller.c:
>>
>> /**************************************************************************\
>>  * To test for memory leaks, set MEMORY_LEAK_DEBUG to 1 using
>>  * "configure --enable-memory-leak-debug" then execute
>>  * $ valgrind --tool=memcheck --leak-check=yes --num-callers=8 \
>>  *   --leak-resolution=med ./slurmctld -Dc >valg.ctld.out 2>&1
>>  *
>>  * Then exercise the slurmctld functionality before executing
>>  * > scontrol shutdown
>
>
> This is a production system, how much of an overhead will valgrind  
> have here? And so far I've built slurm as rpm package I guess it  
> won't check versions between controller (custom built then with  
> debug) and clients.
>
> Also, what is the expected memory footprint of slurm controller as a  
> function of cores/jobs or their flux?
>
> Thanks,
>
> Mario Kadastik, PhD
> Researcher
>
> ---
>   "Physics is like sex, sure it may have practical reasons, but  
> that's not why we do it"
>      -- Richard P. Feynman
>

Reply via email to