[slurm-users] Topology configuration questions:

[Ryan Novosielski]

Prentice (and others) — if the NodeWeight/topology plugin interaction bothers you, feel free to tack onto bug 6384.

https://bugs.schedmd.com/show_bug.cgi?id=6384

> On Jan 22, 2019, at 1:15 PM, Prentice Bisbal <pbisbal at pppl.gov> wrote:
> 
> Killian,
> 
> Thanks for the input. Unfortunately, all of this information from you, Ryan and others, is really ruining my plans, since it makes it look like my plan to fix a problem wit my cluster will not be as easy to fix as I'd hoped. One of the issues with my "Frankencluster" is that I'd like to assign jobs to different nodes based on the network they're on (1 GbE, 10 GbE, IB), along with other criteria, such as features requested.
> 
> I think it might be best if I write a longer e-mail to this list describing my cluster architecture, the problems I'm trying to address, and different possible approaches, and then get this list's feedback.
> 
> Prentice
> 
> On 1/18/19 11:53 AM, Kilian Cavalotti wrote:
>> On Fri, Jan 18, 2019 at 6:31 AM Prentice Bisbal <pbisbal at pppl.gov> wrote:
>>>> Note that if you care about node weights (eg. NodeName=whatever001 Weight=2, etc. in slurm.conf), using the topology function will disable it. I believe I was promised a warning about that in the future in a conversation with SchedMD.
>>> Well, that's going to be a big problem for me. One of the goals of me
>>> overhauling our Slurm config is to take advantage of the node weighting
>>> function to prioritize certain hardware over others in our very
>>> heterogeneous cluster.
>> I've heard that too (that enabling the Topology plugin would disable
>> node weighting), but I don't think it's accurate, both from the
>> documentation and from observation.
>> 
>> The doc actually says (https://slurm.schedmd.com/topology.html)
>> 
>> """
>> NOTE:Slurm first identifies the network switches which provide the
>> best fit for pending jobs and then selectes the nodes with the lowest
>> "weight" within those switches. If optimizing resource selection by
>> node weight is more important than optimizing network topology then do
>> NOT use the topology/tree plugin.
>> """
>> 
>> So the Topology plugin does take precedence over the weighting
>> algorithm, but it doesn't disable it, AFAIK. And for sites using
>> disjoint networks, as we do, this is a sane behavior.
>> 
>> Cheers,
> 

--
____
|| \\UTGERS,  	 |---------------------------*O*---------------------------
||_// the State	 |         Ryan Novosielski - novosirj at rutgers.edu
|| \\ University | Sr. Technologist - 973/972.0922 (2x0922) ~*~ RBHS Campus
||  \\    of NJ	 | Office of Advanced Research Computing - MSB C630, Newark
     `'