[slurm-users] Running Containerized Slurmctld and Slurmdb in Production?

Rigoberto Corujo rcorujo at yahoo.com
Wed Mar 15 17:57:27 UTC 2023

 Hi Mike,
If you run the Slurm daemons in a container, but the Slurm commands are run from the host, you need to make sure that the Slurm commands on the host and the Slurm daemons in the container are running similar versions of Slurm. Otherwise, the commands may not be able to communicate with the daemons if there's a protocol change.  We were running the Slurm daemons in a container and ran into a problem where the commands could no longer communicate with the daemons when the version of Slurm on the host was updated, but the container was still running an older version of the daemons.
    On Wednesday, February 15, 2023 at 01:52:33 PM EST, Hanby, Mike <mhanby at uab.edu> wrote:  
  <!--#yiv0249574192 filtered {}#yiv0249574192 filtered {}#yiv0249574192 p.yiv0249574192MsoNormal, #yiv0249574192 li.yiv0249574192MsoNormal, #yiv0249574192 div.yiv0249574192MsoNormal {margin:0in;font-size:11.0pt;font-family:"Calibri", sans-serif;}#yiv0249574192 a:link, #yiv0249574192 span.yiv0249574192MsoHyperlink {color:#0563C1;text-decoration:underline;}#yiv0249574192 span.yiv0249574192EmailStyle17 {font-family:"Calibri", sans-serif;color:windowtext;}#yiv0249574192 .yiv0249574192MsoChpDefault {}#yiv0249574192 filtered {}#yiv0249574192 div.yiv0249574192WordSection1 {}-->
Just wondering if any sites are running containerized Slurmctld and Slurmdbd in production?
We are in the process of planning migrating from a single host running slurmctld, slurmdbd, and MySQL (and other HPC services) to separate OpenStack VMs. Our site averages less than 1000’s running / pending jobs at any given time. Like many HPC sites, our jobs are a mix of long running, large arrays, very short…
I ran across this Github project “Slurm Docker Cluster”https://github.com/giovtorres/slurm-docker-cluster and got me thinking that this method might be great for simpler upgrades, ease of reproducing the cluster in development, etc…
How about it, anyone running containerized Slurm server processes in production?
Thanks, Mike
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.schedmd.com/pipermail/slurm-users/attachments/20230315/48d4b65b/attachment.htm>

More information about the slurm-users mailing list