Do you mean the second configuration scheme?
I think configuring `dbdhost=localhost` is the same as configuring ` DbdAddr
=nodeC` and ` DbdAddr =nodeD` on the two nodes respectively.
The key point is whether we should set the DbdBackupHost option and how it work?
发件人: Daniel Letai
发送时间:
How about using cpusets
Create a boot cpusets with the e cores and start slurm in the p cores
Yeah showing my age by talking about cpusets
On Wed, Feb 19, 2025, 6:05 PM Timo Rothenpieler via slurm-users <
slurm-users@lists.schedmd.com> wrote:
> On 19.02.2025 14:06, Luke Sudbery via slurm-users w
On 19.02.2025 14:06, Luke Sudbery via slurm-users wrote:
How much RAM does your laptop have? How much have you told slurm it has?
How much is needed by the system? Does your task actually need 2GB?
Also your CPU/cores/threads counts don't appear to make sense.
It's probably one of those newer
How much RAM does your laptop have? How much have you told slurm it has? How
much is needed by the system? Does your task actually need 2GB?
Also your CPU/cores/threads counts don't appear to make sense.
The node/partition info from slurm.conf might help. What does `slurmd -C` say
on your lapto
Hi there,
we use haproxy to distribute SLURM REST API requests to multiple
instances of slurmrestd. For the haproxy we need a health check. At the
moment we are just checking that we get a 401 status. This works but we
are ending up with a lot of noise in the log files.
It would be very nice if th
I’d put something in cloud-init or the EC2 user data script to synchronise them
as the instance comes up, whatever your preference is for doing that sort of
thing; ansible, or just simply copying the file (if you’re certain they should
be identical on every node, and I’d hope they are!)
Tim
--
I'm not sure it will work, didn't test it, but could you just do
`dbdhost=localhost` to solve this?
On 18/02/2025 11:59, hermes via
slurm-users wrote:
The deployment scenario
is as follows:
There are a couple of options here, not exactly convenient but
will get the job done:
1. Use array, with `-N 1 -w ` defined for each
array task. You can do the same without array, using for loop to
submit different sbatchs.
2. Use `scontrol reboot`. Set the reb
