Hi,
I’m running 2 slurmds on a single host (built with --enable-multiple-slurmd).
The total cpus are divided equally among the 2 nodes.
I’m trying to test the distribution modes=block/cyclic but the tasks are always
allocated on the first node unless I use --ntasks-per-node=1
$ srun -n2
Hartley,
Sounds like you might be wanting srun.
If I ask for 5 nodes on our rzmerl system:
salloc -p pdebug -N 5
salloc: Granted job allocation 1966117
srun hostname
rzmerl1
rzmerl2
rzmerl4
rzmerl3
rzmerl5
Phil Eckert
LLNL
From: Hartley Greenwald
You could also use pdsh (https://code.google.com/p/pdsh/)
Uwe
Am 30.06.2014 23:41, schrieb Eckert, Phil:
Hartley,
Sounds like you might be wanting srun.
If I ask for 5 nodes on our rzmerl system:
salloc -p pdebug -N 5
salloc: Granted job allocation 1966117
srun hostname
rzmerl1
rzmerl2
Hi Phil,
Won't that just distribute the work among the nodes? I need a command that
will give one copy of the command to each node rather than distributing it.
Hartley
On Mon, Jun 30, 2014 at 4:02 PM, Uwe Sauter uwe.sauter...@gmail.com wrote:
You could also use pdsh
I may be wrong about this because I'm pretty new to all this stuff, but I
think that I want to give a copy to every node allocated for the job.
On Mon, Jun 30, 2014 at 5:13 PM, Gary Brown gbr...@adaptivecomputing.com
wrote:
Hartley,
To clarify, you want to run a command on every node in the
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
On 01/07/14 09:18, Hartley Greenwald wrote:
I may be wrong about this because I'm pretty new to all this stuff,
but I think that I want to give a copy to every node allocated for
the job.
To emulate pbsdsh you are quite correct.
According to