[slurm-dev] Cyclic distribution problem

2014-06-30 Thread Tsai Li Ming

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 --distribution=block/cyclic sleep 100

I’m using:
SelectType=select/cons_res
SelectTypeParameters=CR_CPU_MEMORY
NodeName=ltsai-dev-rhel7-1 NodeHostname=ltsai-dev-rhel7 Port=17001 Sockets=1 
CoresPerSocket=2 ThreadsPerCore=1 RealMemory=1841 State=UNKNOWN
NodeName=ltsai-dev-rhel7-2 NodeHostname=ltsai-dev-rhel7 Port=17002 Sockets=1 
CoresPerSocket=2 ThreadsPerCore=1 RealMemory=1841 State=UNKNOWN
PartitionName=compute Nodes=ltsai-dev-rhel7-[1-2] Default=YES MaxTime=INFINITE 
State=UP

Did I misconfigure something?

Thanks!=

[slurm-dev] Re: pbsdsh -u equivalent

2014-06-30 Thread 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
rzmerl4
rzmerl3
rzmerl5

Phil Eckert
LLNL

From: Hartley Greenwald jhgreenw...@gmail.commailto:jhgreenw...@gmail.com
Reply-To: slurm-dev slurm-dev@schedmd.commailto:slurm-dev@schedmd.com
Date: Monday, June 30, 2014 at 2:23 PM
To: slurm-dev slurm-dev@schedmd.commailto:slurm-dev@schedmd.com
Subject: [slurm-dev] pbsdsh -u equivalent

Hi,

Is there an equivalent command on slurm for the pbs command pbsdsh -u?  That is 
to say, is there some command which will give one copy of a command to each 
node in a given allocation?  I've combed through the documentation and there 
doesn't seem to be, but that struck me as odd that there wouldn't, so that's 
why I'm asking

Thank you,
Hartley



[slurm-dev] Re: pbsdsh -u equivalent

2014-06-30 Thread Uwe Sauter

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
rzmerl4
rzmerl3
rzmerl5

Phil Eckert
LLNL

From: Hartley Greenwald jhgreenw...@gmail.com 
mailto:jhgreenw...@gmail.com

Reply-To: slurm-dev slurm-dev@schedmd.com mailto:slurm-dev@schedmd.com
Date: Monday, June 30, 2014 at 2:23 PM
To: slurm-dev slurm-dev@schedmd.com mailto:slurm-dev@schedmd.com
Subject: [slurm-dev] pbsdsh -u equivalent

pbsdsh -u equivalent
Hi,

Is there an equivalent command on slurm for the pbs command pbsdsh 
-u?  That is to say, is there some command which will give one copy of 
a command to each node in a given allocation?  I've combed through the 
documentation and there doesn't seem to be, but that struck me as odd 
that there wouldn't, so that's why I'm asking


Thank you,
Hartley




[slurm-dev] Re: pbsdsh -u equivalent

2014-06-30 Thread Hartley Greenwald
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 (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
 rzmerl4
 rzmerl3
 rzmerl5

  Phil Eckert
 LLNL

   From: Hartley Greenwald jhgreenw...@gmail.com
 Reply-To: slurm-dev slurm-dev@schedmd.com
 Date: Monday, June 30, 2014 at 2:23 PM
 To: slurm-dev slurm-dev@schedmd.com
 Subject: [slurm-dev] pbsdsh -u equivalent

   Hi,

 Is there an equivalent command on slurm for the pbs command pbsdsh -u?
 That is to say, is there some command which will give one copy of a command
 to each node in a given allocation?  I've combed through the documentation
 and there doesn't seem to be, but that struck me as odd that there
 wouldn't, so that's why I'm asking

  Thank you,
  Hartley





[slurm-dev] Re: pbsdsh -u equivalent

2014-06-30 Thread Hartley Greenwald
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 cluster, not
 just on every node allocated to a job, correct?

 Gary Brown


 On Mon, Jun 30, 2014 at 5:01 PM, Hartley Greenwald jhgreenw...@gmail.com
 wrote:

  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 (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
 rzmerl4
 rzmerl3
 rzmerl5

  Phil Eckert
 LLNL

   From: Hartley Greenwald jhgreenw...@gmail.com
 Reply-To: slurm-dev slurm-dev@schedmd.com
 Date: Monday, June 30, 2014 at 2:23 PM
 To: slurm-dev slurm-dev@schedmd.com
 Subject: [slurm-dev] pbsdsh -u equivalent

   Hi,

 Is there an equivalent command on slurm for the pbs command pbsdsh -u?
 That is to say, is there some command which will give one copy of a command
 to each node in a given allocation?  I've combed through the documentation
 and there doesn't seem to be, but that struck me as odd that there
 wouldn't, so that's why I'm asking

  Thank you,
  Hartley







[slurm-dev] Re: pbsdsh -u equivalent

2014-06-30 Thread Christopher Samuel

-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 the manual page the --ntasks-per-node=1 option for srun
should do what you want.

cheers,
Chris
- -- 
 Christopher SamuelSenior Systems Administrator
 VLSCI - Victorian Life Sciences Computation Initiative
 Email: sam...@unimelb.edu.au Phone: +61 (0)3 903 55545
 http://www.vlsci.org.au/  http://twitter.com/vlsci

-BEGIN PGP SIGNATURE-
Version: GnuPG v1
Comment: Using GnuPG with Thunderbird - http://www.enigmail.net/

iEYEARECAAYFAlOx+JUACgkQO2KABBYQAh/+uQCdHWQEQ/H+aJMJ8ppeMD+C/r88
jb0An2qJT4FZxloNNOqP2owAC2N3W7eZ
=7BJX
-END PGP SIGNATURE-