[slurm-dev] Re: tirivial question regarding node ranges

2015-09-25 Thread Antonia Mey
I see, I had put a space there..programming habit! Thank you for the help. On 25 September 2015 at 16:08, Michael Gutteridge < michael.gutteri...@gmail.com> wrote: > Hi > > Search for "node range expression" in the slurm.conf manpage. You want: > > PartitionName=serial Nodes=node0[01-07,10-13]

[slurm-dev] Slurm Notification Email Body Empty

2015-09-25 Thread Mike Hanby
Howdy, We are migrating from using SGE to Slurm on our new cluster and have just started running some test jobs. We are running Slurm 14.11.6 on CentOS 7. Slurm email notifications are being sent with a subject and no email body. Is this as expected, or should their be job related metrics in

[slurm-dev] Re: Nodes dropping offline after replacing switch

2015-09-25 Thread Moe Jette
This may help. Especially the section "Networking and configuration problems". http://slurm.schedmd.com/troubleshoot.html Quoting Bob Healey : Hello. I've spent a week or two trying to figure this one out. Recently, I replaced a two of my four dying SMC 8648T switches

[slurm-dev] Re: tirivial question regarding node ranges

2015-09-25 Thread Michael Gutteridge
Hi Search for "node range expression" in the slurm.conf manpage. You want: PartitionName=serial Nodes=node0[01-07,10-13] ... HTH On Fri, Sep 25, 2015 at 7:17 AM, Antonia Mey wrote: > Hi all, > I am sure this is a trivial question, but I can't seem to find a working >

[slurm-dev] Re: pam_slurm: how can I exclude some users from pam_slurm?

2015-09-25 Thread Koji Tanaka
Thank you Marcin and Michael. pam_listfile worked great. I leave the link to my note for someone who wants to do the same thing. https://gist.github.com/kjtanaka/e38eaf45b2255310033e Best regards, Koji On Fri, Sep 25, 2015 at 2:18 AM, Michael Jennings wrote: > > On Thu, Sep 24,

[slurm-dev] Re: slurm-dev summary, was Re: What follows PMI-2?

2015-09-25 Thread Ralph Castain
Hi Andy Let me see if I can clarify this for you and the others on this mailing list. The Ohio State group has been focused on improving the wireup algorithm in PMI-2, which focuses on the allgather operation. Hence their “ring” implementation. PMIx has been focused on two goals: 1.

[slurm-dev] RE: Slurm Notification Email Body Empty

2015-09-25 Thread Dennis McRitchie
Hi Mike, Yes, this is normal behavior for Slurm. If you were running v15.08, then you could simply use smail and seff, as described here: http://bugs.schedmd.com/show_bug.cgi?id=1611 But if you have to use 14.11, then you could still use smail, but would need to populate the body with

[slurm-dev] Re: jobs arrays & slurm_load_job changes in 14.11+

2015-09-25 Thread E V
Getting a chance to start working on this. Changing the slurm-drmaa callers in job.c to use the {kill,update,resume}..2() versions seems straightforward, and I've done that. However, now I'm dieing calling slurm_load_job() with a string, ie 7_1. I don't see a slurm_load_job2() in 14.11.9. What's

[slurm-dev] Re: jobs arrays & slurm_load_job changes in 14.11+

2015-09-25 Thread Moe Jette
Call slurm_load_job() with the job ID number (i.e. 7). That will return information about all tasks (job array elements) associated with the specified job ID. You can then look for the desired task ID value(s) in the returned array. Quoting E V : Getting a chance to

[slurm-dev] Slurm version 15.08.1 is now availabe

2015-09-25 Thread Moe Jette
We are pleased to announce the availability of Slurm version 15.08.1 with about 40 bug fixes to 15.08.0. A list of changes is appended. Slurm downloads are available from http://www.schedmd.com/#repos * Changes in Slurm 15.08.1 == -- Fix test21.30 and 21.34 to check

[slurm-dev] Re: slurm-dev summary, was Re: What follows PMI-2?

2015-09-25 Thread Sourav Chakraborty
Hi All, To clarify things, we have had similar goals and have been working on improving the PMI-2 plugin for some time. We evaluated several designs and strategies: 1. Designs and detailed performance evaluations (up to 16K cores) for on-demand PMI gets (similar to instant startup if I

[slurm-dev] Re: pam_slurm: how can I exclude some users from pam_slurm?

2015-09-25 Thread Michael Jennings
On Thu, Sep 24, 2015 at 9:18 PM, Koji Tanaka wrote: > Is there a way to exclude some users from pam_slurm? > > I've successfully set up ssh restriction with using pam_slurm, but there's > one problem. When we deploy our system, we use a regular user > account+sudo+ansible,

[slurm-dev] Re: pam_slurm: how can I exclude some users from pam_slurm?

2015-09-25 Thread Marcin Stolarek
pam_listfile before pam_slurm with "sufficient" key word in pam.d/ssh configuration? cheers, marcin 2015-09-25 6:18 GMT+02:00 Koji Tanaka : > Hello Slurm Community, > > Is there a way to exclude some users from pam_slurm? > > I've successfully set up ssh restriction with

[slurm-dev] slurm-dev summary, was Re: What follows PMI-2?

2015-09-25 Thread Andy Riebs
Synthesizing what I think I've learned over the past 24 hours, [*]The PMIx implementation described at describes a complete, upward-compatible [I hope!] highly-scalable (exascale) replacement for the PMI-1 and PMI-2 job launch

[slurm-dev] tirivial question regarding node ranges

2015-09-25 Thread Antonia Mey
Hi all, I am sure this is a trivial question, but I can't seem to find a working solution. I have two partitions on my small cluster a serial queue and a GPU queue. I recently acquired some new nodes and now I would like my partition config to look something like this: PartitionName=serial