[slurm-users] slurm-wlm package OpenMPI PMIx implementation

Christopher J Cawley ccawley2 at gmu.edu
Thu Dec 10 17:55:38 UTC 2020


Hi Avery -

No worries,

I took all of the defaults for software, etc.
Jetson's are locked into ubuntu 18.04.5,
slurm 19.05.7, etc.

Do you have code to test?  I'm more of a python person.

Thanks
Chris


Christopher J. Cawley

Systems Engineer/Linux Engineer, Information Technology Services

223 Aquia Building, Ffx, MSN: 1B5

George Mason University


Phone: (703) 993-6397

Email: ccawley2 at gmu.edu

​

________________________________
From: slurm-users <slurm-users-bounces at lists.schedmd.com> on behalf of Avery Grieve <agrieve at umich.edu>
Sent: Thursday, December 10, 2020 11:38 AM
To: Slurm User Community List <slurm-users at lists.schedmd.com>
Subject: Re: [slurm-users] slurm-wlm package OpenMPI PMIx implementation

Oop, sorry I meant to also include the following:

# srun --mpi=list
srun: MPI types are...
srun: none
srun: pmi2
srun: openmpi

running srun with --mpi=openmpi gives the same errors as with MpiDefault=none.

~Avery Grieve
They/Them/Theirs please!
University of Michigan


On Thu, Dec 10, 2020 at 11:34 AM Avery Grieve <agrieve at umich.edu<mailto:agrieve at umich.edu>> wrote:
Hi Chris,

Thank you for the offer. Here's some quick information on my system:

All nodes on Debian 10 (armbian buster converted to DietPi v6.33.3).
sinfo --version: slurm-wlm 18.08.5-2

With MpiDefault=pmix I get the following srun errors:
srun: error: Couldn't find the specified plugin name for mpi/pmix looking at all files
srun: error: cannot find mpi plugin for mpi/pmix
srun: error: cannot create mpi context for mpi/pmix
srun: error: invalid MPI type 'pmix', --mpi=list for acceptable types

With MpiDefault=none
I get OpenMPI yelling at me and giving me two options, only one relevant to the version of Slurm I'm running:
version 16.05 or later: you can use SLURM's PMIx support. This
  requires that you configure and build SLURM --with-pmix.

However, as I stated, I'm using the slurm-wlm package which seems to not include the pmix functionality by default.

The other option provided:
Versions earlier than 16.05: you must use either SLURM's PMI-1 or
  PMI-2 support. SLURM builds PMI-1 by default, or you can manually
  install PMI-2. You must then build Open MPI using --with-pmi pointing
  to the SLURM PMI library location.

Similar issue, not building slurm from source doesn't include the PMI library. I've installed some develop level packages, including the libpmi2-0 package<https://secure-web.cisco.com/10RRF9yf9i-7-zx463otbTEYwHQ8PfAu0MWZDt-sp7LOW0FINJnwC3j6h5vCPjyEOcW_d4xkUjeu3yTU6e1aZhW7bYufUDkpZVQ_-IyrDmd5Zl9_4fUvMFvlohRkxN3_18FcN6caXv3CyLnSbizh35atzHBeuC4aREJBiZNIfqjJfrO5LI5pK6coWiyFVqweLpTWOQUWbdjzpnAG7whBZiDXOyp20-eAgY5v3ChNlgtjLNr_9d-OV97ux4pQyrfVyOZ2yTcVNF-THuyFtghkAO6wbbfRVQ9bRhzVsADarrzAyye3nTdVUQeehuf2hANuF7JLIXPuBmV-cAwMpZfuoC6PYr_FI0PoBsPUDaBCrFbagrJzfPr3ufkZsVxor3fyBaY8Vcphc-CfnpwfraZSpFHI8BC4Xq0l475bH5OSBCoQAFV8aE_hF-rycPo-gDRkmSqqHnKTUMuyHb5G46NQ7NQ/https%3A%2F%2Fpackages.debian.org%2Fbuster%2Flibpmi2-0> which didn't seem to actually install anything useful as far as I can tell using the "find" command.

It's sort of looking like I should be looking at building slurm from source again, I guess.

Thanks,

~Avery Grieve
They/Them/Theirs please!
University of Michigan


On Thu, Dec 10, 2020 at 11:16 AM Christopher J Cawley <ccawley2 at gmu.edu<mailto:ccawley2 at gmu.edu>> wrote:
I have a 7 node jetson nano cluster running at home.

Send me what you want me to take a look at .  If it's not
a big deal, then I can let you know.

Ubuntu 18 / slurm <some version from rpm>

Thanks
Chris


Christopher J. Cawley

Systems Engineer/Linux Engineer, Information Technology Services

223 Aquia Building, Ffx, MSN: 1B5

George Mason University


Phone: (703) 993-6397

Email: ccawley2 at gmu.edu

​

________________________________
From: slurm-users <slurm-users-bounces at lists.schedmd.com<mailto:slurm-users-bounces at lists.schedmd.com>> on behalf of Avery Grieve <agrieve at umich.edu<mailto:agrieve at umich.edu>>
Sent: Thursday, December 10, 2020 10:51 AM
To: slurm-users at lists.schedmd.com<mailto:slurm-users at lists.schedmd.com> <slurm-users at lists.schedmd.com<mailto:slurm-users at lists.schedmd.com>>
Subject: [slurm-users] slurm-wlm package OpenMPI PMIx implementation

Hi Forum,

I've been putting together an ARM cluster for fun/learning and I've been a bit lost about how to get OpenMPI and slurm to behave together.

I have installed the slurm-wlm package <https://secure-web.cisco.com/14EwNb3UZYABzVqRN7IxszUw4L04o_2Bv7wm3a5vivtuqZhDuY3UrhulGE47J31qdoC16rhtMefWeyLXhK10TMim7oOCehTuBJR_47pTBDKcO_xYDX3yqOG1yzamsO31hXo3HS9tSUpOssM40vTLwy4Mxfggu2Qu_yXjJqtLE43mV2CrECvinY7hMt_cRMzi4b8xrKZXqngR31DMmyA9DzimeyLsN7nwxh6kJRMhcg2MjHlCOhu356VVZrErEM9ZafOD66sDUMluigARg1icclZaJOLhXE-7PlFRtAdk2dhXLEvRqSL3SUKrVeBy01MCmSi7sH8bkIijrujncTBU-DfWxY_JOwqhhsJAyXl0XJgjoOiGWHKcLPRRvrCbn_SGHGSw2Ogq3aC4sJLY1tBLwpgvXcOxFoURgb6y6WfJJg04H9ewyQ-Azr7kA_en7DIk_4KOux310uOWzo7XrHTxnLg/https%3A%2F%2Fpackages.debian.org%2Fbuster%2Fslurm-wlm> from the Debian apt search and compiled OpenMPI from source on my compute nodes. OpenMPI has been compiled with the option --with-slurm and the configure time log indicates openmpi has pmix v3 built in. I thought that would be enough for slurm and calling a job with "srun -n 4 -N1 executable" (with slurm.conf having MpiDefault=pmix_v3) would be enough.

Not the case, unfortunately as slurm doesn't have any idea what pmix_v3 means without being compiled against it I guess. I have also attempted to compile openmpi from source with the --with-pmi option but the slurm-wlm package doesn't install any of the libraries/headers (pmi.h pmi2.h pmix.h etc). Neither does any of the slurm-llnl develop packages, so I'm at a loss of what to do here.

A few notes: OpenMPI is working across my compute nodes. I'm able to ssh to my compute node and start a job manually with mpirun that executes successfully across the nodes. My slurmctld and slurmd daemons work for single thread resource allocation (and presumably OpenMP multithreading, though I haven't tested this).

Beyond compiling slurm from source (assuming this installs the pmi headers that I can use to build openmpi), which I have tried with no luck on my devices, is there a way to get slurm and openmpi to behave together using the precompiled package slurm-wlm?

Thank you,

~Avery Grieve
They/Them/Theirs please!
University of Michigan
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.schedmd.com/pipermail/slurm-users/attachments/20201210/05f9a1a1/attachment-0001.htm>


More information about the slurm-users mailing list