Skip to content

Latest commit

 

History

History
 
 

contribs

This is the contribs dir for Slurm.

SOURCE DISTRIBUTION HIERARCHY
-----------------------------

Subdirectories contain the source-code for the various contributations for
Slurm as their documentation. A quick description of the subdirectories
of the Slurm contribs distribution follows:

  cray/               [Tools for use on Cray systems]
     capmc                 - Script used to emulate some capmc functionality
                             for testing without access to a Cray system
     capmc_resume.c        - Program used to reboot Cray nodes. Resets KNL node
                             MCDRAM and/or NUMA mode as requested.
     capmc_suspend.c       - Program used to power dowen Cray nodes.
     cnselect              - Script used to emulate some cnselect functionality
                             for testing without access to a Cray system.
     etc_sysconfig_slurm   - /etc/sysconfig/slurm for Cray XT/XE systems
     libalps_test_programs.tar.gz - set of tools to verify ALPS/BASIL support
			     logic. Note that this currently requires:
			     * hardcoding in libsdb/basil_mysql_routines.c:
			       mysql_real_connect(handle, "localhost", NULL, NULL, "XT5istanbul"
			     * suitable /etc/my.cnf, containing at least the lines
			       [client]
			       user=basic
			       password=basic
			     * setting the APBASIL in the libalps/Makefile, e.g.
			       APBASIL := slurm/alps_simulator/apbasil.sh
			     To use, extract the files then:
			     > cd libasil/
			     > make -C alps_tests all   # runs basil parser tests
			     > make -C sdb_tests  all   # checks if database routines work
			     A tool named tuxadmin is also also included. When
			     executed with the -s or --slurm.conf option, this
			     contact the SDB to generate system-specific information
			     needed in slurm.conf (e.g. "NodeName=nid..." and
			     "PartitionName= Nodes=nid... MaxNodes=...".
     opt_modulefiles_slurm - enables use of Munge as soon as built
     pam_job.c             - Less verbose version of the default Cray job service.

  gcp/               [Google Cloud Platform integration scripts]

  lua/               [ LUA scripts ]
     Example LUA scripts that can serve as Slurm plugins.
     job_submit.lua - job_submit plugin that can set a job's default partition
		      using a very simple algorithm
     job_submit_license.lua - job_submit plugin that can set a job's use of
		      system licenses
     proctrack.lua  - proctrack (process tracking) plugin that implements a
		      very simple job step container using CPUSETs

  make-3.81.slurm.patch   [ Patch to "make" command for parallel build ]
  make-4.0.slurm.patch    [ Patch to "make" command for parallel build ]
     This patch will use Slurm to launch tasks across a job's current resource
     allocation. Depending upon the size of modules to be compiled, this may
     or may not improve performance. If most modules are thousands of lines
     long, the use of additional resources should more than compensate for the
     overhead of Slurm's task launch. Use with make's "-j" option within an
     existing Slurm allocation. Outside of a Slurm allocation, make's behavior
     will be unchanged. Designed for GNU make-3.81 or make-4.0.

  mic                [Tools for use on Intel MIC processors]

  openlava/          [ Wrapper Scripts for OpenLava/LSF migration to Slurm ]
     Helpful scripts to make transition to Slurm easier from OpenLava or LSF.
     These scripts are easily updatable if there is functionality missing.

  pam/               [ PAM (Pluggable Authentication Module) for Slurm ]
     This PAM module will restrict who can login to a node to users who have
     been allocated resources on the node and user root.

  pam_slurm_adopt/   [ Plugin for PAM to place incoming connections into
                       existing Slurm job container ]
     This Slurm plugin provides a mechanism for new incomming connections to
     be placed into existing Slurm jobs containers so that then can be accounted
     for and killed at job termination. See the README file in the subdirectory
     for more details.

  perlapi/           [ Perl API to Slurm source ]
     API to Slurm using perl.  Making available all Slurm command that exist
     in the Slurm proper API.

  pmi2/              [ PMI2 client library ]
     User applications can link with this library to use Slurm's mpi/pmi2
     plugin.

  seff/              [Tools to include job include job accounting in email]
     Expand information in job state change notification (e.g. job start, job
     ended, etc.) to include job accounting information in the email. Configure
     Slurm's MailProg to "smail" from this package.

  sgather/           [ shell script ]
     Gather remote files from a job into a central location. Reverse of of
     sbcast command.

  sgi/               [Tools for use on SGI systems]
     netloc_to_topology.c   [ C program ]
     Used to construct a Slurm topology.conf file based upon SGI network APIs.
     README.txt      [Documentation]

  sjobexit/          [ Perl programs ]
     Tools for managing job exit code records

  sjstat             [ Perl program ]
     Lists attributes of jobs under Slurm control

  skilling.c         [ C program ]
     This program can be used to order the hostnames in a 2+ dimensional
     architecture for use in the slurm.conf file. It is used to generate
     the Hilbert number based upon a node's physical location in the
     computer. Nodes close together in their Hilbert number will also be
     physically close in 2-D or 3-D space, so we can reduce the 2-D or 3-D
     job placement problem to a 1-D problem that Slurm can easily handle
     by defining the node names in the slurm.conf file in order of their
     Hilbert number. If the computer is not a perfect square or cube with
     power of two size, then collapse the node list maintaining the numeric
     order based upon the Hilbert number.

  slurm_completion_help/     [shell script, vim file]
     Scripts to help in option completion when using slurm commands.

  slurm.spec-legacy  [ RPM build script ]
     A version of slurm.spec that may still work on older platforms.
     DEPRECATED, NOT MAINTAINED.

  spank_core.c       [ SPANK plugin, C program ]
     A Slurm SPANK plugin that can be used to permit users to generated
     light-weight core files rather than full core files.

  time_login.c       [ C program ]
     This program will report how long a pseudo-login will take for specific
     users or all users on the system. Users identified by this program
     will not have their environment properly set for jobs submitted through
     Moab. Build with "make -f /dev/null time_login" and execute as user root.

  torque/            [ Wrapper Scripts for Torque migration to Slurm ]
     Helpful scripts to make transition to Slurm easier from PBS or Torque.
     These scripts are easily updatable if there is functionality missing.
     NOTE: For the showq command, see https://github.com/pedmon/slurm_showq

  web_apps/          [ Script to display job usage statistics and cluster utilization ]