TORQUE creates many files for array jobs with a large index.


Issue:

TORQUE creates many files for array jobs with a large index.  This results in

1) Using the filesystem as a database is problematic at scale. 

2) having large number of jobs vastly slows down TORQUE and Moab. 

 

Solution:

Starting in 5.1.2,6.0.1 a new parameter "use_job_subdirs" can be used.

"use_jobs_subdirs"

 

http://docs.adaptivecomputing.com/torque/6-0-2/adminGuide/help.htm#topics/torque/13-appendices/serverParameters.htm#use_jobs_subdirs

use_jobs_subdirs
Format <BOOLEAN>
Default Not set (FALSE).
Description

Lets an administrator direct the way pbs_server will store its job-related files.

  • When use_jobs_subdirs is unset (or set to FALSE), job and job array files will be stored directly under $PBS_HOME/server_priv/jobs and $PBS_HOME/server_priv/arrays.
  • When use_job_subdirs is set to TRUE, job and job array files will be distributed over 10 subdirectories under their respective parent directories. This method helps to keep a smaller number of files in a given directory.

    This setting does not automatically move existing job and job array files into the respective subdirectories. If you choose to use this setting (TRUE), you must first

    • set use_jobs_subdirs to TRUE,
    • shutdown the Torque server daemon,
    • in the contrib directory, run the "use_jobs_subdirs_setup" python script with -m option,
    • start the Torque server daemon.


Jira:

TRQ-3725

Tags: lots of files, use_jobs_subdirs
Last update:
2016-08-08 19:00
Author:
Jason Booth
Revision:
1.0
Average rating:0 (0 Votes)

You cannot comment on this entry

Chuck Norris has counted to infinity. Twice.

Records in this category

Tags