/
HPC System and Job Queries

HPC System and Job Queries

Owned by Abigail Smith (Unlicensed)
Last updated: Jan 09, 2025 by Lisa Stafford
12 min read

Overview: HPC Information and Compute Job Information

System querying is helpful to understand what is happening with the system. Meaning, what compute jobs are running, storage quotas, job history, etc. This page contains commands and examples of how to find that information.

Common SLURM Commands

The following describes common SLURM commands and common flags you may want to include when running them. SLURM commands are often run with flags (appended to the command with --flag) to stipulate specific information that should be included in output.

SQUEUE: Get information about running and queued jobs on the cluster with squeue

This command is used to pull up information about the jobs that currently exist in the SLURM queue. This command run as default will print all running and queued jobs on the cluster listing each job’s job ID, partition, username, job status, number of nodes, and a node list, with the name of the nodes allocated to each job:

squeue JOBID PARTITION NAME USER ST TIME NODES NODELIST(REASON) 1000001 inv-arcc myjob_11 user5 R 2-15:39:34 1 mba30-005 1000002 inv-lab2 AIML-CE joeblow R 6-13:02:32 1 mba30-004 1000005 inv-lab2 AIML-CE joeblow R 6-17:31:53 1 mba30-004 1000012 mb interact cowboyjoe R 2-21:28:49 1 mbcpu-010 1000015 mb sys/dash jsmith R 1:05:19 1 mbcpu-001 1000019 mb-a30 sys/dash janesmit R 8:45:36 1 mba30-006 1000022 mb-a30 Script.s doctorm PD 0:00 1 (Resources) 1000025 mb-a30 Script.22 doctorz R 7:05:44 1 mba30-001 1000028 mb-h100 sys/dash mmajor PD 0:00 1 (Resources) 1000033 mb-h100 sys/dash mmajor PD 0:00 1 (Priority) 1000037 mb-h100 sys/dash kjohnson PD 0:00 1 (Priority) 1000041 mb-h100 sys/dash kjohnson PD 0:00 1 (Priority) 1000045 mb-h100 sys/dash mmajor R 2-02:25:37 1 mbh100-003 1000058 mb-l40s Script.se doctorz R 1-00:58:25 1 mbl40s-003 1000062 teton C1225-TT user17 R 3-19:54:48 1 t507 1000065 teton C1225-TT user17 R 4-17:36:26 1 t502

Helpful flags when calling squeue to tailor your query

Flag

Used this when

Short Form

Short Form Ex.

Long Form

Useful flag info, Long Form Example & Output

Flag

Used this when

Short Form

Short Form Ex.

Long Form

Useful flag info, Long Form Example & Output

me

To get a printout with just your jobs

n/a

n/a

--me

The --me flag, will print the squeue info, specifically about jobs submitted by you:

[jsmith@mblog1 ~]$ squeue --me JOBID PARTITION NAME USER ST TIME NODES NODELIST(REASON) 1000002 inv-lab2 AIML-CE jsmith R 6-13:02:32 1 mba30-004 1000005 inv-lab2 AIML-CE jsmith R 6-17:31:53 1 mba30-004

user

To get a printout of a specific user’s jobs

-u

squeue -u joeblow

--user

The --user or -u flag, (shown in the expandable example below specifying a username), prints squeue info, specifically about jobs submitted by a specified user:

[jsmith@mblog1 ~]$ squeue --user=joeblow JOBID PARTITION NAME USER ST TIME NODES NODELIST(REASON) 1000002 inv-lab2 AIML-CE joeblow R 6-13:02:32 1 mba30-004 1000005 inv-lab2 AIML-CE joeblow R 6-17:31:53 1 mba30-004

long

To get a printout of jobs including wall time

-l

squeue -l

--long

The --long flag (shown in the expandable example below) will print the above information as well as the wall time requested for the job.

format

To get squeue printout with specified format & output

-o

squeue -o Account,UserName,JobID,SubmitTime,StartTime,TimeLeft

--format

If appended with the --format flag, squeue info is given using specified format & output. Format should be indicated using column names recognized by SLURM (hint: run squeue --helpFormat to get a list of SLURM’s recognized column names)

** you can also run squeue --help to get a comprehensive list of flags available to run with the squeue command

SACCT: Get information about recent or completed jobs on the cluster with sacct

The default sacct command: This print a list of your recent or recently completed jobs

Helpful flags when calling sacct to tailor your query

Flag

Use this when

Short Form

Short Form Ex.

Long Form

Useful flag info, Long Form Example & Output

Flag

Use this when

Short Form

Short Form Ex.

Long Form

Useful flag info, Long Form Example & Output

job

To get info about specific job#(s)

-j

sacct -j 1000013

--jobs

batch script

To view batch / submission script for a specific job

-B

sacct -j 1000101 -B

--batch-script

You must specify a job with the --jobs or -j flag to use the -B or --batch-script flag and see it’s associated batch / submission script. This will not work on interactive jobs run from an salloc command, or jobs that were not called from a script.

user

To get a printout of a specific user’s jobs

-u

sacct -u joeblow

--user

The --user or -u flag, (shown in the expandable example below specifying a username), prints squeue info, specifically about jobs submitted by a specified user:

start

To get a printout of job(s) starting after a date/time

-S

sacct -S 2024-11-01

--start

Dates and times should be specified with format YYYY-MM-DD-HH:MM

end

To get a printout of job(s) ending before a given date/time

-E

sacct -E 2024-11-24:12:00:00

--end

 

Dates and times should be specified with format YYYY-MM-DD-HH:MM

 

format

To get sacct printout with specified format & output

-O

sacct -O Account,JobID

--format

If appended with the --format flag, sacct info is given using specified format & output. Format should be indicated using column names recognized by SLURM (hint: run sacct --helpformat to get a list of SLURM’s recognized column names)

submit line

To view the submit command for a specified job

-o SubmitLine

sacct -o SubmitLine -j 1000101

--format=SubmitLine

This is a way of using the --format flag from above to see a print out of the command your entered to submit the specified job after the -j flag.

WorkDir

To view the working directory used by the job to execute commands

-o WorkDir

sacct -o WorkDir -j 1000101

--format=WorkDir

My Job Failed. What Do these Exit Codes Mean?

Slurm records error codes in the form of numerical values that seem rather cryptic. While we don’t always know for sure why they’re caused without investigation, some causes are more likely than others. Exit codes usually consist of 2 sets of numbers (one before a colon and one after) or a single number. Common error codes and their likely causes are below:

Exit Code

Likely Cause

Exit Code

Likely Cause

0

The job ran successfully

Any non-zero value

The job failed in some form or another

1

A general failure

2

Something was wrong with a shell command in the script

3 and above

Job error associated with software commands (check software specific exit codes)

0:9

The job was cancelled (usually the user or Slurm/System)

0:15

The job was cancelled (usually because the user cancelled the job, or it ran over specified walltime)

0:53

Some file or directory referenced in the script was not readable or writable

0:125

Job ran out of memory

Anything else

Contact arcc-help@uwyo.edu to have us investigate

 

** you can also run sacct --help to get a comprehensive list of flags available to run with the sacct command

SINFO: Get information about cluster nodes and partitions

The default sinfo command: This print a list of all partitions, their states, availability, and associated nodes on the cluster

Helpful flags when calling sinfo to tailor your query

Flag

Used this when

Short Form

Short Form Ex.

Long Form

Useful flag info, Long Form Example & Output

Flag

<