Ticket 4592 - Can't find state codes for slurmctld.log entries
Summary: Can't find state codes for slurmctld.log entries
Status: RESOLVED INFOGIVEN
Alias: None
Product: Slurm
Classification: Unclassified
Component: Documentation (show other tickets)
Version: 17.02.7
Hardware: Linux Linux
: 4 - Minor Issue
Assignee: Marshall Garey
QA Contact:
URL:
: 3731 (view as ticket list)
Depends on:
Blocks:
 
Reported: 2018-01-08 10:55 MST by GSK-ONYX-SLURM
Modified: 2018-01-09 11:31 MST (History)
2 users (show)

See Also:
Site: GSK
Slinky Site: ---
Alineos Sites: ---
Atos/Eviden Sites: ---
Confidential Site: ---
Coreweave sites: ---
Cray Sites: ---
DS9 clusters: ---
Google sites: ---
HPCnow Sites: ---
HPE Sites: ---
IBM Sites: ---
NOAA SIte: ---
NoveTech Sites: ---
Nvidia HWinf-CS Sites: ---
OCF Sites: ---
Recursion Pharma Sites: ---
SFW Sites: ---
SNIC sites: ---
Tzag Elita Sites: ---
Linux Distro: ---
Machine Name:
CLE Version:
Version Fixed:
Target Release: ---
DevPrio: ---
Emory-Cloud Sites: ---


Attachments

Note You need to log in before you can comment on or make changes to this ticket.
Description GSK-ONYX-SLURM 2018-01-08 10:55:12 MST
Hi.

I have looked through multiple documents but cannot find an explanation for the meaning of the state codes in the slurm control daemon log file,eg

 job_complete: JobID=846 State=0x8003 NodeCnt=1 done

 job_complete: JobID=222 State=0x8005 NodeCnt=1 done

 job_complete: JobID=224 State=0x1 NodeCnt=1 WEXITSTATUS 13

I'm assuming 0x1 means success, but what do 0x8003 and 0x8005 mean and what other values might I expect to see?

Thanks.
Mark.
Comment 1 Marshall Garey 2018-01-08 11:33:28 MST
Hi Mark. The job states can be found in slurm/slurm.h.in. 0-15 are mutually exclusive "states" the job can be in; the rest are bit flags that may be set in addition to the regular state.

State 0x8003 is COMPLETE (state 3) with the flag JOB_COMPLETING (0x8000).
State 0x8005 is FAILED (state 5) with the flag JOB_COMPLETING (0x8000).
State 1 is RUNNING.

Does that help?
Comment 3 Felip Moll 2018-01-08 11:44:41 MST
*** Ticket 3731 has been marked as a duplicate of this ticket. ***
Comment 9 GSK-ONYX-SLURM 2018-01-09 05:45:00 MST
(In reply to Marshall Garey from comment #1)
> Hi Mark. The job states can be found in slurm/slurm.h.in. 0-15 are mutually
> exclusive "states" the job can be in; the rest are bit flags that may be set
> in addition to the regular state.
> 
> State 0x8003 is COMPLETE (state 3) with the flag JOB_COMPLETING (0x8000).
> State 0x8005 is FAILED (state 5) with the flag JOB_COMPLETING (0x8000).
> State 1 is RUNNING.
> 
> Does that help?

Yes, thankyou.

Please go ahead and close the case.

Thanks.
Mark.