[slurm-users] sacctmgr - bug listing accounts?

[Loris Bennett]

Loris Bennett <loris.bennett at fu-berlin.de> writes:

[snip (93 lines)]

> Unfortunately sacctmgr just doesn't list 'geochemie' as being an
> account.  It only appears as the parent of the research groups which are
> below it in the hierarchy:
>
>   $ /usr/bin/sacctmgr -or show accounts | egrep 'geo|Acc|---'
>      Account                Descr                  Org 
>   ---------- -------------------- -------------------- 
>      agalpha              agalpha            geochemie 
>      agbravo              agbravo            geophysik 
>    agcharlie            agcharlie             geologie 
>      agdelta              agdelta           geographie 
>       agecho               agecho             geologie 
>    agfoxtrot            agfoxtrot           geographie 
>   geographie           geographie              geowiss 
>     geologie             geologie              geowiss 
>    geophysik            geophysik              geowiss 
>      geowiss              geowiss                 root 
>   meteorolo+         meteorologie              geowiss 
>
> It doesn't appear as a child of 'geowiss'.  It does however turn up in
> the list of associations:
>
>   $ /usr/bin/sacctmgr -or show assoc format=account | egrep 'geo|Acc|---'
>      Account 
>   ---------- 
>      geowiss 
>    geochemie 
>   geographie 
>     geologie 
>    geophysik 

[snip (21 lines)]

I have subsequently come across a similar case.  In August 2017 I
created an account, a user and a corresponding association.  Today I
found myself unable to create a new association with a new user and the
account from August.  Looking into the Slurm database, I saw that the
account was missing from 'acct_table'.  However, trying to add it with

  $ sacctmgr -v add account agschmidt parent=chemie

gave me

  sacctmgr: Accounting storage SLURMDBD plugin loaded with AuthInfo=(null)
   No associations created.

I have ended up having to insert a record directly into the database,
which seems to have worked in that I was then able to create the new
association.

This is all with 17.02.11.

Cheers,

Loris

-- 
Dr. Loris Bennett (Mr.)
ZEDAT, Freie Universität Berlin         Email loris.bennett at fu-berlin.de