-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1
On 03/03/14 12:01, Christopher Samuel wrote:
> and I can see the expected values when I do:
>
> # sacctmgr show assoc where cluster=barcoo account=foo
>
> but it doesn't appear to have any effect. I've tried restarting
> slurmctld on the node just in case.
To add to my confusion I've tried to achieve the same outcome by using
a QoS per cluster and setting the MaxJobsPerUser value for the QoS and
then moving all the jobs for a cluster into that QoS (after having set
appropriate values for accounts QoS lists and defaults).
[root@barcoo-m ~]# sacctmgr list qos format=name,maxjobsperuser
Name MaxJobsPU
- ---------- ---------
normal 1
bruce
merri 192
barcoo 192
avoca
But that too seems to have no effect.
Now if I su to the problem user in question and submit a new job as them
then it does get correctly blocked as QOSResourceLimit, but this doesn't
appear to happen for already queued jobs.
Any ideas?
cheers!
Chris
- --
Christopher Samuel Senior Systems Administrator
VLSCI - Victorian Life Sciences Computation Initiative
Email: [email protected] Phone: +61 (0)3 903 55545
http://www.vlsci.org.au/ http://twitter.com/vlsci
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.14 (GNU/Linux)
Comment: Using GnuPG with Thunderbird - http://www.enigmail.net/
iEYEARECAAYFAlMUGvwACgkQO2KABBYQAh92JwCfZetFVe0wm4Pmu5VGr5uEFCV2
X3YAn3uPv/0fmHiFZcXjePzRCZd2k0C8
=c1a6
-----END PGP SIGNATURE-----
