I don't really have enough experience with QoS's to give a slicker
method but you could use squeue --qos to poll the QoS and then write a
wrapper to do the summarization. It's hacky but it should work.
-Paul Edmon-
On 8/19/2018 9:26 PM, Christopher Samuel wrote:
Hi folks,
After an extended hiatus (I forgot to resubscribe after going away for a
few weeks) I'm back.. ;-)
We are using QOS's for projects which have been granted a fixed set of
time for higher priority work which works nicely, but have just been
asked the obvious question "how much time do we have left?".
The QOS's are set up with:
sacctmgr create qos astac_oz045 priority=10000 flags=NoDecay
GrpTRESMins=cpu=15000000
so once they hit that GrpTRESMins limit they should stop being able
to run with the priority boost (as NoDecay stops the usage accrued
being decayed as it is for fair-share).
It seems that neither sreport nor "sacctmgr list qos" has a way of
reporting the overall usage against a QOS (with sacctmgr you can set
the rawusage to 0 you can't actually see what it is).
Anyone found a way to do this?
All the best,
Chris
