It has been pointed by someone here, who clearly reads the documentation a lot closer than most, that there appears to be an inconsistency in the way that the SLURM documentation, explains the link between CompleteWait and KillWait.
The default values for CompleteWait and KillWait are (cut and paste taken from the schedmd website docs as this email was writte) 0 and 30 seconds respectively: CompleteWait The default value of CompleteWait is zero seconds. KillWait The default value is 30 seconds. The inconsistency arises when we read how CompleteWait is further explained, vis: To minimize fragmentation of resources, a value equal to KillWait plus two is recommended. In that case, setting KillWait to a small value may be beneficial. which would appear to be suggesting that the default for CompleteWait should be 32 seconds. Any thoughts? Kevin -- Supercomputing Systems Administrator Pawsey Supercomputing Centre
