"Jette, Moe" <[email protected]> writes: > The problem was that if there was more than one job running on the node when > drained, then when the running job completed another job could be started on > the node (at least for some time). The following patch fixes the problem and > will > be in slurm v2.2.4, which we plan to release next week.
Thanks! -- Bjørn-Helge Mevik, dr. scient, Research Computing Services, University of Oslo
