Hi Sean, Hi Marcus, Changing from localhost to the actual IP seems to have solved the problem. Is that because not only the slurmctld process on the control node but also the slurmd processes on the compute nodes need to have access to the accounting information?
Because although slurmdbd and slurmctld are running on the same computer, obviously the compute nodes are on different machines. Anyways, thank you very much for the help. We still experience some delays until the information in sshare is updated with the data shown by sacct, but I will create a different thread for that. Best Pascal
