This is the first of three tickets concerning slurm's inability to "read" various file systems. Here, I'm seeing: slurmstepd[148497]: debug3: jobacct_gather_linux: unable to read requested pattern in /proc/148502/status Here's a sample count of hits for just part of today grep -c "unable to read requested pattern" /log/syslogs/2019.05.28/t05* /log/syslogs/2019.05.28/t0500:23061 /log/syslogs/2019.05.28/t0501:22165 /log/syslogs/2019.05.28/t0502:26200 /log/syslogs/2019.05.28/t0503:20169 /log/syslogs/2019.05.28/t0504:21024 /log/syslogs/2019.05.28/t0505:41840 /log/syslogs/2019.05.28/t0506:29901 /log/syslogs/2019.05.28/t0507:29695 Would you please guide me in understanding why the slurmd daemons are spewing out so many of these and how to correct the issue? Short of turning off debug3, there must be some setting that will permit me to reduce or eliminate these messages from the logs. Thanks, Tony.
Hi Tony, This is resolved in the following commit which is part of the 19.05 release. https://github.com/SchedMD/slurm/commit/585b81d0424526ce7906da8e0818476f1aa3ba4a For now, I would suggest you lower your log level since these messages will be dumped at debug2 or higher and a production system should not go beyond "debug" unless absolutely needed. *** This ticket has been marked as a duplicate of ticket 6501 ***