Summary: | Job rejected with Invalid job array specification | ||
---|---|---|---|
Product: | Slurm | Reporter: | David Backeberg <david.backeberg> |
Component: | Scheduling | Assignee: | Tim Wickberg <tim> |
Status: | RESOLVED INFOGIVEN | QA Contact: | |
Severity: | 4 - Minor Issue | ||
Priority: | --- | CC: | natchiagenter |
Version: | 16.05.10 | ||
Hardware: | Linux | ||
OS: | Linux | ||
Site: | Yale | Alineos Sites: | --- |
Atos/Eviden Sites: | --- | Confidential Site: | --- |
Coreweave sites: | --- | Cray Sites: | --- |
DS9 clusters: | --- | HPCnow Sites: | --- |
HPE Sites: | --- | IBM Sites: | --- |
NOAA SIte: | --- | OCF Sites: | --- |
Recursion Pharma Sites: | --- | SFW Sites: | --- |
SNIC sites: | --- | Linux Distro: | --- |
Machine Name: | CLE Version: | ||
Version Fixed: | Target Release: | --- | |
DevPrio: | --- | Emory-Cloud Sites: | --- |
Description
David Backeberg
2017-04-26 14:27:50 MDT
(In reply to David Backeberg from comment #0) > [root@grace2.grace ~]# scontrol show config | grep Max > MaxArraySize = 10001 > MaxJobCount = 100000 > MaxJobId = 2147418112 > MaxMemPerNode = UNLIMITED > MaxStepCount = 40000 > MaxTasksPerNode = 512 > PriorityMaxAge = 14-00:00:00 Did you happen to change MaxArraySize recently, then update it with 'scontrol reconfigure'? If so, restarting it completely should clear this up - that value is cached internally and needs a full restart to change (although it will start to appear as the new value in 'scontrol show config' even with the older limit still in force). Marking resolved/infogiven; please reopen is there is anything further I can help with on this. cheers, - Tim |