Actions
Bug #21929
closedDefault kernel.pid_max is easily exceeded during recovery on high OSD-count system
% Done:
0%
Source:
Tags:
Backport:
luminous, jewel
Regression:
No
Severity:
3 - minor
Reviewed:
Affected Versions:
ceph-qa-suite:
Pull request ID:
Crash signature (v1):
Crash signature (v2):
Description
For CONFIG_BASE_FULL Linux kernels, the maximum number of process / thread IDs is set to 32768 by default. This default limit can be quite easily hit during recovery on nodes with high OSD counts.
Changing this limit is already recommended in Ceph documentation http://docs.ceph.com/docs/master/rados/troubleshooting/troubleshooting-osd/#an-osd-won-t-start , but this would be better done automatically via sysctl.d.
Updated by David Disseldorp over 6 years ago
Fix submitted via
https://github.com/ceph/ceph/pull/18544
Updated by Nathan Cutler over 6 years ago
- Status changed from New to Fix Under Review
- Backport set to luminous
Updated by Nathan Cutler over 6 years ago
- Backport changed from luminous to luminous, jewel
Updated by Nathan Cutler over 6 years ago
Note: related to https://github.com/ceph/ceph/pull/17894 which was backported to luminous by https://github.com/ceph/ceph/pull/18540
Updated by Kefu Chai over 6 years ago
- Status changed from Fix Under Review to Pending Backport
Updated by Nathan Cutler over 6 years ago
- Copied to Backport #22194: luminous: Default kernel.pid_max is easily exceeded during recovery on high OSD-count system added
Updated by Nathan Cutler over 6 years ago
- Copied to Backport #22195: jewel: Default kernel.pid_max is easily exceeded during recovery on high OSD-count system added
Updated by Nathan Cutler over 5 years ago
- Status changed from Pending Backport to Resolved
Actions