Actions
Support #22466
closedPG failing to map to any OSDs
Status:
Closed
Priority:
Normal
Assignee:
-
Category:
-
Target version:
-
% Done:
0%
Component(RADOS):
Pull request ID:
Description
osdmap e88997 pg 9.d07 (9.d07) -> up [] acting []
health HEALTH_ERR
319 pgs are stuck inactive for more than 300 seconds
12424 pgs degraded
318 pgs stale
12424 pgs stuck degraded
1 pgs stuck inactive
318 pgs stuck stale
15284 pgs stuck unclean
12424 pgs stuck undersized
12424 pgs undersized
recovery 119711728/448170822 objects degraded (26.711%)
recovery 29939216/448170822 objects misplaced (6.680%)
11165 active+undersized+degraded
5196 active+clean
2859 active+remapped
941 active+undersized+degraded+remapped
282 stale+active+undersized+degraded+remapped
36 stale+active+undersized+degraded
1 creating
client io 178 kB/s rd, 1253 kB/s wr, 2 op/s rd, 2 op/s wr
Updated by John Spray over 6 years ago
- Project changed from Ceph to RADOS
- Subject changed from cluster hold by a empty pg was creating to PG failing to map to any OSDs
- Category deleted (
Monitor)
More info will be needed to work out if this is a bug -- are the CRUSH rules customized? What is the topology ("ceph osd tree") of the OSDs?
Updated by Amine Liu over 6 years ago
When delete the osds outside of the default root , the problem's solved.
Updated by Josh Durgin over 6 years ago
- Tracker changed from Bug to Support
- Status changed from New to Closed
Actions