Rene Diepstraten
- Login: RPDiep
- Email: rene@renediepstraten.nl
- Registered on: 01/16/2015
- Last sign in: 05/25/2019
Issues
open | closed | Total | |
---|---|---|---|
Assigned issues | 0 | 0 | 0 |
Reported issues | 1 | 1 | 2 |
Activity
05/25/2019
- 08:44 PM RADOS Bug #39555: backfill_toofull while OSDs are not full (Unneccessary HEALTH_ERR)
- Note: I've only seen this in a relatively busy and full environment with quite a few backfills going on.
- 08:21 PM RADOS Bug #39555: backfill_toofull while OSDs are not full (Unneccessary HEALTH_ERR)
- Thanks for the PR.
The problem itself seems to be caused as follows:
- A backfill starts to a set osds
- One of th...
05/21/2019
- 10:41 PM RADOS Bug #39555: backfill_toofull while OSDs are not full (Unneccessary HEALTH_ERR)
- I know that, but the issue doesn't occur with those osds. The issue occurs with the ssds (checked with `ceph pg ls ba...
- 09:36 PM RADOS Bug #39555: backfill_toofull while OSDs are not full (Unneccessary HEALTH_ERR)
- Here I can reproduce the issue with the ssd class.
We're in the process of reinstalling/redeploying (one host with a...
05/06/2019
- 09:18 AM RADOS Bug #39555: backfill_toofull while OSDs are not full (Unneccessary HEALTH_ERR)
- This may be the case indeed, but I'd expect that unless pgs are evacuated, the state would be backfill_wait, not back...
05/01/2019
- 08:10 AM RADOS Bug #39555 (Resolved): backfill_toofull while OSDs are not full (Unneccessary HEALTH_ERR)
- This week I ran into an issue where ceph reports HEALTH_ERR because pgs are backfill_toofull.
None of the OSDs are o...
03/13/2019
- 09:30 AM Ceph Feature #38708 (New): Rados import is potentially dangerous and should need confirmation
- With `rados import`, the default behaviour is to overwrite, without any confirmation from the user.
As this is poten...
Also available in: Atom