Ceph

09/14/2023

10:10 AM RADOS Bug #62836: CEPH zero iops after upgrade to Reef and manual read balancer

@Mosharaf Hossain:
What kind of client do you use to access the VM storage (i.e. kernel client rbd, krbd, or librb...

09:52 AM RADOS Bug #62836: CEPH zero iops after upgrade to Reef and manual read balancer

The dashboard values show all "0", but the graph indicates it's still doing IO, as does "ceph -s". It might (also) be...

09:47 AM RADOS Bug #62836: CEPH zero iops after upgrade to Reef and manual read balancer

@Mosharaf Hossain:
Do you also have a performance overview when you were running Quincy? Quincy would then be the ...

08/10/2023

06:13 AM Ceph Bug #59491: OSD segfault when OSD primary-temp active and the CRUSH map changes

It's a couple of months ago I did this test (system is still in the same state though). The read-balancer code produc...

07/20/2023

05:07 PM RADOS Bug #61948: Failed assert "pg_upmap_primaries.empty()" in the read balancer

> Can you tell me whether just one mon crashed when you applied the upmaps, or did they all crash?
The second clus...

07/19/2023

08:25 PM RADOS Bug #61948: Failed assert "pg_upmap_primaries.empty()" in the read balancer

I recreated yet another cluster and enabled debug logging for osd / mon, but I could not reproduce.

07/14/2023

10:19 AM RADOS Bug #61948: Failed assert "pg_upmap_primaries.empty()" in the read balancer

I deleted all OSDs, and recreated them. Repeated the tests, but could not reproduce. So there must be (a) condition(s...

07/13/2023

07:55 PM RADOS Bug #61948: Failed assert "pg_upmap_primaries.empty()" in the read balancer

I have created a new cluster. Upgraded it to 18.1.2 (from 18.0.0) before I created any OSDs (and pool/image). I redid...

07/10/2023

07:59 PM RADOS Bug #61948: Failed assert "pg_upmap_primaries.empty()" in the read balancer

In the attachment the first osd map I used (om_old), and the osd map used the second time with version 18.1.2 (om).

06/21/2023

04:10 AM Ceph Feature #61747 (New): Add "postpone PG removal" flag for OSD

A "postpone PG removal" flag would be useful if you know beforehand that the OSD will be removed after it's PGs have ...