Ceph

11/08/2023

01:50 PM rbd Bug #63422: librbd crash in journal discard wait_event

As a consequence for the above, a very simple workaround for this crash appears to be to set rbd_skip_partial_discard...

11/07/2023

10:20 PM rbd Bug #63422: librbd crash in journal discard wait_event

As I've been trying to write a unit test covering this, I've come to realize that I don't think this condition is pos...

11/06/2023

11:25 PM rbd Bug #63422: librbd crash in journal discard wait_event

Here's another attempt at fixing this that I think better honours the original intent of the relationship between ima...

06:33 PM rbd Bug #63422: librbd crash in journal discard wait_event

Digging into journal events further, there already is a mechanism for keeping an event around until all parts have be...

05:19 PM rbd Bug #63422: librbd crash in journal discard wait_event

Note that the solution as currently posted is incorrect - between the two days that I worked on it I conveniently for...

01:47 PM rbd Bug #63422: librbd crash in journal discard wait_event

Thanks Mykola - that confirms what I suspected was the intent here. I've posted a proposed fix for the issue reported...

11/03/2023

09:38 PM rbd Bug #63422: librbd crash in journal discard wait_event

OK, looking forward to more info! I started to look into modifications along the line of my thinking in #3, but quick...

09:29 PM bluestore Bug #63353: resharding RocksDB after upgrade to Pacific breaks OSDs

Denis: Note that 'o' should actually be 'O' (the PR missed that part of the doc fix)

08:48 PM rbd Bug #63422: librbd crash in journal discard wait_event

Looking at the code, I'm not sure how this was supposed to work. In AbstractImageWriteRequest<I>::send_request(), if ...

08:35 PM rbd Bug #63422: librbd crash in journal discard wait_event

(to be clear - in that log, the problem happens on the second wait_event for tid=132078)