Dear Igor, thanks for posting this crucial Information on ceph-users. As this is a very important Information it should become special attention. I think the risk is quite high that when such important news are posted on ceph-users it could get lost in the shuffle. I would propose to either create a separate Mailing list for these kind of Information from the Ceph Dev Community or use a Mailing list where not that much is happening, e.g. ceph-announce What do you think? Am 28.10.21 um 17:37 schrieb Igor Fedotov:
Dear Ceph users. On behalf of Ceph's developers community I have to inform about a recently discovered severe bug which might cause data corruption. The issue occurs during OMAP format conversion for clusters upgraded to Pacific, new clusters aren't affected. OMAP format conversion's trigger is BlueStore repair/quick-fix functionality which might be invoked either manually via ceph-bluestore-tool or automatically by OSD if 'bluestore_fsck_quick_fix_on_mount' is set to true. Both OSD and MDS daemons are known to be suffering from the issue, potentially other ones, e.g. RGW might be affected as well - the major symptom is daemon's inability to startup/proceed operating after some OSDs have been "repaired". More details on the bug and its status tracking can be found at: https://tracker.ceph.com/issues/53062 We're currently working on the fix which is expected to be available in the upcoming v16.2.7 release. Meanwhile please DO NOT SET bluestore_fsck_quick_fix_on_mount to true (please immediately switch it to false if already set) and DO NOT RUN ceph-bluestore-tool's repair/quick-fix commands. Appologies for all the troubles this could cause.
best regards, Tobi Clyso GmbH - Ceph Foundation Member support@xxxxxxxxx https://www.clyso.com _______________________________________________ ceph-users mailing list -- ceph-users@xxxxxxx To unsubscribe send an email to ceph-users-leave@xxxxxxx
