From: Nathan Cutler Date: Fri, 15 Mar 2019 16:18:32 +0000 (+0100) Subject: Merge pull request #26597 from smithfarm/wip-release-notes-12_2_12-luminous X-Git-Tag: v12.2.12~42 X-Git-Url: http://git-server-git.apps.pok.os.sepia.ceph.com/?a=commitdiff_plain;h=064d26430f58a03665e47a37a7e99cc96054cc07;p=ceph.git Merge pull request #26597 from smithfarm/wip-release-notes-12_2_12-luminous luminous: doc: move keyring caps RN to correct point release Reviewed-by: Abhishek Lekshmanan --- 064d26430f58a03665e47a37a7e99cc96054cc07 diff --cc PendingReleaseNotes index be06785b63e,238b46b28cd..03daee301e6 --- a/PendingReleaseNotes +++ b/PendingReleaseNotes @@@ -7,31 -14,7 +14,27 @@@ operations that dump journal information to file will now dump to per-rank suffixed dump files. Importing journal information from dump files is disallowed if operation is targetted for all ranks. - * In 12.2.9 and earlier releases, keyring caps were not checked for validity, - so the caps string could be anything. As of 12.2.10, caps strings are - validated and providing a keyring with an invalid caps string to, e.g., - "ceph auth add" will result in an error. +* The MDS cache trimming is now throttled. Dropping the MDS cache + via the `ceph tell mds. cache drop` command or large reductions in the + cache size will no longer cause service unavailability. + +* The CephFS MDS behavior with recalling caps has been significantly improved + to not attempt recalling too many caps at once, leading to instability. + MDS with a large cache (64GB+) should be more stable. + +* MDS now provides a config option "mds_max_caps_per_client" (default: 1M) to + limit the number of caps a client session may hold. Long running client + sessions with a large number of caps have been a source of instability in the + MDS when all of these caps need to be processed during certain session + events. It is recommended to not unnecessarily increase this value. + +* The MDS config mds_recall_state_timeout has been removed. Late client recall + warnings are now generated based on the number of caps the MDS has recalled + which have not been released. The new configs mds_recall_warning_threshold + (default: 32K) and mds_recall_warning_decay_rate (default: 60s) sets the + threshold for this warning. + >= 12.1.2 --------- * When running 'df' on a CephFS filesystem comprising exactly one data pool,