diff options
| author | Patrick Donnelly <pdonnell@redhat.com> | 2019-01-23 15:41:55 +0100 |
|---|---|---|
| committer | Patrick Donnelly <pdonnell@redhat.com> | 2019-01-30 00:16:30 +0100 |
| commit | ef46216d8d0b659549925481b4eff6bd7d2c43c9 (patch) | |
| tree | fefd0e2f707df28985320091845e6f60f515ad10 /PendingReleaseNotes | |
| parent | mds: adapt drop cache for incremental trim (diff) | |
| download | ceph-ef46216d8d0b659549925481b4eff6bd7d2c43c9.tar.xz ceph-ef46216d8d0b659549925481b4eff6bd7d2c43c9.zip | |
mds: recall caps incrementally
As with trimming, use DecayCounters to throttle the number of caps we recall,
both globally and per-session.
Signed-off-by: Patrick Donnelly <pdonnell@redhat.com>
Diffstat (limited to 'PendingReleaseNotes')
| -rw-r--r-- | PendingReleaseNotes | 4 |
1 files changed, 4 insertions, 0 deletions
diff --git a/PendingReleaseNotes b/PendingReleaseNotes index 61424bc62f4..c9b869a3602 100644 --- a/PendingReleaseNotes +++ b/PendingReleaseNotes @@ -169,6 +169,10 @@ via the `ceph tell mds.<foo> 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. + >=13.1.0 -------- |