From: Sage Weil Date: Thu, 21 Mar 2013 05:11:15 +0000 (-0700) Subject: doc/release-notes: v0.59 X-Git-Tag: v0.60~26 X-Git-Url: http://git-server-git.apps.pok.os.sepia.ceph.com/?a=commitdiff_plain;h=17d4a7c457de67e3dd953959eca41be8318be4e3;p=ceph.git doc/release-notes: v0.59 Signed-off-by: Sage Weil --- diff --git a/PendingReleaseNotes b/PendingReleaseNotes index 6a05b46743d8..e69de29bb2d1 100644 --- a/PendingReleaseNotes +++ b/PendingReleaseNotes @@ -1,21 +0,0 @@ - - -* The meaning of 'osd scrub max interval' has been changed: it is now - the amount of time after which a PG will be scrubbed regardless of - the system load. The option 'osd scrub min interval' now has the - previous meaning: the amount of time before a PG is scrubbed if the - load is low. The defaults have been adjusted such that the only - change in behavior is that PGs will now be scrubbed after a week - even if the system load remains high. However, if either of these - options have been changed in ceph.conf, those settings should be - reviewed in light of their adjusted meanings. - -* The 'ceph osd pool delete ' and 'rados rmpool ' - now have safety interlocks with loud warnings that make you confirm - pool removal. Any scripts that rely on these functions zapping data - without confirmation need to be adjusted accordingly. - -* ceph-mon now requires the creation of its data directory prior to - --mkfs, similarly to what happens on ceph-osd. This directory is - no longer automatically created, and custom scripts should be - adjusted to reflect just that. diff --git a/doc/release-notes.rst b/doc/release-notes.rst index 29a3128eafd9..11c9c3cda428 100644 --- a/doc/release-notes.rst +++ b/doc/release-notes.rst @@ -2,6 +2,53 @@ Release Notes =============== +v0.59 +----- + +Upgrading +~~~~~~~~~ + +* The monitor is using a completely new storage strategy and + intra-cluster protocol. This means that v0.59 and pre-v0.59 + monitors do not talk to each other. When you upgrade each one, it + will convert its local data store to the new format. Once you + upgrade a majority, the quorum will be formed using the new protocol + and the old monitors will be blocked out until they too get + upgraded. For this reason, we recommend not running a mixed-version + cluster for very long. + +* ceph-mon now requires the creation of its data directory prior to + --mkfs, similarly to what happens on ceph-osd. This directory is no + longer automatically created, and custom scripts should be adjusted to + reflect just that. + + +Notable Changes +~~~~~~~~~~~~~~~ + + * mon: rearchitected to utilize single instance of paxos and a key/value store (Joao Luis) + * mon: new 'ceph df [detail]' command + * osd: support for improved hashing of PGs across OSDs via HASHPSPOOL pool flag and feature + * osd: refactored watch/notify infrastructure (fixes protocol, removes many bugs) (Sam Just) + * osd, librados: ability to list watchers (David Zafman) + * osd, librados: new listsnaps command (David Zafman) + * osd: trim log more aggressively, avoid appearance of leak memory + * osd: misc split fixes + * osd: a few journaling bug fixes + * osd: connection handling bug fixes + * rbd: avoid FIEMAP when importing from file (it can be buggy) + * librados: fix linger bugs (Josh Durgin) + * librbd: fixed flatten deadlock (Josh Durgin) + * rgw: fixed >4MB range requests (Jan Harkes) + * rgw: fix log rotation + * mds: allow xattrs on root + * ceph-fuse: fix statfs(2) reporting + * msgr: optionally tune TCP buffer size to avoid throughput collapse (Jim Schutt) + * consume less memory for logging by default + * always use system leveldb (Gary Lowell) + + + v0.58 ----- @@ -18,7 +65,7 @@ Upgrading Notable Changes ~~~~~~~~~~~~~~~ - * mon: rearchitected to utilize single instance of paxos and a key/value store (Joao Luis) + * librbd: fixed some locking issues with flatten (Josh Durgin) * rbd: udevadm settle on map/unmap to avoid various races (Dan Mick) * osd: move pg info, log into leveldb (== better performance) (David Zafman)