commit 38b73c67d375a2552d8ed67843c8a65c2c0feba6 (tag: refs/tags/v0.80.5, refs/remotes/gh/last, refs/remotes/gh/firefly) Author: Jenkins Date: Tue Jul 29 05:24:39 2014 -0700 0.80.5 commit b576d5a242c16bc9e38ba283a9784f838614882a Author: Sage Weil Date: Fri May 9 08:41:33 2014 -0700 osd: cancel agent_timer events on shutdown We need to cancel all agent timer events on shutdown. This also needs to happen early so that any in-progress events will execute before we start flushing and cleaning up PGs. Backport: firefly Signed-off-by: Sage Weil (cherry picked from commit c0dc245b662f1f9c640d7dd15fdf4cf26e729782) Conflicts: src/osd/OSD.cc commit 6213130f76b1ee89947bae578a1fccf16b845956 Author: Sage Weil Date: Tue Jul 8 16:11:44 2014 -0700 osd: s/applying repop/canceling repop/ The 'applying' language dates back to when we would wait for acks from replicas before applying writes locally. We don't do any of that any more; now, this loop just cancels the repops with remove_repop() and some other cleanup. Signed-off-by: Sage Weil (cherry picked from commit ef40737eee4389faa7792661a0f9d15b3d0440f2) commit 2e7c91587d99c9eba85ab7bd407a5b722b25a81e Author: Sage Weil Date: Tue Jul 8 16:11:27 2014 -0700 osd: clear PGBackend state on shutdown This was leaking state on shutdown whenever there were in-flight repops that were canceled. Fixes: #7891 Signed-off-by: Sage Weil (cherry picked from commit cafceae6c243369d3616af8217884e7e029896b9) commit f03110f3889ce7340c64f19358840b2425c93f68 Author: Sage Weil Date: Tue Jul 8 16:10:58 2014 -0700 osd: separate cleanup from PGBackend::on_change() The generic portion of on_change() cleaned up temporary on-disk objects and requires a Transaction. The rest is clearing out in-memory state and does not. Separate the two. Signed-off-by: Sage Weil (cherry picked from commit e299357e2a24474ab7a02e65ca0279336fd04b76) commit 42ad241efab751a1d4f50d5a748d91d0fe967844 Merge: 5f4ceb2 5049fc4 Author: Josh Durgin Date: Wed Jul 23 10:09:19 2014 -0700 Merge remote-tracking branch 'origin/wip-8858-firefly' into firefly Reviewed-by: Josh Durgin commit 5f4ceb208b55fab7fd1530dcf8fe03198b044148 Author: Joao Eduardo Luis Date: Tue Jul 22 00:25:37 2014 +0100 mon: AuthMonitor: always encode full regardless of keyserver having keys On clusters without cephx, assuming an admin never added a key to the cluster, the monitors have empty key servers. A previous patch had the AuthMonitor not encoding an empty keyserver as a full version. As such, whenever the monitor restarts we will have to read the whole state from disk in the form of incrementals. This poses a problem upon trimming, as we do every now and then: whenever we start the monitor, it will start with an empty keyserver, waiting to be populated from whatever we have on disk. This is performed in update_from_paxos(), and the AuthMonitor's will rely on the keyserver version to decide which incrementals we care about -- basically, all versions > keyserver version. Although we started with an empty keyserver (version 0) and are expecting to read state from disk, in this case it means we will attempt to read version 1 first. If the cluster has been running for a while now, and even if no keys have been added, it's fair to assume that version is greater than 0 (or even 1), as the AuthMonitor also deals and keeps track of auth global ids. As such, we expect to read version 1, then version 2, and so on. If we trim at some point however this will not be possible, as version 1 will not exist -- and we will assert because of that. This is fixed by ensuring the AuthMonitor keeps track of full versions of the key server, even if it's of an empty key server -- it will still keep track of the key server's version, which is incremented each time we update from paxos even if it is empty. Fixes: #8851 Backport: dumpling, firefly Signed-off-by: Joao Eduardo Luis (cherry picked from commit b551ae2bcea2dd17b37f5f5ab34251cc78de0e26) commit 5c1d74848863b45aa9e98d134cbe0cd1c8199557 Merge: 442c3fd c390ec4 Author: Sage Weil Date: Mon Jul 21 13:10:28 2014 -0700 Merge pull request #2122 from ceph/wip-dencoder-firefly fix linking deps, cpeh-dencoder, etc., firefly backport commit 5049fc4c9d6513bc58c3c4464f3de18949ac0aa5 Author: Yehuda Sadeh Date: Fri Jul 18 14:52:48 2014 -0700 rgw: dump prefix unconditionally As part of issue #8858, and to be more in line with S3, dump the Prefix field when listing bucket even if bucket is empty. Signed-off-by: Yehuda Sadeh (cherry picked from commit d7209c11251d42227608bc54cc69232ef62ffe80) commit 7fdd6d94262d8e6c81d168f5b997b3a5f030e6fa Author: Yehuda Sadeh Date: Thu Jul 17 15:48:26 2014 -0700 rgw: list extra objects to set truncation flag correctly Otherwise we end up returning wrong truncated value, and no data on the next iteration. Signed-off-by: Yehuda Sadeh (cherry picked from commit dc417e477d4ad262885c6b5f5987cf06d63b159d) commit 1f8774e01a616739ab70a78c348ab986b64b8fce Author: Yehuda Sadeh Date: Thu Jul 17 11:45:44 2014 -0700 rgw: account common prefixes for MaxKeys in bucket listing To be more in line with the S3 api. Beforehand we didn't account the common prefixes towards the MaxKeys (a single common prefix counts as a single key). Also need to adjust the marker now if it is pointing at a common prefix. Signed-off-by: Yehuda Sadeh (cherry picked from commit 82d2d612e700f94a0bb2d9fb7555abf327be379b) commit cb0a7ab8eb1d2fc8799b97c5a387b5f4f93b515c Author: Yehuda Sadeh Date: Thu Jul 17 11:24:51 2014 -0700 rgw: add NextMarker param for bucket listing Partially fixes #8858. Signed-off-by: Yehuda Sadeh (cherry picked from commit 924686f0b6593deffcd1d4e80ab06b1e7af00dcb) commit 34aa7086ba5293ee4d008016558dcdb1ada02e83 Author: Yehuda Sadeh Date: Wed Jul 16 15:21:09 2014 -0700 rgw: improve delmited listing of bucket If found a prefix, calculate a string greater than that so that next request we can skip to that. This is still not the most efficient way to do it. It'll be better to push it down to the objclass, but that'll require a much bigger change. Signed-off-by: Yehuda Sadeh (cherry picked from commit e6cf618c257f26f97f60a4c1df1d23a14496cab0) commit d027ff1b432a265ad49ddfeafab45093bcd03e6c Author: Yehuda Sadeh Date: Wed Jul 16 16:05:58 2014 -0700 utf8: export encode_utf8() and decode_utf8() Signed-off-by: Yehuda Sadeh (cherry picked from commit 49fc68cf8c3122c878ea9503c9c74d7046bc9c6f) commit c390ec4fa919e0a17e646e595b30cfa878c3454f Author: Sage Weil Date: Fri Jul 18 22:44:51 2014 -0700 ceph-dencoder: don't link librgw.la (and rados, etc.) Signed-off-by: Sage Weil (cherry picked from commit 34671108ce0b7597dba4f619732ecdb8933cda6e) commit 3d89380c90ab632eb76d3e429788fd81630e7a57 Author: Sage Weil Date: Fri Jul 18 22:27:25 2014 -0700 rgw: move a bunch of stuff into rgw_dencoder This will help out ceph-dencoder ... Signed-off-by: Sage Weil (cherry picked from commit b1a641f307942cbf43036f75ef67fb30441dfe95) commit dc6c9bf2b92d28bbd2bc822c267b0555f74c87fc Author: Sage Weil Date: Fri Jul 18 21:58:29 2014 -0700 libosd_types, libos_types, libmon_types Signed-off-by: Sage Weil (cherry picked from commit 1c170776cb8c0266f0f54f049ed07bbdb9c9ab5e) Conflicts: src/os/Makefile.am src/os/ObjectStore.cc src/osd/Makefile.am commit 7be91e8c5d935f7094033842bde1da2486905c70 Author: Sage Weil Date: Fri Jul 18 20:55:39 2014 -0700 Revert "ceph.spec: move ceph-dencoder to ceph from ceph-common" This reverts commit 95f5a448b52db545a2b9bbad47fdb287254f93ea. (cherry picked from commit 58cc894b3252a848ebc2169bcc4980a0ae6cc375) commit 04ad08a18a773e104a826b2a77ab0b2ffaac1e5f Author: Sage Weil Date: Fri Jul 18 20:55:35 2014 -0700 Revert "debian: move ceph-dencoder to ceph from ceph-common" This reverts commit b37e3bde3bd31287b11c069062280258666df7c5. (cherry picked from commit f181f78b7473260a717bc8ab4fc4d73a80e3b5ba) commit 442c3fd5a3b6a6c6a85d9bd7755923f14aa598e7 Author: Dan Mick Date: Thu Jul 17 21:44:06 2014 -0700 configure: do not link leveldb with everything Detect leveldb, but do not let autoconf blindly link it with everything on the planet. Signed-off-by: Dan Mick Sighed-off-by: Sage Weil (cherry picked from commit 06a8f7b99c5533f397b34f448138220384df60ac) commit c1073e430eafeb1f213f80636a3a24966b292698 Author: Sage Weil Date: Mon Jul 14 17:02:05 2014 -0700 ceph.spec: move ceph-dencoder to ceph from ceph-common Signed-off-by: Sage Weil (cherry picked from commit 95f5a448b52db545a2b9bbad47fdb287254f93ea) commit f4e9e0ef2eab3174584f1695122b114549feff57 Author: Sage Weil Date: Mon Jul 14 14:16:43 2014 -0700 debian: move ceph-dencoder to ceph from ceph-common It links against the world currently (notably leveldb). Not nice for the client-side lib. Signed-off-by: Sage Weil (cherry picked from commit b37e3bde3bd31287b11c069062280258666df7c5) commit 681c399e83df4c6ebd7e0836203eb2466455f548 Author: Sage Weil Date: Thu Jul 17 16:40:06 2014 -0700 logrotate.conf: fix osd log rotation under upstart In commit 7411c3c6a42bef5987bdd76b1812b01686303502 we generalized this enumeration code by copying what was in the upstart scripts. However, while the mon and mds directories get a 'done' file, the OSDs get a 'ready' file. Bah! Trigger off of either one. Backport: firefly Signed-off-by: Sage Weil (cherry picked from commit 14a9ca602fa9573b0b6b94709b384bca02d12fac) commit 794ec7fb43da4db930d28571a84c1c1cec1eb066 Author: Yehuda Sadeh Date: Wed Jul 16 12:23:31 2014 -0700 rgw: don't try to wait for pending if list is empty Fixes: #8846 Backport: firefly, dumpling This was broken at ea68b9372319fd0bab40856db26528d36359102e. We ended up calling wait_pending_front() when pending list was empty. This commit also moves the need_to_wait check to a different place, where we actually throttle (and not just drain completed IOs). Reported-by: Sylvain Munaut Signed-off-by: Yehuda Sadeh (cherry picked from commit f9f2417d7db01ecf2425039539997901615816a9) commit e75dd2e4b7adb65c2de84e633efcd6c19a6e457b Author: Alfredo Deza Date: Thu Jul 17 10:06:37 2014 -0400 remove suse service restarts Signed-off-by: Alfredo Deza (cherry picked from commit 0f11aaeefd7e8b49f88607937aade6113ebda52c) commit 361c1f8554ce1fedfd0020cd306c41b0ba25f53e Author: Alfredo Deza Date: Wed Jul 16 16:12:12 2014 -0400 remove ceph restarts on upgrades for RPMs Signed-off-by: Alfredo Deza (cherry picked from commit e3a5756f58ef5d07badf18ab08a26f47f7d232cb) commit 88f694dcd3d3342f764f3790572988b7808028ae Author: Alfredo Deza Date: Wed Jul 16 11:07:13 2014 -0400 set the default log level to WARNING Signed-off-by: Alfredo Deza (cherry picked from commit 420f0a471a31d1e56359ea642ed831e8a38b1e90) commit 67b5193f73a2c9ec9e503ad3431473998217375d Author: Sage Weil Date: Tue Jul 15 18:11:41 2014 -0700 init-ceph: wrap daemon startup with systemd-run when running under systemd We want to make sure the daemon runs in its own systemd environment. Check for systemd as pid 1 and, when present, use systemd-run -r to do this. Probably fixes #7627 Signed-off-by: Sage Weil Reviewed-by: Dan Mick Tested-by: Dan Mick (cherry picked from commit 3e0d9800767018625f0e7d797c812aa44c426dab)