X-Git-Url: https://gerrit.opnfv.org/gerrit/gitweb?a=blobdiff_plain;f=src%2Fceph%2Fdoc%2Fchangelog%2Fv0.56.4.txt;fp=src%2Fceph%2Fdoc%2Fchangelog%2Fv0.56.4.txt;h=f48fd834a2d5952a594648e2856c639626a4670e;hb=812ff6ca9fcd3e629e49d4328905f33eee8ca3f5;hp=0000000000000000000000000000000000000000;hpb=15280273faafb77777eab341909a3f495cf248d9;p=stor4nfv.git diff --git a/src/ceph/doc/changelog/v0.56.4.txt b/src/ceph/doc/changelog/v0.56.4.txt new file mode 100644 index 0000000..f48fd83 --- /dev/null +++ b/src/ceph/doc/changelog/v0.56.4.txt @@ -0,0 +1,1126 @@ +commit 63b0f854d1cef490624de5d6cf9039735c7de5ca +Author: Gary Lowell +Date: Mon Mar 25 11:02:31 2013 -0700 + + v0.56.4 + +commit 90ab120a3c08f30654207c9c67fb0a4ff1476aff +Author: Yehuda Sadeh +Date: Mon Mar 25 09:50:33 2013 -0700 + + rgw: bucket index ops on system buckets shouldn't do anything + + Fixes: #4508 + Backport: bobtail + On certain bucket index operations we didn't check whether + the bucket was a system bucket, which caused the operations + to fail. This triggered an error message on bucket removal + operations. + + Signed-off-by: Yehuda Sadeh + Reviewed-by: Greg Farnum + (cherry picked from commit 70e0ee8ba955322832f0c366537ddf7a0288761e) + +commit b8657fa08d0fe176c71a60c1654c53c3156a9c53 +Author: Josh Durgin +Date: Mon Feb 25 15:02:50 2013 -0800 + + systest: restrict list error acceptance + + Only ignore errors after the midway point if the midway_sem_post is + defined. + + Signed-off-by: Josh Durgin + (cherry picked from commit 5b24a68b6e7d57bac688021b822fb2f73494c3e9) + +commit 5af3d64f62b30cbaac13ccc7c23fc884ee1b7ae3 +Author: Josh Durgin +Date: Mon Feb 25 14:55:34 2013 -0800 + + systest: fix race with pool deletion + + The second test have pool deletion and object listing wait on the same + semaphore to connect and start. This led to errors sometimes when the + pool was deleted before it could be opened by the listing process. Add + another semaphore so the pool deletion happens only after the listing + has begun. + + Fixes: #4147 + Signed-off-by: Josh Durgin + (cherry picked from commit b0271e390564119e998e18189282252d54f75eb6) + +commit 3569489b541ac0643520d20b08c788c26dfaff7f +Author: Sage Weil +Date: Tue Mar 19 14:26:16 2013 -0700 + + os/FileJournal: fix aio self-throttling deadlock + + This block of code tries to limit the number of aios in flight by waiting + for the amount of data to be written to grow relative to a function of the + number of aios. Strictly speaking, the condition we are waiting for is a + function of both aio_num and the write queue, but we are only woken by + changes in aio_num, and were (in rare cases) waiting when aio_num == 0 and + there was no possibility of being woken. + + Fix this by verifying that aio_num > 0, and restructuring the loop to + recheck that condition on each wakeup. + + Fixes: #4079 + Signed-off-by: Sage Weil + Reviewed-by: Samuel Just + (cherry picked from commit e5940da9a534821d0d8f872c13f9ac26fb05a0f5) + +commit 664ffa7d2178e486b00fa0706067f19b1bb9ab82 +Author: Sage Weil +Date: Fri Mar 22 13:25:49 2013 -0700 + + common/MemoryModel: remove logging to /tmp/memlog + + This was a hack for dev purposes ages ago; remove it. The predictable + filename is a security issue. + + CVE-2013-1882 + + Reported-by: Michael Scherer + Signed-off-by: Sage Weil + Reviewed-by: Dan Mick + (cherry picked from commit c524e2e01da41ab5b6362c117939ea1efbd98095) + +commit 901fa435bb4be29b72cec39e5ff77570d13cbc6c +Author: Sage Weil +Date: Fri Mar 22 13:25:43 2013 -0700 + + init-ceph: clean up temp ceph.conf filename on exit + + Signed-off-by: Sage Weil + Reviewed-by: Dan Mick + (cherry picked from commit 6a7ad2eac1db6abca3d7edb23ca9b80751400a23) + +commit 951f7e562afb4ae91b8d037ef793a96779461e96 +Author: Sage Weil +Date: Fri Mar 22 13:25:33 2013 -0700 + + init-ceph: push temp conf file to a unique location on remote host + + The predictable file name is a security problem. + + CVE-2013-1882 + + Reported-by: Michael Scherer + Signed-off-by: Sage Weil + Reviewed-by: Dan Mick + (cherry picked from commit 051734522fea92878dd8139f28ec4e6b01371ede) + +commit dd670afccfd3ae58c03ea3b4c213dd8db22f618e +Author: Sage Weil +Date: Fri Mar 22 13:25:23 2013 -0700 + + mkcephfs: make remote temp directory name unique + + The predictable file name is a security problem. + + CVE-2013-1882 + + Reported-by: Michael Scherer + Signed-off-by: Sage Weil + Reviewed-by: Dan Mick + (cherry picked from commit f463ef78d77b11b5ad78b31e9a3a88d0a6e62bca) + +commit 1cd51eb63a91fa0aa395c41572cfee4d53fbc7f5 +Author: Samuel Just +Date: Fri Mar 22 13:51:14 2013 -0700 + + PG::GetMissing: need to check need_up_thru in MLogRec handler + + Backport: bobtail + Fixes: #4534 + Signed-off-by: Samuel Just + Reviewed-by: Sage Weil + (cherry picked from commit 4fe4deafbe1758a6b3570048aca57485bd562440) + +commit d866814285667c7f9cd9205dca6cf95f3634c5fc +Author: Samuel Just +Date: Fri Mar 22 13:48:49 2013 -0700 + + PG,osd_types: improve check_new_interval debugging + + Backport: bobtail + Signed-off-by: Samuel Just + Reviewed-by: Sage Weil + (cherry picked from commit d611eba9caf45f2d977c627b123462a073f523a4) + +commit fc3406f395103737e5784611e2b38fd1c4f26369 +Author: Samuel Just +Date: Tue Mar 5 16:06:20 2013 -0800 + + FileStore: fix reversed collection_empty return value + + Backport: bobtail + Fixes: #4380 + Signed-off-by: Samuel Just + Reviewed-by: Greg Farnum + (cherry picked from commit 7a434d10da0f77e1b329de0b06b6645cd73cc81b) + + Conflicts: + src/os/FileStore.cc + +commit 9f7c6ad395653b1039ea957cfaa7689699f510e7 +Author: Samuel Just +Date: Mon Feb 11 12:52:07 2013 -0800 + + FileStore: set replay guard on create_collection + + This should prevent sequences like: + + rmcoll a + mkcoll a + touch a foo + + + from causing trouble by preventing the rmcoll + and mkcoll from being replayed. + + Fixes: 4064 + Backport: bobtail + Signed-off-by: Samuel Just + (cherry picked from commit 411770c45734c9827745ddc4018d86c14f2858a6) + +commit 9932c9f0a0503f1902549a3c39e5d51488fff3ef +Author: Samuel Just +Date: Mon Feb 11 12:24:14 2013 -0800 + + FileStore: _split_collection should not create the collection + + This will simplify adding a replay guard to create_collection. + + Backport: bobtail + Signed-off-by: Samuel Just + (cherry picked from commit b184ff581a08c9e6ce5b858f06ccbe9d0e2a170b) + +commit 7e7ea8266ee45d96863e1edc5a567dcc2977680c +Author: Sage Weil +Date: Fri Feb 22 15:15:27 2013 -0800 + + client: use 4MB f_bsize and f_frsize for statfs + + Old stat(1) reports: + + Block size: 1048576 Fundamental block size: 1048576 + + and the df(1) arithmetic works out. New stat(1) reports: + + Block size: 1048576 Fundamental block size: 4096 + + which is what we are shoving into statvfs, but we have the b_size and + fr_size arithmetic swapped. However, doing the *correct* reporting would + then break the old stat by making both sizes appear to be 4KB (or + whatever). + + Sidestep the issue by making *both* values 4MB.. which is both large enough + to report large FS sizes, and also the default stripe size and thus a + "reasonable" value to report for a block size. + + Perhaps in the future, when we no longer care about old userland, we can + report the page size for f_bsize, which is probably the "most correct" + thing to do. + + Fixes: #3794. See also #3793. + Signed-off-by: Sage Weil + Reviewed-by: Greg Farnum + (cherry picked from commit 7c94083643891c9d66a117352f312b268bdb1135) + +commit 66dca7730006dffbce12e6b27016ea5469b7691b +Author: Sage Weil +Date: Mon Feb 18 17:39:46 2013 -0800 + + os/FileStore: check replay guard on src for collection rename + + This avoids a problematic sequence like: + + - rename A/ -> B/ + - remove B/1...100 + - destroy B/ + - create A/ + - write A/101... + + - replay A/ -> B/ + - remove B/1...100 (fails but tolerated) + - destroy B/ (fails with ENOTEMPTY) + + Signed-off-by: Sage Weil + Reviewed-by: Samuel Just + (cherry picked from commit 5fc83c8d9887d2a916af11436ccc94fcbfe59b7a) + +commit ea570591b0d9dda102bece0f4cc7d263c3e2a3b0 +Author: Samuel Just +Date: Fri Feb 22 14:12:28 2013 -0800 + + PG::proc_replica_log: oinfo.last_complete must be *before* first entry in omissing + + Fixes: #4189 + Signed-off-by: Samuel Just + (cherry picked from commit 2dae6a68ee85a20220ee940dbe33a2144d43457b) + +commit aa38d87c6237ccfb8b3b03bc7c28dcadb927237b +Author: Sage Weil +Date: Thu Feb 21 17:55:21 2013 -0800 + + osd/PG: fix typo, missing -> omissing + + From ce7ffc34408bf32c66dc07e6f42d54b7ec489d41. + + Signed-off-by: Sage Weil + (cherry picked from commit dc181224abf6fb8fc583730ae3d90acdf0b80f39) + +commit ac914834ba4fb0e4770f63c60713be7a48aa3fa1 +Author: Samuel Just +Date: Thu Feb 21 15:31:36 2013 -0800 + + PG::proc_replica_log: adjust oinfo.last_complete based on omissing + + Otherwise, search_for_missing may neglect to check the missing + set for some objects assuming that if the need version is + prior to last_complete, the replica must have it. + + Fixes: #4994 + Signed-off-by: Samuel Just + (cherry picked from commit ce7ffc34408bf32c66dc07e6f42d54b7ec489d41) + +commit 7f39704b0903fb11e3f1e102599bf0c540f93623 +Author: Sage Weil +Date: Sat Feb 9 00:05:33 2013 -0800 + + osd: fix load_pgs collection handling + + On a _TEMP pg, is_pg() would succeed, which meant we weren't actually + hitting the cleanup checks. Instead, restructure this loop as positive + checks and handle each type of collection we understand. + + This fixes _TEMP cleanup. + + Signed-off-by: Sage Weil + Reviewed-by: Samuel Just + (cherry picked from commit b19b6dced85617d594c15631571202aab2f94ae8) + +commit 0a09be99f3e9d2b68a052ff63ea858a7c8e5626c +Author: Sage Weil +Date: Sat Feb 9 00:04:29 2013 -0800 + + osd: fix load_pgs handling of pg dirs without a head + + If there is a pgid that passes coll_t::is_pg() but there is no head, we + will populate the pgs map but then fail later when we try to do + read_state. This is a side-effect of 55f8579. + + Take explicit note of _head collections we see, and then warn when we + find stray snap collections. + + Signed-off-by: Sage Weil + Reviewed-by: Samuel Just + (cherry picked from commit 1f80a0b576c0af1931f743ad988b6293cbf2d6d9) + +commit 2dc25dfd47de8d3602bdb3699c82b8b118b0fb28 +Author: Samuel Just +Date: Thu Feb 7 13:34:47 2013 -0800 + + OSD::load_pgs: first scan colls before initing PGs + + Backport: bobtail + Signed-off-by: Samuel Just + Reviewed-by: Sage Weil + (cherry picked from commit 073f58ede2e473af91f76d01679631c169274af7) + +commit 2fd8db29ccf56fd5473826f20e351edfe200419d +Author: David Zafman +Date: Tue Jan 8 19:24:13 2013 -0800 + + osd: Add digest of omap for deep-scrub + + Add ScrubMap encode/decode v4 message with omap digest + Compute digest of header and key/value. Use bufferlist + to reflect structure and compute as we go, clearing + bufferlist to reduce memory usage. + + Signed-off-by: David Zafman + Reviewed-by: Samuel Just + (cherry picked from commit 509a93e89f04d7e9393090563cf7be8e0ea53891) + +commit ee59f517ccc195e591e0b1b6ddf6d1d054c4e2fd +Author: Samuel Just +Date: Fri Mar 15 15:13:46 2013 -0700 + + OSD: split temp collection as well + + Otherwise, when we eventually remove the temp collection, there might be + objects in the temp collection which were independently pulled into the child + pg collection. Thus, removing the old stale parent link from its temp + collection also blasts the omap entries and snap mappings for the real child + object. + + Backport: bobtail + Fixes: #4452 + Signed-off-by: Samuel Just + Reviewed-by: Josh Durgin + (cherry picked from commit f8d66e87a5c155b027cc6249006b83b4ac9b6c9b) + +commit 7ec68e2d45b431a3a77458939622e6ea1e396d0e +Author: Samuel Just +Date: Thu Mar 14 19:59:36 2013 -0700 + + PG: ignore non MISSING pg query in ReplicaActive + + 1) Replica sends notify + 2) Prior to processing notify, primary queues query to replica + 3) Primary processes notify and activates sending MOSDPGLog + to replica. + 4) Primary does do_notifies at end of process_peering_events + and sends to Query. + 5) Replica sees MOSDPGLog and activates + 6) Replica sees Query and asserts. + + In the above case, the Replica should simply ignore the old + Query. + + Fixes: #4050 + Backport: bobtail + Signed-off-by: Samuel Just + Reviewed-by: Sage Weil + (cherry picked from commit 8222cbc8f35c359a35f8381ad90ff0eed5615dac) + +commit b279b148b38c755d2dcca6524d7b8a95daf123a0 +Author: Samuel Just +Date: Wed Mar 13 16:04:23 2013 -0700 + + FileJournal: queue_pos \in [get_top(), header.max_size) + + If queue_pos == header.max_size when we create the entry + header magic, the entry will be rejected at get_top() on + replay. + + Fixes: #4436 + Backport: bobtail + Signed-off-by: Samuel Just + Reviewed-by: Sage Weil + (cherry picked from commit de8edb732e3a5ce4471670e43cfe6357ae6a2758) + +commit 56e0a129b0d9ad463f4300999ed2c15173cbe603 +Author: Samuel Just +Date: Thu Mar 14 18:52:02 2013 -0700 + + OSD: expand_pg_num after pg removes + + Otherwise: + 1) expand_pg_num removes a splitting pg entry + 2) peering thread grabs pg lock and starts split + 3) OSD::consume_map grabs pg lock and starts removal + + At step 2), we run afoul of the assert(is_splitting) + check in split_pgs. This way, the would be splitting + pg is marked as removed prior to the splitting state + being updated. + + Backport: bobtail + Fixes: #4449 + Signed-off-by: Samuel Just + Reviewed-by: Sage Weil + (cherry picked from commit f1b031b3cf195cf6df3d3c47c7d606fba63ed4c4) + +commit d6e678a62950ccc16d010a76500705e176ba9c73 +Author: Sage Weil +Date: Mon Feb 11 06:23:54 2013 -0800 + + osd: update snap collections for sub_op_modify log records conditionaly + + The only remaining caller is sub_op_modify(). If we do have a non-empty + op transaction, we want to do this update, regardless of what we think + last_backfill is (our notion may be not completely in sync with the + primary). In particular, our last_backfill may be the same object but + a different snapid, but the primary disagrees and is pushing an op + transaction through. + + Instead, update the collections if we have a non-empty transaction. + + Signed-off-by: Sage Weil + Reviewed-by: Samuel Just + (cherry picked from commit 31e911b63d326bdd06981ec4029ad71b7479ed70) + +commit 51c2c4d7ccb25617967689d7e531eb145ee7011d +Author: Sage Weil +Date: Sun Feb 10 17:02:45 2013 -0800 + + osd: include snaps in pg_log_entry_t::dump() + + Signed-off-by: Sage Weil + Reviewed-by: Samuel Just + (cherry picked from commit 715d8717a0e8a08fbe97a3e7d3ffd33aa9529d90) + +commit f0bf68ff500f7337103aef2a9d6d10c3597e410f +Author: Sage Weil +Date: Sun Feb 10 16:59:48 2013 -0800 + + osd: unconditionally encode snaps buffer + + Previously we would only encode the updated snaps vector for CLONE ops. + This doesn't work for MODIFY ops generated by the snap trimmer, which + may also adjust the clone collections. It is also possible that other + operations may need to populate this field in the future (e.g., + LOST_REVERT may, although it currently does not). + + Fixes: #4071, and possibly #4051. + + Signed-off-by: Sage Weil + Reviewed-by: Samuel Just + (cherry picked from commit 54b6dd924fea3af982f3d729150b6449f318daf2) + +commit aa74fabd90b776e9938f3d59ea5ed04bd4027dbb +Author: Sage Weil +Date: Sun Feb 10 10:57:12 2013 -0800 + + osd: improve debug output on snap collections + + Signed-off-by: Sage Weil + Reviewed-by: Samuel Just + (cherry picked from commit 8b05492ca5f1479589bb19c1ce058b0d0988b74f) + +commit a30903c6adaa023587d3147179d6038ad37ca520 +Author: Samuel Just +Date: Thu Mar 7 12:53:51 2013 -0800 + + PG: check_recovery_sources must happen even if not active + + missing_loc/missing_loc_sources also must be cleaned up + if a peer goes down during peering: + + 1) pg is in GetInfo, acting is [3,1] + 2) we find object A on osd [0] in GetInfo + 3) 0 goes down, no new peering interval since it is neither up nor + acting, but peer_missing[0] is removed. + 4) pg goes active and try to pull A from 0 since missing_loc did not get + cleaned up. + + Backport: bobtail + Fixes: #4371 + Signed-off-by: Samuel Just + Reviewed-by: Greg Farnum + (cherry picked from commit de22b186c497ce151217aecf17a8d35cdbf549bb) + +commit 19f6df28337307ce6d8617524f88f222c0ffcab3 +Author: Samuel Just +Date: Tue Mar 5 15:49:26 2013 -0800 + + HashIndex: _collection_list_partial must tolerate NULL next + + Backport: bobtail + Fixes: #4379 + Signed-off-by: Samuel Just + Reviewed-by: Greg Farnum + (cherry picked from commit ce4432adc67dc2fc06dd21ea08e59d179496bcc6) + +commit 1b5c1564bad3574db257cb17d48190958d870f51 +Author: Samuel Just +Date: Tue Mar 5 14:35:39 2013 -0800 + + OSD: lock not needed in ~DeletingState() + + No further refs to the object can remain at this point. + Furthermore, the callbacks might lock mutexes of their + own. + + Backport: bobtail + Fixes: #4378 + Signed-off-by: Samuel Just + Reviewed-by: Greg Farnum + (cherry picked from commit e4bf1bcab159d7c5b720f5da01877c0f67c16d16) + +commit 50d2d4a77f339d489703c1125dc5c1159d08ca8a +Author: Samuel Just +Date: Sun Mar 10 12:50:01 2013 -0700 + + ReplicatedPG: don't leak reservation on removal + + Fixes: 4431 + Signed-off-by: Samuel Just + Reviewed-by: Greg Farnum + (cherry picked from commit 32bf131e0141faf407b5ff993f75f97516b27c12) + + Conflicts: + + src/osd/ReplicatedPG.cc + +commit c6b7c4be3fc44d065c29ea76b744b39272c2ba05 +Author: Yehuda Sadeh +Date: Tue Mar 12 12:56:01 2013 -0700 + + rgw: set up curl with CURL_NOSIGNAL + + Fixes: #4425 + Backport: bobtail + Apparently, libcurl needs that in order to be thread safe. Side + effect is that if libcurl is not compiled with c-ares support, + domain name lookups are not going to time out. + Issue affected keystone. + + Signed-off-by: Yehuda Sadeh + Reviewed-by: Greg Farnum + (cherry picked from commit 88725316ddcfa02ff110e659f7a8131dc1ea2cfc) + +commit 8c16a376a9cbfd6812824fb71e2cc9935e14e667 +Author: Sage Weil +Date: Fri Mar 8 08:56:44 2013 -0800 + + osd: mark down connections from old peers + + Close out any connection with an old peer. This avoids a race like: + + - peer marked down + - we get map, mark down the con + - they reconnect and try to send us some stuff + - we share our map to tell them they are old and dead, but leave the con + open + ... + - peer marks itself up a few times, eventually reuses the same port + - sends messages on their fresh con + - we discard because of our old con + + This could cause a tight reconnect loop, but it is better than wrong + behavior. + + Other possible fixes: + - make addr nonce truly unique (augment pid in nonce) + - make a smarter 'disposable' msgr state (bleh) + + Signed-off-by: Sage Weil + (cherry picked from commit 881e9d850c6762290f8be24da9e74b9dc112f1c9) + +commit 1affc8b6e8cb82510aed524f90a6165c6edf7513 +Author: Sage Weil +Date: Fri Mar 8 08:53:40 2013 -0800 + + osd/PG: rename require_same_or_newer_map -> is_same_or_newer_map + + This avoids confusion with the OSD method of the same name, and better + matches what the function tests (and does not do). + + Signed-off-by: Sage Weil + (cherry picked from commit ba7e815a18cad110525f228db1b3fe39e011409e) + + Conflicts: + + src/osd/ReplicatedPG.cc + +commit 7ca55d36c4007be5880102fa1ed314d3d66e9d87 +Author: Sage Weil +Date: Mon Mar 11 16:25:16 2013 -0700 + + log: drop default 'log max recent' from 100k -> 10k + + Use less memory. + + Signed-off-by: Sage Weil + (cherry picked from commit c021c5ccf0c063cccd7314964420405cea6406de) + +commit 33ac786ddc14d0904f4835cbf684a51f4815d45b +Author: Jan Harkes +Date: Fri Mar 8 12:45:57 2013 -0500 + + Fix radosgw actually reloading after rotating logs. + + The --signal argument to Debian's start-stop-daemon doesn't + make it send a signal, but defines which signal should be send + when --stop is specified. + + Signed-off-by: Jan Harkes + (cherry picked from commit 44f1cc5bc42f9bb6d5a386037408d2de17dc5413) + +commit 6838b8db9a3d4ceaf121a261e2ded4af9bfeaeb9 +Author: Josh Durgin +Date: Wed Mar 6 17:42:03 2013 -0800 + + common: reduce default in-memory logs for non-daemons + + The default of 100000 can result in hundreds of MBs of extra memory + used. This was most obvious when using librbd with caching enabled, + since there was a dout(0) accidentally left in the ObjectCacher. + + refs: #4352 + backport: bobtail + Signed-off-by: Josh Durgin + (cherry picked from commit 7c208d2f8e3f28f4055a4ae51eceae892dcef1dc) + +commit f80f64cf024bd7519d5a1fb2a5698db97a003ce8 +Author: Sage Weil +Date: Fri Feb 22 17:01:53 2013 -0800 + + osd: allow (some) log trim when degraded, but not during recovery + + We allow some trim during degraded, although we keep more entries around to + improve our chances of a restarting OSD of doing log-based recovery. + + Still disallow during recovery... + + Signed-off-by: Sage Weil + Reviewed-by: Samuel Just + (cherry picked from commit 6d89b34e5608c71b49ef33ab58340e90bd8da6e4) + +commit e502a65da1779564059e74c09ab87aca1d901bd2 +Author: Sage Weil +Date: Mon Feb 25 15:33:35 2013 -0800 + + osd: restructure calc_trim + + No functional change, except that we log more debug, yay! + + Signed-off-by: Sage Weil + Reviewed-by: Samuel Just + (cherry picked from commit 86df164d04f6e31a0f20bbb94dbce0599c0e8b3d) + +commit 3a3123033d7d9e1574be3fb18c807eeb0f4678eb +Author: Sage Weil +Date: Fri Feb 22 16:48:02 2013 -0800 + + osd: allow pg log trim during (non-classic) scrub + + Chunky (and deep) scrub do not care about PG log trimming. Classic scrub + still does. + + Deep scrub can take a long time, so not trimming the log during that period + may eat lots of RAM; avoid that! + + Might fix: #4179 + Signed-off-by: Sage Weil + Reviewed-by: Samuel Just + (cherry picked from commit 0ba8db6b664205348d5499937759916eac0997bf) + +commit cde0f224dac21b2e17e06d396ac52e18034a4262 +Author: Sage Weil +Date: Thu Feb 28 12:46:00 2013 -0800 + + msgr: drop messages on cons with CLOSED Pipes + + Back in commit 6339c5d43974f4b495f15d199e01a141e74235f5, we tried to make + this deal with a race between a faulting pipe and new messages being + queued. The sequence is + + - fault starts on pipe + - fault drops pipe_lock to unregister the pipe + - user (objecter) queues new message on the con + - submit_message reopens a Pipe (due to this bug) + - the message managed to make it out over the wire + - fault finishes faulting, calls ms_reset + - user (objecter) closes the con + - user (objecter) resends everything + + It appears as though the previous patch *meant* to drop *m on the floor in + this case, which is what this patch does. And that fixes the crash I am + hitting; see #4271. + + Signed-off-by: Sage Weil + Reviewed-by: Greg Farnum + (cherry picked from commit 0f42eddef5da6c1babe9ed51ceaa3212a42c2ec4) + +commit 2fa2546c90e7a6eab9a3de7ab4e4271f8b25bad6 +Author: Concubidated +Date: Fri Mar 8 13:44:39 2013 -0800 + + Fix output of 'ceph osd tree --format=json' + + Signed-off-by: Tyler Brekke + (cherry picked from commit 9bcba944c6586ad5f007c0a30e69c6b5a886510b) + +commit b70e2c270b9eb3fce673b7e51b527ebf88214f14 +Author: Sam Lang +Date: Tue Feb 12 11:32:29 2013 -0600 + + deb: Add ceph-coverage to ceph-test deb package + + Teuthology uses the ceph-coverage script extensively + and expects it to be installed by the ceph task. Add + the script to the ceph-test debian package so that it + gets installed for that use case. + + Signed-off-by: Sam Lang + (cherry picked from commit 376cca2d4d4f548ce6b00b4fc2928d2e6d41038f) + +commit ca9aac785eb9e2d1ee955792d2f4d1d911727fb3 +Author: Yehuda Sadeh +Date: Fri Feb 22 15:04:37 2013 -0800 + + rgw: set attrs on various list bucket xml results (swift) + + Fixes: #4247 + The list buckets operation was missing some attrs on the different + xml result entities. This fixes it. + + Signed-off-by: Yehuda Sadeh + (cherry picked from commit 4384e59ad046afc9ec53a2d2f1fff6a86e645505) + +commit e39660c901756d5e722308e72a9d8ee4893f70f7 +Author: Yehuda Sadeh +Date: Fri Feb 22 15:02:02 2013 -0800 + + formatter: add the ability to dump attrs in xml entities + + xml entities may have attrs assigned to them. Add the ability + to set them. A usage example: + + formatter->open_array_section_with_attrs("container", + FormatterAttrs("name", "foo", NULL)); + + This will generate the following xml entity: + + + Signed-off-by: Yehuda Sadeh + Reviewed-by: Greg Farnum + (cherry picked from commit 7cb6ee28073824591d8132a87ea09a11c44efd66) + + Conflicts: + src/common/Formatter.cc + +commit 0304b85e5c12c30459b94ec5d332dfaa04d20d5b +Author: Yehuda Sadeh +Date: Wed Mar 6 19:32:21 2013 -0800 + + rgw: don't iterate through all objects when in namespace + + Fixes: #4363 + Backport: argonaut, bobtail + When listing objects in namespace don't iterate through all the + objects, only go though the ones that starts with the namespace + prefix + + Signed-off-by: Yehuda Sadeh + (cherry picked from commit 6669e73fa50e3908ec825ee030c31a6dbede6ac0) + +commit d0dafaa77f96fa91785df0796806ea07fd93f319 +Author: Josh Durgin +Date: Thu Feb 28 12:13:45 2013 -0800 + + ObjectCacher: fix debug log level in split + + Level 0 should never be used for this kind of debugging. + + Signed-off-by: Josh Durgin + Reviewed-by: Dan Mick + (cherry picked from commit cb3ee33532fb60665f39f6ccb1d69d67279fd5e1) + +commit ff014ed26bfa4fbf40acffec4eb4805b95a9982c +Author: Dan Mick +Date: Thu Jan 24 13:38:25 2013 -0800 + + rados: remove unused "check_stdio" parameter + + Signed-off-by: Dan Mick + (cherry picked from commit bb860e49a7faeaf552538a9492ef0ba738c99760) + +commit e89884da9f76b713372a79b772ba3cc2f3b03048 +Author: Sage Weil +Date: Wed Jan 23 21:31:11 2013 -0800 + + rados: obey op_size for 'get' + + Otherwise we try to read the whole object in one go, which doesn't bode + well for large objects (either non-optimal or simply broken). + + Signed-off-by: Sage Weil + Reviewed-by: Dan Mick + (cherry picked from commit 234becd3447a679a919af458440bc31c8bd6b84f) + +commit ee943c8bcf36f1e2218d8e25edfa38ec5fe4bec2 +Author: Samuel Just +Date: Wed Feb 27 16:58:45 2013 -0800 + + FileJournal::wrap_read_bl: adjust pos before returning + + Otherwise, we may feed an offset past the end of the journal to + check_header in read_entry and incorrectly determine that the entry is + corrupt. + + Fixes: 4296 + Backport: bobtail + Backport: argonaut + Reviewed-by: Sage Weil + Signed-off-by: Samuel Just + (cherry picked from commit 5d54ab154ca790688a6a1a2ad5f869c17a23980a) + +commit 8c6f52215240f48b5e4d5bb99a5f2f451e7ce70a +Author: Sage Weil +Date: Wed Jan 16 13:14:00 2013 -0800 + + osd: leave osd_lock locked in shutdown() + + No callers expect the lock to be dropped. + + Fixes: #3816 + Signed-off-by: Sage Weil + (cherry picked from commit 98a763123240803741ac9f67846b8f405f1b005b) + +commit a324d999804b4648f245ee36b3bd611b3d139d5d +Author: Sage Weil +Date: Tue Feb 26 14:07:12 2013 -0800 + + msg: fix entity_addr_t::is_same_host() for IPv6 + + We weren't checking the memcmp return value properly! Aie... + + Backport: bobtail + Signed-off-by: Sage Weil + (cherry picked from commit c8dd2b67b39a8c70e48441ecd1a5cc3c6200ae97) + +commit 79d68ae8581141c3fb4cfafd76d5111ff009b762 +Author: Sage Weil +Date: Sun Feb 17 22:35:50 2013 -0800 + + osd: requeue pg waiters at the front of the finished queue + + We could have a sequence like: + + - op1 + - notify + - op2 + + in the finished queue. Op1 gets put on waiting_for_pg, the notify + creates the pg and requeues op1 (and the end), op2 is handled, and + finally op1 is handled. That breaks ordering; see #2947. + + Instead, when we wake up a pg, queue the waiting messages at the front + of the dispatch queue. + + Signed-off-by: Sage Weil + Reviewed-by: Samuel Just + (cherry picked from commit 56c5a07708d52de1699585c9560cff8b4e993d0a) + +commit 79c4e7e91becc497843d96251776bdc176706aa0 +Author: Sage Weil +Date: Sun Feb 17 20:49:52 2013 -0800 + + osd: pull requeued requests off one at a time + + Pull items off the finished queue on at a time. In certain cases, an + event may result in new items betting added to the finished queue that + will be put at the *front* instead of the back. See latest incarnation + of #2947. + + Note that this is a significant changed in behavior in that we can + theoretically starve if an event keeps resulting in new events getting + generated. Beware! + + Signed-off-by: Sage Weil + Reviewed-by: Samuel Just + (cherry picked from commit f1841e4189fce70ef5722d508289e516faa9af6a) + +commit 3a6ce5d0355beaa56199465e94666cae40bd8da1 +Author: Sage Weil +Date: Thu Jan 17 22:00:42 2013 -0800 + + mds: open mydir after replay + + In certain cases, we may replay the journal and not end up with the + dirfrag for mydir open. This is fine--we just need to open it up and + fetch it below. + + Signed-off-by: Sage Weil + (cherry picked from commit e51299fbce6bdc3d6ec736e949ba8643afc965ec) + +commit 36ed407e0f939a9bca57c3ffc0ee5608d50ab7ed +Author: Greg Farnum +Date: Thu Feb 21 09:21:01 2013 -0800 + + mds: use inode_t::layout for dir layout policy + + Remove the default_file_layout struct, which was just a ceph_file_layout, + and store it in the inode_t. Rip out all the annoying code that put this + on the heap. + + To aid in this usage, add a clear_layout() function to inode_t. + + Signed-off-by: Sage Weil + Signed-off-by: Greg Farnum + Reviewed-by: Sage Weil + +commit b4fd196cae5ab76aeb8f82f0581d0a6a2133a3ed +Author: Sage Weil +Date: Sun Jan 20 21:53:37 2013 -0800 + + mds: parse ceph.*.layout vxattr key/value content + + Use qi to parse a strictly formatted set of key/value pairs. Be picky + about whitespace. Any subset of recognized keys is allowed. Parse the + same set of keys as the ceph.*.layout.* vxattrs. + + Signed-off-by: Sage Weil + (cherry picked from commit 5551aa5b3b5c2e9e7006476b9cd8cc181d2c9a04) + +commit 5f92adca26b509aed5655e85ad53174fa7b574b9 +Author: Yehuda Sadeh +Date: Mon Feb 18 09:10:43 2013 -0800 + + rgw: fix multipart uploads listing + + Fixes: #4177 + Backport: bobtail + Listing multipart uploads had a typo, and was requiring the + wrong resource (uploadId instead of uploads). + + Signed-off-by: Yehuda Sadeh + Reviewed-by: Greg Farnum + (cherry picked from commit db99fb4417b87301a69cb37b00c35c838b77197e) + +commit a44df9343594099fecb3897df393249d3d1992e2 +Author: Yehuda Sadeh +Date: Fri Feb 15 10:22:54 2013 -0800 + + rgw: don't copy object when it's copied into itself + + Fixes: #4150 + Backport: bobtail + + When object copied into itself, object will not be fully copied: tail + reference count stays the same, head part is rewritten. + + Signed-off-by: Yehuda Sadeh + Reviewed-by: Greg Farnum + (cherry picked from commit 34f885be536d0ac89c10fd29b1518751d2ffc547) + +commit 91d6be8353259ca30dc87062422e9ae334c3c344 +Author: Samuel Just +Date: Tue Feb 19 10:49:33 2013 -0800 + + PG: remove weirdness log for last_complete < log.tail + + In the case of a divergent object prior to log.tail, + last_complete may end up before log.tail. + + Backport: bobtail + Fixes #4174 + Signed-off-by: Samuel Just + Reviewed-by: Sage Weil + (cherry picked from commit dbadb3e2921297882c5836c67ca32bb8ecdc75db) + + Conflicts: + + src/osd/PG.cc + +commit 7889c5412deaab1e7ba53d66814d0f25659229c1 +Author: James Page +Date: Mon Feb 18 16:24:54 2013 +0000 + + Strip any trailing whitespace from rbd showmapped + + More recent versions of ceph append a bit of whitespace to the line + after the name of the /dev/rbdX device; this causes the monitor check + to fail as it can't find the device name due to the whitespace. + + This fix excludes any characters after the /dev/rbdN match. + (cherry picked from commit ad84ea07cac5096de38b51b8fc452c99f016b8d8) + +commit 42fba772c3c0e2396124a9d6ec39297dd9af4cc9 +Merge: 290a352 ad6655e +Author: Sage Weil +Date: Sun Feb 17 21:52:55 2013 -0800 + + Merge pull request #64 from dalgaaf/wip-bobtail-memleaks + + cherry-pick some memleak fixes from master to bobtail + +commit ad6655e976916d3b62e0c91fd469eeb49fe7da3e +Author: Danny Al-Gaaf +Date: Fri Feb 8 17:17:59 2013 +0100 + + rgw/rgw_rest.cc: fix 4K memory leak + + Fix 4K memory leak in case RGWClientIO::read() fails in + read_all_chunked_input(). + + Error from cppcheck was: + Checking src/rgw/rgw_rest.cc... + [src/rgw/rgw_rest.cc:688]: (error) Memory leak: data + + Signed-off-by: Danny Al-Gaaf + (cherry picked from commit 89df090e04ef9fc5aae29122df106b0347786fab) + +commit 3de692753c28ddbeb3c86b51466be16e94c9c458 +Author: Danny Al-Gaaf +Date: Fri Feb 8 17:14:19 2013 +0100 + + SyntheticClient.cc: fix some memory leaks in the error handling + + Fix some memory leaks in case of error handling due to failed + client->open() calls. + + Error from cppcheck was: + [src/client/SyntheticClient.cc:1980]: (error) Memory leak: buf + [src/client/SyntheticClient.cc:2040]: (error) Memory leak: buf + [src/client/SyntheticClient.cc:2090]: (error) Memory leak: buf + (cherry picked from commit f0ba80756d1c3c313014ad7be18191981fb545be) + +commit f19d228c6a49222659c769099aaa4e755b80331d +Author: Danny Al-Gaaf +Date: Fri Feb 8 16:57:20 2013 +0100 + + rgw/rgw_xml.cc: fix realloc memory leak in error case + + Fix error from cppcheck: + + [src/rgw/rgw_xml.cc:212]: (error) Common realloc mistake: 'buf' + nulled but not freed upon failure + + Signed-off-by: Danny Al-Gaaf + (cherry picked from commit d48cc789ea075ba2745754035640ada4131b2119) + +commit b0c6be95b03d9f3dd2badcdcff359ae7bc9684f4 +Author: Danny Al-Gaaf +Date: Fri Feb 8 16:54:33 2013 +0100 + + os/FileStore.cc: fix realloc memory leak in error case + + Fix error from cppcheck: + + [src/os/FileStore.cc:512]: (error) Common realloc mistake: 'fiemap' + nulled but not freed upon failure + + Signed-off-by: Danny Al-Gaaf + (cherry picked from commit c92a0f552587a232f66620170660d6b2ab6fb3a5) + +commit f3e5cedbc11005701ac0a8e70909a6372cd2fe6f +Author: Danny Al-Gaaf +Date: Fri Feb 8 16:49:36 2013 +0100 + + common/fiemap.cc: fix realloc memory leak + + Fix error from cppcheck: + + [src/common/fiemap.cc:73]: (error) Common realloc mistake: 'fiemap' + nulled but not freed upon failure + + Signed-off-by: Danny Al-Gaaf + (cherry picked from commit f26f1470e7af36fa1eb8dc59c8a7c62c3c3a22ba) + +commit 290a352c3f9e241deac562e980ac8c6a74033ba6 +Author: Sage Weil +Date: Thu Feb 14 11:37:57 2013 -0800 + + osd/OSDCap: add unit test for parsing pools/objects with _ and - + + Hunting #4122, where a user saw + + 2013-02-13 19:39:25.467916 7f766fdb4700 10 osd.0 10 session 0x2c8cc60 client.libvirt has caps osdcap[grant(object_prefix rbd^@children class-read),grant(pool libvirt^@pool^@test rwx)] 'allow class-read object_prefix rbd_children, allow pool libvirt-pool-test rwx' + + Signed-off-by: Sage Weil + (cherry picked from commit 2ce28ef1d7f95e71e1043912dfa269ea3b0d1599) + (cherry picked from commit a6534bc8a0247418d5263b765772d5266f99229c) + +commit f47916353547c77a65c7b70e609a9096f09c6d28 +Author: Sage Weil +Date: Thu Feb 14 15:39:43 2013 -0800 + + osd/OSDCap: tweak unquoted_word parsing in osd caps + + Newer versions of spirit (1.49.0-3.1ubuntu1.1 in quantal, in particular) + dislike the construct with alnum and replace the - and _ with '\0' in the + resulting string. + + Fixes: #4122 + Backport: bobtail + Signed-off-by: Sage Weil + Reviewed-by: Josh Durgin + (cherry picked from commit 6c504d96c1e4fbb67578fba0666ca453b939c218)