发布于 2017-10-09 00:55:04 | 277 次阅读 | 评论: 0 | 来源: 网友投递
Ceph PB 级分布式文件系统
Ceph是一个 Linux PB 级分布式文件系统。Ceph 最初是一项关于存储系统的 PhD 研究项目，由 Sage Weil 在 University of California, SantaCruz（UCSC）实施。
Ceph 10.2.10 发布了，该版本包含重要的 Bug 修复，建议所有 10.2.x 的用户升级。
值得关注的改进包括：
build/ops: Add fix subcommand to ceph-disk, fix SELinux denials, and speed up upgrade from non-SELinux enabled ceph to an SELinux enabled one (issue#20077, issue#20184, issue#19545, pr#14346, Boris Ranto)
build/ops: deb: Fix logrotate packaging (issue#19938, pr#15428, Nathan Cutler)
build/ops: extended, customizable systemd ceph-disk timeout (issue#18740, pr#15051, Alexey Sheplyakov)
build/ops: rpm: fix python-Sphinx package name for SUSE (issue#19924, pr#15196, Nathan Cutler, Jan Matejek)
build/ops: rpm: set subman cron attributes in spec file (issue#20074, pr#15473, Thomas Serlin)
cephfs: ceph-fuse segfaults at mount time, assert in ceph::log::Log::stop (issue#18157, pr#16963, Greg Farnum)
cephfs: df reports negative disk “used” value when quota exceed (issue#20178, pr#16151, John Spray)
cephfs: get_quota_root sends lookupname op for every buffered write (issue#20945, pr#17396, Dan van der Ster)
cephfs: osdc/Filer: truncate large file party by party (issue#19755, pr#15442, “Yan, Zheng”)
core: an OSD was seen getting ENOSPC even with osd_failsafe_full_ratio passed (issue#20544, issue#16878, issue#19733, issue#15912, pr#15050, Sage Weil, David Zafman)
core: disable skewed utilization warning by default (issue#20730, pr#17210, David Zafman)
core: interval_set: optimize intersect_of insert operations (issue#21229, pr#17514, Zac Medico)
core: kv: let ceph_logger destructed after db reset (issue#21336, pr#17626, wumingqiao)
core: test_envlibrados_for_rocksdb.yaml fails on crypto restart (issue#19741, pr#16293, Kefu Chai)
libradosstriper silently fails to delete empty objects in jewel (issue#20325, pr#15760, Stan K)
librbd: fail IO request when exclusive lock cannot be obtained (issue#20168, issue#21251, pr#17402, Jason Dillaman)
librbd: prevent self-blacklisting during break lock (issue#18666, pr#17412, Jason Dillaman)
librbd: reacquire lock should update lock owner client id (issue#19929, pr#17385, Jason Dillaman)
mds: damage reporting by ino number is useless (issue#18509, issue#16016, pr#14699, John Spray, Michal Jarzabek)
mds: log rotation doesn’t work if mds has respawned (issue#19291, pr#14673, Patrick Donnelly)
mds: save projected path into inode_t::stray_prior_path (issue#20340, pr#16150, “Yan, Zheng”)
mon: crash on shutdown, lease_ack_timeout event (issue#19825, pr#15083, Kefu Chai, Michal Jarzabek, Alexey Sheplyakov)
mon: Disallow enabling ‘hashpspool’ option to a pool without some kind of –i-understand-this-will-remap-all-pgs flag (issue#18468, pr#13507, Vikhyat Umrao)
mon: factor mon_osd_full_ratio into MAX AVAIL calc (issue#18522, pr#15236, Sage Weil)
mon: fail to form large quorum; msg/async busy loop (issue#20230, pr#15726, Haomai Wang, Michal Jarzabek)
mon: fix force_pg_create pg stuck in creating bug (issue#18298, pr#17008, Alexey Sheplyakov)
mon: osd crush set crushmap need sanity check (issue#19302, pr#16144, Loic Dachary)
osd: Add heartbeat message for Jumbo Frames (MTU 9000) (issue#20087, issue#20323, pr#16059, Piotr Dałek, Sage Weil, Greg Farnum)
osd: fix infinite loops in fiemap (issue#19996, pr#15189, Sage Weil, Ning Yao)
osd: leaked MOSDMap (issue#18293, pr#14943, Sage Weil)
osd: objecter full_try behavior not consistent with osd (issue#19430, pr#15474, Sage Weil)
osd: omap threadpool heartbeat is only reset every 100 values (issue#20375, pr#16167, Josh Durgin)
osd: osd_internal_types: wake snaptrimmer on put_read lock, too (issue#19131, pr#16015, Sage Weil)
osd: PrimaryLogPG: do not call on_shutdown() if (pg.deleting) (issue#19902, pr#15065, Kefu Chai)
osd: rados ls on pool with no access returns no error (issue#20043, issue#19790, pr#16473, Nathan Cutler, Kefu Chai, John Spray, Sage Weil, Brad Hubbard)
osd: ReplicatedPG: solve cache tier osd high memory consumption (issue#20464, pr#16169, Peng Xie)
osd: Reset() snaptrimmer on shutdown and do not default-abort on leaked pg refs (issue#19931, pr#15322, Greg Farnum)
osd: scrub_to specifies clone ver, but transaction include head write ver (issue#20041, pr#16405, David Zafman)
osd: unlock sdata_op_ordering_lock with sdata_lock hold to avoid missing wakeup signal (issue#20427, pr#15947, Alexey Sheplyakov)
qa: add a sleep after restarting osd before “tell”ing it (issue#16239, pr#15475, Kefu Chai)
rbd: api: is_exclusive_lock_owner shouldn’t return -EBUSY (issue#20182, pr#16296, Jason Dillaman)
rbd: cli: ensure positional arguments exist before casting (issue#20185, pr#16295, Jason Dillaman)
rbd: cli: map with cephx disabled results in error message (issue#19035, pr#16297, Jason Dillaman)
rbd: default features should be negotiated with the OSD (issue#17010, pr#14874, Mykola Golub, Jason Dillaman)
rbd: Enabling mirroring for a pool with clones may fail (issue#19798, issue#19130, pr#14663, Mykola Golub, Jason Dillaman)
rbd-mirror: image sync should send NOCACHE advise flag (issue#17127, pr#16285, Mykola Golub)
rbd: object-map: batch updates during trim operation (issue#17356, pr#15460, Mykola Golub, Venky Shankar, Nathan Cutler)
rbd: Potential IO hang if image is flattened while read request is in-flight (issue#19832, pr#15464, Jason Dillaman)
rbd: rbd_clone_copy_on_read ineffective with exclusive-lock (issue#18888, pr#16124, Nathan Cutler, Venky Shankar, Jason Dillaman)
rbd: rbd-mirror: ensure missing images are re-synced when detected (issue#19811, pr#15488, Jason Dillaman)
rbd: rbd-mirror: failover and failback of unmodified image results in split-brain (issue#19858, pr#14977, Jason Dillaman)
rbd: rbd-nbd: kernel reported invalid device size (0, expected 1073741824) (issue#19871, pr#15463, Mykola Golub)
rgw: add the remove-x-delete feature to cancel swift object expiration (issue#19074, pr#14659, Jing Wenjun)
rgw: aws4: add rgw_s3_auth_aws4_force_boto2_compat conf option (issue#16463, pr#17009, Javier M. Mellid)
rgw: bucket index check in radosgw-admin removes valid index (issue#18470, pr#16856, Zhang Shaowen, Pavan Rallabhandi)
rgw: cls: ceph::timespan tag_timeout wrong units (issue#20380, pr#16289, Matt Benjamin)
rgw: Custom data header support (issue#19644, pr#15966, Pavan Rallabhandi)
rgw: datalog trim can’t work as expected (issue#20190, pr#16299, Zhang Shaowen)
rgw: Delete non-empty bucket in slave zonegroup (issue#19313, pr#15477, Zhang Shaowen)
rgw: Do not decrement stats cache when the cache values are zero (issue#20661, issue#20934, pr#16720, Aleksei Gutikov, Pavan Rallabhandi)
rgw: fix crash caused by shard id out of range when listing data log (issue#19732, pr#15465, redickwang)
rgw: fix hangs in RGWRealmReloader::reload on SIGHUP (issue#20686, pr#17281, fang.yuxiang)
rgw: fix infinite loop in rest api for log list (issue#20386, pr#15988, xierui, Casey Bodley)
rgw: fix race in RGWCompleteMultipart (issue#20861, pr#16767, Abhishek Varshney, Matt Benjamin)
rgw: Fix up to 1000 entries at a time in check_bad_index_multipart (issue#20772, pr#16880, Orit Wasserman, Matt Benjamin)
rgw: folders starting with _ underscore are not in bucket index (issue#19432, pr#16276, Giovani Rinaldi, Orit Wasserman)
rgw: ‘gc list –include-all’ command infinite loop the first 1000 items (issue#19978, pr#15719, Shasha Lu, fang yuxiang)
rgw: meta sync thread crash at RGWMetaSyncShardCR (issue#20251, pr#16711, fang yuxiang, Nathan Cutler)
rgw: multipart copy-part remove ‘/’ for s3 java sdk request header (issue#20075, pr#16266, donglingpeng)
rgw: multipart parts on versioned bucket create versioned bucket index entries (issue#19604, issue#17964, pr#17278, Zhang Shaowen)
rgw: multisite: after CreateBucket is forwarded to master, local bucket may use different value for bucket index shards (issue#19745, pr#15450, Shasha Lu)
rgw: multisite: bucket zonegroup redirect not working (issue#19488, pr#15448, Casey Bodley)
rgw: multisite: fixes for meta sync across periods (issue#18639, pr#15556, Casey Bodley)
rgw: multisite: lock is not released when RGWMetaSyncShardCR::full_sync() fails to write marker (issue#18077, pr#17155, Zhang Shaowen)
rgw: multisite: log_meta on secondary zone causes continuous loop of metadata sync (issue#20357, issue#20244, pr#17148, Orit Wasserman, Casey Bodley)
rgw: multisite: memory leak on failed lease in RGWDataSyncShardCR (issue#19861, issue#19834, issue#19446, pr#15457, Casey Bodley, weiqiaomiao)
rgw: multisite: operating bucket’s acl&cors is not restricted on slave zone (issue#16888, pr#15453, Casey Bodley, Shasha Lu, Guo Zhandong)
rgw: multisite: realm rename does not propagate to other clusters (issue#19746, pr#15454, Casey Bodley)
rgw: multisite: rest api fails to decode large period on “period commit” (issue#19505, pr#15447, Casey Bodley)
rgw: multisite: RGWPeriodPuller does not call RGWPeriod::reflect() on new period (issue#19816, issue#19817, pr#17167, Casey Bodley)
rgw: multisite: RGWRadosRemoveOmapKeysCR::request_complete return val is wrong (issue#20539, pr#17156, Shasha Lu)
rgw: not initialized pointer cause rgw crash with ec data pool (issue#20542, pr#17164, Aleksei Gutikov, fang yuxiang)
rgw: radosgw-admin: bucket rm with –bypass-gc and without –purge-data doesn’t throw error message (issue#20688, pr#17159, Abhishek Varshney)
rgw: radosgw-admin data sync run crash (issue#20423, pr#17165, Shasha Lu)
rgw: radosgw-admin: fix bucket limit check argparse, div(0) (issue#20966, pr#16952, Matt Benjamin)
rgw: reduce log level of ‘storing entry at’ in cls_log (issue#19835, pr#15455, Willem Jan Withagen)
rgw: remove unnecessary ‘error in read_id for object name: default’ (issue#19922, pr#15197, weiqiaomiao)
rgw: replace ‘+’ with “%20” in canonical query string for s3 v4 auth (issue#20501, pr#16951, Zhang Shaowen, Matt Benjamin)
rgw: rgw_common.cc: modify the end check in RGWHTTPArgs::sys_get (issue#16072, pr#16268, zhao kun)
rgw: rgw_file: cannot delete bucket w/uxattrs (issue#20061, issue#20047, issue#19214, issue#20045, pr#15459, Matt Benjamin)
rgw: rgw_file: fix size and (c|m)time unix attrs in write_finish (issue#19653, pr#15449, Matt Benjamin)
rgw: rgw_file: incorrect lane lock behavior in evict_block() (issue#21141, pr#17597, Matt Benjamin)
rgw: rgw_file: prevent conflict of mkdir between restarts (issue#20275, pr#17147, Gui Hecheng)
rgw: rgw_file: v3 write timer does not close open handles (issue#19932, pr#15456, Matt Benjamin)
rgw: Segmentation fault when exporting rgw bucket in nfs-ganesha (issue#20663, pr#17285, Matt Benjamin)
rgw: send data-log list infinitely (issue#20951, pr#17287, fang.yuxiang)
rgw: set latest object’s acl failed (issue#18649, pr#15451, Zhang Shaowen)
rgw: Truncated objects (issue#20107, pr#17166, Yehuda Sadeh)
rgw: uninitialized memory is accessed during creation of bucket’s metadata (issue#20774, pr#17280, Radoslaw Zarzynski)
rgw: usage logging on tenated buckets causes invalid memory reads (issue#20779, pr#17279, Radoslaw Zarzynski)
rgw: user quota did not work well on multipart upload (issue#19285, issue#19602, pr#17277, Zhang Shaowen)
rgw: VersionIdMarker and NextVersionIdMarker are not returned when listing object versions (issue#19886, pr#16316, Zhang Shaowen)
rgw: when uploading objects continuously into a versioned bucket, some objects will not sync (issue#18208, pr#15452, lvshuhua)
tools: ceph cli: Rados object in state configuring race (issue#16477, pr#15762, Loic Dachary)
tools: ceph-disk: dmcrypt cluster must default to ceph (issue#20893, pr#16870, Loic Dachary)
tools: ceph-disk: don’t activate suppressed journal devices (issue#19489, pr#16703, David Disseldorp)
tools: ceph-disk: separate ceph-osd –check-needs-* logs (issue#19888, pr#15503, Loic Dachary)
tools: ceph-disk: systemd unit timesout too quickly (issue#20229, pr#17133, Loic Dachary)
tools: ceph-disk: Use stdin for ‘config-key put’ command (issue#21059, pr#17084, Brad Hubbard, Loic Dachary, Sage Weil)
tools: libradosstriper processes arbitrary printf placeholders in user input (issue#20240, pr#17574, Stan K)