-
Notifications
You must be signed in to change notification settings - Fork 5.9k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
bluestore: latest and greatest #6896
Commits on Jan 1, 2016
-
Configuration menu - View commit details
-
Copy full SHA for feb2d3f - Browse repository at this point
Copy the full SHA feb2d3fView commit details -
os/newstore: recycle rocksdb log files
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for be0528f - Browse repository at this point
Copy the full SHA be0528fView commit details -
os/newstore: fixed fragment size
Instead of a single, variable-length fragment for each object, set a fixed size (newstore_min_frag_size = 1 MB) and stripe the object over these. The last fragment will be smaller than 1 MB if the object is not a multiple of 1 MB. On write, this is basically free: we can just as cheaply write 4 inodes created together and fsync them than we can one. On overwrite, it allows us to replace individual fragments and avoid write-ahead many cases. On read it is a bit slower because of inode lookups and disk seeks. In the common case (big object written sequentially) we hope that fs prefetching will hide most of it (e.g., all inodes will be loaded together in the same metadata btree node, and the files' data is written sequentially on disk). Allowing for a singe large fragment in the case of a sequentially written large object may save us something, but it complicates the code significantly. Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 2993504 - Browse repository at this point
Copy the full SHA 2993504View commit details -
os/newstore: dump onode contents
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for f0f815f - Browse repository at this point
Copy the full SHA f0f815fView commit details -
os/newstore: set alloc hint on new frags
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 0af0dbd - Browse repository at this point
Copy the full SHA 0af0dbdView commit details -
os/newstoer: add newstore types to ceph-dencoder
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for b2db842 - Browse repository at this point
Copy the full SHA b2db842View commit details -
os/newstore: define a fid_backpointer_t type
Signed-off-by: Sage Weil <sage@redhat.com> fix wal_oP_t
Configuration menu - View commit details
-
Copy full SHA for 9291e16 - Browse repository at this point
Copy the full SHA 9291e16View commit details -
os/newstore: do not set/change frag_size if there are overlays
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 84646ab - Browse repository at this point
Copy the full SHA 84646abView commit details -
os/newstore: fix collection_list vs max entries
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 5e566dd - Browse repository at this point
Copy the full SHA 5e566ddView commit details -
os/newstore: make key names more efficient
- pack u32 and u64 in binary (instead of in hex) - avoid duplicating the object name while making things still sort by (key,name). Use < when key < name, = when key == name, > when key > name) as a prefix. And in the = case (which is basically always) include the name just once. Note that this breaks on-disk compatibility. Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 2dae3df - Browse repository at this point
Copy the full SHA 2dae3dfView commit details -
os/newstore: make collection_list tolerate sloppy start position
Because of this change (ceph#6076), the hobject_t will contain pool id, hence the ghobject_t having this hobject_t will be not equal to ghobject_t(). In newstore, this will cause assertion failure: FAILED assert(k >= start_key && k < end_key) The fix is to make compatible with previous change to create a ghobject_t object with pool id and shard id in newstore. Fixes: ceph#13801 Reported-by: Zhi Zhang <zhangz.david@outlook.com> Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 32e7683 - Browse repository at this point
Copy the full SHA 32e7683View commit details -
os/newstore: consume a raw block device
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 5658665 - Browse repository at this point
Copy the full SHA 5658665View commit details -
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for ad9f9fa - Browse repository at this point
Copy the full SHA ad9f9faView commit details -
os/newstore: always create db.wal
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 3a4d583 - Browse repository at this point
Copy the full SHA 3a4d583View commit details -
Configuration menu - View commit details
-
Copy full SHA for a62ffb0 - Browse repository at this point
Copy the full SHA a62ffb0View commit details -
os/bluestore: separate Allocator from freelist storage
FreelistManager perists our freelist. Allocator is a policy that allocates it. Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 9d01b8d - Browse repository at this point
Copy the full SHA 9d01b8dView commit details -
os/bluestore/BlockDevice: fix read return value
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for d704628 - Browse repository at this point
Copy the full SHA d704628View commit details -
os/bluestore: fix _do_read return value
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for a869f92 - Browse repository at this point
Copy the full SHA a869f92View commit details -
kv/RocksDBStore: take custom Env
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 65f720a - Browse repository at this point
Copy the full SHA 65f720aView commit details -
os/bluestore/Allocator: init_rm_free
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 08a94d9 - Browse repository at this point
Copy the full SHA 08a94d9View commit details -
os/bluestore/StupidAllocator: fix misc bugs
Can't use invalid iterator; fix init_rm_free. Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 1446048 - Browse repository at this point
Copy the full SHA 1446048View commit details -
os/bluestore/StupidAllocator: fix locking
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 1ffd5e6 - Browse repository at this point
Copy the full SHA 1ffd5e6View commit details -
os/bluestore/BlueStore: fix _do_read
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 1b8d5b6 - Browse repository at this point
Copy the full SHA 1b8d5b6View commit details -
ceph_test_objectstore: less verbose on hash collision test
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 226b347 - Browse repository at this point
Copy the full SHA 226b347View commit details -
ceph_test_objectstore: less verbose
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 6f5ac50 - Browse repository at this point
Copy the full SHA 6f5ac50View commit details -
os/bluestore/BlueFS: simple file system to back rocksdb
BlueFS is a simple file system that will back rocksdb. BlueRocksEnv is the rocksdb::Env implementation that glues them together. Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for dd04391 - Browse repository at this point
Copy the full SHA dd04391View commit details -
os/bluestore/BlockDevice: move to simple mutex model
Just for now, while we get the rest of this working. Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 653882c - Browse repository at this point
Copy the full SHA 653882cView commit details -
os/bluestore/BlueStore: share space with BlueFS
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for e4f6148 - Browse repository at this point
Copy the full SHA e4f6148View commit details -
os/bluestore/BlueFS: many fixes
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 2d05378 - Browse repository at this point
Copy the full SHA 2d05378View commit details -
ceph-bluefs-tool: simple tool to export bluefs content
Currently we just do a dump. We'll add more functionality later. Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for b8630ee - Browse repository at this point
Copy the full SHA b8630eeView commit details -
os/bluestore/BlueFS: readdir list dirs, too
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 98485de - Browse repository at this point
Copy the full SHA 98485deView commit details -
os/bluestore/BlueFS: ref count BlueFS::File *
There are FileWriters that exist when the file is deleted. Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 3649a80 - Browse repository at this point
Copy the full SHA 3649a80View commit details -
kv/RocksDBStore: rocksdb_separate_wal_dir option
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 9341eec - Browse repository at this point
Copy the full SHA 9341eecView commit details -
ceph_test_objectstore: trivial init fix
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for ac05b4c - Browse repository at this point
Copy the full SHA ac05b4cView commit details -
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for b073028 - Browse repository at this point
Copy the full SHA b073028View commit details -
os/bluestore/BlueFS: simplify extent list
Merge contiguous extents. Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for dd90149 - Browse repository at this point
Copy the full SHA dd90149View commit details -
os/bluestore/BlueFS: periodically compact log
Rewrite only the current metadata in a fresh log periodically to free log space. Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 73adec4 - Browse repository at this point
Copy the full SHA 73adec4View commit details -
vstart.sh: debug bluefs and rocksdb
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 9785bc9 - Browse repository at this point
Copy the full SHA 9785bc9View commit details -
os/bluestore/BlueFS: prevent read+write sharing
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 05be4c6 - Browse repository at this point
Copy the full SHA 05be4c6View commit details -
os/bluestore/BlueFS: avoid lock during reads
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for e7cce09 - Browse repository at this point
Copy the full SHA e7cce09View commit details -
os/bluestore/BlockDevice: check aio return values
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for db754e7 - Browse repository at this point
Copy the full SHA db754e7View commit details -
os/bluestore/BlockDevice: fix alignment check
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for f6f4ed3 - Browse repository at this point
Copy the full SHA f6f4ed3View commit details -
os/bluestore/BlockDevice: debug read result
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for e3fd279 - Browse repository at this point
Copy the full SHA e3fd279View commit details -
os/bluestore/BlockDevice: lock device while open
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for ef06380 - Browse repository at this point
Copy the full SHA ef06380View commit details -
os/bluestore: reenable rocksdb recycling
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for ccce793 - Browse repository at this point
Copy the full SHA ccce793View commit details -
os/bluestore/BlueFS: fix writes spanning extents
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 13655fb - Browse repository at this point
Copy the full SHA 13655fbView commit details -
os/bluestore/BlueFS: fix overwrite
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 1727ceb - Browse repository at this point
Copy the full SHA 1727cebView commit details -
os/bluestore/BlockDevice: restructure interface
use atomics, do not track in-flight extents or magically cope with racing ios (that is the users responsibility). Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for b487987 - Browse repository at this point
Copy the full SHA b487987View commit details -
os/bluestore: disable overlay for now
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 9f114ac - Browse repository at this point
Copy the full SHA 9f114acView commit details -
os/bluestore/BlueStore: fix zero gap bug
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 02605a6 - Browse repository at this point
Copy the full SHA 02605a6View commit details -
os/bluestore: support second block.wal device
Use this device for the bluefs log. Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 3745afb - Browse repository at this point
Copy the full SHA 3745afbView commit details -
os/bluestore/BlueFS: fix replay of unlink
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 2e1edef - Browse repository at this point
Copy the full SHA 2e1edefView commit details -
os/bluestore/BlueFS: flush log if needed
If a file has dirty metadata (but no dirty data), we still need to flush the log when it is flushed. Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 9565f0d - Browse repository at this point
Copy the full SHA 9565f0dView commit details -
os/bluestore: label all block devices
Label all of our block devices with a simple label that includes the osd_uuid. Wire this into the ObjectStore and OSD probe mechanism. Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 31307a5 - Browse repository at this point
Copy the full SHA 31307a5View commit details -
rocksdb: pull up to master, include EnvMirror
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 07a47a3 - Browse repository at this point
Copy the full SHA 07a47a3View commit details -
os/bluestore/BlueStore: drop internal EnvMirror
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for de300b1 - Browse repository at this point
Copy the full SHA de300b1View commit details -
os/bluestore/BlueFS: all overwrites on open_for_write
rocksdb will occasionally overwrite an existing file if it is not present/valid in the manifest. Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for f80b335 - Browse repository at this point
Copy the full SHA f80b335View commit details -
os/bluestore: less debug noise
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 8094355 - Browse repository at this point
Copy the full SHA 8094355View commit details -
os/bluestore: block.db support
Support a mid- to fast device that will preferentially store the rocksdb data (and wal, if block.wal is not present). Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 485557a - Browse repository at this point
Copy the full SHA 485557aView commit details -
ceph_test_objectstore: clean up synthetic collections
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for c96e025 - Browse repository at this point
Copy the full SHA c96e025View commit details -
os/bluestore/BlockDevice: inject block failures
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 5fb09a9 - Browse repository at this point
Copy the full SHA 5fb09a9View commit details -
Configuration menu - View commit details
-
Copy full SHA for a17fe3e - Browse repository at this point
Copy the full SHA a17fe3eView commit details -
os/bluestore: record kv backend
Record kv backend at mkfs time instead of relying on current value of config option. Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 423f797 - Browse repository at this point
Copy the full SHA 423f797View commit details -
os/bluestore/FreelistManager: drop unused db ref
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 7664ffa - Browse repository at this point
Copy the full SHA 7664ffaView commit details -
os/bluestore: add extent_ref_map_t
This will be used to refcount extents for some subset of the store (objects with same name or hash value?). Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 648f132 - Browse repository at this point
Copy the full SHA 648f132View commit details -
os/bluestore/bluestore_types: localize types
Prefix with bluestore_ Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for bc0f2e6 - Browse repository at this point
Copy the full SHA bc0f2e6View commit details -
os/kstore: add new KStore backend
This is based on BlueStore, but with all of the block-related code and complexity ripped out, and a simple striping strategy added in its place. Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 669bec7 - Browse repository at this point
Copy the full SHA 669bec7View commit details -
os/KeyValueStore: drop kinetic #include
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for e3affe6 - Browse repository at this point
Copy the full SHA e3affe6View commit details -
ceph_objectstore_test: fix warning
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 02bd7d5 - Browse repository at this point
Copy the full SHA 02bd7d5View commit details -
os/bluestore/BlueStore: fix object key decode with key
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 196786d - Browse repository at this point
Copy the full SHA 196786dView commit details -
os/kstore/KStore: fix object key decode with key
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 499b40f - Browse repository at this point
Copy the full SHA 499b40fView commit details -
os/bluestore: clear coll_map on umount, fsck finish
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 197c5ae - Browse repository at this point
Copy the full SHA 197c5aeView commit details -
kv/RocksDBStore: behave if options string is empty
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 08f919e - Browse repository at this point
Copy the full SHA 08f919eView commit details -
os/bluestore/BlueStore: fix _open_bdev() failure path
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 65e5ff4 - Browse repository at this point
Copy the full SHA 65e5ff4View commit details -
os/bluestore: default to 64k min_alloc_size
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 22073a0 - Browse repository at this point
Copy the full SHA 22073a0View commit details -
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for aa844e5 - Browse repository at this point
Copy the full SHA aa844e5View commit details -
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 3f8d46c - Browse repository at this point
Copy the full SHA 3f8d46cView commit details -
os/bluestore/BlueStore: fix error path if label set fails
Reported-by: David Zafman <dzafman@redhat.com> Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 8c04a3b - Browse repository at this point
Copy the full SHA 8c04a3bView commit details -
rpm, debian: package ceph-bluefs-tool
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 0633468 - Browse repository at this point
Copy the full SHA 0633468View commit details -
os/bluestore: bluestore bluefs = true
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 6b28449 - Browse repository at this point
Copy the full SHA 6b28449View commit details -
os/bluestore: fix fsck contains vs intersects
Any overlap is an error. Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 993c87f - Browse repository at this point
Copy the full SHA 993c87fView commit details -
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 1f05196 - Browse repository at this point
Copy the full SHA 1f05196View commit details -
os/bluestore: don't create block.{db,wal} by default
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 510b4c7 - Browse repository at this point
Copy the full SHA 510b4c7View commit details -
os/bluestore/BlueStore: better error msg for bdev label check
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 4ebe78c - Browse repository at this point
Copy the full SHA 4ebe78cView commit details -
Allocate aligned buffer. Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 6925a06 - Browse repository at this point
Copy the full SHA 6925a06View commit details -
os/bluestore: fail mount of fsck finds errors
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 2158371 - Browse repository at this point
Copy the full SHA 2158371View commit details -
script/crash_bdev: simple script to inject bdev failures
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 9df3d96 - Browse repository at this point
Copy the full SHA 9df3d96View commit details -
os/bluestore: better debugging on fsck alloc errors
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for b1df8cb - Browse repository at this point
Copy the full SHA b1df8cbView commit details -
os/bluestore: update freelist in individual transactions
We submit each operation's transaction individually to rocksdb, and then since a final transction to flush them all. However, they may not commit atomically (all together), which means we need to leave the individual freelist updates within each transaction. Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 5e4d3d2 - Browse repository at this point
Copy the full SHA 5e4d3d2View commit details -
os/bluestore/BlueFS: ignore flush when buffer is small
Rocksdb does a flush after every append, each of which is often less than a full block. This is very inefficient when our _flush() will send that to disk (and block). Avoid this most of the time by ignoring small flush requests entirely, unless the force flag is set (e.g., by fsync). Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 1605e04 - Browse repository at this point
Copy the full SHA 1605e04View commit details -
os/bluestore/BlueFS: do not dirty file when overwriting bytes
The rocksdb log recycle option allows us to overwrite previously allocated space in an old log file to avoid updating the file metadata on normal file systems. Take advantage of that here to by implementing what is effectively O_NOCMTIME semantics: we do not dirty the file metadata just because mtime is updated. Instead, we dirty the file only if we allocate new space or if the size has to be increased. Note that on my NVME drive a single-thread rados bench test, we jump from 30MB/sec to 50MB/sec 128KB writes as soon as we start recycling previous logs (about 40 second into the run). Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for be598b7 - Browse repository at this point
Copy the full SHA be598b7View commit details -
os/bluestore/BlueFS: get_usage()
Return (and log) usage for all bdevs. Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for cf5d139 - Browse repository at this point
Copy the full SHA cf5d139View commit details -
os/bluestore/BlueStore: use BlueFS::get_usage()
...just so we log bdev utilization in the log. Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 3d2bb7a - Browse repository at this point
Copy the full SHA 3d2bb7aView commit details -
os/bluestore/BlockDevice: rename bdev options
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for a3de5b6 - Browse repository at this point
Copy the full SHA a3de5b6View commit details -
os/bluestore: handle both buffered and direct+async IO
Prefer aio unless explicitly directed otherwise. Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 9be0b53 - Browse repository at this point
Copy the full SHA 9be0b53View commit details -
rocksdb: debug log writes/reads
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for e07fc75 - Browse repository at this point
Copy the full SHA e07fc75View commit details -
os/bluestore/BlueStore: do WAL ops buffered to avoid RMW issues
We may have multiple WAL ops that do read/modify/write covering the same blocks. To avoid the complexity of identifying those situations and ensuring that we, say, wait for writes to complete before reading them back again, just make the IO buffered and let the page cache handle that for us. This fixes the failure of LibRadosAio.RoundTripWriteFull. Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 6d41758 - Browse repository at this point
Copy the full SHA 6d41758View commit details -
os/bluestore/BlockDevice: fix path
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for e63dbda - Browse repository at this point
Copy the full SHA e63dbdaView commit details -
os/bluestore/BlockDevice: adjust debug output
5 helpful (read/write offsets) 10 more, with aio completions 20 everything 30 fire hose 40 data hexdumps Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 95b81e5 - Browse repository at this point
Copy the full SHA 95b81e5View commit details -
os/bluestore/BlueStore: remove unused OnodeMap::remove
We install negative entries instead. Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for bf1f02c - Browse repository at this point
Copy the full SHA bf1f02cView commit details -
os/bluestore/BlueStore: fix rename
Install a negative onode entry at the old name position. Otherwise, a simple transaction like rename a -> b touch b will re-read the old b onode key on the second op, and chaos will ensue (e.g., because it'll reference the same extents from a different object). Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for c206832 - Browse repository at this point
Copy the full SHA c206832View commit details -
Configuration menu - View commit details
-
Copy full SHA for 134a0e4 - Browse repository at this point
Copy the full SHA 134a0e4View commit details -
os/bluestore/BlueStore: fix read bug when there is a hole
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 8941e32 - Browse repository at this point
Copy the full SHA 8941e32View commit details -
os/bluestore/BlueStore: note wal releases in fsck
Include these in used_blocks (they are about to be released but not reflected in the onode). Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for dc5d33b - Browse repository at this point
Copy the full SHA dc5d33bView commit details -
os/bluestore: clean up comments a bit
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 27e44dd - Browse repository at this point
Copy the full SHA 27e44ddView commit details -
os/bluestore: add some slow debug path
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 3133eca - Browse repository at this point
Copy the full SHA 3133ecaView commit details -
ceph_test_objectstore: clone objects with same hash
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 7e86bfd - Browse repository at this point
Copy the full SHA 7e86bfdView commit details -
ceph_test_objectstore: clone non-empty objects, not empty ones
This condition was backwards. Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 48595ad - Browse repository at this point
Copy the full SHA 48595adView commit details -
ceph_test_objectstore: simplify object name generation
The long names don't exercise useful code paths, and having consistent naming makes it easier to grep through logs. Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 1769163 - Browse repository at this point
Copy the full SHA 1769163View commit details -
ceph_test_objectstore: fix clone
Copy the buffer, in case other threads modify it in place. Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 549a335 - Browse repository at this point
Copy the full SHA 549a335View commit details -
ceph_test_objectstore: fix locking for a few ops
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 2162990 - Browse repository at this point
Copy the full SHA 2162990View commit details -
ceph_test_objectstore: save map lookups for a few ops
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for c9659f9 - Browse repository at this point
Copy the full SHA c9659f9View commit details -
ceph_test_objectstore: debug enter/exit points
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for a77363c - Browse repository at this point
Copy the full SHA a77363cView commit details -
ceph_test_objectstore: validate full object contents after writes
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for ac08664 - Browse repository at this point
Copy the full SHA ac08664View commit details -
ceph_test_objectstore: add many clone tests
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for f884edf - Browse repository at this point
Copy the full SHA f884edfView commit details -
ceph_test_objectstore: dump actual vs expected on read data mismatch
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 82d2132 - Browse repository at this point
Copy the full SHA 82d2132View commit details -
ceph_test_objectstore: use a few hash values for objects; clone betwe…
…en them We only guarantee support for clone between objects with the same hash. Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for eeb2251 - Browse repository at this point
Copy the full SHA eeb2251View commit details -
ceph_test_objectstore: do Synthetic tests over larger objects
400k for objects. Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for a583e5d - Browse repository at this point
Copy the full SHA a583e5dView commit details -
os/bluestore: add bluestore_debug_no_reuse_blocks
This makes debugging a bit easier because we never use the same extent of the disk twice, leaving useful evidence behind. Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 2f9be0c - Browse repository at this point
Copy the full SHA 2f9be0cView commit details -
os/bluestore/BlockDevice: fix waiter wakeup use-after-free race
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for d927919 - Browse repository at this point
Copy the full SHA d927919View commit details -
os/bluestore/BlueStore: wal_op_t::OP_COPY
Assume block-aligned. Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 97bf343 - Browse repository at this point
Copy the full SHA 97bf343View commit details -
os/bluestore/bluestore_types: add contains(), clear(), empty() to ext…
…ent_ref_map Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 45801ed - Browse repository at this point
Copy the full SHA 45801edView commit details -
unittest_bluefs, unittest_bluestore_types
These should run during make check. Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for e93e926 - Browse repository at this point
Copy the full SHA e93e926View commit details -
os/bluestore/bluestore_types: add extent FLAG_COW_{HEAD,TAIL}
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for fd75b4e - Browse repository at this point
Copy the full SHA fd75b4eView commit details -
os/bluestore: Enode infrastructure
Enodes will track extent ref counts for any extent that is marked shared. There will be an enode for any unique hash value that has any refs. We will keep in-memory copies of only those Enodes that are referenced by in-memory Onodes, and only if the enode is requested (e.g., the enode won't be loaded as a result of an object read because we never need to call get_enode.). Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 64b4e2f - Browse repository at this point
Copy the full SHA 64b4e2fView commit details -
os/bluestore/BlueStore: only allow clone if hash matches
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 8ebb390 - Browse repository at this point
Copy the full SHA 8ebb390View commit details -
os/bluestore: support copy-on-write clones
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for b758d9f - Browse repository at this point
Copy the full SHA b758d9fView commit details -
os/bluestore/BlueStore: fix _zero when previous extent partially unwr…
…itten Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 4aa5f02 - Browse repository at this point
Copy the full SHA 4aa5f02View commit details -
os/bluestore/StupidAllocator: bluestore_debug_small_allocations
Force small allocations for debugging purposes. Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for a684a59 - Browse repository at this point
Copy the full SHA a684a59View commit details -
os/bluestore/BlueStore: fsck_on_umount
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 5534d2b - Browse repository at this point
Copy the full SHA 5534d2bView commit details -
ceph_test_objectstore: enable bluestore debug options
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for de8a99d - Browse repository at this point
Copy the full SHA de8a99dView commit details -
os/bluestore: optimize _dump_onode slightly
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 0a6f35d - Browse repository at this point
Copy the full SHA 0a6f35dView commit details -
os/bluestore: debug msg on statfs
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for e25cf20 - Browse repository at this point
Copy the full SHA e25cf20View commit details -
os/bluestore: simplify _do_remove
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 8e965db - Browse repository at this point
Copy the full SHA 8e965dbView commit details -
os/bluestore/BlockDevice: add invalidate_cache
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 225d3cd - Browse repository at this point
Copy the full SHA 225d3cdView commit details -
os/bluestore/BlueFS: implement invalidate_cache
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 5662bd8 - Browse repository at this point
Copy the full SHA 5662bd8View commit details -
os/bluestore/FreelistManager: audit
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for d48a2ba - Browse repository at this point
Copy the full SHA d48a2baView commit details -
os/bluestore/BlockDevice: helpful error when aio cannot init
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for cff5dc5 - Browse repository at this point
Copy the full SHA cff5dc5View commit details -
os/bluestore/BlueFS: do not flush metadata on flush()
That's what fsync is for. Moreover, this can lead to some squirreliness if we trigger this from _flush_log(). Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 93964a7 - Browse repository at this point
Copy the full SHA 93964a7View commit details -
os: remove {get,set}_allow_sharded_objects from interface
We've already forced everyone to upgrade through hammer, so everyone supports this. Just unconditionally set the feature if it is not set (for consistency's sake). Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 56375c5 - Browse repository at this point
Copy the full SHA 56375c5View commit details -
osd/PGBackend: fix omap digest error message
Print the *omap* digest, not *data* digest. Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for fd2659d - Browse repository at this point
Copy the full SHA fd2659dView commit details -
os/bluestore: clear onode in _do_remove
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 9aca4ad - Browse repository at this point
Copy the full SHA 9aca4adView commit details -
os/kstore: clear onode on _do_remove
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 789e99c - Browse repository at this point
Copy the full SHA 789e99cView commit details -
os/ObjectStore: add fsck to interface
Only bluestore and kstore implement this currently. Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for da9266d - Browse repository at this point
Copy the full SHA da9266dView commit details -
ceph-objectstore-tool: add fsck command
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 5f87bab - Browse repository at this point
Copy the full SHA 5f87babView commit details -
ceph_test_objectstore: add omap iterator test
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 0cde589 - Browse repository at this point
Copy the full SHA 0cde589View commit details -
osd/ReplicatedPG: print omap_digest in debug log
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 0f85d86 - Browse repository at this point
Copy the full SHA 0f85d86View commit details -
os/bluestore: do not include header in iterator result
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for b25a242 - Browse repository at this point
Copy the full SHA b25a242View commit details -
os/kstore: do not include header in omap iterator result
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 624e996 - Browse repository at this point
Copy the full SHA 624e996View commit details -
os/bluestore/StupidAllocator: add reservation assertions
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 193d25f - Browse repository at this point
Copy the full SHA 193d25fView commit details -
os/bluestore/StupidAllocator: fix reservation release on allocate
Use up the amount we allocated, not the amount we asked for. Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 2b2cc88 - Browse repository at this point
Copy the full SHA 2b2cc88View commit details -
os/bluestore/Allocator: add unreserve()
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 6641482 - Browse repository at this point
Copy the full SHA 6641482View commit details -
os/bluestore: allocate shouldn't fail if reserve succeeded
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 5b57b09 - Browse repository at this point
Copy the full SHA 5b57b09View commit details -
This is an ancient obsolete test that is never used. Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for f941642 - Browse repository at this point
Copy the full SHA f941642View commit details -
ceph-objectstore-tool: drop unused FileSTore include
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 6c1ef47 - Browse repository at this point
Copy the full SHA 6c1ef47View commit details -
ceph:small_io_bench_dumb: drop unused include
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for e07ab3e - Browse repository at this point
Copy the full SHA e07ab3eView commit details -
os/filestore: move FileStore to os/filestore/*
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for ba2cc1e - Browse repository at this point
Copy the full SHA ba2cc1eView commit details -
os/memstore: move MemStore into os/memstore/*
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 82cbc07 - Browse repository at this point
Copy the full SHA 82cbc07View commit details -
os/keyvaluestore: move KeyValueStore into os/keyvaluestore/*
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 98a0e10 - Browse repository at this point
Copy the full SHA 98a0e10View commit details -
Configuration menu - View commit details
-
Copy full SHA for 8fc65e1 - Browse repository at this point
Copy the full SHA 8fc65e1View commit details -
os/fs: move btrfs_ioctl.h to os/fs
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for d2b5e92 - Browse repository at this point
Copy the full SHA d2b5e92View commit details -
Configuration menu - View commit details
-
Copy full SHA for b16f591 - Browse repository at this point
Copy the full SHA b16f591View commit details -
os/bluestore/bluestore_types: fix bluestore_extent_ref_map_t test inst
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 893bfc7 - Browse repository at this point
Copy the full SHA 893bfc7View commit details -
unittest_bluestore_types: fix warnings
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 602b8de - Browse repository at this point
Copy the full SHA 602b8deView commit details -
os/bluestore/StupidAllocator: be less stupid about alloc_unit
Make sure the extent we return is aligned to alloc_unit. If the first extent isn't suitable, try the next one. Keep bin 0 for things that are smaller than min_alloc_size. Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 34a0f30 - Browse repository at this point
Copy the full SHA 34a0f30View commit details -
osd: do not catch mkfs exceptions
We either want to take a clean error path, or dump core. Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 97373a7 - Browse repository at this point
Copy the full SHA 97373a7View commit details -
os/kstore: clear coll_map on umount
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 81243c0 - Browse repository at this point
Copy the full SHA 81243c0View commit details -
ceph_test_objectstore: clean out test dir for each test
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 5950eae - Browse repository at this point
Copy the full SHA 5950eaeView commit details -
os/kstore: fix bugs in read stripe logic
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for b57fcf6 - Browse repository at this point
Copy the full SHA b57fcf6View commit details -
Configuration menu - View commit details
-
Copy full SHA for e4e1a7f - Browse repository at this point
Copy the full SHA e4e1a7fView commit details -
common/buffer: make hexdump look like 'hexdump -C ...'
...the better to diff them with. Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 5c62690 - Browse repository at this point
Copy the full SHA 5c62690View commit details -
os/kstore: cache in-flight stripe updates in memory
The write process may do a read/modify/write on a stripe. In order to allow multiple writes to coexist within the same transaction, we need to be able to "see" our writes. Clear the "cached" stripe values when the last TransContext touching an onode is finished. In theory we could pin memory with a constant stream of updates to an object; we may need to address that later. Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 645b535 - Browse repository at this point
Copy the full SHA 645b535View commit details -
Configuration menu - View commit details
-
Copy full SHA for 491e2ce - Browse repository at this point
Copy the full SHA 491e2ceView commit details -
CMakeLists: update for os/ reorg
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 88c3ee8 - Browse repository at this point
Copy the full SHA 88c3ee8View commit details -
os/bluestore: be tolerant of collection_list bounds
In particular, we may get a shard specified along with hobject_t min or max (from PGBackend::objects_list_range()). Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 3fa09f0 - Browse repository at this point
Copy the full SHA 3fa09f0View commit details -
It didn't like k=1 with the default profile. Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for fc9d952 - Browse repository at this point
Copy the full SHA fc9d952View commit details -
vstart.sh: no need for 'quit' to ceph cli
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for a3ef0ec - Browse repository at this point
Copy the full SHA a3ef0ecView commit details -
os/bluestore/BlockDevice: fix FS leak
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for acc8217 - Browse repository at this point
Copy the full SHA acc8217View commit details -
kv/RocksDBStore: fix leak of custom Env
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for ef26205 - Browse repository at this point
Copy the full SHA ef26205View commit details -
os/bluestore/BlueFS: fix leak of iocs in writer
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 3f4bd46 - Browse repository at this point
Copy the full SHA 3f4bd46View commit details -
os/bluestore/BlueRocksEnv: fix several leaks
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 3f8e2bd - Browse repository at this point
Copy the full SHA 3f8e2bdView commit details -
ceph_test_objectstore: close cct on shutdown
This lets us do leak checking. Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 64b80f3 - Browse repository at this point
Copy the full SHA 64b80f3View commit details -
os/bluestore/BlueFS: fix a few leaks
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 7cb901c - Browse repository at this point
Copy the full SHA 7cb901cView commit details -
os/bluestore/BlueFS: delay IOContext dtor until after io completes
It's possible for the IO to be in flight when the caller closes the writer handle (although dangerous of them). Queue the IOContext for async cleanup when we sync everything to disk. Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 0336279 - Browse repository at this point
Copy the full SHA 0336279View commit details -
os/bluestore/BlockDevice: clean up aio completion a bit
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 7172a7e - Browse repository at this point
Copy the full SHA 7172a7eView commit details -
os/bluestore/BlueFS: wait for flush aios to complete before returning
This makes all the IOs effectively synchronous (while holding the lock), which isn't great, but at least it's correct. We can contemplate async later.. Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 198b156 - Browse repository at this point
Copy the full SHA 198b156View commit details -
ceph-objectstore-tool: get store type from 'type' file, if present
Just like ceph-osd. Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 7dddecb - Browse repository at this point
Copy the full SHA 7dddecbView commit details -
ceph-objectstore-tool: don't require journal path
Assume journal symlink is present. Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for ee01a7a - Browse repository at this point
Copy the full SHA ee01a7aView commit details -
os/bluestore: write 'type' file
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 56a964b - Browse repository at this point
Copy the full SHA 56a964bView commit details -
os/bluestore: Don't forget close fd in _setup_block_symlink_or_file.
Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 20dc14b - Browse repository at this point
Copy the full SHA 20dc14bView commit details -
os/bluestore/BlueFS: remove deleted file from dirty list
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for e7a84fe - Browse repository at this point
Copy the full SHA e7a84feView commit details -
qa/workunits/cephtool/test.sh: leave sortbitwise set
New backends don't work if it's off. Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 37c6390 - Browse repository at this point
Copy the full SHA 37c6390View commit details -
fs: fix unclosed formatter session
Fixes: ceph#14210 Signed-off-by: xie.xingguo <xie.xingguo@zte.com.cn>
Configuration menu - View commit details
-
Copy full SHA for d6043d9 - Browse repository at this point
Copy the full SHA d6043d9View commit details -
os/bluestore/BlueStore: fix overlay keys
Signed-off-by: YiQiang Chen <cyqsign@163.com>
Configuration menu - View commit details
-
Copy full SHA for 757152f - Browse repository at this point
Copy the full SHA 757152fView commit details -
Signed-off-by: Ning Yao <zay11022@gmail.com>
Configuration menu - View commit details
-
Copy full SHA for bc1cf95 - Browse repository at this point
Copy the full SHA bc1cf95View commit details
Commits on Jan 3, 2016
-
qa/workunits/rados/test_rados_tool: adapt to new buffer hexdump
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 1097bd2 - Browse repository at this point
Copy the full SHA 1097bd2View commit details -
qa/workunits/rados/test_rados_tool.sh: fix path
Signed-off-by: Sage Weil <sage@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 4502446 - Browse repository at this point
Copy the full SHA 4502446View commit details