History log of /4.0.0/forestdb/ (Results 1 - 25 of 768)
Revision (<<< Hide revision tags) (Show revision tags >>>)Date Author Comments
(<<< Hide modified files)
(Show modified files >>>)
Revision tags: v1.2, v1.1, v1.0
606c32b517-Aug-2015 Chiyoung Seo <chiyoung.seo@gmail.com>

MB-16076 Determine the writer backoff time adaptively based on probability

Change-Id: I295efe59f73d25d1428198ba768d05b88c03b798

41a273e313-Aug-2015 Sundar Sridharan <sundar.sridharan@gmail.com>

MB-16060: Do not free buffer cache blocks twice

If the blocks are freed by filemgr_remove_all_buffer_blocks() then
there it is not necessary to call the same set of functions again
e

MB-16060: Do not free buffer cache blocks twice

If the blocks are freed by filemgr_remove_all_buffer_blocks() then
there it is not necessary to call the same set of functions again
even if the file was picked as victim by another thread.
This prevents assertion in _fname_try_free, blockcache.cc, line 794

Change-Id: I9016097fd400718ff01e6194af5896c98cac8573

show more ...

3155b82d13-Aug-2015 Jung-Sang Ahn <jungsang.ahn@gmail.com>

MB-16038 Use intentional sleep instead of grabbing mutex for throttling writer

- Since it is hard to control writer speed using mutex, we use sleep instead.

Change-Id: I51a6af7077fe

MB-16038 Use intentional sleep instead of grabbing mutex for throttling writer

- Since it is hard to control writer speed using mutex, we use sleep instead.

Change-Id: I51a6af7077fe56e74b5e0976993f36e25b6abd1c

show more ...

abe8dd5413-Aug-2015 Jung-Sang Ahn <jungsang.ahn@gmail.com>

MB-16038 Don't load KVS header for snapshot handle

- This routine grab file manager mutex unnecessarily.

e62631c512-Aug-2015 Chiyoung Seo <chiyoung.seo@gmail.com>

MB-16038 Don't grab the file manager lock in restoring the WAL for snapshot

Change-Id: If32891c18f0c27e192346ef00ffac5c38f6bdad2

3614941812-Aug-2015 Chiyoung Seo <chiyoung.seo@gmail.com>

MB-16038 Avoid grabbing the file manager lock upon creating KVS info instance

As creating the KVS info instance per handle is already synchronized by the KV
header lock and KV handle lis

MB-16038 Avoid grabbing the file manager lock upon creating KVS info instance

As creating the KVS info instance per handle is already synchronized by the KV
header lock and KV handle list lock, the file manager lock is not required in
creating the KVS info instance per handle.

Change-Id: I1e5b93a807262ba56e1db6c0cfde1ff691991955

show more ...

17f72b6309-Jul-2015 Chiyoung Seo <chiyoung.seo@gmail.com>

[BP] MB-16038 Reduce the filemgr lock contention in fdb_open()

This commit removes the unnecessary critical section synchronization
in fdb_open().

Change-Id: I08fd00f7c6ae0ea86e

[BP] MB-16038 Reduce the filemgr lock contention in fdb_open()

This commit removes the unnecessary critical section synchronization
in fdb_open().

Change-Id: I08fd00f7c6ae0ea86e490f38fd5502a1cf9b5308

Conflicts:
src/forestdb.cc

show more ...

5f7821ba11-Aug-2015 Chiyoung Seo <chiyoung.seo@gmail.com>

MB-16038 Support the lazy cleanup of a file's buffer cache blocks

If a given file is compacted ans no longer accessed, then its cache
blocks in the buffer cache should be cleaned up and

MB-16038 Support the lazy cleanup of a file's buffer cache blocks

If a given file is compacted ans no longer accessed, then its cache
blocks in the buffer cache should be cleaned up and moved to the free list.

As this operation can takes up to several seconds depending on the number
of cache blocks belonging to the file, it is better to support the lazy
cleanup of these cache blocks to avoid the long blocking period in the
application.

Change-Id: I3d607f17e189b63c592298c822672b9178356b0a

show more ...

52ade7a410-Aug-2015 Sundar Sridharan <sundar.sridharan@gmail.com>

MB-16018: Prevent free of zombie file still in use

Only allow free of those zombie files which are no longer
still in use.
Test case to catch this bug.

Change-Id: I71f325295

MB-16018: Prevent free of zombie file still in use

Only allow free of those zombie files which are no longer
still in use.
Test case to catch this bug.

Change-Id: I71f325295b7f092e3b576fd577ffb13633706e03

show more ...

0f2f680a07-Aug-2015 Sundar Sridharan <sundar.sridharan@gmail.com>

CBQE-3016:Windows2012 fdb_functional_test get_offset_test

Out of memory bound write can affect other platforms also

Change-Id: I39b332843d292bb21232b983469963abad939821

2f5c544307-Aug-2015 Chiyoung Seo <chiyoung@couchbase.com>

Merge "MB-15908 Support lazy deletion of old DB file" into sherlock


d6eb040e05-Aug-2015 Jung-Sang Ahn <jungsang.ahn@gmail.com>

MB-15908 Support lazy deletion of old DB file

- To avoid API blocking by high latency of file removal, we support
lazy deletion of old DB file after compaction.

- Once the ref_c

MB-15908 Support lazy deletion of old DB file

- To avoid API blocking by high latency of file removal, we support
lazy deletion of old DB file after compaction.

- Once the ref_count of an old file becomes zero, then it is registered
to the file list of background compaction daemon, and then the daemon
compactor threads periodically check and remove the pending files.

Change-Id: Ie0705a681a05df8ccd68e87ba87576cb81f92156

show more ...

8bbaa72406-Aug-2015 Chiyoung Seo <chiyoung.seo@gmail.com>

Relax error checking for e2e_concurrency_scan_test

In e2e_concurrency_scan_test, all writers threads share the same
key space which means when one thread is inserting a key, another thre

Relax error checking for e2e_concurrency_scan_test

In e2e_concurrency_scan_test, all writers threads share the same
key space which means when one thread is inserting a key, another thread
could be doing an update_index which deletes the same key. Since this
is not an error, relax set validation for this test.

Change-Id: Idcc3fc313f9e4cd129e81ce51de5352fc8ca5a99

show more ...

bda6f42624-Jul-2015 Sundar Sridharan <sundar.sridharan@gmail.com>

Spawn gdb to get backtrace of all threads on assert (Linux only)

Change-Id: I8507161d13a23d2ca08398f13cf4d586f0ad449c

e5d8350a24-Jul-2015 Jung-Sang Ahn <jungsang.ahn@gmail.com>

Avoid grabbing destroyed spin lock during shutdown on Windows

- Since spin lock in Windows is not a primitive type, crash can occur
when multiple threads are racing; the first thread des

Avoid grabbing destroyed spin lock during shutdown on Windows

- Since spin lock in Windows is not a primitive type, crash can occur
when multiple threads are racing; the first thread destroys spin lock
and then the second thread attempts to grab the spin lock.

- To avoid this, we need to use atomic CAS.

Change-Id: I0f97d7082ba73d95be4eb074af5eed423a05a3c3

show more ...

4178fbe123-Jul-2015 Sundar Sridharan <sundar.sridharan@gmail.com>

dump backtrace on assert

Change-Id: I369f10269f2bc17228f1214eb7399c4821f8acdf

adab8ed523-Jul-2015 Jung-Sang Ahn <jungsang.ahn@gmail.com>

Avoid duplicated shutdown

- When more than one thread is going to shut down ForestDB, we have
to ignore the second shutdown call if ForestDB is already shut down
by the first call.

Avoid duplicated shutdown

- When more than one thread is going to shut down ForestDB, we have
to ignore the second shutdown call if ForestDB is already shut down
by the first call.

Change-Id: I7ce5068379dfba8a39ceee49c7a25d8ff9b22d66

show more ...

6270ab5a17-Jul-2015 Sundar Sridharan <sundar.sridharan@gmail.com>

Relax error checking for robust test

In robust test all writers threads share the same key space
which means when one thread is inserting a key another thread
could be doing an updat

Relax error checking for robust test

In robust test all writers threads share the same key space
which means when one thread is inserting a key another thread
could be doing an update_index which deletes same key. Since this
is not an error, relax set validation for robust_test

Change-Id: I575856417a01b6b8550437b473be57be34a74eae

show more ...

eda2b6e517-Jul-2015 Sundar Sridharan <sundar.sridharan@gmail.com>

hang process instead of crash if env HANG_ON_ASSERTION set

Change-Id: I477bbf0169ec8b5981f2e172aa2ef2607c85c2f4

2d5b425b07-Jul-2015 Sundar Sridharan <sundar.sridharan@gmail.com>

MB-12613: NULL ptr crash fix, static analyzer warnings

Encountered a crash in fdb_close() if passed in handle was NULL.
Return error to caller if compact_move_delta fails.
So fixed i

MB-12613: NULL ptr crash fix, static analyzer warnings

Encountered a crash in fdb_close() if passed in handle was NULL.
Return error to caller if compact_move_delta fails.
So fixed it along with a ~100 static analyzer warnings.

Change-Id: Id6d1c8efd749587e504541897a39ef253d9b3e55

show more ...

0d42366402-Jul-2015 Sundar Sridharan <sundar.sridharan@gmail.com>

fix garbage value to thread_create in compactor

init num_threads else an arbitary large value of
threads can be created.

Change-Id: I75bc7648757b03ab324961f4de7125b836a8dca8

76143cfa26-Jun-2015 Chiyoung Seo <chiyoung.seo@gmail.com>

MB-15429 Avoid calling _fdb_open() when cloning the snapshot handle

Cloning the snapshot handle can be simply done using the internal states of
the source handle.

Change-Id: Ida

MB-15429 Avoid calling _fdb_open() when cloning the snapshot handle

Cloning the snapshot handle can be simply done using the internal states of
the source handle.

Change-Id: Ida0c390f7da1c7da97ad24f93cef4d56d11abff6

show more ...

ccb5315425-Jun-2015 Sundar Sridharan <sundar.sridharan@gmail.com>

MB-15383: Use hbtrie_remove if multi-kv mode for seqtrie

Using btree_remove in _fdb_wal_flush_func causes crash in
multi-kv mode since we use hbtrie for sequence numbers.
This crash

MB-15383: Use hbtrie_remove if multi-kv mode for seqtrie

Using btree_remove in _fdb_wal_flush_func causes crash in
multi-kv mode since we use hbtrie for sequence numbers.
This crash is seen in ep-engine where more than 256 kv stores
are present and a single byte can no longer fit the kv id
of the kvstore. The corruption is present nevertheless.

Change-Id: I7b16c07a2fec41b5d1498ce53ee42ba16c473827

show more ...

847006a224-Jun-2015 Sundar Sridharan <sundar.sridharan@gmail.com>

Validate cloning fdb_snapshot_open() can share i/p handle

Change-Id: I91835b16fd9bf838a6f07ff0317cf44583d443c2

9f432c3424-Jun-2015 Chiyoung Seo <chiyoung.seo@gmail.com>

Merge "MB-15429 Don't grab file manager lock when cloning from in-memory snapshot" into sherlock


12345678910>>...31