Apache
/
druid
mirror of https://github.com/apache/druid.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
4,466 Commits 113 Branches 506 Tags 732 MiB
Commit Graph

881 Commits

Author SHA1 Message Date
Fangjin Yang 6ee8029462 Merge pull request #866 from metamx/mutableBitmapBenchmark 
Add benchmarking for bitmaps
 2014-11-14 14:16:21 -07:00
xvrl a4fc64ca3f Merge pull request #856 from metamx/druid-845 
Fix query by segment
 2014-11-14 13:10:54 -08:00
Charles Allen 4b7ab23289 Remove getIntervalString from BySegmentResultValue 2014-11-14 13:03:48 -08:00
Charles Allen 648759e9f6 Add deserialization benchmark to BitmapCreationBenchmark 2014-11-13 13:43:14 -08:00
Charles Allen 483b2c7be0 Add copyright notice to BitmapCreationBenchmark 2014-11-13 12:55:02 -08:00
Charles Allen 228fb0cf40 Add benchmarking for bitmaps 
Here are the results on my laptop:

BitmapCreationBenchmark.testRandomAddition[0]: [measured 10 out of 20 rounds, threads: 1 (sequential)]
 round: 0.49 [+- 0.07], round.block: 0.00 [+- 0.00], round.gc: 0.00 [+- 0.00], GC.calls: 16, GC.time: 0.01, time.total: 9.91, time.warmup: 5.06, time.bench: 4.86
BitmapCreationBenchmark.testLinearAdditionDescending[0]: [measured 1000 out of 1010 rounds, threads: 1 (sequential)]
 round: 0.01 [+- 0.00], round.block: 0.00 [+- 0.00], round.gc: 0.00 [+- 0.00], GC.calls: 74, GC.time: 0.03, time.total: 5.82, time.warmup: 0.06, time.bench: 5.76
BitmapCreationBenchmark.testToImmutableByteArray[0]: [measured 1000 out of 1010 rounds, threads: 1 (sequential)]
 round: 0.00 [+- 0.00], round.block: 0.00 [+- 0.00], round.gc: 0.00 [+- 0.00], GC.calls: 0, GC.time: 0.00, time.total: 1.80, time.warmup: 0.02, time.bench: 1.78
BitmapCreationBenchmark.testRandomAddition[1]: [measured 10 out of 20 rounds, threads: 1 (sequential)]
 round: 0.00 [+- 0.00], round.block: 0.00 [+- 0.00], round.gc: 0.00 [+- 0.00], GC.calls: 0, GC.time: 0.00, time.total: 0.12, time.warmup: 0.08, time.bench: 0.04
BitmapCreationBenchmark.testLinearAdditionDescending[1]: [measured 1000 out of 1010 rounds, threads: 1 (sequential)]
 round: 0.00 [+- 0.00], round.block: 0.00 [+- 0.00], round.gc: 0.00 [+- 0.00], GC.calls: 10, GC.time: 0.01, time.total: 4.26, time.warmup: 0.04, time.bench: 4.22
BitmapCreationBenchmark.testToImmutableByteArray[1]: [measured 1000 out of 1010 rounds, threads: 1 (sequential)]
 round: 0.01 [+- 0.00], round.block: 0.00 [+- 0.00], round.gc: 0.00 [+- 0.00], GC.calls: 27, GC.time: 0.01, time.total: 5.11, time.warmup: 0.05, time.bench: 5.06
BitmapCreationBenchmark.testLinearAddition[0]: [measured 1000 out of 1010 rounds, threads: 1 (sequential)]
 round: 0.00 [+- 0.00], round.block: 0.00 [+- 0.00], round.gc: 0.00 [+- 0.00], GC.calls: 0, GC.time: 0.00, time.total: 3.48, time.warmup: 0.04, time.bench: 3.45
BitmapCreationBenchmark.testLinearAddition[1]: [measured 1000 out of 1010 rounds, threads: 1 (sequential)]
 round: 0.00 [+- 0.00], round.block: 0.00 [+- 0.00], round.gc: 0.00 [+- 0.00], GC.calls: 9, GC.time: 0.00, time.total: 2.95, time.warmup: 0.03, time.bench: 2.92
2014-11-13 12:47:23,995 INFO [main] io.druid.segment.data.BitmapCreationBenchmark - Entry [0] is io.druid.segment.data.ConciseBitmapSerdeFactory
2014-11-13 12:47:23,995 INFO [main] io.druid.segment.data.BitmapCreationBenchmark - Entry [1] is io.druid.segment.data.RoaringBitmapSerdeFactory
 2014-11-13 12:48:04 -08:00
Fangjin Yang 4a3c0fc5c4 Merge pull request #848 from metamx/druid-0.7.x-fastTopN-rebase 
TopN performance improvements
 2014-11-13 11:56:20 -07:00
Charles Allen 34c3464bc9 Added more explanatory comments in PooledTopNAlgorithm 2014-11-13 10:47:56 -08:00
Charles Allen 9a9238a801 Merge remote-tracking branch 'origin/master' into druid-845 2014-11-13 10:04:56 -08:00
Xavier Léauté 19a37f773f test for groupBy order 2014-11-12 22:48:16 -08:00
Charles Allen 31fed7d329 Fix query by segment 
* Changed topN queries to use joda Interval instead of string values
* topN by segment now implements BySegmentResultValue<Result<TopNResultValue>> instead of BySegmentResultValue<TopNResultValue>
* Added a unit test which failed uner the prior implementation.
 2014-11-12 21:20:59 -08:00
Xavier Léauté 4ac1aaf90e Merge remote-tracking branch 'origin/master' into druid-0.7.x 
Conflicts:
	processing/src/main/java/io/druid/segment/QueryableIndexStorageAdapter.java
 2014-11-12 14:08:51 -08:00
Fangjin Yang 4b4f1c7d38 Merge pull request #846 from vikramakrishnan/cacheKeyFix 
Include origin when creating the cacheKey for period Grans
 2014-11-12 11:15:21 -07:00
Fangjin Yang 7ef19009db Merge pull request #834 from metamx/optimize-timestampchecking 
skip timestamp checking if not required, remove duplicate code
 2014-11-12 09:45:34 -07:00
Vikram Ramakrishnan 8151d14786 Include origin when creating the cacheKey for period Grans 2014-11-12 21:36:46 +05:30
Charles Allen 581e6830d5 Merge pull request #840 from metamx/powers-of-2-buffers 
make buffer size a power of 2 and optimize buffer lookup
 2014-11-11 19:54:00 -08:00
Xavier Léauté 60e98c35d7 workaround for annotations requiring class literals 2014-11-11 18:48:49 -08:00
Xavier Léauté b580269f6d Distinguish between default and legacy bitmaps 2014-11-11 18:35:45 -08:00
fjy bc5c56e441 fix default impl 2014-11-11 18:00:46 -08:00
fjy 63ca2375a3 remove dead code and cleanup some defaults 2014-11-11 17:57:24 -08:00
fjy 5629307548 address a few more comments on roaring 2014-11-11 17:50:03 -08:00
Charles Allen a89b539b4f Merge pull request #823 from metamx/roaring 
Configurable bitmap indexes: roaring and concise
 2014-11-11 17:26:38 -08:00
Xavier Léauté 007e57f876 make buffer size a power of 2 and optimize 2014-11-11 16:24:37 -08:00
fjy 1cc162727b address code review 2014-11-11 14:05:37 -08:00
Xavier Léauté 3f5449d40a loop unrolling provides no benefit for timeseries 2014-11-11 10:58:37 -08:00
Xavier Léauté e817db8b6c unroll timeseries aggregations + naming 2014-11-11 10:09:37 -08:00
fjy e6b7b03b5b fix conversion 2014-11-10 17:13:28 -08:00
fjy eb457c280e revert change 2014-11-10 17:00:53 -08:00
fjy 336c73bdc2 cleanup dead code 2014-11-10 16:53:13 -08:00
fjy df886fac1b fix 2014-11-10 16:49:27 -08:00
fjy d68bc3bdea cleanup unused imports 2014-11-10 16:15:28 -08:00
Charles Allen 92e71be864 Change TopNQueryRunnerBenchmark to use a ByteBuffer as per OffheapBufferPool 2014-11-10 15:40:54 -08:00
Charles Allen a093f3728a Reformat on TopNNumericResultBuilder 2014-11-10 15:26:09 -08:00
Charles Allen 2b0f4534bf Modify formatting in TopNQueryRunnerBenchmark 2014-11-10 15:17:26 -08:00
Charles Allen fc78f215c4 Aggressive dimValue unrolling in PooledTopNAlgorithm 2014-11-10 15:14:45 -08:00
fjy 6188315293 Merge branch 'master' into druid-0.7.x 
Conflicts:
	processing/src/test/java/io/druid/query/search/SearchQueryRunnerTest.java
 2014-11-10 14:52:10 -08:00
Xavier Léauté 49e878cf1a unroll multi-value dimensions 2014-11-10 14:21:56 -08:00
fjy df9be030db remove more legacy code 2014-11-10 14:09:00 -08:00
Charles Allen dbb6401fbe Aggressive unrolling in PooledTopNAlgorithm 2014-11-10 14:04:37 -08:00
fjy 72c355e8ae remove crazy handler code 2014-11-10 13:58:23 -08:00
fjy fc34858e95 fix things for real-time ingestion 2014-11-10 13:48:21 -08:00
fjy c5cc826998 make things actually work with roaring 2014-11-10 13:42:26 -08:00
fjy 358b2add17 make things actually work with roaring 2014-11-10 13:42:06 -08:00
Charles Allen 9ac8589143 Merge remote-tracking branch 'origin/druid-0.7.x-fastTopN-rebase' into druid-0.7.x-fastTopN-rebase 2014-11-10 12:55:08 -08:00
Xavier Léauté 70468400bf stupid mistake 2014-11-10 12:54:48 -08:00
Charles Allen bfc9d9f283 Merge remote-tracking branch 'origin/druid-0.7.x-fastTopN-rebase' into druid-0.7.x-fastTopN-rebase 2014-11-10 12:52:36 -08:00
Xavier Léauté 17d32a2561 try to benefit from out of order execution 2014-11-10 12:50:10 -08:00
Charles Allen 5aad149b24 Make some variables in PooledTopNAlgorithm final 2014-11-10 12:19:04 -08:00
nishantmonu51 0ca60e0334 skip timestamp checking, remove duplicate code 
1) No need compare all timestamps when all the values are within range
2) remove redundant code.
 2014-11-10 22:36:07 +05:30
fjy 3c21f62afd a whole bunch of fixes and some ugly conversion code 2014-11-07 16:03:22 -08:00