Commit Graph

173 Commits

Author SHA1 Message Date
Gian Merlino c622a25236 BenchmarkDataGenerator: Don't generate timestamps at the end instant of the interval. (#3242)
Because timestamps at the end instant are not actually part of the interval. This
affected benchmark numbers, since it meant some data points would not be queried
(the interval for the query was based on getDataInterval) and also the
TimestampCheckingOffsets could not use the allWithinThreshold optimization.
2016-07-14 10:20:10 +05:30
Gian Merlino ea03906fcf Configurable compressRunOnSerialization for Roaring bitmaps. (#3228)
Defaults to true, which is a change in behavior (this used to be false and unconfigurable).
2016-07-08 10:24:19 +05:30
Hyukjin Kwon 45f553fc28 Replace the deprecated usage of NoneShardSpec (#3166) 2016-06-25 10:27:25 -07:00
Gian Merlino 4cc39b2ee7 Alternative groupBy strategy. (#2998)
This patch introduces a GroupByStrategy concept and two strategies: "v1"
is the current groupBy strategy and "v2" is a new one. It also introduces
a merge buffers concept in DruidProcessingModule, to try to better
manage memory used for merging.

Both of these are described in more detail in #2987.

There are two goals of this patch:

1. Make it possible for historical/realtime nodes to return larger groupBy
   result sets, faster, with better memory management.
2. Make it possible for brokers to merge streams when there are no order-by
   columns, avoiding materialization.

This patch does not do anything to help with memory management on the broker
when there are order-by columns or when there are nested queries. That could
potentially be done in a future patch.
2016-06-24 18:06:09 -07:00
Jonathan Wei 24860a1391 Two-stage filtering (#3018)
* Two-stage filtering

* PR comment
2016-06-22 16:08:21 -07:00
Jonathan Wei b72c54c4f8 Add benchmark data generator, basic ingestion/persist/merge/query benchmarks (#2875) 2016-05-25 16:39:37 -07:00
Charles Allen 15ccf451f9 Move QueryGranularity static fields to QueryGranularities (#2980)
* Move QueryGranularity static fields to QueryGranularityUtil
* Fixes #2979

* Add test showing #2979

* change name to QueryGranularities
2016-05-17 16:23:48 -07:00
Xavier Léauté e79284da59 new interval based cost function (#2972)
* new interval based cost function

Addresses issues with balancing of segments in the existing cost function
- `gapPenalty` led to clusters of segments ~30 days apart
- `recencyPenalty` caused imbalance among recent segments
- size-based cost could be skewed by compression

New cost function is purely based on segment intervals:
- assumes each time-slice of a partition is a constant cost
- cost is additive, i.e. cost(A, B union C) = cost(A, B) + cost(A, C)
- cost decays exponentially based on distance between time-slices

* comments and formatting

* add more comments to explain the calculation
2016-05-17 09:56:00 -07:00
John Wang 5658bd99eb added contextual time parse (#2867) 2016-04-25 13:35:10 -07:00
Gian Merlino 7c0b1dde3a DimensionPredicateFilter: Skip unnecessary dictionary lookup. (#2850) 2016-04-18 12:38:25 -07:00
jon-wei 0e481d6f93 Allow filters to use extraction functions 2016-04-05 13:24:56 -07:00
Gian Merlino 2970b49adc BoundFilter optimizations, and related interface changes.
BoundFilter:

- For lexicographic bounds, use bitmapIndex.getIndex to find the start and end points,
  then union all bitmaps between those points.
- For alphanumeric bounds, iterate through dimValues, and union all bitmaps for values
  matching the predicate.
- Change behavior for nulls: it used to be that the BoundFilter would never match nulls,
  now it matches nulls if "" is allowed by the lower limit and not excluded by the
  upper limit.

Interface changes:

- BitmapIndex: add `int getIndex(value)` to make it possible to get the index for a
  value without retrieving the bitmap.
- BitmapIndex: remove `ImmutableBitmap getBitmap(value)`, change callers to `getBitmap(getIndex(value))`.
- BitmapIndexSelector: allow retrieving the underlying BitmapIndex through getBitmapIndex.
- Clarified contract of indexOf in Indexed, GenericIndexed.

Also added tests for SelectorFilter, NotFilter, and BoundFilter.
2016-03-25 14:11:48 -07:00
Gian Merlino 1869c350d8 Move FlattenJSONBenchmarkUtilTest into the correct location. 2016-03-24 15:47:54 -07:00
Himanshu Gupta 02dfd5cd80 update IncrementalIndex to support unsorted facts map that can be used in groupBy merging to improve performance 2016-03-10 16:11:48 -06:00
jon-wei c17ce02467 Allow IncrementalIndex to store Long/Float dimensions 2016-02-24 13:51:57 -08:00
jon-wei c53bf85d83 Add docs and benchmark for JSON flattening parser 2015-12-09 16:13:30 -08:00
Himanshu Gupta 62ba9ade37 unifying license header in all java files 2015-12-05 22:16:23 -06:00
Xavier Léauté fa6142e217 cleanup and remove unused imports 2015-11-11 12:25:21 -08:00
Charles Allen 7fe8562980 Remove locks from StupidPool 2015-08-05 19:24:56 -07:00
nishant efb6e0649e simplify merging of results on broker.
add benchmark

formatting and review comments

organize imports
2015-07-27 11:46:11 -07:00
Charles Allen b72a70522b Add basic ConciseComplementBenchmark for testing concise complements 2015-06-19 16:47:41 -07:00
nishant 37873eb4f0 more benchmarks + filter
fix test

Modify test to access random filtered rows

formatting

fix test

remove main method

Add newline

Add newline
2015-06-04 22:12:29 +05:30
nishant 81415282aa Enabling compression for multiValued dimension
Add test and refactoring

Add benchmark tests
2015-05-27 00:09:14 +05:30