richardstartin opened a new pull request #7582: URL: https://github.com/apache/pinot/pull/7582
## Description This saves uses the default settings in the RoaringBitmap library to produce smaller file sizes. before: ``` Benchmark (_assignment) (_cardinality) (_numDocs) Mode Cnt Score Error Units BenchmarkOffheapBitmapInvertedIndexCreator.seal ROUND_ROBIN 10 1000000 ss 5 0.015 ± 0.004 s/op BenchmarkOffheapBitmapInvertedIndexCreator.seal:b ROUND_ROBIN 10 1000000 ss 5 6320620.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:kb ROUND_ROBIN 10 1000000 ss 5 6170.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:mb ROUND_ROBIN 10 1000000 ss 5 5.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal ROUND_ROBIN 10 10000000 ss 5 0.148 ± 0.018 s/op BenchmarkOffheapBitmapInvertedIndexCreator.seal:b ROUND_ROBIN 10 10000000 ss 5 62706300.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:kb ROUND_ROBIN 10 10000000 ss 5 61235.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:mb ROUND_ROBIN 10 10000000 ss 5 55.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal ROUND_ROBIN 10 100000000 ss 5 1.562 ± 0.030 s/op BenchmarkOffheapBitmapInvertedIndexCreator.seal:b ROUND_ROBIN 10 100000000 ss 5 625660620.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:kb ROUND_ROBIN 10 100000000 ss 5 610995.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:mb ROUND_ROBIN 10 100000000 ss 5 595.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal ROUND_ROBIN 1000 1000000 ss 5 0.020 ± 0.008 s/op BenchmarkOffheapBitmapInvertedIndexCreator.seal:b ROUND_ROBIN 1000 1000000 ss 5 10700020.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:kb ROUND_ROBIN 1000 1000000 ss 5 10445.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:mb ROUND_ROBIN 1000 1000000 ss 5 10.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal ROUND_ROBIN 1000 10000000 ss 5 0.147 ± 0.010 s/op BenchmarkOffheapBitmapInvertedIndexCreator.seal:b ROUND_ROBIN 1000 10000000 ss 5 106180020.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:kb ROUND_ROBIN 1000 10000000 ss 5 103690.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:mb ROUND_ROBIN 1000 10000000 ss 5 100.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal ROUND_ROBIN 1000 100000000 ss 5 1.708 ± 0.074 s/op BenchmarkOffheapBitmapInvertedIndexCreator.seal:b ROUND_ROBIN 1000 100000000 ss 5 1061100020.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:kb ROUND_ROBIN 1000 100000000 ss 5 1036230.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:mb ROUND_ROBIN 1000 100000000 ss 5 1010.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal ROUND_ROBIN 10000 1000000 ss 5 0.030 ± 0.032 s/op BenchmarkOffheapBitmapInvertedIndexCreator.seal:b ROUND_ROBIN 10000 1000000 ss 5 17000020.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:kb ROUND_ROBIN 10000 1000000 ss 5 16600.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:mb ROUND_ROBIN 10000 1000000 ss 5 15.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal ROUND_ROBIN 10000 10000000 ss 5 0.210 ± 0.025 s/op BenchmarkOffheapBitmapInvertedIndexCreator.seal:b ROUND_ROBIN 10000 10000000 ss 5 161800020.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:kb ROUND_ROBIN 10000 10000000 ss 5 158005.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:mb ROUND_ROBIN 10000 10000000 ss 5 150.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal ROUND_ROBIN 10000 100000000 ss 5 2.226 ± 0.327 s/op BenchmarkOffheapBitmapInvertedIndexCreator.seal:b ROUND_ROBIN 10000 100000000 ss 5 1611000020.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:kb ROUND_ROBIN 10000 100000000 ss 5 1573240.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:mb ROUND_ROBIN 10000 100000000 ss 5 1535.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal SORTED_UNIFORM 10 1000000 ss 5 0.019 ± 0.012 s/op BenchmarkOffheapBitmapInvertedIndexCreator.seal:b SORTED_UNIFORM 10 1000000 ss 5 1018580.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:kb SORTED_UNIFORM 10 1000000 ss 5 990.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:mb SORTED_UNIFORM 10 1000000 ss 5 ≈ 0 # BenchmarkOffheapBitmapInvertedIndexCreator.seal SORTED_UNIFORM 10 10000000 ss 5 0.123 ± 0.023 s/op BenchmarkOffheapBitmapInvertedIndexCreator.seal:b SORTED_UNIFORM 10 10000000 ss 5 6624700.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:kb SORTED_UNIFORM 10 10000000 ss 5 6465.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:mb SORTED_UNIFORM 10 10000000 ss 5 5.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal SORTED_UNIFORM 10 100000000 ss 5 1.299 ± 0.148 s/op BenchmarkOffheapBitmapInvertedIndexCreator.seal:b SORTED_UNIFORM 10 100000000 ss 5 62934340.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:kb SORTED_UNIFORM 10 100000000 ss 5 61455.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:mb SORTED_UNIFORM 10 100000000 ss 5 60.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal SORTED_UNIFORM 1000 1000000 ss 5 0.018 ± 0.009 s/op BenchmarkOffheapBitmapInvertedIndexCreator.seal:b SORTED_UNIFORM 1000 1000000 ss 5 10100620.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:kb SORTED_UNIFORM 1000 1000000 ss 5 9860.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:mb SORTED_UNIFORM 1000 1000000 ss 5 5.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal SORTED_UNIFORM 1000 10000000 ss 5 0.137 ± 0.020 s/op BenchmarkOffheapBitmapInvertedIndexCreator.seal:b SORTED_UNIFORM 1000 10000000 ss 5 44750580.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:kb SORTED_UNIFORM 1000 10000000 ss 5 43700.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:mb SORTED_UNIFORM 1000 10000000 ss 5 40.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal SORTED_UNIFORM 1000 100000000 ss 5 1.321 ± 0.023 s/op BenchmarkOffheapBitmapInvertedIndexCreator.seal:b SORTED_UNIFORM 1000 100000000 ss 5 101056060.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:kb SORTED_UNIFORM 1000 100000000 ss 5 98685.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:mb SORTED_UNIFORM 1000 100000000 ss 5 95.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal SORTED_UNIFORM 10000 1000000 ss 5 0.023 ± 0.014 s/op BenchmarkOffheapBitmapInvertedIndexCreator.seal:b SORTED_UNIFORM 10000 1000000 ss 5 11000620.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:kb SORTED_UNIFORM 10000 1000000 ss 5 10740.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:mb SORTED_UNIFORM 10000 1000000 ss 5 10.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal SORTED_UNIFORM 10000 10000000 ss 5 0.147 ± 0.017 s/op BenchmarkOffheapBitmapInvertedIndexCreator.seal:b SORTED_UNIFORM 10000 10000000 ss 5 101006060.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:kb SORTED_UNIFORM 10000 10000000 ss 5 98635.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:mb SORTED_UNIFORM 10000 10000000 ss 5 95.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal SORTED_UNIFORM 10000 100000000 ss 5 1.438 ± 0.020 s/op BenchmarkOffheapBitmapInvertedIndexCreator.seal:b SORTED_UNIFORM 10000 100000000 ss 5 447554380.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:kb SORTED_UNIFORM 10000 100000000 ss 5 437060.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:mb SORTED_UNIFORM 10000 100000000 ss 5 425.000 # ``` after: ``` Benchmark (_assignment) (_cardinality) (_numDocs) Mode Cnt Score Error Units BenchmarkOffheapBitmapInvertedIndexCreator.seal ROUND_ROBIN 10 1000000 ss 5 0.015 ± 0.003 s/op BenchmarkOffheapBitmapInvertedIndexCreator.seal:b ROUND_ROBIN 10 1000000 ss 5 6320620.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:kb ROUND_ROBIN 10 1000000 ss 5 6170.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:mb ROUND_ROBIN 10 1000000 ss 5 5.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal ROUND_ROBIN 10 10000000 ss 5 0.150 ± 0.024 s/op BenchmarkOffheapBitmapInvertedIndexCreator.seal:b ROUND_ROBIN 10 10000000 ss 5 62706300.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:kb ROUND_ROBIN 10 10000000 ss 5 61235.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:mb ROUND_ROBIN 10 10000000 ss 5 55.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal ROUND_ROBIN 10 100000000 ss 5 1.535 ± 0.061 s/op BenchmarkOffheapBitmapInvertedIndexCreator.seal:b ROUND_ROBIN 10 100000000 ss 5 625660620.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:kb ROUND_ROBIN 10 100000000 ss 5 610995.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:mb ROUND_ROBIN 10 100000000 ss 5 595.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal ROUND_ROBIN 1000 1000000 ss 5 0.020 ± 0.011 s/op BenchmarkOffheapBitmapInvertedIndexCreator.seal:b ROUND_ROBIN 1000 1000000 ss 5 10700020.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:kb ROUND_ROBIN 1000 1000000 ss 5 10445.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:mb ROUND_ROBIN 1000 1000000 ss 5 10.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal ROUND_ROBIN 1000 10000000 ss 5 0.199 ± 0.097 s/op BenchmarkOffheapBitmapInvertedIndexCreator.seal:b ROUND_ROBIN 1000 10000000 ss 5 106180020.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:kb ROUND_ROBIN 1000 10000000 ss 5 103690.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:mb ROUND_ROBIN 1000 10000000 ss 5 100.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal ROUND_ROBIN 1000 100000000 ss 5 1.960 ± 0.292 s/op BenchmarkOffheapBitmapInvertedIndexCreator.seal:b ROUND_ROBIN 1000 100000000 ss 5 1061100020.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:kb ROUND_ROBIN 1000 100000000 ss 5 1036230.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:mb ROUND_ROBIN 1000 100000000 ss 5 1010.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal ROUND_ROBIN 10000 1000000 ss 5 0.029 ± 0.008 s/op BenchmarkOffheapBitmapInvertedIndexCreator.seal:b ROUND_ROBIN 10000 1000000 ss 5 17000020.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:kb ROUND_ROBIN 10000 1000000 ss 5 16600.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:mb ROUND_ROBIN 10000 1000000 ss 5 15.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal ROUND_ROBIN 10000 10000000 ss 5 0.249 ± 0.042 s/op BenchmarkOffheapBitmapInvertedIndexCreator.seal:b ROUND_ROBIN 10000 10000000 ss 5 161800020.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:kb ROUND_ROBIN 10000 10000000 ss 5 158005.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:mb ROUND_ROBIN 10000 10000000 ss 5 150.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal ROUND_ROBIN 10000 100000000 ss 5 2.294 ± 0.094 s/op BenchmarkOffheapBitmapInvertedIndexCreator.seal:b ROUND_ROBIN 10000 100000000 ss 5 1611000020.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:kb ROUND_ROBIN 10000 100000000 ss 5 1573240.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:mb ROUND_ROBIN 10000 100000000 ss 5 1535.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal SORTED_UNIFORM 10 1000000 ss 5 0.013 ± 0.003 s/op BenchmarkOffheapBitmapInvertedIndexCreator.seal:b SORTED_UNIFORM 10 1000000 ss 5 1720.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:kb SORTED_UNIFORM 10 1000000 ss 5 ≈ 0 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:mb SORTED_UNIFORM 10 1000000 ss 5 ≈ 0 # BenchmarkOffheapBitmapInvertedIndexCreator.seal SORTED_UNIFORM 10 10000000 ss 5 0.121 ± 0.041 s/op BenchmarkOffheapBitmapInvertedIndexCreator.seal:b SORTED_UNIFORM 10 10000000 ss 5 11870.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:kb SORTED_UNIFORM 10 10000000 ss 5 10.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:mb SORTED_UNIFORM 10 10000000 ss 5 ≈ 0 # BenchmarkOffheapBitmapInvertedIndexCreator.seal SORTED_UNIFORM 10 100000000 ss 5 1.320 ± 0.055 s/op BenchmarkOffheapBitmapInvertedIndexCreator.seal:b SORTED_UNIFORM 10 100000000 ss 5 108870.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:kb SORTED_UNIFORM 10 100000000 ss 5 105.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:mb SORTED_UNIFORM 10 100000000 ss 5 ≈ 0 # BenchmarkOffheapBitmapInvertedIndexCreator.seal SORTED_UNIFORM 1000 1000000 ss 5 0.019 ± 0.014 s/op BenchmarkOffheapBitmapInvertedIndexCreator.seal:b SORTED_UNIFORM 1000 1000000 ss 5 95770.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:kb SORTED_UNIFORM 1000 1000000 ss 5 90.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:mb SORTED_UNIFORM 1000 1000000 ss 5 ≈ 0 # BenchmarkOffheapBitmapInvertedIndexCreator.seal SORTED_UNIFORM 1000 10000000 ss 5 0.140 ± 0.026 s/op BenchmarkOffheapBitmapInvertedIndexCreator.seal:b SORTED_UNIFORM 1000 10000000 ss 5 102620.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:kb SORTED_UNIFORM 1000 10000000 ss 5 100.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:mb SORTED_UNIFORM 1000 10000000 ss 5 ≈ 0 # BenchmarkOffheapBitmapInvertedIndexCreator.seal SORTED_UNIFORM 1000 100000000 ss 5 1.428 ± 0.222 s/op BenchmarkOffheapBitmapInvertedIndexCreator.seal:b SORTED_UNIFORM 1000 100000000 ss 5 171270.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:kb SORTED_UNIFORM 1000 100000000 ss 5 165.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:mb SORTED_UNIFORM 1000 100000000 ss 5 ≈ 0 # BenchmarkOffheapBitmapInvertedIndexCreator.seal SORTED_UNIFORM 10000 1000000 ss 5 0.017 ± 0.003 s/op BenchmarkOffheapBitmapInvertedIndexCreator.seal:b SORTED_UNIFORM 10000 1000000 ss 5 950770.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:kb SORTED_UNIFORM 10000 1000000 ss 5 925.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:mb SORTED_UNIFORM 10000 1000000 ss 5 ≈ 0 # BenchmarkOffheapBitmapInvertedIndexCreator.seal SORTED_UNIFORM 10000 10000000 ss 5 0.145 ± 0.023 s/op BenchmarkOffheapBitmapInvertedIndexCreator.seal:b SORTED_UNIFORM 10000 10000000 ss 5 957570.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:kb SORTED_UNIFORM 10000 10000000 ss 5 935.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:mb SORTED_UNIFORM 10000 10000000 ss 5 ≈ 0 # BenchmarkOffheapBitmapInvertedIndexCreator.seal SORTED_UNIFORM 10000 100000000 ss 5 1.432 ± 0.066 s/op BenchmarkOffheapBitmapInvertedIndexCreator.seal:b SORTED_UNIFORM 10000 100000000 ss 5 1026170.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:kb SORTED_UNIFORM 10000 100000000 ss 5 1000.000 # BenchmarkOffheapBitmapInvertedIndexCreator.seal:mb SORTED_UNIFORM 10000 100000000 ss 5 ≈ 0 # ``` Pinot wouldn't create an inverted index on a sorted column, but doesn't track correlations between columns, and RLE is effective when a column is partially sorted, so in general, this will lead to much smaller inverted index files. ## Upgrade Notes Does this PR prevent a zero down-time upgrade? (Assume upgrade order: Controller, Broker, Server, Minion) * [ ] Yes (Please label as **<code>backward-incompat</code>**, and complete the section below on Release Notes) Does this PR fix a zero-downtime upgrade introduced earlier? * [ ] Yes (Please label this as **<code>backward-incompat</code>**, and complete the section below on Release Notes) Does this PR otherwise need attention when creating release notes? Things to consider: - New configuration options - Deprecation of configurations - Signature changes to public methods/interfaces - New plugins added or old plugins removed * [ ] Yes (Please label this PR as **<code>release-notes</code>** and complete the section on Release Notes) ## Release Notes <!-- If you have tagged this as either backward-incompat or release-notes, you MUST add text here that you would like to see appear in release notes of the next release. --> <!-- If you have a series of commits adding or enabling a feature, then add this section only in final commit that marks the feature completed. Refer to earlier release notes to see examples of text. --> ## Documentation <!-- If you have introduced a new feature or configuration, please add it to the documentation as well. See https://docs.pinot.apache.org/developers/developers-and-contributors/update-document --> -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
