ODIn/spark-instrumented-optimizer
1
0
Fork 0
Code Issues Pull requests Projects Releases Wiki Activity
spark-instrumented-optimizer/sql/core/benchmarks/IntervalBenchmark-results.txt

30 lines
3.2 KiB
Plaintext
Raw Normal View History

[SPARK-31129][SQL][TESTS] Fix IntervalBenchmark and DateTimeBenchmark ### What changes were proposed in this pull request? This PR aims to recover `IntervalBenchmark` and `DataTimeBenchmark` due to banning intervals as output. ### Why are the changes needed? This PR recovers the benchmark suite. ### Does this PR introduce any user-facing change? No. ### How was this patch tested? Manually, re-run the benchmark. Closes #27885 from yaooqinn/SPARK-31111-2. Authored-by: Kent Yao <yaooqinn@hotmail.com> Signed-off-by: Dongjoon Hyun <dongjoon@apache.org>
2020-03-12 15:59:29 -04:00
Java HotSpot(TM) 64-Bit Server VM 1.8.0_231-b11 on Mac OS X 10.15.3
Intel(R) Core(TM) i9-9980HK CPU @ 2.40GHz
[SPARK-29533][SQL][TEST] Benchmark casting strings to intervals ### What changes were proposed in this pull request? Added new benchmark `IntervalBenchmark` to measure performance of interval related functions. In the PR, I added benchmarks for casting strings to interval. In particular, interval strings with `interval` prefix and without it because there is special code for this https://github.com/apache/spark/blob/da576a737c2db01e5ba5ce19ed0e8f900cb5efaf/common/unsafe/src/main/java/org/apache/spark/unsafe/types/CalendarInterval.java#L100-L103 . And also I added benchmarks for different number of units in interval strings, for example 1 unit is `interval 10 years`, 2 units w/o interval is `10 years 5 months`, and etc. ### Why are the changes needed? - To find out current performance issues in casting to intervals - The benchmark can be used while refactoring/re-implementing `CalendarInterval.fromString()` or `CalendarInterval.fromCaseInsensitiveString()`. ### Does this PR introduce any user-facing change? No ### How was this patch tested? By running the benchmark via the command: ```shell SPARK_GENERATE_BENCHMARK_FILES=1 build/sbt "sql/test:runMain org.apache.spark.sql.execution.benchmark.IntervalBenchmark" ``` Closes #26189 from MaxGekk/interval-from-string-benchmark. Authored-by: Maxim Gekk <max.gekk@gmail.com> Signed-off-by: HyukjinKwon <gurwls223@apache.org>
2019-10-21 21:47:04 -04:00
cast strings to intervals: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative
------------------------------------------------------------------------------------------------------------------------
[SPARK-31129][SQL][TESTS] Fix IntervalBenchmark and DateTimeBenchmark ### What changes were proposed in this pull request? This PR aims to recover `IntervalBenchmark` and `DataTimeBenchmark` due to banning intervals as output. ### Why are the changes needed? This PR recovers the benchmark suite. ### Does this PR introduce any user-facing change? No. ### How was this patch tested? Manually, re-run the benchmark. Closes #27885 from yaooqinn/SPARK-31111-2. Authored-by: Kent Yao <yaooqinn@hotmail.com> Signed-off-by: Dongjoon Hyun <dongjoon@apache.org>
2020-03-12 15:59:29 -04:00
prepare string w/ interval 389 410 21 2.6 388.7 1.0X
prepare string w/o interval 340 360 18 2.9 340.5 1.1X
1 units w/ interval 378 389 16 2.6 377.8 1.0X
1 units w/o interval 346 350 5 2.9 346.2 1.1X
2 units w/ interval 444 457 11 2.3 444.2 0.9X
2 units w/o interval 455 464 12 2.2 455.1 0.9X
3 units w/ interval 942 964 20 1.1 941.5 0.4X
3 units w/o interval 927 1020 93 1.1 927.3 0.4X
4 units w/ interval 1114 1127 17 0.9 1113.9 0.3X
4 units w/o interval 1100 1105 4 0.9 1100.3 0.4X
5 units w/ interval 1180 1244 57 0.8 1180.1 0.3X
5 units w/o interval 1135 1141 6 0.9 1135.2 0.3X
6 units w/ interval 1284 1316 48 0.8 1284.0 0.3X
6 units w/o interval 1276 1357 122 0.8 1276.1 0.3X
7 units w/ interval 1609 1636 32 0.6 1609.1 0.2X
7 units w/o interval 1551 1578 36 0.6 1550.9 0.3X
8 units w/ interval 1787 1874 129 0.6 1787.1 0.2X
8 units w/o interval 1751 1767 15 0.6 1750.6 0.2X
9 units w/ interval 1960 2065 141 0.5 1959.7 0.2X
9 units w/o interval 1885 1908 39 0.5 1885.1 0.2X
10 units w/ interval 2178 2185 11 0.5 2177.9 0.2X
10 units w/o interval 2150 2255 164 0.5 2150.1 0.2X
11 units w/ interval 2457 2542 139 0.4 2456.7 0.2X
11 units w/o interval 2557 2770 188 0.4 2556.7 0.2X
[SPARK-29533][SQL][TEST] Benchmark casting strings to intervals ### What changes were proposed in this pull request? Added new benchmark `IntervalBenchmark` to measure performance of interval related functions. In the PR, I added benchmarks for casting strings to interval. In particular, interval strings with `interval` prefix and without it because there is special code for this https://github.com/apache/spark/blob/da576a737c2db01e5ba5ce19ed0e8f900cb5efaf/common/unsafe/src/main/java/org/apache/spark/unsafe/types/CalendarInterval.java#L100-L103 . And also I added benchmarks for different number of units in interval strings, for example 1 unit is `interval 10 years`, 2 units w/o interval is `10 years 5 months`, and etc. ### Why are the changes needed? - To find out current performance issues in casting to intervals - The benchmark can be used while refactoring/re-implementing `CalendarInterval.fromString()` or `CalendarInterval.fromCaseInsensitiveString()`. ### Does this PR introduce any user-facing change? No ### How was this patch tested? By running the benchmark via the command: ```shell SPARK_GENERATE_BENCHMARK_FILES=1 build/sbt "sql/test:runMain org.apache.spark.sql.execution.benchmark.IntervalBenchmark" ``` Closes #26189 from MaxGekk/interval-from-string-benchmark. Authored-by: Maxim Gekk <max.gekk@gmail.com> Signed-off-by: HyukjinKwon <gurwls223@apache.org>
2019-10-21 21:47:04 -04:00
Reference in a new issue Copy permalink