ODIn/spark-instrumented-optimizer
1
0
Fork 0
Code Issues Pull requests Projects Releases Wiki Activity
spark-instrumented-optimizer/sql/core/benchmarks/IntervalBenchmark-jdk11-results.txt

41 lines
4.3 KiB
Plaintext
Raw Normal View History

[SPARK-32071][SQL][TESTS] Add `make_interval` benchmark ### What changes were proposed in this pull request? Add benchmarks for interval constructor `make_interval` and measure perf of 4 cases: 1. Constant (year, month) 2. Constant (week, day) 3. Constant (hour, minute, second, second fraction) 4. All fields are NOT constant. The benchmark results are generated in the environment: | Item | Description | | ---- | ----| | Region | us-west-2 (Oregon) | | Instance | r3.xlarge | | AMI | ubuntu/images/hvm-ssd/ubuntu-bionic-18.04-amd64-server-20190722.1 (ami-06f2f779464715dc5) | | Java | OpenJDK 64-Bit Server VM 1.8.0_252 and OpenJDK 64-Bit Server VM 11.0.7+10 | ### Why are the changes needed? To have a base line for future perf improvements of `make_interval`, and to prevent perf regressions in the future. ### Does this PR introduce _any_ user-facing change? No ### How was this patch tested? By running `IntervalBenchmark` via: ``` $ SPARK_GENERATE_BENCHMARK_FILES=1 build/sbt "sql/test:runMain org.apache.spark.sql.execution.benchmark.IntervalBenchmark" ``` Closes #28905 from MaxGekk/benchmark-make_interval. Authored-by: Max Gekk <max.gekk@gmail.com> Signed-off-by: Dongjoon Hyun <dongjoon@apache.org>
2020-06-27 20:54:06 -04:00
OpenJDK 64-Bit Server VM 11.0.7+10-post-Ubuntu-2ubuntu218.04 on Linux 4.15.0-1063-aws
Intel(R) Xeon(R) CPU E5-2670 v2 @ 2.50GHz
[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-32071][SQL][TESTS] Add `make_interval` benchmark ### What changes were proposed in this pull request? Add benchmarks for interval constructor `make_interval` and measure perf of 4 cases: 1. Constant (year, month) 2. Constant (week, day) 3. Constant (hour, minute, second, second fraction) 4. All fields are NOT constant. The benchmark results are generated in the environment: | Item | Description | | ---- | ----| | Region | us-west-2 (Oregon) | | Instance | r3.xlarge | | AMI | ubuntu/images/hvm-ssd/ubuntu-bionic-18.04-amd64-server-20190722.1 (ami-06f2f779464715dc5) | | Java | OpenJDK 64-Bit Server VM 1.8.0_252 and OpenJDK 64-Bit Server VM 11.0.7+10 | ### Why are the changes needed? To have a base line for future perf improvements of `make_interval`, and to prevent perf regressions in the future. ### Does this PR introduce _any_ user-facing change? No ### How was this patch tested? By running `IntervalBenchmark` via: ``` $ SPARK_GENERATE_BENCHMARK_FILES=1 build/sbt "sql/test:runMain org.apache.spark.sql.execution.benchmark.IntervalBenchmark" ``` Closes #28905 from MaxGekk/benchmark-make_interval. Authored-by: Max Gekk <max.gekk@gmail.com> Signed-off-by: Dongjoon Hyun <dongjoon@apache.org>
2020-06-27 20:54:06 -04:00
prepare string w/ interval 708 829 110 1.4 708.0 1.0X
prepare string w/o interval 660 672 14 1.5 660.3 1.1X
1 units w/ interval 514 543 33 1.9 514.2 1.4X
1 units w/o interval 476 492 20 2.1 475.9 1.5X
2 units w/ interval 751 767 14 1.3 751.0 0.9X
2 units w/o interval 709 716 11 1.4 709.0 1.0X
3 units w/ interval 1541 1551 15 0.6 1540.9 0.5X
3 units w/o interval 1531 1532 1 0.7 1531.5 0.5X
4 units w/ interval 1764 1768 5 0.6 1763.5 0.4X
4 units w/o interval 1737 1745 8 0.6 1736.6 0.4X
5 units w/ interval 1920 1930 10 0.5 1919.7 0.4X
5 units w/o interval 1928 1936 11 0.5 1927.9 0.4X
6 units w/ interval 2124 2127 4 0.5 2124.2 0.3X
6 units w/o interval 2124 2125 1 0.5 2123.7 0.3X
7 units w/ interval 2525 2541 15 0.4 2525.5 0.3X
7 units w/o interval 2512 2518 11 0.4 2511.5 0.3X
8 units w/ interval 2578 2597 19 0.4 2578.1 0.3X
8 units w/o interval 2558 2562 6 0.4 2558.1 0.3X
9 units w/ interval 2742 2750 9 0.4 2741.8 0.3X
9 units w/o interval 2752 2762 11 0.4 2751.8 0.3X
10 units w/ interval 3112 3123 10 0.3 3111.9 0.2X
10 units w/o interval 3116 3130 14 0.3 3115.7 0.2X
11 units w/ interval 3255 3273 20 0.3 3255.3 0.2X
11 units w/o interval 3294 3305 14 0.3 3293.6 0.2X
OpenJDK 64-Bit Server VM 11.0.7+10-post-Ubuntu-2ubuntu218.04 on Linux 4.15.0-1063-aws
Intel(R) Xeon(R) CPU E5-2670 v2 @ 2.50GHz
make_interval(): Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative
--------------------------------------------------------------------------------------------------------------------------
prepare make_interval() 3395 3410 16 0.3 3395.0 1.0X
make_interval(0, 1, 2, 3, 4, 5, 50.123456) 94 102 9 10.7 93.8 36.2X
make_interval(*, *, 2, 3, 4, 5, 50.123456) 136 139 4 7.3 136.5 24.9X
make_interval(0, 1, *, *, 4, 5, 50.123456) 115 119 4 8.7 114.8 29.6X
make_interval(0, 1, 2, 3, *, *, *) 3359 3382 37 0.3 3358.7 1.0X
make_interval(*, *, *, *, *, *, *) 3382 3388 9 0.3 3382.3 1.0X
[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