spark-instrumented-optimizer/sql/hive/benchmarks/ObjectHashAggregateExecBenchmark-results.txt
Maxim Gekk a6a663c437 [SPARK-29141][SQL][TEST] Use SqlBasedBenchmark in SQL benchmarks
### What changes were proposed in this pull request?

Refactored SQL-related benchmark and made them depend on `SqlBasedBenchmark`. In particular, creation of Spark session are moved into `override def getSparkSession: SparkSession`.

### Why are the changes needed?

This should simplify maintenance of SQL-based benchmarks by reducing the number of dependencies. In the future, it should be easier to refactor & extend all SQL benchmarks by changing only one trait. Finally, all SQL-based benchmarks will look uniformly.

### Does this PR introduce any user-facing change?
No

### How was this patch tested?

By running the modified benchmarks.

Closes #25828 from MaxGekk/sql-benchmarks-refactoring.

Lead-authored-by: Maxim Gekk <max.gekk@gmail.com>
Co-authored-by: Dongjoon Hyun <dongjoon@apache.org>
Signed-off-by: Dongjoon Hyun <dhyun@apple.com>
2019-09-18 17:52:23 -07:00

46 lines
3.5 KiB
Plaintext

================================================================================================
Hive UDAF vs Spark AF
================================================================================================
OpenJDK 64-Bit Server VM 1.8.0_222-b10 on Linux 3.10.0-862.3.2.el7.x86_64
Intel(R) Xeon(R) CPU E5-2670 v2 @ 2.50GHz
hive udaf vs spark af: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative
------------------------------------------------------------------------------------------------------------------------
hive udaf w/o group by 6741 6759 22 0.0 102864.5 1.0X
spark af w/o group by 56 66 9 1.2 851.6 120.8X
hive udaf w/ group by 4610 4642 25 0.0 70350.3 1.5X
spark af w/ group by w/o fallback 60 67 8 1.1 916.7 112.2X
spark af w/ group by w/ fallback 135 144 9 0.5 2065.6 49.8X
================================================================================================
ObjectHashAggregateExec vs SortAggregateExec - typed_count
================================================================================================
OpenJDK 64-Bit Server VM 1.8.0_222-b10 on Linux 3.10.0-862.3.2.el7.x86_64
Intel(R) Xeon(R) CPU E5-2670 v2 @ 2.50GHz
object agg v.s. sort agg: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative
------------------------------------------------------------------------------------------------------------------------
sort agg w/ group by 41568 41894 461 2.5 396.4 1.0X
object agg w/ group by w/o fallback 10314 10494 149 10.2 98.4 4.0X
object agg w/ group by w/ fallback 26720 26951 326 3.9 254.8 1.6X
sort agg w/o group by 6638 6681 38 15.8 63.3 6.3X
object agg w/o group by w/o fallback 5665 5706 30 18.5 54.0 7.3X
================================================================================================
ObjectHashAggregateExec vs SortAggregateExec - percentile_approx
================================================================================================
OpenJDK 64-Bit Server VM 1.8.0_222-b10 on Linux 3.10.0-862.3.2.el7.x86_64
Intel(R) Xeon(R) CPU E5-2670 v2 @ 2.50GHz
object agg v.s. sort agg: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative
------------------------------------------------------------------------------------------------------------------------
sort agg w/ group by 794 862 33 2.6 378.8 1.0X
object agg w/ group by w/o fallback 605 622 10 3.5 288.5 1.3X
object agg w/ group by w/ fallback 840 860 15 2.5 400.5 0.9X
sort agg w/o group by 555 570 12 3.8 264.6 1.4X
object agg w/o group by w/o fallback 544 562 12 3.9 259.6 1.5X