95ae209461
## What changes were proposed in this pull request? Refactor `DatasetBenchmark` to use main method. Generate benchmark result: ```sh SPARK_GENERATE_BENCHMARK_FILES=1 build/sbt "sql/test:runMain org.apache.spark.sql.DatasetBenchmark" ``` ## How was this patch tested? manual tests Closes #22488 from wangyum/SPARK-25479. Lead-authored-by: Yuming Wang <yumwang@ebay.com> Co-authored-by: Dongjoon Hyun <dongjoon@apache.org> Signed-off-by: Dongjoon Hyun <dongjoon@apache.org>
47 lines
3.2 KiB
Plaintext
47 lines
3.2 KiB
Plaintext
================================================================================================
|
|
Dataset Benchmark
|
|
================================================================================================
|
|
|
|
OpenJDK 64-Bit Server VM 1.8.0_181-b13 on Linux 3.10.0-862.3.2.el7.x86_64
|
|
Intel(R) Xeon(R) CPU E5-2670 v2 @ 2.50GHz
|
|
back-to-back map long: Best/Avg Time(ms) Rate(M/s) Per Row(ns) Relative
|
|
------------------------------------------------------------------------------------------------
|
|
RDD 11800 / 12042 8.5 118.0 1.0X
|
|
DataFrame 1927 / 2189 51.9 19.3 6.1X
|
|
Dataset 2483 / 2605 40.3 24.8 4.8X
|
|
|
|
OpenJDK 64-Bit Server VM 1.8.0_181-b13 on Linux 3.10.0-862.3.2.el7.x86_64
|
|
Intel(R) Xeon(R) CPU E5-2670 v2 @ 2.50GHz
|
|
back-to-back map: Best/Avg Time(ms) Rate(M/s) Per Row(ns) Relative
|
|
------------------------------------------------------------------------------------------------
|
|
RDD 16286 / 16301 6.1 162.9 1.0X
|
|
DataFrame 8101 / 8104 12.3 81.0 2.0X
|
|
Dataset 17445 / 17811 5.7 174.4 0.9X
|
|
|
|
OpenJDK 64-Bit Server VM 1.8.0_181-b13 on Linux 3.10.0-862.3.2.el7.x86_64
|
|
Intel(R) Xeon(R) CPU E5-2670 v2 @ 2.50GHz
|
|
back-to-back filter Long: Best/Avg Time(ms) Rate(M/s) Per Row(ns) Relative
|
|
------------------------------------------------------------------------------------------------
|
|
RDD 2971 / 3184 33.7 29.7 1.0X
|
|
DataFrame 1243 / 1296 80.5 12.4 2.4X
|
|
Dataset 3062 / 3091 32.7 30.6 1.0X
|
|
|
|
OpenJDK 64-Bit Server VM 1.8.0_181-b13 on Linux 3.10.0-862.3.2.el7.x86_64
|
|
Intel(R) Xeon(R) CPU E5-2670 v2 @ 2.50GHz
|
|
back-to-back filter: Best/Avg Time(ms) Rate(M/s) Per Row(ns) Relative
|
|
------------------------------------------------------------------------------------------------
|
|
RDD 5253 / 5269 19.0 52.5 1.0X
|
|
DataFrame 211 / 234 473.4 2.1 24.9X
|
|
Dataset 9550 / 9552 10.5 95.5 0.6X
|
|
|
|
OpenJDK 64-Bit Server VM 1.8.0_181-b13 on Linux 3.10.0-862.3.2.el7.x86_64
|
|
Intel(R) Xeon(R) CPU E5-2670 v2 @ 2.50GHz
|
|
aggregate: Best/Avg Time(ms) Rate(M/s) Per Row(ns) Relative
|
|
------------------------------------------------------------------------------------------------
|
|
RDD sum 5086 / 5108 19.7 50.9 1.0X
|
|
DataFrame sum 65 / 73 1548.9 0.6 78.8X
|
|
Dataset sum using Aggregator 9024 / 9320 11.1 90.2 0.6X
|
|
Dataset complex Aggregator 15079 / 15171 6.6 150.8 0.3X
|
|
|
|
|