[SPARK-25486][TEST] Refactor SortBenchmark to use main method

## What changes were proposed in this pull request? Refactor SortBenchmark to use main method. Generate benchmark result: ``` SPARK_GENERATE_BENCHMARK_FILES=1 build/sbt "sql/test:runMain org.apache.spark.sql.execution.benchmark.SortBenchmark" ``` ## How was this patch tested? manual tests Closes #22495 from yucai/SPARK-25486. Authored-by: yucai <[email protected]> Signed-off-by: Dongjoon Hyun <[email protected]>
apache · Sep 25, 2018 · 04db035 · 04db035
1 parent 9cbd001
commit 04db035
Show file tree

Hide file tree

Showing 2 changed files with 33 additions and 22 deletions.
diff --git a/sql/core/benchmarks/SortBenchmark-results.txt b/sql/core/benchmarks/SortBenchmark-results.txt
@@ -0,0 +1,17 @@
+================================================================================================
+radix sort
+================================================================================================
+
+Java HotSpot(TM) 64-Bit Server VM 1.8.0_162-b12 on Mac OS X 10.13.6
+Intel(R) Core(TM) i7-7820HQ CPU @ 2.90GHz
+
+radix sort 25000000:                     Best/Avg Time(ms)    Rate(M/s)   Per Row(ns)   Relative
+------------------------------------------------------------------------------------------------
+reference TimSort key prefix array          11770 / 11960          2.1         470.8       1.0X
+reference Arrays.sort                         2106 / 2128         11.9          84.3       5.6X
+radix sort one byte                             93 /  100        269.7           3.7     126.9X
+radix sort two bytes                           171 /  179        146.0           6.9      68.7X
+radix sort eight bytes                         659 /  664         37.9          26.4      17.9X
+radix sort key prefix array                   1024 / 1053         24.4          41.0      11.5X
+
+
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/execution/benchmark/SortBenchmark.scala b/sql/core/src/test/scala/org/apache/spark/sql/execution/benchmark/SortBenchmark.scala
@@ -19,7 +19,7 @@ package org.apache.spark.sql.execution.benchmark
 
 import java.util.{Arrays, Comparator}
 
-import org.apache.spark.benchmark.Benchmark
+import org.apache.spark.benchmark.{Benchmark, BenchmarkBase}
 import org.apache.spark.unsafe.array.LongArray
 import org.apache.spark.unsafe.memory.MemoryBlock
 import org.apache.spark.util.collection.Sorter
@@ -28,12 +28,15 @@ import org.apache.spark.util.random.XORShiftRandom
 
 /**
  * Benchmark to measure performance for aggregate primitives.
- * To run this:
- *  build/sbt "sql/test-only *benchmark.SortBenchmark"
- *
- * Benchmarks in this file are skipped in normal builds.
+ * {{{
+ *   To run this benchmark:
+ *   1. without sbt: bin/spark-submit --class <this class> <spark sql test jar>
+ *   2. build/sbt "sql/test:runMain <this class>"
+ *   3. generate result: SPARK_GENERATE_BENCHMARK_FILES=1 build/sbt "sql/test:runMain <this class>"
+ *      Results will be written to "benchmarks/<this class>-results.txt".
+ * }}}
  */
-class SortBenchmark extends BenchmarkWithCodegen {
+object SortBenchmark extends BenchmarkBase {
 
   private def referenceKeyPrefixSort(buf: LongArray, lo: Int, hi: Int, refCmp: PrefixComparator) {
     val sortBuffer = new LongArray(MemoryBlock.fromLongArray(new Array[Long](buf.size().toInt)))
@@ -54,10 +57,10 @@ class SortBenchmark extends BenchmarkWithCodegen {
       new LongArray(MemoryBlock.fromLongArray(extended)))
   }
 
-  ignore("sort") {
+  def sortBenchmark(): Unit = {
     val size = 25000000
     val rand = new XORShiftRandom(123)
-    val benchmark = new Benchmark("radix sort " + size, size)
+    val benchmark = new Benchmark("radix sort " + size, size, output = output)
     benchmark.addTimerCase("reference TimSort key prefix array") { timer =>
       val array = Array.tabulate[Long](size * 2) { i => rand.nextLong }
       val buf = new LongArray(MemoryBlock.fromLongArray(array))
@@ -114,20 +117,11 @@ class SortBenchmark extends BenchmarkWithCodegen {
       timer.stopTiming()
     }
     benchmark.run()
+  }
 
-    /*
-      Running benchmark: radix sort 25000000
-      Java HotSpot(TM) 64-Bit Server VM 1.8.0_66-b17 on Linux 3.13.0-44-generic
-      Intel(R) Core(TM) i7-4600U CPU @ 2.10GHz
-
-      radix sort 25000000:                Best/Avg Time(ms)    Rate(M/s)   Per Row(ns)   Relative
-      -------------------------------------------------------------------------------------------
-      reference TimSort key prefix array     15546 / 15859          1.6         621.9       1.0X
-      reference Arrays.sort                    2416 / 2446         10.3          96.6       6.4X
-      radix sort one byte                       133 /  137        188.4           5.3     117.2X
-      radix sort two bytes                      255 /  258         98.2          10.2      61.1X
-      radix sort eight bytes                    991 /  997         25.2          39.6      15.7X
-      radix sort key prefix array              1540 / 1563         16.2          61.6      10.1X
-    */
+  override def benchmark(): Unit = {
+    runBenchmark("radix sort") {
+      sortBenchmark()
+    }
   }
 }