[GitHub] [spark] dongjoon-hyun commented on a change in pull request #26169: [SPARK-29515] [Core] MapStatuses SerDeser Benchmark

[GitBox <gi...@apache.org>]

dongjoon-hyun commented on a change in pull request #26169: [SPARK-29515] [Core] MapStatuses SerDeser Benchmark
URL: https://github.com/apache/spark/pull/26169#discussion_r336654234
 
 

 ##########
 File path: core/src/test/scala/org/apache/spark/MapStatusesSerDeserBenchmark.scala
 ##########
 @@ -0,0 +1,131 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements.  See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License.  You may obtain a copy of the License at
+ *
+ *    http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark
+
+import org.apache.spark.benchmark.Benchmark
+import org.apache.spark.benchmark.BenchmarkBase
+import org.apache.spark.scheduler.CompressedMapStatus
+import org.apache.spark.storage.BlockManagerId
+
+/**
+ * Benchmark for MapStatuses serialization & deserialization performance.
+ * {{{
+ *   To run this benchmark:
+ *   1. without sbt: bin/spark-submit --class <this class>
+ *        --jars <catalyst test jar>,<core test jar>
+ *   2. build/sbt "core/test:runMain <this class>"
+ *   3. generate result: SPARK_GENERATE_BENCHMARK_FILES=1 build/sbt "core/test:runMain <this class>"
+ *      Results will be written to "benchmarks/MapStatusesSerDeserBenchmark-results.txt".
+ * }}}
+ */
+object MapStatusesSerDeserBenchmark extends BenchmarkBase {
+
+  var sc: SparkContext = null
+  var tracker: MapOutputTrackerMaster = null
+
+  def serDeserBenchmark(numMaps: Int, blockSize: Int, enableBroadcast: Boolean): Unit = {
+    val minBroadcastSize = if (enableBroadcast) {
+      0
+    } else {
+      Int.MaxValue
+    }
+
+    val benchmark = new Benchmark(s"$numMaps MapOutputs, $blockSize blocks " + {
+      if (enableBroadcast) "w/ " else "w/o "
+    } + "broadcast", numMaps, output = output)
+
+    val shuffleId = 10
+
+    tracker.registerShuffle(shuffleId, numMaps)
+    val r = new scala.util.Random(912)
+    (0 until numMaps).foreach { i =>
+      tracker.registerMapOutput(shuffleId, i,
+        new CompressedMapStatus(BlockManagerId(s"node$i", s"node$i.spark.apache.org", 1000),
+          Array.fill(blockSize) {
+            // Creating block size ranging from 0byte to 1GB
+            (r.nextDouble() * 1024 * 1024 * 1024).toLong
+          }, i))
+    }
+
+    val shuffleStatus = tracker.shuffleStatuses.get(shuffleId).head
+
+    var serializedMapStatusSizes = 0
+    var serializedBroadcastSizes = 0
+
+    val (serializedMapStatus, serializedBroadcast) = MapOutputTracker.serializeMapStatuses(
+      shuffleStatus.mapStatuses, tracker.broadcastManager, tracker.isLocal, minBroadcastSize)
+    serializedMapStatusSizes = serializedMapStatus.length
+    if (serializedBroadcast != null) {
+      serializedBroadcastSizes = serializedBroadcast.value.length
+    }
+
+    benchmark.addCase("Serialization") { _ =>
+      MapOutputTracker.serializeMapStatuses(
+        shuffleStatus.mapStatuses, tracker.broadcastManager, tracker.isLocal, minBroadcastSize)
+    }
+
+    benchmark.addCase("Deserialization") { _ =>
+      val result = MapOutputTracker.deserializeMapStatuses(serializedMapStatus)
+      assert(result.length == numMaps)
+    }
+
+    benchmark.run()
+    // scalastyle:off
+    import org.apache.commons.io.FileUtils
+    benchmark.out.println("Compressed Serialized MapStatus sizes: " +
+      FileUtils.byteCountToDisplaySize(serializedMapStatusSizes))
+    benchmark.out.println(s"Compressed Serialized Broadcast MapStatus sizes: " +
 
 Review comment:
   nit. `s"` -> `"`.

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
users@infra.apache.org


With regards,
Apache Git Services

---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org