[GitHub] [spark] pan3793 commented on a diff in pull request #33721: [SPARK-32210][CORE] Fix NegativeArraySizeException in MapOutputTracker with large spark.default.parallelism

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

pan3793 commented on code in PR #33721:
URL: https://github.com/apache/spark/pull/33721#discussion_r844051919


##########
core/src/test/scala/org/apache/spark/MapOutputTrackerSuite.scala:
##########
@@ -664,4 +664,74 @@ class MapOutputTrackerSuite extends SparkFunSuite with LocalSparkContext {
     tracker.stop()
     rpcEnv.shutdown()
   }
+
+  test("SPARK-32210: serialize mapStatuses to a nested Array and deserialize them") {
+    val newConf = new SparkConf
+
+    // needs TorrentBroadcast so need a SparkContext
+    withSpark(new SparkContext("local", "MapOutputTrackerSuite", newConf)) { sc =>
+      val tracker = sc.env.mapOutputTracker.asInstanceOf[MapOutputTrackerMaster]
+      val rpcEnv = sc.env.rpcEnv
+      val masterEndpoint = new MapOutputTrackerMasterEndpoint(rpcEnv, tracker, sc.getConf)
+      rpcEnv.stop(tracker.trackerEndpoint)
+      rpcEnv.setupEndpoint(MapOutputTracker.ENDPOINT_NAME, masterEndpoint)
+      val shuffleId = 20
+      val numMaps = 1000
+
+      tracker.registerShuffle(shuffleId, numMaps, MergeStatus.SHUFFLE_PUSH_DUMMY_NUM_REDUCES)
+      val r = new scala.util.Random(912)
+      (0 until numMaps).foreach { i =>
+        tracker.registerMapOutput(shuffleId, i, HighlyCompressedMapStatus(
+          BlockManagerId(s"node$i", s"node$i.spark.apache.org", 1000),
+          Array.fill[Long](1000)((r.nextDouble() * 1024 * 1024 * 1024).toLong), i))
+      }
+
+      val shuffleStatus = tracker.shuffleStatuses.get(shuffleId).head
+      val (serializedMapStatus, serializedBroadcast) = MapOutputTracker.serializeOutputStatuses(
+        shuffleStatus.mapStatuses, tracker.broadcastManager, tracker.isLocal, 0, sc.getConf)
+      assert(serializedBroadcast.value.length > 1)
+      assert(serializedBroadcast.value.dropRight(1).forall(_.length == 1024 * 1024))
+
+      val result = MapOutputTracker.deserializeOutputStatuses(serializedMapStatus, sc.getConf)
+      assert(result.length == numMaps)
+
+      tracker.unregisterShuffle(shuffleId)
+      tracker.stop()
+    }
+  }
+
+  ignore("SPARK-32210: serialize and deserialize over 2GB compressed mapStatuses") {
+    // This test requires 8GB heap memory settings

Review Comment:
   How can I run it in local? 
   Still encounter `sbt.ForkMain$ForkError: java.lang.OutOfMemoryError: Java heap space` with `SBT_OPTS="-Xmx16G"` 



-- 
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.

To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


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