You are viewing a plain text version of this content. The canonical link for it is here.
Posted to reviews@spark.apache.org by GitBox <gi...@apache.org> on 2021/10/02 23:38:38 UTC

[GitHub] [spark] rmcyang commented on a change in pull request #34158: [WIP][SPARK-36705][FOLLOW-UP] Support the case when user's classes need to register for Kryo serialization

rmcyang commented on a change in pull request #34158:
URL: https://github.com/apache/spark/pull/34158#discussion_r720742585



##########
File path: core/src/main/scala/org/apache/spark/util/Utils.scala
##########
@@ -2603,18 +2603,28 @@ private[spark] object Utils extends Logging {
    *   - IO encryption disabled
    *   - serializer(such as KryoSerializer) supports relocation of serialized objects
    */
-  def isPushBasedShuffleEnabled(conf: SparkConf): Boolean = {
+  def isPushBasedShuffleEnabled(conf: SparkConf,
+      isDriver: Boolean,
+      checkSerializer: Boolean = true): Boolean = {
     val pushBasedShuffleEnabled = conf.get(PUSH_BASED_SHUFFLE_ENABLED)
     if (pushBasedShuffleEnabled) {
-      val serializer = Utils.classForName(conf.get(SERIALIZER)).getConstructor(classOf[SparkConf])
-        .newInstance(conf).asInstanceOf[Serializer]
-      val canDoPushBasedShuffle = conf.get(IS_TESTING).getOrElse(false) ||
-        (conf.get(SHUFFLE_SERVICE_ENABLED) &&
-          conf.get(SparkLauncher.SPARK_MASTER, null) == "yarn" &&
-          // TODO: [SPARK-36744] needs to support IO encryption for push-based shuffle
-          !conf.get(IO_ENCRYPTION_ENABLED) &&
-          serializer.supportsRelocationOfSerializedObjects)
-
+      val canDoPushBasedShuffle = {
+        val isTesting = conf.get(IS_TESTING).getOrElse(false)
+        val isShuffleServiceAndYarn = conf.get(SHUFFLE_SERVICE_ENABLED) &&
+            conf.get(SparkLauncher.SPARK_MASTER, null) == "yarn"
+        lazy val serializerIsSupported = {
+          if (checkSerializer) {
+            instantiateSerializerFromConf[Serializer](SERIALIZER, conf, isDriver)
+              .supportsRelocationOfSerializedObjects

Review comment:
       ```
   Option(SparkEnv.get)
     .map(_.serializer)
      .getOrElse(instantiateSerializerFromConf[Serializer](SERIALIZER, conf, isDriver))
   ```
   throw NPE after the test `test migration of shuffle blocks during decommissioning` succeeded in `BlockManagerSuite.beforeEach(BlockManagerSuite.scala:188)`. Seems SparkEnv wasn't configured properly. Adding `SparkEnv.set(null)` in `afterEach()` seems fixed the issue:
   ```
   org.apache.spark.storage.BlockManagerSuite *** ABORTED *** (41 seconds, 221 milliseconds)
   [info]   java.lang.NullPointerException:
   [info]   at org.apache.spark.util.Utils$.isPushBasedShuffleEnabled(Utils.scala:2619)
   [info]   at org.apache.spark.storage.BlockManagerMasterEndpoint.<init>(BlockManagerMasterEndpoint.scala:104)
   [info]   at org.apache.spark.storage.BlockManagerSuite.beforeEach(BlockManagerSuite.scala:188)
   [info]   at org.scalatest.BeforeAndAfterEach.runTest(BeforeAndAfterEach.scala:233)
   [info]   at org.scalatest.BeforeAndAfterEach.runTest$(BeforeAndAfterEach.scala:227)
   [info]   at org.apache.spark.SparkFunSuite.runTest(SparkFunSuite.scala:62)
   [info]   at org.scalatest.funsuite.AnyFunSuiteLike.$anonfun$runTests$1(AnyFunSuiteLike.scala:269)
   [info]   at org.scalatest.SuperEngine.$anonfun$runTestsInBranch$1(Engine.scala:413)
   [info]   at scala.collection.immutable.List.foreach(List.scala:431)
   [info]   at org.scalatest.SuperEngine.traverseSubNodes$1(Engine.scala:401)
   [info]   at org.scalatest.SuperEngine.runTestsInBranch(Engine.scala:396)
   [info]   at org.scalatest.SuperEngine.runTestsImpl(Engine.scala:475)
   [info]   at org.scalatest.funsuite.AnyFunSuiteLike.runTests(AnyFunSuiteLike.scala:269)
   [info]   at org.scalatest.funsuite.AnyFunSuiteLike.runTests$(AnyFunSuiteLike.scala:268)
   [info]   at org.scalatest.funsuite.AnyFunSuite.runTests(AnyFunSuite.scala:1563)
   [info]   at org.scalatest.Suite.run(Suite.scala:1112)
   [info]   at org.scalatest.Suite.run$(Suite.scala:1094)
   [info]   at org.scalatest.funsuite.AnyFunSuite.org$scalatest$funsuite$AnyFunSuiteLike$$super$run(AnyFunSuite.scala:1563)
   [info]   at org.scalatest.funsuite.AnyFunSuiteLike.$anonfun$run$1(AnyFunSuiteLike.scala:273)
   [info]   at org.scalatest.SuperEngine.runImpl(Engine.scala:535)
   [info]   at org.scalatest.funsuite.AnyFunSuiteLike.run(AnyFunSuiteLike.scala:273)
   [info]   at org.scalatest.funsuite.AnyFunSuiteLike.run$(AnyFunSuiteLike.scala:272)
   [info]   at org.apache.spark.SparkFunSuite.org$scalatest$BeforeAndAfterAll$$super$run(SparkFunSuite.scala:62)
   [info]   at org.scalatest.BeforeAndAfterAll.liftedTree1$1(BeforeAndAfterAll.scala:213)
   [info]   at org.scalatest.BeforeAndAfterAll.run(BeforeAndAfterAll.scala:210)
   [info]   at org.scalatest.BeforeAndAfterAll.run$(BeforeAndAfterAll.scala:208)
   [info]   at org.apache.spark.SparkFunSuite.run(SparkFunSuite.scala:62)
   [info]   at org.scalatest.tools.Framework.org$scalatest$tools$Framework$$runSuite(Framework.scala:318)
   [info]   at org.scalatest.tools.Framework$ScalaTestTask.execute(Framework.scala:513)
   [info]   at sbt.ForkMain$Run.lambda$runTest$1(ForkMain.java:413)
   [info]   at java.util.concurrent.FutureTask.run(FutureTask.java:266)
   [info]   at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
   [info]   at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
   [info]   at java.lang.Thread.run(Thread.java:748) 
   ```




-- 
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