Ngone51 commented on a change in pull request #28911:
URL: https://github.com/apache/spark/pull/28911#discussion_r447553884



##########
File path: 
core/src/test/scala/org/apache/spark/shuffle/HostLocalShuffleFetchSuite.scala
##########
@@ -0,0 +1,62 @@
+/*
+ * 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.shuffle
+
+import org.scalatest.Matchers
+
+import org.apache.spark.{LocalSparkContext, SparkConf, SparkContext, SparkEnv, 
SparkFunSuite, TestUtils}
+import org.apache.spark.internal.config._
+import org.apache.spark.network.netty.NettyBlockTransferService
+
+/**
+ * This test suite is used to test host local shuffle reading with external 
shuffle service disabled
+ */
+class HostLocalShuffleFetchSuite extends SparkFunSuite with Matchers with 
LocalSparkContext {
+  test("read host local shuffle from disk with external shuffle service 
disabled") {
+    val conf = new SparkConf()
+      .set(SHUFFLE_HOST_LOCAL_DISK_READING_ENABLED, true)
+      .set(SHUFFLE_SERVICE_ENABLED, false)
+      .set(DYN_ALLOCATION_ENABLED, false)
+    sc = new SparkContext("local-cluster[2,1,1024]", "test", conf)
+    sc.getConf.get(SHUFFLE_HOST_LOCAL_DISK_READING_ENABLED) should equal(true)
+    sc.env.blockManager.externalShuffleServiceEnabled should equal(false)
+    sc.env.blockManager.hostLocalDirManager.isDefined should equal(true)
+    sc.env.blockManager.blockStoreClient.getClass should 
equal(classOf[NettyBlockTransferService])
+    TestUtils.waitUntilExecutorsUp(sc, 2, 60000)
+
+    val rdd = sc.parallelize(0 until 1000, 10)
+      .map { i => (i, 1) }
+      .reduceByKey(_ + _)
+
+    rdd.count()
+    rdd.count()
+
+    val cachedExecutors = rdd.mapPartitions { _ =>
+      SparkEnv.get.blockManager.hostLocalDirManager.map { localDirManager =>
+        localDirManager.getCachedHostLocalDirs().keySet.iterator
+      }.getOrElse(Iterator.empty)
+    }.collect().toSet
+
+    // both executors are caching the dirs of the other one
+    cachedExecutors should equal(sc.getExecutorIds().toSet)
+
+    // Now Spark will not receive FetchFailed as host local blocks are read 
from the cached local
+    // disk directly

Review comment:
       I see, thanks.




----------------------------------------------------------------
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:
us...@infra.apache.org



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

Reply via email to