[GitHub] [hadoop] zhengchenyu commented on a diff in pull request #4270: YARN-11127. Potential deadlock in AsyncDispatcher caused by RMNodeImp…

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

zhengchenyu commented on code in PR #4270:
URL: https://github.com/apache/hadoop/pull/4270#discussion_r893034291


##########
hadoop-yarn-project/hadoop-yarn/hadoop-yarn-client/src/test/java/org/apache/hadoop/yarn/client/api/impl/TestRMDeadLockTriggerByApp.java:
##########
@@ -0,0 +1,343 @@
+/**
+ * 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.hadoop.yarn.client.api.impl;
+
+import static org.junit.Assert.assertEquals;
+import static org.junit.Assert.assertTrue;
+
+import java.io.IOException;
+import java.nio.ByteBuffer;
+import java.util.Arrays;
+import java.util.Collections;
+import java.util.HashMap;
+import java.util.List;
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.security.UserGroupInformation;
+import org.apache.hadoop.service.Service.STATE;
+import org.apache.hadoop.yarn.api.protocolrecords.SubmitApplicationRequest;
+import org.apache.hadoop.yarn.api.records.ApplicationAccessType;
+import org.apache.hadoop.yarn.api.records.ApplicationAttemptId;
+import org.apache.hadoop.yarn.api.records.ApplicationId;
+import org.apache.hadoop.yarn.api.records.ApplicationReport;
+import org.apache.hadoop.yarn.api.records.ApplicationSubmissionContext;
+import org.apache.hadoop.yarn.api.records.ContainerId;
+import org.apache.hadoop.yarn.api.records.ContainerLaunchContext;
+import org.apache.hadoop.yarn.api.records.ExecutionType;
+import org.apache.hadoop.yarn.api.records.ExecutionTypeRequest;
+import org.apache.hadoop.yarn.api.records.LocalResource;
+import org.apache.hadoop.yarn.api.records.LogAggregationStatus;
+import org.apache.hadoop.yarn.api.records.NodeReport;
+import org.apache.hadoop.yarn.api.records.NodeState;
+import org.apache.hadoop.yarn.api.records.Priority;
+import org.apache.hadoop.yarn.api.records.Resource;
+import org.apache.hadoop.yarn.api.records.YarnApplicationState;
+import org.apache.hadoop.yarn.client.ClientRMProxy;
+import org.apache.hadoop.yarn.client.api.AMRMClient;
+import org.apache.hadoop.yarn.client.api.AMRMClient.ContainerRequest;
+import org.apache.hadoop.yarn.client.api.YarnClient;
+import org.apache.hadoop.yarn.conf.YarnConfiguration;
+import org.apache.hadoop.yarn.event.AsyncDispatcher;
+import org.apache.hadoop.yarn.event.Event;
+import org.apache.hadoop.yarn.exceptions.YarnException;
+import org.apache.hadoop.yarn.server.MiniYARNCluster;
+import org.apache.hadoop.yarn.server.api.protocolrecords.LogAggregationReport;
+import org.apache.hadoop.yarn.server.nodemanager.NodeManager;
+import org.apache.hadoop.yarn.server.resourcemanager.ResourceManager;
+import org.apache.hadoop.yarn.server.resourcemanager.rmapp.attempt.RMAppAttempt;
+import org.apache.hadoop.yarn.server.resourcemanager.rmapp.attempt.RMAppAttemptState;
+import org.apache.hadoop.yarn.server.resourcemanager.scheduler.capacity.CapacityScheduler;
+import org.apache.hadoop.yarn.server.utils.BuilderUtils;
+import org.apache.hadoop.yarn.util.Records;
+import org.junit.After;
+import org.junit.Assert;
+import org.junit.Before;
+import org.junit.Test;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+public class TestRMDeadLockTriggerByApp {
+
+  private static final Logger LOG = LoggerFactory
+      .getLogger(TestRMDeadLockTriggerByApp.class);
+
+  int interval = 1;
+  int loop = 5000;
+  float checkDeadLockRatio = 2.0f;
+  boolean deadLock = false;
+  String errString = null;
+
+  Configuration conf = null;
+  MiniYARNCluster yarnCluster = null;
+
+  List<NodeReport> nodeReports = null;
+  ApplicationId appId = null;
+  ApplicationAttemptId attemptId = null;
+
+  YarnClient yarnClient = null;
+  AMRMClient<ContainerRequest> amClient = null;
+
+  ResourceManager rm;
+  NodeManager nm;
+  int nodeCount = 1;
+
+  @Before
+  public void setup() throws Exception {
+    conf = new YarnConfiguration();
+    createClusterAndStartApplication(conf);
+  }
+
+  void createClusterAndStartApplication(Configuration conf)
+      throws Exception {
+    // start minicluster
+    this.conf = conf;
+    conf.set(YarnConfiguration.RM_SCHEDULER, CapacityScheduler.class.getName());
+    conf.setInt(YarnConfiguration.RM_SCHEDULER_MINIMUM_ALLOCATION_MB, 512);
+    conf.setLong(YarnConfiguration.NM_LOG_RETAIN_SECONDS, 1);
+    conf.setInt(
+        YarnConfiguration.NM_OPPORTUNISTIC_CONTAINERS_MAX_QUEUE_LENGTH, 10);
+    conf.setBoolean(YarnConfiguration.LOG_AGGREGATION_ENABLED, true);
+    conf.setInt(YarnConfiguration.NM_VCORES, loop);
+    conf.setInt(YarnConfiguration.YARN_MINICLUSTER_NM_PMEM_MB, 512 * loop);
+    conf.setInt(YarnConfiguration.RM_NM_HEARTBEAT_INTERVAL_MS, this.interval);
+
+    yarnCluster = new MiniYARNCluster(
+        TestAMRMClient.class.getName(), nodeCount, 1, 1);
+    yarnCluster.init(conf);
+    yarnCluster.start();
+
+    // start rm client
+    yarnClient = YarnClient.createYarnClient();
+    yarnClient.init(conf);
+    yarnClient.start();
+
+    // get node info
+    assertTrue("All node managers did not connect to the RM within the "
+            + "allotted 5-second timeout",
+        yarnCluster.waitForNodeManagersToConnect(5000L));
+    nodeReports = yarnClient.getNodeReports(NodeState.RUNNING);
+    assertEquals("Not all node managers were reported running",
+        nodeCount, nodeReports.size());
+
+    // get rm and nm info
+    rm = yarnCluster.getResourceManager(0);
+    nm = yarnCluster.getNodeManager(0);
+
+    // submit new app
+    ApplicationSubmissionContext appContext =
+        yarnClient.createApplication().getApplicationSubmissionContext();
+    appId = appContext.getApplicationId();
+    // set the application name
+    appContext.setApplicationName("Test");
+    // Set the priority for the application master
+    Priority pri = Records.newRecord(Priority.class);
+    pri.setPriority(0);
+    appContext.setPriority(pri);
+    // Set the queue to which this application is to be submitted in the RM
+    appContext.setQueue("default");
+    // Set up the container launch context for the application master
+    ContainerLaunchContext amContainer =
+        BuilderUtils.newContainerLaunchContext(
+            Collections.<String, LocalResource>emptyMap(),
+            new HashMap<String, String>(), Arrays.asList("sleep", "100"),
+            new HashMap<String, ByteBuffer>(), null,
+            new HashMap<ApplicationAccessType, String>());
+    appContext.setAMContainerSpec(amContainer);
+    appContext.setResource(Resource.newInstance(1024, 1));
+    // Create the request to send to the applications manager
+    SubmitApplicationRequest appRequest = Records
+        .newRecord(SubmitApplicationRequest.class);
+    appRequest.setApplicationSubmissionContext(appContext);
+    // Submit the application to the applications manager
+    yarnClient.submitApplication(appContext);
+
+    // wait for app to start
+    RMAppAttempt appAttempt = null;
+    while (true) {
+      ApplicationReport appReport = yarnClient.getApplicationReport(appId);
+      if (appReport.getYarnApplicationState() ==
+          YarnApplicationState.ACCEPTED) {
+        attemptId = appReport.getCurrentApplicationAttemptId();
+        appAttempt =
+            yarnCluster.getResourceManager().getRMContext().getRMApps()
+                .get(attemptId.getApplicationId()).getCurrentAppAttempt();
+        while (true) {
+          if (appAttempt.getAppAttemptState() == RMAppAttemptState.LAUNCHED) {
+            break;
+          }
+        }
+        break;
+      }
+    }
+    // Just dig into the ResourceManager and get the AMRMToken just for the sake
+    // of testing.
+    UserGroupInformation.setLoginUser(UserGroupInformation
+        .createRemoteUser(UserGroupInformation.getCurrentUser().getUserName()));
+
+    // emulate RM setup of AMRM token in credentials by adding the token
+    // *before* setting the token service
+    UserGroupInformation.getCurrentUser().addToken(appAttempt.getAMRMToken());
+    appAttempt.getAMRMToken().setService(
+        ClientRMProxy.getAMRMTokenService(conf));
+
+    // create AMRMClient
+    amClient = AMRMClient.createAMRMClient();
+    amClient.init(conf);
+    amClient.start();
+    amClient.registerApplicationMaster("Host", 10000, "");
+  }
+
+  @After
+  public void teardown() throws YarnException, IOException {
+    if (yarnClient != null && yarnClient.getServiceState() == STATE.STARTED) {
+      yarnClient.stop();
+    }
+
+    if (amClient != null && amClient.getServiceState() == STATE.STARTED) {
+      amClient.stop();
+    }
+
+    // Avoid the EventHandlingThread struck forever
+    if (deadLock) {
+      LOG.info("Found dead lock, stop EventHandlingThread manually!");
+      ((AsyncDispatcher) rm.getRMContext().getDispatcher())
+          .forceEventHandlingThreadStop();

Review Comment:
   When the unit test run without this patch, tearDown will stuck forever. 



-- 
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: common-issues-unsubscribe@hadoop.apache.org

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


---------------------------------------------------------------------
To unsubscribe, e-mail: common-issues-unsubscribe@hadoop.apache.org
For additional commands, e-mail: common-issues-help@hadoop.apache.org