[ 
https://issues.apache.org/jira/browse/YARN-3574?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14531078#comment-14531078
 ] 

Rohith commented on YARN-3574:
------------------------------

Done some more investigation on this modifying the above program that start 
ServerSocket. It is found that SocketInputStream.read() is NOT Interruptible!!
{code}
package com.rohith;

import java.io.DataInputStream;
import java.io.IOException;
import java.io.InputStream;
import java.net.ServerSocket;
import java.net.Socket;
import java.net.UnknownHostException;

public class Test {
  Thread sinkThread;
  Socket socket = null;
  InputStream in = null;
  private volatile boolean stopping = false;

  public void start() {
    sinkThread = new Thread() {
      public void run() {

        try {
          socket = new Socket("localhost", 4444);
        } catch (UnknownHostException e2) {
          e2.printStackTrace();
        } catch (IOException e2) {
          e2.printStackTrace();
        }


        try {
          in = socket.getInputStream();
        } catch (IOException e1) {
          e1.printStackTrace();
        }
        while (!stopping) {
          try {
            System.out.println("in.read");
            in.read();
          } catch (IOException e) {
            e.printStackTrace();
          }
        }
      };
    };
    sinkThread.setDaemon(true);
    sinkThread.start();
  }

  public void stop() {
    stopping = true;

    try {
      socket.close();
    } catch (IOException e1) {
      e1.printStackTrace();
    }

    System.out.println("Interrupting.. ");
    System.out.println(sinkThread.getState());
    sinkThread.interrupt();
    try {
      System.out.println("Joining.. ");
      sinkThread.join();
    } catch (InterruptedException e) {
      System.out.println("Stop interrupted " + e);
    }
    System.out.println("Stopped successfully");
  }

  public static void main(String[] args) throws InterruptedException {
    try {
      ServerSocket ss = new ServerSocket(4444);
    } catch (IOException e) {
      e.printStackTrace();
    }

    System.out.println("Made socket, now reading from socket");

    Test t1 = new Test();
    t1.start();
    Thread.sleep(2000);
    t1.stop();
  }

}
{code}

> RM hangs on stopping MetricsSinkAdapter when transitioning to standby
> ---------------------------------------------------------------------
>
>                 Key: YARN-3574
>                 URL: https://issues.apache.org/jira/browse/YARN-3574
>             Project: Hadoop YARN
>          Issue Type: Bug
>            Reporter: Jian He
>            Assignee: Brahma Reddy Battula
>
> We've seen a situation that one RM hangs on stopping the MetricsSinkAdapter
> {code}
> "main-EventThread" daemon prio=10 tid=0x00007f9b24031000 nid=0x2d18 in 
> Object.wait() [0x00007f9afe7eb000]
>    java.lang.Thread.State: WAITING (on object monitor)
>         at java.lang.Object.wait(Native Method)
>         - waiting on <0x00000000c058dcf8> (a 
> org.apache.hadoop.metrics2.impl.MetricsSinkAdapter$1)
>         at java.lang.Thread.join(Thread.java:1281)
>         - locked <0x00000000c058dcf8> (a 
> org.apache.hadoop.metrics2.impl.MetricsSinkAdapter$1)
>         at java.lang.Thread.join(Thread.java:1355)
>         at 
> org.apache.hadoop.metrics2.impl.MetricsSinkAdapter.stop(MetricsSinkAdapter.java:202)
>         at 
> org.apache.hadoop.metrics2.impl.MetricsSystemImpl.stopSinks(MetricsSystemImpl.java:472)
>         - locked <0x00000000c04cc1a0> (a 
> org.apache.hadoop.metrics2.impl.MetricsSystemImpl)
>         at 
> org.apache.hadoop.metrics2.impl.MetricsSystemImpl.stop(MetricsSystemImpl.java:213)
>         - locked <0x00000000c04cc1a0> (a 
> org.apache.hadoop.metrics2.impl.MetricsSystemImpl)
>         at 
> org.apache.hadoop.metrics2.impl.MetricsSystemImpl.shutdown(MetricsSystemImpl.java:592)
>         - locked <0x00000000c04cc1a0> (a 
> org.apache.hadoop.metrics2.impl.MetricsSystemImpl)
>         at 
> org.apache.hadoop.metrics2.lib.DefaultMetricsSystem.shutdownInstance(DefaultMetricsSystem.java:72)
>         at 
> org.apache.hadoop.metrics2.lib.DefaultMetricsSystem.shutdown(DefaultMetricsSystem.java:68)
>         at 
> org.apache.hadoop.yarn.server.resourcemanager.ResourceManager$RMActiveServices.serviceStop(ResourceManager.java:605)
>         at 
> org.apache.hadoop.service.AbstractService.stop(AbstractService.java:221)
>         - locked <0x00000000c0503568> (a java.lang.Object)
>         at 
> org.apache.hadoop.yarn.server.resourcemanager.ResourceManager.stopActiveServices(ResourceManager.java:1024)
>         at 
> org.apache.hadoop.yarn.server.resourcemanager.ResourceManager.transitionToStandby(ResourceManager.java:1076)
>         - locked <0x00000000c03fe3b8> (a 
> org.apache.hadoop.yarn.server.resourcemanager.ResourceManager)
>         at 
> org.apache.hadoop.yarn.server.resourcemanager.AdminService.transitionToStandby(AdminService.java:322)
>         - locked <0x00000000c0502b10> (a 
> org.apache.hadoop.yarn.server.resourcemanager.AdminService)
>         at 
> org.apache.hadoop.yarn.server.resourcemanager.EmbeddedElectorService.becomeStandby(EmbeddedElectorService.java:135)
>         at 
> org.apache.hadoop.ha.ActiveStandbyElector.becomeStandby(ActiveStandbyElector.java:911)
>         at 
> org.apache.hadoop.ha.ActiveStandbyElector.processResult(ActiveStandbyElector.java:428)
>         - locked <0x00000000c0718940> (a 
> org.apache.hadoop.ha.ActiveStandbyElector)
>         at 
> org.apache.zookeeper.ClientCnxn$EventThread.processEvent(ClientCnxn.java:605)
>         at 
> org.apache.zookeeper.ClientCnxn$EventThread.run(ClientCnxn.java:498)
> {code}
> {code}
> "timeline" daemon prio=10 tid=0x00007f9b34d55000 nid=0x1d93 runnable 
> [0x00007f9b0cbbf000]
>    java.lang.Thread.State: RUNNABLE
>         at java.net.SocketInputStream.socketRead0(Native Method)
>         at java.net.SocketInputStream.read(SocketInputStream.java:152)
>         at java.net.SocketInputStream.read(SocketInputStream.java:122)
>         at java.io.BufferedInputStream.fill(BufferedInputStream.java:235)
>         at java.io.BufferedInputStream.read(BufferedInputStream.java:254)
>         - locked <0x00000000c0f522c8> (a java.io.BufferedInputStream)
>         at 
> org.apache.commons.httpclient.HttpParser.readRawLine(HttpParser.java:78)
>         at 
> org.apache.commons.httpclient.HttpParser.readLine(HttpParser.java:106)
>         at 
> org.apache.commons.httpclient.HttpConnection.readLine(HttpConnection.java:1116)
>         at 
> org.apache.commons.httpclient.HttpMethodBase.readStatusLine(HttpMethodBase.java:1973)
>         at 
> org.apache.commons.httpclient.HttpMethodBase.readResponse(HttpMethodBase.java:1735)
>         at 
> org.apache.commons.httpclient.HttpMethodBase.execute(HttpMethodBase.java:1098)
>         at 
> org.apache.commons.httpclient.HttpMethodDirector.executeWithRetry(HttpMethodDirector.java:398)
>         at 
> org.apache.commons.httpclient.HttpMethodDirector.executeMethod(HttpMethodDirector.java:171)
>         at 
> org.apache.commons.httpclient.HttpClient.executeMethod(HttpClient.java:397)
>         at 
> org.apache.commons.httpclient.HttpClient.executeMethod(HttpClient.java:323)
>         at 
> org.apache.hadoop.metrics2.sink.timeline.AbstractTimelineMetricsSink.emitMetrics(AbstractTimelineMetricsSink.java:66)
>         at 
> org.apache.hadoop.metrics2.sink.timeline.HadoopTimelineMetricsSink.putMetrics(HadoopTimelineMetricsSink.java:203)
>         at 
> org.apache.hadoop.metrics2.impl.MetricsSinkAdapter.consume(MetricsSinkAdapter.java:175)
>         at 
> org.apache.hadoop.metrics2.impl.MetricsSinkAdapter.consume(MetricsSinkAdapter.java:43)
>         at 
> org.apache.hadoop.metrics2.impl.SinkQueue.consumeAll(SinkQueue.java:87)
>         at 
> org.apache.hadoop.metrics2.impl.MetricsSinkAdapter.publishMetricsFromQueue(MetricsSinkAdapter.java:129)
>         at 
> org.apache.hadoop.metrics2.impl.MetricsSinkAdapter$1.run(MetricsSinkAdapter.java:88)
> {code}
>  looks like the {{sinkThread.interrupt();}} in MetricsSinkAdapter#stop 
> doesn't really interrupt the thread, which cause it to hang at join.
> This appears only once.



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)

Reply via email to