现象

在对ResourceManager做了基于Zookeeper的HA后, 在YARN集群上执行Spark application后, 打开Spark Application Tracking UI显示以下错误:

HTTP ERROR 500

Problem accessing /proxy/application_1405708541410_0001/. Reason:

    Connection refused

Caused by:

java.net.ConnectException: Connection refused
    at java.net.PlainSocketImpl.socketConnect(Native Method)
    at java.net.AbstractPlainSocketImpl.doConnect(AbstractPlainSocketImpl.java:345)
    at java.net.AbstractPlainSocketImpl.connectToAddress(AbstractPlainSocketImpl.java:206)
    at java.net.AbstractPlainSocketImpl.connect(AbstractPlainSocketImpl.java:188)
    at java.net.SocksSocketImpl.connect(SocksSocketImpl.java:392)
    at java.net.Socket.connect(Socket.java:589)
    at java.net.Socket.connect(Socket.java:538)
    at java.net.Socket.<init>(Socket.java:434)
    at java.net.Socket.<init>(Socket.java:286)
    at org.apache.commons.httpclient.protocol.DefaultProtocolSocketFactory.createSocket(DefaultProtocolSocketFactory.java:80)
    at org.apache.commons.httpclient.protocol.DefaultProtocolSocketFactory.createSocket(DefaultProtocolSocketFactory.java:122)
    at org.apache.commons.httpclient.HttpConnection.open(HttpConnection.java:707)
    at org.apache.commons.httpclient.HttpMethodDirector.executeWithRetry(HttpMethodDirector.java:387)
    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:346)
    at org.apache.hadoop.yarn.server.webproxy.WebAppProxyServlet.proxyLink(WebAppProxyServlet.java:187)
    at org.apache.hadoop.yarn.server.webproxy.WebAppProxyServlet.doGet(WebAppProxyServlet.java:344)
    at javax.servlet.http.HttpServlet.service(HttpServlet.java:707)
    at javax.servlet.http.HttpServlet.service(HttpServlet.java:820)
    at org.mortbay.jetty.servlet.ServletHolder.handle(ServletHolder.java:511)
    at org.mortbay.jetty.servlet.ServletHandler$CachedChain.doFilter(ServletHandler.java:1221)
    at com.google.inject.servlet.FilterChainInvocation.doFilter(FilterChainInvocation.java:66)
    at com.sun.jersey.spi.container.servlet.ServletContainer.doFilter(ServletContainer.java:900)
    at com.sun.jersey.spi.container.servlet.ServletContainer.doFilter(ServletContainer.java:834)
    at org.apache.hadoop.yarn.server.resourcemanager.webapp.RMWebAppFilter.doFilter(RMWebAppFilter.java:84)
    at com.sun.jersey.spi.container.servlet.ServletContainer.doFilter(ServletContainer.java:795)
    at com.google.inject.servlet.FilterDefinition.doFilter(FilterDefinition.java:163)
    at com.google.inject.servlet.FilterChainInvocation.doFilter(FilterChainInvocation.java:58)
    at com.google.inject.servlet.ManagedFilterPipeline.dispatch(ManagedFilterPipeline.java:118)
    at com.google.inject.servlet.GuiceFilter.doFilter(GuiceFilter.java:113)
    at org.mortbay.jetty.servlet.ServletHandler$CachedChain.doFilter(ServletHandler.java:1212)
    at org.apache.hadoop.http.lib.StaticUserWebFilter$StaticUserFilter.doFilter(StaticUserWebFilter.java:109)
    at org.mortbay.jetty.servlet.ServletHandler$CachedChain.doFilter(ServletHandler.java:1212)
    at org.apache.hadoop.http.HttpServer2$QuotingInputFilter.doFilter(HttpServer2.java:1192)
    at org.mortbay.jetty.servlet.ServletHandler$CachedChain.doFilter(ServletHandler.java:1212)
    at org.apache.hadoop.http.NoCacheFilter.doFilter(NoCacheFilter.java:45)
    at org.mortbay.jetty.servlet.ServletHandler$CachedChain.doFilter(ServletHandler.java:1212)
    at org.apache.hadoop.http.NoCacheFilter.doFilter(NoCacheFilter.java:45)
    at org.mortbay.jetty.servlet.ServletHandler$CachedChain.doFilter(ServletHandler.java:1212)
    at org.mortbay.jetty.servlet.ServletHandler.handle(ServletHandler.java:399)
    at org.mortbay.jetty.security.SecurityHandler.handle(SecurityHandler.java:216)
    at org.mortbay.jetty.servlet.SessionHandler.handle(SessionHandler.java:182)
    at org.mortbay.jetty.handler.ContextHandler.handle(ContextHandler.java:766)
    at org.mortbay.jetty.webapp.WebAppContext.handle(WebAppContext.java:450)
    at org.mortbay.jetty.handler.ContextHandlerCollection.handle(ContextHandlerCollection.java:230)
    at org.mortbay.jetty.handler.HandlerWrapper.handle(HandlerWrapper.java:152)
    at org.mortbay.jetty.Server.handle(Server.java:326)
    at org.mortbay.jetty.HttpConnection.handleRequest(HttpConnection.java:542)
    at org.mortbay.jetty.HttpConnection$RequestHandler.headerComplete(HttpConnection.java:928)
    at org.mortbay.jetty.HttpParser.parseNext(HttpParser.java:549)
    at org.mortbay.jetty.HttpParser.parseAvailable(HttpParser.java:212)
    at org.mortbay.jetty.HttpConnection.handle(HttpConnection.java:404)
    at org.mortbay.io.nio.SelectChannelEndPoint.run(SelectChannelEndPoint.java:410)
    at org.mortbay.thread.QueuedThreadPool$PoolThread.run(QueuedThreadPool.java:582)

解决方案

• 在Active ResourceManager和Standby ResourceManager及所有NodeManager上的yarn-site.xml上添加yarn.resourcemanager.webapp.address属性, 并重启相应的ResourceManager及NodeManager