我们在生产环境常用的提交job模式一般通过web,如livy等restful api方式提交job.或者是通过spark-shell直接提交,对于大部分企业来说,都是在集群之外通过在集群之外的client节点提交job的方式,本人使用的集群环境是aws emr,提交job的方式是第二种,但是在client节点执行spark-shell的时候,通过yarn后台点击job的application manager ui,始终报如下错误:
HTTP ERROR 500
Problem accessing /proxy/application_1551347016430_0037/. Reason:
Connect to ip-172-32-0-250.cn-north-1.compute.internal:4040 [ip-172-32-0-250.cn-north-1.compute.internal/172.32.0.250] failed: Connection refused (Connection refused)
Caused by:
org.apache.http.conn.HttpHostConnectException: Connect to ip-172-32-0-250.cn-north-1.compute.internal:4040 [ip-172-32-0-250.cn-north-1.compute.internal/172.32.0.250] failed: Connection refused (Connection refused)
at org.apache.http.impl.conn.DefaultHttpClientConnectionOperator.connect(DefaultHttpClientConnectionOperator.java:159)
at org.apache.http.impl.conn.PoolingHttpClientConnectionManager.connect(PoolingHttpClientConnectionManager.java:373)
at org.apache.http.impl.execchain.MainClientExec.establishRoute(MainClientExec.java:381)
at org.apache.http.impl.execchain.MainClientExec.execute(MainClientExec.java:237)
at org.apache.http.impl.execchain.ProtocolExec.execute(ProtocolExec.java:185)
at org.apache.http.impl.execchain.RetryExec.execute(RetryExec.java:89)
at org.apache.http.impl.execchain.RedirectExec.execute(RedirectExec.java:111)
at org.apache.http.impl.client.InternalHttpClient.doExecute(InternalHttpClient.java:185)
at org.apache.http.impl.client.CloseableHttpClient.execute(CloseableHttpClient.java:83)
at org.apache.http.impl.client.CloseableHttpClient.execute(CloseableHttpClient.java:108)
at org.apache.hadoop.yarn.server.webproxy.WebAppProxyServlet.proxyLink(WebAppProxyServlet.java:259)
at org.apache.hadoop.yarn.server.webproxy.WebAppProxyServlet.methodAction(WebAppProxyServlet.java:478)
at org.apache.hadoop.yarn.server.webproxy.WebAppProxyServlet.doGet(WebAppProxyServlet.java:307)
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$CachedChain.doFilter(ServletHandler.java:1221)
at org.apache.hadoop.http.lib.StaticUserWebFilter$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:1353)
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)
Caused by: java.net.ConnectException: Connection refused (Connection refused)
at java.net.PlainSocketImpl.socketConnect(Native Method)
at java.net.AbstractPlainSocketImpl.doConnect(AbstractPlainSocketImpl.java:350)
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 org.apache.http.conn.socket.PlainConnectionSocketFactory.connectSocket(PlainConnectionSocketFactory.java:75)
at org.apache.http.impl.conn.DefaultHttpClientConnectionOperator.connect(DefaultHttpClientConnectionOperator.java:142)
... 39 more
Caused by:
java.net.ConnectException: Connection refused (Connection refused)
at java.net.PlainSocketImpl.socketConnect(Native Method)
at java.net.AbstractPlainSocketImpl.doConnect(AbstractPlainSocketImpl.java:350)
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 org.apache.http.conn.socket.PlainConnectionSocketFactory.connectSocket(PlainConnectionSocketFactory.java:75)
at org.apache.http.impl.conn.DefaultHttpClientConnectionOperator.connect(DefaultHttpClientConnectionOperator.java:142)
at org.apache.http.impl.conn.PoolingHttpClientConnectionManager.connect(PoolingHttpClientConnectionManager.java:373)
at org.apache.http.impl.execchain.MainClientExec.establishRoute(MainClientExec.java:381)
at org.apache.http.impl.execchain.MainClientExec.execute(MainClientExec.java:237)
at org.apache.http.impl.execchain.ProtocolExec.execute(ProtocolExec.java:185)
at org.apache.http.impl.execchain.RetryExec.execute(RetryExec.java:89)
at org.apache.http.impl.execchain.RedirectExec.execute(RedirectExec.java:111)
at org.apache.http.impl.client.InternalHttpClient.doExecute(InternalHttpClient.java:185)
at org.apache.http.impl.client.CloseableHttpClient.execute(CloseableHttpClient.java:83)
at org.apache.http.impl.client.CloseableHttpClient.execute(CloseableHttpClient.java:108)
at org.apache.hadoop.yarn.server.webproxy.WebAppProxyServlet.proxyLink(WebAppProxyServlet.java:259)
at org.apache.hadoop.yarn.server.webproxy.WebAppProxyServlet.methodAction(WebAppProxyServlet.java:478)
at org.apache.hadoop.yarn.server.webproxy.WebAppProxyServlet.doGet(WebAppProxyServlet.java:307)
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 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$QuotingInputFilter.doFilter(HttpServer2.java:1353)
at org.mortbay.jetty.servlet.ServletHandler$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)
Powered by Jetty://
经过仔细研究,梳理了spark提交job的yarn-client模式和yarn-master模式二者的内在区别,以及spark web ui和spark job history的运作方式之后,终于找到问题,之所以报以上错误信息,是因为SPARK_PUBLIC_DNS 这个配置不正确,以上错误信息中的URL是master节点(我们的client节点是直接用master节点做的镜像,所以默认是master节点的)改成client机器的私有dns即可
PYSPARK_PYTHON Python binary executable to use for PySpark.
SPARK_LOCAL_IP IP address of the machine to bind to.
SPARK_PUBLIC_DNS Hostname your Spark program will advertise to other machines.