[YARN-4955] Add retry for SocketTimeoutException in TimelineClient

• Type: Bug
• Status: Resolved
• Priority: Critical
• Resolution: Fixed
• Fix Version/s: 2.8.0, 3.0.0-alpha1
• Hadoop Flags: Reviewed
• Assignee: Xuan Gong
• Reporter: Xuan Gong
• Created: 13/Apr/16 16:02
• Updated: 25/Oct/19 20:25
• Resolved: 28/Apr/16 08:55

Description

We saw this exception several times when we tried to getDelegationToken from ATS.

java.io.IOException: org.apache.hadoop.security.authentication.client.AuthenticationException: java.net.SocketTimeoutException: Read timed out
at org.apache.hadoop.yarn.client.api.impl.TimelineClientImpl$5.run(TimelineClientImpl.java:569)
at org.apache.hadoop.yarn.client.api.impl.TimelineClientImpl$TimelineClientConnectionRetry.retryOn(TimelineClientImpl.java:234)
at org.apache.hadoop.yarn.client.api.impl.TimelineClientImpl.operateDelegationToken(TimelineClientImpl.java:582)
at org.apache.hadoop.yarn.client.api.impl.TimelineClientImpl.getDelegationToken(TimelineClientImpl.java:479)
at org.apache.hadoop.yarn.client.api.impl.YarnClientImpl.getTimelineDelegationToken(YarnClientImpl.java:349)
at org.apache.hadoop.yarn.client.api.impl.YarnClientImpl.addTimelineDelegationToken(YarnClientImpl.java:330)
at org.apache.hadoop.yarn.client.api.impl.YarnClientImpl.submitApplication(YarnClientImpl.java:250)
at org.apache.hadoop.mapred.ResourceMgrDelegate.submitApplication(ResourceMgrDelegate.java:291)
at org.apache.hadoop.mapred.YARNRunner.submitJob(YARNRunner.java:290)
at org.apache.hadoop.mapreduce.JobSubmitter.submitJobInternal(JobSubmitter.java:240)
at org.apache.hadoop.mapreduce.Job$10.run(Job.java:1290)
at org.apache.hadoop.mapreduce.Job$10.run(Job.java:1287)
at java.security.AccessController.doPrivileged(Native Method)
at javax.security.auth.Subject.doAs(Subject.java:415)
at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1657)
at org.apache.hadoop.mapreduce.Job.submit(Job.java:1287)
at org.apache.hadoop.mapreduce.lib.jobcontrol.ControlledJob.submit(ControlledJob.java:335)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at org.apache.pig.backend.hadoop23.PigJobControl.submit(PigJobControl.java:128)
at org.apache.pig.backend.hadoop23.PigJobControl.run(PigJobControl.java:194)
at java.lang.Thread.run(Thread.java:745)
at org.apache.pig.backend.hadoop.executionengine.mapReduceLayer.MapReduceLauncher$1.run(MapReduceLauncher.java:276)
Caused by: org.apache.hadoop.security.authentication.client.AuthenticationException: java.net.SocketTimeoutException: Read timed out
at org.apache.hadoop.security.authentication.client.KerberosAuthenticator.doSpnegoSequence(KerberosAuthenticator.java:332)
at org.apache.hadoop.security.authentication.client.KerberosAuthenticator.authenticate(KerberosAuthenticator.java:205)
at org.apache.hadoop.security.token.delegation.web.DelegationTokenAuthenticator.authenticate(DelegationTokenAuthenticator.java:128)
at org.apache.hadoop.security.authentication.client.AuthenticatedURL.openConnection(AuthenticatedURL.java:215)
at org.apache.hadoop.security.token.delegation.web.DelegationTokenAuthenticator.doDelegationTokenOperation(DelegationTokenAuthenticator.java:285)
at org.apache.hadoop.security.token.delegation.web.DelegationTokenAuthenticator.getDelegationToken(DelegationTokenAuthenticator.java:166)
at org.apache.hadoop.security.token.delegation.web.DelegationTokenAuthenticatedURL.getDelegationToken(DelegationTokenAuthenticatedURL.java:371)
at org.apache.hadoop.yarn.client.api.impl.TimelineClientImpl$2.run(TimelineClientImpl.java:475)
at org.apache.hadoop.yarn.client.api.impl.TimelineClientImpl$2.run(TimelineClientImpl.java:467)
at java.security.AccessController.doPrivileged(Native Method)
at javax.security.auth.Subject.doAs(Subject.java:415)
at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1657)
at org.apache.hadoop.yarn.client.api.impl.TimelineClientImpl$5.run(TimelineClientImpl.java:567)
... 24 more
Caused by: java.net.SocketTimeoutException: Read timed out
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.read1(BufferedInputStream.java:275)
at java.io.BufferedInputStream.read(BufferedInputStream.java:334)
at sun.net.www.http.HttpClient.parseHTTPHeader(HttpClient.java:690)
at sun.net.www.http.HttpClient.parseHTTP(HttpClient.java:633)
at sun.net.www.protocol.http.HttpURLConnection.getInputStream(HttpURLConnection.java:1325)
at java.net.HttpURLConnection.getResponseCode(HttpURLConnection.java:468)
at org.apache.hadoop.security.authentication.client.KerberosAuthenticator.readToken(KerberosAuthenticator.java:357)
at org.apache.hadoop.security.authentication.client.KerberosAuthenticator.access$300(KerberosAuthenticator.java:54)
at org.apache.hadoop.security.authentication.client.KerberosAuthenticator$1.run(KerberosAuthenticator.java:317)
at org.apache.hadoop.security.authentication.client.KerberosAuthenticator$1.run(KerberosAuthenticator.java:287)
at java.security.AccessController.doPrivileged(Native Method)
at javax.security.auth.Subject.doAs(Subject.java:415)
at org.apache.hadoop.security.authentication.client.KerberosAuthenticator.doSpnegoSequence(KerberosAuthenticator.java:287)
... 36 more

Issue Links

• depends upon: HADOOP-13026 Should not wrap IOExceptions into a AuthenticationException in KerberosAuthenticator