MAPREDUCE-4458. Warn if java.library.path is used for AM or Task (Robert Parker via jeagles)

git-svn-id: https://svn.apache.org/repos/asf/hadoop/common/trunk@1435386 13f79535-47bb-0310-9956-ffa450edef68

hadoop-mapreduce-project/CHANGES.txt

@@ -652,6 +652,9 @@ Release 0.23.7 - UNRELEASED
 
   BUG FIXES
 
+    MAPREDUCE-4458. Warn if java.library.path is used for AM or Task
+    (Robert Parker via jeagles)
+
 Release 0.23.6 - UNRELEASED
 
   INCOMPATIBLE CHANGES

hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/MRJobConfig.java

@@ -530,6 +530,9 @@ public interface MRJobConfig {
   public static final String MR_AM_ENV =
       MR_AM_PREFIX + "env";
   
+  public static final String MR_AM_ADMIN_USER_ENV =
+      MR_AM_PREFIX + "admin.user.env";
+  
   public static final String MAPRED_MAP_ADMIN_JAVA_OPTS =
       "mapreduce.admin.map.child.java.opts";
 

hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/resources/mapred-default.xml

@@ -857,6 +857,17 @@
   </description>
 </property>
 
+<property>
+  <name>yarn.app.mapreduce.am.admin.user.env</name>
+  <value></value>
+  <description> Environment variables for the MR App Master 
+  processes for admin purposes. These values are set first and can be 
+  overridden by the user env (yarn.app.mapreduce.am.env) Example :
+  1) A=foo  This will set the env variable A to foo
+  2) B=$B:c This is inherit app master's B env variable.  
+  </description>
+</property>
+
 <property>
   <name>yarn.app.mapreduce.am.command-opts</name>
   <value>-Xmx1024m</value>

hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-jobclient/src/main/java/org/apache/hadoop/mapred/YARNRunner.java

@@ -101,7 +101,7 @@ public class YARNRunner implements ClientProtocol {
   private Configuration conf;
   private final FileContext defaultFileContext;
   
-  /* usually is false unless the jobclient getdelegation token is 
+  /* usually is false unless the jobclient get delegation token is 
    *  called. This is a hack wherein we do return a token from RM 
    *  on getDelegationtoken but due to the restricted api on jobclient
    *  we just add a job history DT token when submitting a job.
@@ -165,12 +165,12 @@ public class YARNRunner implements ClientProtocol {
   @Override
   public TaskTrackerInfo[] getActiveTrackers() throws IOException,
       InterruptedException {
-	  return resMgrDelegate.getActiveTrackers();
+    return resMgrDelegate.getActiveTrackers();
   }
 
   @Override
   public JobStatus[] getAllJobs() throws IOException, InterruptedException {
-   return resMgrDelegate.getAllJobs();
+    return resMgrDelegate.getAllJobs();
   }
 
   @Override
@@ -394,14 +394,31 @@ public class YARNRunner implements ClientProtocol {
         MRJobConfig.MR_AM_LOG_LEVEL, MRJobConfig.DEFAULT_MR_AM_LOG_LEVEL);
     MRApps.addLog4jSystemProperties(logLevel, logSize, vargs);
 
+    // Check for Java Lib Path usage in MAP and REDUCE configs
+    warnForJavaLibPath(conf.get(MRJobConfig.MAP_JAVA_OPTS,""), "map", 
+        MRJobConfig.MAP_JAVA_OPTS, MRJobConfig.MAP_ENV);
+    warnForJavaLibPath(conf.get(MRJobConfig.MAPRED_MAP_ADMIN_JAVA_OPTS,""), "map", 
+        MRJobConfig.MAPRED_MAP_ADMIN_JAVA_OPTS, MRJobConfig.MAPRED_ADMIN_USER_ENV);
+    warnForJavaLibPath(conf.get(MRJobConfig.REDUCE_JAVA_OPTS,""), "reduce", 
+        MRJobConfig.REDUCE_JAVA_OPTS, MRJobConfig.REDUCE_ENV);
+    warnForJavaLibPath(conf.get(MRJobConfig.MAPRED_REDUCE_ADMIN_JAVA_OPTS,""), "reduce", 
+        MRJobConfig.MAPRED_REDUCE_ADMIN_JAVA_OPTS, MRJobConfig.MAPRED_ADMIN_USER_ENV);   
+
     // Add AM admin command opts before user command opts
     // so that it can be overridden by user
-    vargs.add(conf.get(MRJobConfig.MR_AM_ADMIN_COMMAND_OPTS,
+    String mrAppMasterAdminOptions = conf.get(MRJobConfig.MR_AM_ADMIN_COMMAND_OPTS,
-        MRJobConfig.DEFAULT_MR_AM_ADMIN_COMMAND_OPTS));
+        MRJobConfig.DEFAULT_MR_AM_ADMIN_COMMAND_OPTS);
+    warnForJavaLibPath(mrAppMasterAdminOptions, "app master", 
+        MRJobConfig.MR_AM_ADMIN_COMMAND_OPTS, MRJobConfig.MR_AM_ADMIN_USER_ENV);
+    vargs.add(mrAppMasterAdminOptions);
+    
+    // Add AM user command opts
+    String mrAppMasterUserOptions = conf.get(MRJobConfig.MR_AM_COMMAND_OPTS,
+        MRJobConfig.DEFAULT_MR_AM_COMMAND_OPTS);
+    warnForJavaLibPath(mrAppMasterUserOptions, "app master", 
+        MRJobConfig.MR_AM_COMMAND_OPTS, MRJobConfig.MR_AM_ENV);
+    vargs.add(mrAppMasterUserOptions);
     
-    vargs.add(conf.get(MRJobConfig.MR_AM_COMMAND_OPTS,
-        MRJobConfig.DEFAULT_MR_AM_COMMAND_OPTS));
-
     vargs.add(MRJobConfig.APPLICATION_MASTER_CLASS);
     vargs.add("1>" + ApplicationConstants.LOG_DIR_EXPANSION_VAR +
         Path.SEPARATOR + ApplicationConstants.STDOUT);
@@ -425,6 +442,9 @@ public class YARNRunner implements ClientProtocol {
     Map<String, String> environment = new HashMap<String, String>();
     MRApps.setClasspath(environment, conf);
     
+    // Setup the environment variables for Admin first
+    MRApps.setEnvFromInputString(environment, 
+        conf.get(MRJobConfig.MR_AM_ADMIN_USER_ENV));
     // Setup the environment variables (LD_LIBRARY_PATH, etc)
     MRApps.setEnvFromInputString(environment, 
         conf.get(MRJobConfig.MR_AM_ENV));
@@ -582,4 +602,15 @@ public class YARNRunner implements ClientProtocol {
       throws IOException {
     return clientCache.getClient(jobID).getLogFilePath(jobID, taskAttemptID);
   }
+
+  private static void warnForJavaLibPath(String opts, String component, 
+      String javaConf, String envConf) {
+    if (opts != null && opts.contains("-Djava.library.path")) {
+      LOG.warn("Usage of -Djava.library.path in " + javaConf + " can cause " +
+               "programs to no longer function if hadoop native libraries " +
+               "are used. These values should be set as part of the " +
+               "LD_LIBRARY_PATH in the " + component + " JVM env using " +
+               envConf + " config settings.");
+    }
+  }
 }

hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-jobclient/src/test/java/org/apache/hadoop/mapred/TestYARNRunner.java

@@ -25,6 +25,7 @@ import static org.mockito.Mockito.spy;
 import static org.mockito.Mockito.verify;
 import static org.mockito.Mockito.when;
 
+import java.io.ByteArrayOutputStream;
 import java.io.File;
 import java.io.FileOutputStream;
 import java.io.IOException;
@@ -83,6 +84,11 @@ import org.apache.hadoop.yarn.api.records.YarnApplicationState;
 import org.apache.hadoop.yarn.conf.YarnConfiguration;
 import org.apache.hadoop.yarn.factories.RecordFactory;
 import org.apache.hadoop.yarn.factory.providers.RecordFactoryProvider;
+import org.apache.log4j.Appender;
+import org.apache.log4j.Layout;
+import org.apache.log4j.Logger;
+import org.apache.log4j.SimpleLayout;
+import org.apache.log4j.WriterAppender;
 import org.junit.Before;
 import org.junit.Test;
 import org.mockito.invocation.InvocationOnMock;
@@ -189,7 +195,7 @@ public class TestYARNRunner extends TestCase {
 
   @Test
   public void testResourceMgrDelegate() throws Exception {
-    /* we not want a mock of resourcemgr deleagte */
+    /* we not want a mock of resource mgr delegate */
     final ClientRMProtocol clientRMProtocol = mock(ClientRMProtocol.class);
     ResourceMgrDelegate delegate = new ResourceMgrDelegate(conf) {
       @Override
@@ -256,6 +262,9 @@ public class TestYARNRunner extends TestCase {
   
   @Test
   public void testHistoryServerToken() throws Exception {
+    //Set the master principal in the config
+    conf.set(YarnConfiguration.RM_PRINCIPAL,"foo@LOCAL");
+
     final String masterPrincipal = Master.getMasterPrincipal(conf);
 
     final MRClientProtocol hsProxy = mock(MRClientProtocol.class);
@@ -265,7 +274,7 @@ public class TestYARNRunner extends TestCase {
             GetDelegationTokenRequest request =
                 (GetDelegationTokenRequest)invocation.getArguments()[0];
             // check that the renewer matches the cluster's RM principal
-            assertEquals(request.getRenewer(), masterPrincipal);
+            assertEquals(masterPrincipal, request.getRenewer() );
 
             DelegationToken token =
                 recordFactory.newRecordInstance(DelegationToken.class);
@@ -357,4 +366,53 @@ public class TestYARNRunner extends TestCase {
       assertTrue("AM admin command opts is after user command opts.", adminIndex < userIndex);
     }
   }
+  @Test
+  public void testWarnCommandOpts() throws Exception {
+    Logger logger = Logger.getLogger(YARNRunner.class);
+    
+    ByteArrayOutputStream bout = new ByteArrayOutputStream();
+    Layout layout = new SimpleLayout();
+    Appender appender = new WriterAppender(layout, bout);
+    logger.addAppender(appender);
+    
+    JobConf jobConf = new JobConf();
+    
+    jobConf.set(MRJobConfig.MR_AM_ADMIN_COMMAND_OPTS, "-Djava.net.preferIPv4Stack=true -Djava.library.path=foo");
+    jobConf.set(MRJobConfig.MR_AM_COMMAND_OPTS, "-Xmx1024m -Djava.library.path=bar");
+    
+    YARNRunner yarnRunner = new YARNRunner(jobConf);
+    
+    File jobxml = new File(testWorkDir, MRJobConfig.JOB_CONF_FILE);
+    OutputStream out = new FileOutputStream(jobxml);
+    conf.writeXml(out);
+    out.close();
+    
+    File jobsplit = new File(testWorkDir, MRJobConfig.JOB_SPLIT);
+    out = new FileOutputStream(jobsplit);
+    out.close();
+    
+    File jobsplitmetainfo = new File(testWorkDir, MRJobConfig.JOB_SPLIT_METAINFO);
+    out = new FileOutputStream(jobsplitmetainfo);
+    out.close();
+    
+    File appTokens = new File(testWorkDir, MRJobConfig.APPLICATION_TOKENS_FILE);
+    out = new FileOutputStream(appTokens);
+    out.close();
+    
+    @SuppressWarnings("unused")
+    ApplicationSubmissionContext submissionContext = 
+        yarnRunner.createApplicationSubmissionContext(jobConf, testWorkDir.toString(), new Credentials());
+   
+    String logMsg = bout.toString();
+    assertTrue(logMsg.contains("WARN - Usage of -Djava.library.path in " + 
+    		"yarn.app.mapreduce.am.admin-command-opts can cause programs to no " +
+        "longer function if hadoop native libraries are used. These values " + 
+    		"should be set as part of the LD_LIBRARY_PATH in the app master JVM " +
+        "env using yarn.app.mapreduce.am.admin.user.env config settings."));
+    assertTrue(logMsg.contains("WARN - Usage of -Djava.library.path in " + 
+        "yarn.app.mapreduce.am.command-opts can cause programs to no longer " +
+        "function if hadoop native libraries are used. These values should " +
+        "be set as part of the LD_LIBRARY_PATH in the app master JVM env " +
+        "using yarn.app.mapreduce.am.env config settings."));
+  }
 }