Add log4j-spark-container.properties and support SPARK_LOG4J_CONF

pdeyhim · Apr 7, 2014 · 10934b8 · 10934b8
1 parent e74450b
commit 10934b8
Show file tree

Hide file tree

Showing 7 changed files with 38 additions and 15 deletions.
diff --git a/yarn/alpha/src/main/resources/log4j-spark-container.properties b/yarn/alpha/src/main/resources/log4j-spark-container.properties
@@ -0,0 +1,11 @@
+# Set everything to be logged to the console
+log4j.rootCategory=INFO, console
+log4j.appender.console=org.apache.log4j.ConsoleAppender
+log4j.appender.console.target=System.err
+log4j.appender.console.layout=org.apache.log4j.PatternLayout
+log4j.appender.console.layout.ConversionPattern=%d{yy/MM/dd HH:mm:ss} %p %c{1}: %m%n
+
+# Settings to quiet third party logs that are too verbose
+log4j.logger.org.eclipse.jetty=WARN
+log4j.logger.org.apache.spark.repl.SparkIMain$exprTyper=INFO
+log4j.logger.org.apache.spark.repl.SparkILoop$SparkILoopInterpreter=INFO
diff --git a/yarn/alpha/src/main/scala/org/apache/spark/deploy/yarn/ExecutorRunnable.scala b/yarn/alpha/src/main/scala/org/apache/spark/deploy/yarn/ExecutorRunnable.scala
@@ -81,7 +81,8 @@ class ExecutorRunnable(
     credentials.writeTokenStorageToStream(dob)
     ctx.setContainerTokens(ByteBuffer.wrap(dob.getData()))
 
-    val commands = prepareCommand(masterAddress, slaveId, hostname, executorMemory, executorCores)
+    val commands = prepareCommand(masterAddress, slaveId, hostname, executorMemory, executorCores,
+      localResources.contains(ClientBase.LOG4J_PROP))
     logInfo("Setting up executor with commands: " + commands)
     ctx.setCommands(commands)
 

diff --git a/yarn/common/src/main/scala/org/apache/spark/deploy/yarn/ClientBase.scala b/yarn/common/src/main/scala/org/apache/spark/deploy/yarn/ClientBase.scala
@@ -266,11 +266,11 @@ trait ClientBase extends Logging {
       localResources: HashMap[String, LocalResource],
       stagingDir: String): HashMap[String, String] = {
     logInfo("Setting up the launch environment")
-    val log4jConfLocalRes = localResources.getOrElse(ClientBase.LOG4J_PROP, null)
 
     val env = new HashMap[String, String]()
 
-    ClientBase.populateClasspath(yarnConf, sparkConf, log4jConfLocalRes != null, env)
+    ClientBase.populateClasspath(yarnConf, sparkConf, localResources.contains(ClientBase.LOG4J_PROP),
+      env)
     env("SPARK_YARN_MODE") = "true"
     env("SPARK_YARN_STAGING_DIR") = stagingDir
     env("SPARK_USER") = UserGroupInformation.getCurrentUser().getShortUserName()
@@ -344,7 +344,9 @@ trait ClientBase extends Logging {
       JAVA_OPTS += " " + env("SPARK_JAVA_OPTS")
     }
 
-    JAVA_OPTS += " " + YarnSparkHadoopUtil.getLoggingArgsForContainerCommandLine()
+    if (!localResources.contains(ClientBase.LOG4J_PROP)) {
+      JAVA_OPTS += " " + YarnSparkHadoopUtil.getLoggingArgsForContainerCommandLine()
+    }
 
     // Command for the ApplicationMaster
     val commands = List[String](

diff --git a/yarn/common/src/main/scala/org/apache/spark/deploy/yarn/ExecutorRunnableUtil.scala b/yarn/common/src/main/scala/org/apache/spark/deploy/yarn/ExecutorRunnableUtil.scala
@@ -50,7 +50,8 @@ trait ExecutorRunnableUtil extends Logging {
       slaveId: String,
       hostname: String,
       executorMemory: Int,
-      executorCores: Int) = {
+      executorCores: Int,
+      userSpecifiedLogFile: Boolean) = {
     // Extra options for the JVM
     var JAVA_OPTS = ""
     // Set the JVM memory
@@ -62,7 +63,10 @@ trait ExecutorRunnableUtil extends Logging {
 
     JAVA_OPTS += " -Djava.io.tmpdir=" +
       new Path(Environment.PWD.$(), YarnConfiguration.DEFAULT_CONTAINER_TEMP_DIR) + " "
-    JAVA_OPTS += YarnSparkHadoopUtil.getLoggingArgsForContainerCommandLine() + " "
+
+    if (!userSpecifiedLogFile) {
+      JAVA_OPTS += " " + YarnSparkHadoopUtil.getLoggingArgsForContainerCommandLine()
+    }
 
     // Commenting it out for now - so that people can refer to the properties if required. Remove
     // it once cpuset version is pushed out.

diff --git a/yarn/common/src/main/scala/org/apache/spark/deploy/yarn/YarnSparkHadoopUtil.scala b/yarn/common/src/main/scala/org/apache/spark/deploy/yarn/YarnSparkHadoopUtil.scala
@@ -71,13 +71,6 @@ class YarnSparkHadoopUtil extends SparkHadoopUtil {
 
 object YarnSparkHadoopUtil {
   def getLoggingArgsForContainerCommandLine(): String = {
-    "-Dlog4j.configuration=container-log4j.properties " +
-      "-Dhadoop.root.logger=INFO,CLA " +
-      // for yarn/stable:
-      "-Dyarn.app.container.log.filesize=0 " +
-      "-Dyarn.app.container.log.dir=" + ApplicationConstants.LOG_DIR_EXPANSION_VAR + " " +
-      // for yarn/alpha:
-      "-Dyarn.app.mapreduce.container.log.dir=" + ApplicationConstants.LOG_DIR_EXPANSION_VAR + " " +
-      "-Dyarn.app.mapreduce.container.log.filesize=0"
+    "-Dlog4j.configuration=log4j-spark-container.properties"
   }
 }
diff --git a/yarn/stable/src/main/resources/log4j-spark-container.properties b/yarn/stable/src/main/resources/log4j-spark-container.properties
@@ -0,0 +1,11 @@
+# Set everything to be logged to the console
+log4j.rootCategory=INFO, console
+log4j.appender.console=org.apache.log4j.ConsoleAppender
+log4j.appender.console.target=System.err
+log4j.appender.console.layout=org.apache.log4j.PatternLayout
+log4j.appender.console.layout.ConversionPattern=%d{yy/MM/dd HH:mm:ss} %p %c{1}: %m%n
+
+# Settings to quiet third party logs that are too verbose
+log4j.logger.org.eclipse.jetty=WARN
+log4j.logger.org.apache.spark.repl.SparkIMain$exprTyper=INFO
+log4j.logger.org.apache.spark.repl.SparkILoop$SparkILoopInterpreter=INFO
diff --git a/yarn/stable/src/main/scala/org/apache/spark/deploy/yarn/ExecutorRunnable.scala b/yarn/stable/src/main/scala/org/apache/spark/deploy/yarn/ExecutorRunnable.scala
@@ -78,7 +78,8 @@ class ExecutorRunnable(
     credentials.writeTokenStorageToStream(dob)
     ctx.setTokens(ByteBuffer.wrap(dob.getData()))
 
-    val commands = prepareCommand(masterAddress, slaveId, hostname, executorMemory, executorCores)
+    val commands = prepareCommand(masterAddress, slaveId, hostname, executorMemory, executorCores,
+      localResources.contains(ClientBase.LOG4J_PROP))
 
     logInfo("Setting up executor with commands: " + commands)
     ctx.setCommands(commands)