Change spark.local.dir -> SPARK_LOCAL_DIRS

conf/spark-env.sh.template

@@ -5,6 +5,8 @@
 #
 # The following variables can be set in this file:
 # - SPARK_LOCAL_IP, to set the IP address Spark binds to on this node
+# - SPARK_PUBLIC_DNS, to set the public dns name of the driver program
+# - SPARK_LOCAL_DIRS, shuffle directories to use on this node
 # - MESOS_NATIVE_LIBRARY, to point to your libmesos.so if you use Mesos
 # - SPARK_JAVA_OPTS, to set node-specific JVM options for Spark. Note that
 #   we recommend setting app-wide options in the application's driver program.

core/src/main/scala/org/apache/spark/SparkConf.scala

@@ -208,6 +208,15 @@ class SparkConf(loadDefaults: Boolean) extends Cloneable with Logging {
     new SparkConf(false).setAll(settings)
   }
 
+  /** Print any necessary deprecation warnings based on the values set in this configuration. */
+  private[spark] def printDeprecationWarnings() {
+    if (settings.contains("spark.local.dir")) {
+      val msg = "In Spark 1.0 and later spark.local.dir will be overridden by the value set by " +
+        "the cluster manager (via SPARK_LOCAL_DIRS in mesos/standalone and LOCAL_DIRS in YARN)."
+      logWarning(msg)
+    }
+  }
+
   /**
    * Return a string listing all keys and values, one per line. This is useful to print the
    * configuration out for debugging.

core/src/main/scala/org/apache/spark/executor/Executor.scala

@@ -64,9 +64,10 @@ private[spark] class Executor(
   // to what Yarn on this system said was available. This will be used later when SparkEnv
   // created.
   if (java.lang.Boolean.valueOf(
-      System.getProperty("SPARK_YARN_MODE", System.getenv("SPARK_YARN_MODE"))))
-  {
+      System.getProperty("SPARK_YARN_MODE", System.getenv("SPARK_YARN_MODE")))) {
     conf.set("spark.local.dir", getYarnLocalDirs())
+  } else if (sys.env.contains("SPARK_LOCAL_DIRS")) {
+    conf.set("spark.local.dir", sys.env("SPARK_LOCAL_DIRS"))
   }
 
   if (!isLocal) {

docs/configuration.md

@@ -73,6 +73,9 @@ there are at least five properties that you will commonly want to control:
     Directory to use for "scratch" space in Spark, including map output files and RDDs that get stored
     on disk. This should be on a fast, local disk in your system. It can also be a comma-separated
     list of multiple directories on different disks.
+
+    NOTE: In Spark 1.0 and later this will be overriden by SPARK_LOCAL_DIRS (Standalone, Mesos) or
+    LOCAL_DIRS (YARN) envrionment variables set by the cluster manager.
   </td>
 </tr>
 <tr>
@@ -671,8 +674,7 @@ The following variables can be set in `spark-env.sh`:
    Note that applications can also add dependencies for themselves through `SparkContext.addJar` -- we recommend
    doing that when possible.
 * `SPARK_JAVA_OPTS`, to add JVM options. This includes Java options like garbage collector settings and any system
-   properties that you'd like to pass with `-D`. One use case is to set some Spark properties differently on this
-   machine, e.g., `-Dspark.local.dir=/disk1,/disk2`.
+   properties that you'd like to pass with `-D`.
 * Options for the Spark [standalone cluster scripts](spark-standalone.html#cluster-launch-scripts), such as number of cores
   to use on each machine and maximum memory.