Fix #SPARK-1149 Bad partitioners can cause Spark to hang

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

@@ -852,6 +852,10 @@ class SparkContext(
       partitions: Seq[Int],
       allowLocal: Boolean,
       resultHandler: (Int, U) => Unit) {
+    // TODO: All RDDs have continuous index space. How to ensure this?
+    partitions.foreach{ p =>
+      require(p >= 0 && p < rdd.partitions.size, s"Invalid partition requested: $p")
+    }
     val callSite = getCallSite
     val cleanedFunc = clean(func)
     logInfo("Starting job: " + callSite)
@@ -955,6 +959,9 @@ class SparkContext(
       resultHandler: (Int, U) => Unit,
       resultFunc: => R): SimpleFutureAction[R] =
   {
+    partitions.foreach{ p =>
+      require(p >= 0 && p < rdd.partitions.size, s"Invalid partition requested: $p")
+    }
     val cleanF = clean(processPartition)
     val callSite = getCallSite
     val waiter = dagScheduler.submitJob(

core/src/test/scala/org/apache/spark/rdd/PairRDDFunctionsSuite.scala

@@ -373,6 +373,22 @@ class PairRDDFunctionsSuite extends FunSuite with SharedSparkContext {
     assert(shuffled.lookup(5) === Seq(6,7))
     assert(shuffled.lookup(-1) === Seq())
   }
+
+  test("lookup with bad partitioner") {
+    val pairs = sc.parallelize(Array((1,2), (3,4), (5,6), (5,7)))
+
+    val p = new Partitioner {
+      def numPartitions: Int = 2
+
+      def getPartition(key: Any): Int = key.hashCode() % 2
+    }
+    val shuffled = pairs.partitionBy(p)
+
+    assert(shuffled.partitioner === Some(p))
+    assert(shuffled.lookup(1) === Seq(2))
+    intercept[IllegalArgumentException] {shuffled.lookup(-1)}
+  }
+
 }
 
 /*