Added registerSource to start() and removeSource to stop(). Wrote a test to check the registration and de-registration

Author: Neelesh Srinivas Salian

streaming/src/main/scala/org/apache/spark/streaming/StreamingContext.scala

@@ -192,11 +192,8 @@ class StreamingContext private[streaming] (
       None
     }
 
-  /** Register streaming source to metrics system */
+  /* Initializing a streamingSource to register metrics */
   private val streamingSource = new StreamingSource(this)
-  assert(env != null)
-  assert(env.metricsSystem != null)
-  env.metricsSystem.registerSource(streamingSource)
 
   private var state: StreamingContextState = INITIALIZED
 
@@ -606,6 +603,9 @@ class StreamingContext private[streaming] (
         }
         shutdownHookRef = Utils.addShutdownHook(
           StreamingContext.SHUTDOWN_HOOK_PRIORITY)(stopOnShutdown)
+        // Registering Streaming Metrics at the start of the StreamingContext
+        assert(env.metricsSystem != null)
+        env.metricsSystem.registerSource(streamingSource)
         uiTab.foreach(_.attach())
         logInfo("StreamingContext started")
       case ACTIVE =>
@@ -682,6 +682,8 @@ class StreamingContext private[streaming] (
           logWarning("StreamingContext has already been stopped")
         case ACTIVE =>
           scheduler.stop(stopGracefully)
+          // Removing the streamingSource to de-register the metrics on stop()
+          env.metricsSystem.removeSource(streamingSource)
           uiTab.foreach(_.detach())
           StreamingContext.setActiveContext(null)
           waiter.notifyStop()

streaming/src/test/scala/org/apache/spark/streaming/StreamingContextSuite.scala

@@ -33,8 +33,12 @@ import org.apache.spark.storage.StorageLevel
 import org.apache.spark.streaming.dstream.DStream
 import org.apache.spark.streaming.receiver.Receiver
 import org.apache.spark.util.Utils
-import org.apache.spark.{Logging, SparkConf, SparkContext, SparkException, SparkFunSuite}
-
+import org.apache.spark.{Logging, SparkConf, SparkContext, SparkFunSuite}
+import org.apache.spark.metrics.MetricsSystem
+import org.apache.spark.metrics.source.Source
+import org.scalatest.{PrivateMethodTester, Assertions, BeforeAndAfter}
+import org.apache.spark.{Logging, SparkConf, SparkContext, SparkFunSuite}
+import scala.collection.mutable.ArrayBuffer
 
 class StreamingContextSuite extends SparkFunSuite with BeforeAndAfter with Timeouts with Logging {
 
@@ -299,6 +303,26 @@ class StreamingContextSuite extends SparkFunSuite with BeforeAndAfter with Timeo
     Thread.sleep(100)
   }
 
+  test ("registering and de-registering of streamingSource") {
+    val conf = new SparkConf().setMaster(master).setAppName(appName)
+    ssc = new StreamingContext(conf, batchDuration)
+    assert(ssc.getState() === StreamingContextState.INITIALIZED)
+    addInputStream(ssc).register()
+    ssc.start()
+
+    val sources = StreamingContextSuite.getSources(ssc.env.metricsSystem)
+    val streamingSource = StreamingContextSuite.getStreamingSource(ssc)
+    assert(sources.contains(streamingSource))
+    assert(ssc.getState() === StreamingContextState.ACTIVE)
+    Thread.sleep(100)
+
+    ssc.stop()
+    val sourcesAfterStop = StreamingContextSuite.getSources(ssc.env.metricsSystem)
+    val streamingSourceAfterStop = StreamingContextSuite.getStreamingSource(ssc)
+    assert(ssc.getState() === StreamingContextState.STOPPED)
+    assert(!sourcesAfterStop.contains(streamingSourceAfterStop))
+  }
+
   test("awaitTermination") {
     ssc = new StreamingContext(master, appName, batchDuration)
     val inputStream = addInputStream(ssc)
@@ -811,3 +835,19 @@ package object testPackage extends Assertions {
     }
   }
 }
+
+/**
+ * Helper methods for testing StreamingContextSuite
+ * This includes methods to access private methods and fields in StreamingContext and MetricsSystem
+ */
+
+private object StreamingContextSuite extends PrivateMethodTester {
+  private val _sources = PrivateMethod[ArrayBuffer[Source]]('sources)
+  private def getSources(metricsSystem: MetricsSystem): ArrayBuffer[Source] = {
+    metricsSystem.invokePrivate(_sources())
+  }
+  private val _streamingSource = PrivateMethod[StreamingSource]('streamingSource)
+  private def getStreamingSource(streamingContext: StreamingContext): StreamingSource = {
+    streamingContext.invokePrivate(_streamingSource())
+  }
+}