[STREAMING] SPARK-1729. Make Flume pull data from source, rather than the current pu...

examples/src/main/scala/org/apache/spark/examples/streaming/FlumePollingEventCount.scala

@@ -0,0 +1,67 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements.  See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License.  You may obtain a copy of the License at
+ *
+ *    http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.examples.streaming
+
+import org.apache.spark.SparkConf
+import org.apache.spark.storage.StorageLevel
+import org.apache.spark.streaming._
+import org.apache.spark.streaming.flume._
+import org.apache.spark.util.IntParam
+import java.net.InetSocketAddress
+
+/**
+ *  Produces a count of events received from Flume.
+ *
+ *  This should be used in conjunction with the Spark Sink running in a Flume agent. See
+ *  the Spark Streaming programming guide for more details.
+ *
+ *  Usage: FlumePollingEventCount <host> <port>
+ *    `host` is the host on which the Spark Sink is running.
+ *    `port` is the port at which the Spark Sink is listening.
+ *
+ *  To run this example:
+ *    `$ bin/run-example org.apache.spark.examples.streaming.FlumePollingEventCount [host] [port] `
+ */
+object FlumePollingEventCount {
+  def main(args: Array[String]) {
+    if (args.length < 2) {
+      System.err.println(
+        "Usage: FlumePollingEventCount <host> <port>")
+      System.exit(1)
+    }
+
+    StreamingExamples.setStreamingLogLevels()
+
+    val Array(host, IntParam(port)) = args
+
+    val batchInterval = Milliseconds(2000)
+
+    // Create the context and set the batch size
+    val sparkConf = new SparkConf().setAppName("FlumePollingEventCount")
+    val ssc = new StreamingContext(sparkConf, batchInterval)
+
+    // Create a flume stream that polls the Spark Sink running in a Flume agent
+    val stream = FlumeUtils.createPollingStream(ssc, host, port)
+
+    // Print out the count of events received from this server in each batch
+    stream.count().map(cnt => "Received " + cnt + " flume events." ).print()
+
+    ssc.start()
+    ssc.awaitTermination()
+  }
+}

external/flume-sink/pom.xml

@@ -0,0 +1,100 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!--
+  ~ Licensed to the Apache Software Foundation (ASF) under one or more
+  ~ contributor license agreements.  See the NOTICE file distributed with
+  ~ this work for additional information regarding copyright ownership.
+  ~ The ASF licenses this file to You under the Apache License, Version 2.0
+  ~ (the "License"); you may not use this file except in compliance with
+  ~ the License.  You may obtain a copy of the License at
+  ~
+  ~    http://www.apache.org/licenses/LICENSE-2.0
+  ~
+  ~ Unless required by applicable law or agreed to in writing, software
+  ~ distributed under the License is distributed on an "AS IS" BASIS,
+  ~ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+  ~ See the License for the specific language governing permissions and
+  ~ limitations under the License.
+  -->
+
+<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
+  <modelVersion>4.0.0</modelVersion>
+  <parent>
+    <groupId>org.apache.spark</groupId>
+    <artifactId>spark-parent</artifactId>
+    <version>1.1.0-SNAPSHOT</version>
+    <relativePath>../../pom.xml</relativePath>
+  </parent>
+
+  <artifactId>spark-streaming-flume-sink_2.10</artifactId>
+  <properties>
+    <sbt.project.name>streaming-flume-sink</sbt.project.name>
+  </properties>
+
+  <packaging>jar</packaging>
+  <name>Spark Project External Flume Sink</name>
+  <url>http://spark.apache.org/</url>
+  <dependencies>
+    <dependency>
+      <groupId>org.apache.flume</groupId>
+      <artifactId>flume-ng-sdk</artifactId>
+      <version>1.4.0</version>
+      <exclusions>
+        <exclusion>
+          <groupId>io.netty</groupId>
+          <artifactId>netty</artifactId>
+        </exclusion>
+        <exclusion>
+          <groupId>org.apache.thrift</groupId>
+          <artifactId>libthrift</artifactId>
+        </exclusion>
+      </exclusions>
+    </dependency>
+    <dependency>
+      <groupId>org.apache.flume</groupId>
+      <artifactId>flume-ng-core</artifactId>
+      <version>1.4.0</version>
+      <exclusions>
+        <exclusion>
+          <groupId>io.netty</groupId>
+          <artifactId>netty</artifactId>
+        </exclusion>
+        <exclusion>
+          <groupId>org.apache.thrift</groupId>
+          <artifactId>libthrift</artifactId>
+        </exclusion>
+      </exclusions>
+    </dependency>
+    <dependency>
+      <groupId>org.scala-lang</groupId>
+      <artifactId>scala-library</artifactId>
+      <version>2.10.4</version>
+    </dependency>
+  </dependencies>
+  <build>
+    <outputDirectory>target/scala-${scala.binary.version}/classes</outputDirectory>
+    <testOutputDirectory>target/scala-${scala.binary.version}/test-classes</testOutputDirectory>
+    <plugins>
+      <plugin>
+        <groupId>org.scalatest</groupId>
+        <artifactId>scalatest-maven-plugin</artifactId>
+      </plugin>
+      <plugin>
+        <groupId>org.apache.avro</groupId>
+        <artifactId>avro-maven-plugin</artifactId>
+        <version>1.7.3</version>
+        <configuration>
+          <!-- Generate the output in the same directory as the sbt-avro-plugin -->
+          <outputDirectory>${project.basedir}/target/scala-${scala.binary.version}/src_managed/main/compiled_avro</outputDirectory>
+        </configuration>
+        <executions>
+          <execution>
+            <phase>generate-sources</phase>
+            <goals>
+              <goal>idl-protocol</goal>
+            </goals>
+          </execution>
+        </executions>
+      </plugin>
+    </plugins>
+  </build>
+</project>

external/flume-sink/src/main/avro/sparkflume.avdl

@@ -0,0 +1,40 @@
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements.  See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership.  The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License.  You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing,
+ * software distributed under the License is distributed on an
+ * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+ * KIND, either express or implied.  See the License for the
+ * specific language governing permissions and limitations
+ * under the License.
+ */
+
+@namespace("org.apache.spark.streaming.flume.sink")
+
+protocol SparkFlumeProtocol {
+
+  record SparkSinkEvent {
+    map<string> headers;
+    bytes body;
+  }
+
+  record EventBatch {
+    string errorMsg = ""; // If this is empty it is a valid message, else it represents an error
+    string sequenceNumber;
+    array<SparkSinkEvent> events;
+  }
+
+  EventBatch getEventBatch (int n);
+
+  void ack (string sequenceNumber);
+
+  void nack (string sequenceNumber);
+}

external/flume-sink/src/main/scala/org/apache/spark/streaming/flume/sink/Logging.scala

@@ -0,0 +1,125 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements.  See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License.  You may obtain a copy of the License at
+ *
+ *    http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.apache.spark.streaming.flume.sink
+
+import org.slf4j.{Logger, LoggerFactory}
+
+/**
+ * Copy of the org.apache.spark.Logging for being used in the Spark Sink.
+ * The org.apache.spark.Logging is not used so that all of Spark is not brought
+ * in as a dependency.
+ */
+private[sink] trait Logging {
+  // Make the log field transient so that objects with Logging can
+  // be serialized and used on another machine
+  @transient private var log_ : Logger = null
+
+  // Method to get or create the logger for this object
+  protected def log: Logger = {
+    if (log_ == null) {
+      initializeIfNecessary()
+      var className = this.getClass.getName
+      // Ignore trailing $'s in the class names for Scala objects
+      if (className.endsWith("$")) {
+        className = className.substring(0, className.length - 1)
+      }
+      log_ = LoggerFactory.getLogger(className)
+    }
+    log_
+  }
+
+  // Log methods that take only a String
+  protected def logInfo(msg: => String) {
+    if (log.isInfoEnabled) log.info(msg)
+  }
+
+  protected def logDebug(msg: => String) {
+    if (log.isDebugEnabled) log.debug(msg)
+  }
+
+  protected def logTrace(msg: => String) {
+    if (log.isTraceEnabled) log.trace(msg)
+  }
+
+  protected def logWarning(msg: => String) {
+    if (log.isWarnEnabled) log.warn(msg)
+  }
+
+  protected def logError(msg: => String) {
+    if (log.isErrorEnabled) log.error(msg)
+  }
+
+  // Log methods that take Throwables (Exceptions/Errors) too
+  protected def logInfo(msg: => String, throwable: Throwable) {
+    if (log.isInfoEnabled) log.info(msg, throwable)
+  }
+
+  protected def logDebug(msg: => String, throwable: Throwable) {
+    if (log.isDebugEnabled) log.debug(msg, throwable)
+  }
+
+  protected def logTrace(msg: => String, throwable: Throwable) {
+    if (log.isTraceEnabled) log.trace(msg, throwable)
+  }
+
+  protected def logWarning(msg: => String, throwable: Throwable) {
+    if (log.isWarnEnabled) log.warn(msg, throwable)
+  }
+
+  protected def logError(msg: => String, throwable: Throwable) {
+    if (log.isErrorEnabled) log.error(msg, throwable)
+  }
+
+  protected def isTraceEnabled(): Boolean = {
+    log.isTraceEnabled
+  }
+
+  private def initializeIfNecessary() {
+    if (!Logging.initialized) {
+      Logging.initLock.synchronized {
+        if (!Logging.initialized) {
+          initializeLogging()
+        }
+      }
+    }
+  }
+
+  private def initializeLogging() {
+    Logging.initialized = true
+
+    // Force a call into slf4j to initialize it. Avoids this happening from mutliple threads
+    // and triggering this: http://mailman.qos.ch/pipermail/slf4j-dev/2010-April/002956.html
+    log
+  }
+}
+
+private[sink] object Logging {
+  @volatile private var initialized = false
+  val initLock = new Object()
+  try {
+    // We use reflection here to handle the case where users remove the
+    // slf4j-to-jul bridge order to route their logs to JUL.
+    val bridgeClass = Class.forName("org.slf4j.bridge.SLF4JBridgeHandler")
+    bridgeClass.getMethod("removeHandlersForRootLogger").invoke(null)
+    val installed = bridgeClass.getMethod("isInstalled").invoke(null).asInstanceOf[Boolean]
+    if (!installed) {
+      bridgeClass.getMethod("install").invoke(null)
+    }
+  } catch {
+    case e: ClassNotFoundException => // can't log anything yet so just fail silently
+  }
+}