diff options
| -rw-r--r-- | docs/building-spark.md | 6 | ||||
| -rw-r--r-- | docs/streaming-flume-integration.md | 2 | ||||
| -rw-r--r-- | external/flume/src/main/scala/org/apache/spark/streaming/flume/FlumeUtils.scala | 8 |
3 files changed, 4 insertions, 12 deletions
diff --git a/docs/building-spark.md b/docs/building-spark.md index 088da7da49..4c3988e819 100644 --- a/docs/building-spark.md +++ b/docs/building-spark.md @@ -111,9 +111,9 @@ To produce a Spark package compiled with Scala 2.11, use the `-Dscala-2.11` prop dev/change-version-to-2.11.sh mvn -Pyarn -Phadoop-2.4 -Dscala-2.11 -DskipTests clean package -Scala 2.11 support in Spark is experimental and does not support a few features. -Specifically, Spark's external Kafka library and JDBC component are not yet -supported in Scala 2.11 builds. +Scala 2.11 support in Spark does not support a few features due to dependencies +which are themselves not Scala 2.11 ready. Specifically, Spark's external +Kafka library and JDBC component are not yet supported in Scala 2.11 builds. # Spark Tests in Maven diff --git a/docs/streaming-flume-integration.md b/docs/streaming-flume-integration.md index ac01dd3d80..40e17246fe 100644 --- a/docs/streaming-flume-integration.md +++ b/docs/streaming-flume-integration.md @@ -64,7 +64,7 @@ configuring Flume agents. 3. **Deploying:** Package `spark-streaming-flume_{{site.SCALA_BINARY_VERSION}}` and its dependencies (except `spark-core_{{site.SCALA_BINARY_VERSION}}` and `spark-streaming_{{site.SCALA_BINARY_VERSION}}` which are provided by `spark-submit`) into the application JAR. Then use `spark-submit` to launch your application (see [Deploying section](streaming-programming-guide.html#deploying-applications) in the main programming guide). -## Approach 2 (Experimental): Pull-based Approach using a Custom Sink +## Approach 2: Pull-based Approach using a Custom Sink Instead of Flume pushing data directly to Spark Streaming, this approach runs a custom Flume sink that allows the following. - Flume pushes data into the sink, and the data stays buffered. diff --git a/external/flume/src/main/scala/org/apache/spark/streaming/flume/FlumeUtils.scala b/external/flume/src/main/scala/org/apache/spark/streaming/flume/FlumeUtils.scala index 4b732c1592..44dec45c22 100644 --- a/external/flume/src/main/scala/org/apache/spark/streaming/flume/FlumeUtils.scala +++ b/external/flume/src/main/scala/org/apache/spark/streaming/flume/FlumeUtils.scala @@ -19,7 +19,6 @@ package org.apache.spark.streaming.flume import java.net.InetSocketAddress -import org.apache.spark.annotation.Experimental import org.apache.spark.storage.StorageLevel import org.apache.spark.streaming.StreamingContext import org.apache.spark.streaming.api.java.{JavaReceiverInputDStream, JavaStreamingContext} @@ -121,7 +120,6 @@ object FlumeUtils { * @param port Port of the host at which the Spark Sink is listening * @param storageLevel Storage level to use for storing the received objects */ - @Experimental def createPollingStream( ssc: StreamingContext, hostname: String, @@ -138,7 +136,6 @@ object FlumeUtils { * @param addresses List of InetSocketAddresses representing the hosts to connect to. * @param storageLevel Storage level to use for storing the received objects */ - @Experimental def createPollingStream( ssc: StreamingContext, addresses: Seq[InetSocketAddress], @@ -159,7 +156,6 @@ object FlumeUtils { * result in this stream using more threads * @param storageLevel Storage level to use for storing the received objects */ - @Experimental def createPollingStream( ssc: StreamingContext, addresses: Seq[InetSocketAddress], @@ -178,7 +174,6 @@ object FlumeUtils { * @param hostname Hostname of the host on which the Spark Sink is running * @param port Port of the host at which the Spark Sink is listening */ - @Experimental def createPollingStream( jssc: JavaStreamingContext, hostname: String, @@ -195,7 +190,6 @@ object FlumeUtils { * @param port Port of the host at which the Spark Sink is listening * @param storageLevel Storage level to use for storing the received objects */ - @Experimental def createPollingStream( jssc: JavaStreamingContext, hostname: String, @@ -212,7 +206,6 @@ object FlumeUtils { * @param addresses List of InetSocketAddresses on which the Spark Sink is running. * @param storageLevel Storage level to use for storing the received objects */ - @Experimental def createPollingStream( jssc: JavaStreamingContext, addresses: Array[InetSocketAddress], @@ -233,7 +226,6 @@ object FlumeUtils { * result in this stream using more threads * @param storageLevel Storage level to use for storing the received objects */ - @Experimental def createPollingStream( jssc: JavaStreamingContext, addresses: Array[InetSocketAddress], |