Github user cfregly commented on a diff in the pull request: https://github.com/apache/spark/pull/6147#discussion_r30775370 --- Diff: extras/kinesis-asl/src/main/scala/org/apache/spark/streaming/kinesis/KinesisUtils.scala --- @@ -79,19 +181,116 @@ object KinesisUtils { * per Kinesis' limit of 24 hours * (InitialPositionInStream.TRIM_HORIZON) or * the tip of the stream (InitialPositionInStream.LATEST). - * @param storageLevel Storage level to use for storing the received objects + * @param storageLevel Storage level to use for storing the received objects. + * StorageLevel.MEMORY_AND_DISK_2 is recommended. + */ + def createStream( + jssc: JavaStreamingContext, + kinesisAppName: String, + streamName: String, + endpointUrl: String, + regionName: String, + initialPositionInStream: InitialPositionInStream, + checkpointInterval: Duration, + storageLevel: StorageLevel + ): JavaReceiverInputDStream[Array[Byte]] = { + createStream(jssc.ssc, kinesisAppName, streamName, endpointUrl, regionName, + initialPositionInStream, checkpointInterval, storageLevel) + } + + /** + * Create an input stream that pulls messages from a Kinesis stream. + * This uses the Kinesis Client Library (KCL) to pull messages from Kinesis. * - * @return JavaReceiverInputDStream[Array[Byte]] + * Note: + * The given AWS credentials will get saved in DStream checkpoints if checkpointing + * is enabled. Make sure that your checkpoint directory is secure. + * + * @param jssc Java StreamingContext object + * @param kinesisAppName Kinesis application name used by the Kinesis Client Library + * (KCL) to update DynamoDB + * @param streamName Kinesis stream name + * @param endpointUrl Url of Kinesis service (e.g., https://kinesis.us-east-1.amazonaws.com) + * @param regionName Name of region used by the Kinesis Client Library (KCL) to update + * DynamoDB (lease coordination and checkpointing) and CloudWatch (metrics) + * @param awsAccessKeyId AWS AccessKeyId (if null, will use DefaultAWSCredentialsProviderChain) + * @param awsSecretKey AWS SecretKey (if null, will use DefaultAWSCredentialsProviderChain) + * @param checkpointInterval Checkpoint interval for Kinesis checkpointing. + * See the Kinesis Spark Streaming documentation for more + * details on the different types of checkpoints. + * @param initialPositionInStream In the absence of Kinesis checkpoint info, this is the + * worker's initial starting position in the stream. + * The values are either the beginning of the stream + * per Kinesis' limit of 24 hours + * (InitialPositionInStream.TRIM_HORIZON) or + * the tip of the stream (InitialPositionInStream.LATEST). + * @param storageLevel Storage level to use for storing the received objects. + * StorageLevel.MEMORY_AND_DISK_2 is recommended. */ - @Experimental def createStream( - jssc: JavaStreamingContext, - streamName: String, - endpointUrl: String, + jssc: JavaStreamingContext, + kinesisAppName: String, + streamName: String, + endpointUrl: String, + regionName: String, + initialPositionInStream: InitialPositionInStream, + checkpointInterval: Duration, + storageLevel: StorageLevel, + awsAccessKeyId: String, + awsSecretKey: String + ): JavaReceiverInputDStream[Array[Byte]] = { + createStream(jssc.ssc, kinesisAppName, streamName, endpointUrl, regionName, + initialPositionInStream, checkpointInterval, storageLevel, awsAccessKeyId, awsSecretKey) + } + + /** + * Create an input stream that pulls messages from a Kinesis stream. + * This uses the Kinesis Client Library (KCL) to pull messages from Kinesis. + * + * Note: + * - The AWS credentials will be discovered using the DefaultAWSCredentialsProviderChain + * on the workers. See AWS documentation to understand how DefaultAWSCredentialsProviderChain + * gets AWS credentials. + * - The region of the `endpointUrl` will be used for DynamoDB and CloudWatch. + * - The Kinesis application name used by the Kinesis Client Library (KCL) will be the app name in + * [[org.apache.spark.SparkConf]]. + * + * @param jssc Java StreamingContext object + * @param streamName Kinesis stream name + * @param endpointUrl Endpoint url of Kinesis service + * (e.g., https://kinesis.us-east-1.amazonaws.com) + * @param checkpointInterval Checkpoint interval for Kinesis checkpointing. + * See the Kinesis Spark Streaming documentation for more + * details on the different types of checkpoints. + * @param initialPositionInStream In the absence of Kinesis checkpoint info, this is the + * worker's initial starting position in the stream. + * The values are either the beginning of the stream + * per Kinesis' limit of 24 hours + * (InitialPositionInStream.TRIM_HORIZON) or + * the tip of the stream (InitialPositionInStream.LATEST). + * @param storageLevel Storage level to use for storing the received objects + * StorageLevel.MEMORY_AND_DISK_2 is recommended. + */ + @deprecated("use other forms of createStream", "1.4.0") + def createStream( + jssc: JavaStreamingContext, + streamName: String, + endpointUrl: String, checkpointInterval: Duration, initialPositionInStream: InitialPositionInStream, - storageLevel: StorageLevel): JavaReceiverInputDStream[Array[Byte]] = { - jssc.receiverStream(new KinesisReceiver(jssc.ssc.sc.appName, streamName, - endpointUrl, checkpointInterval, initialPositionInStream, storageLevel)) + storageLevel: StorageLevel + ): JavaReceiverInputDStream[Array[Byte]] = { + createStream( + jssc.ssc, streamName, endpointUrl, checkpointInterval, initialPositionInStream, storageLevel) + } + + private def getRegionByEndpoint(endpointUrl: String): String = { + RegionUtils.getRegionByEndpoint(endpointUrl).getName() + } + + private def validateRegion(regionName: String): String = { --- End diff -- add scala doc to describe the potential for IllegalArgumentException? /** */
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org