Github user tdas commented on a diff in the pull request: https://github.com/apache/spark/pull/5680#discussion_r29408816 --- Diff: streaming/src/main/scala/org/apache/spark/streaming/scheduler/InputInfoTracker.scala --- @@ -0,0 +1,74 @@ +/* + * 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.scheduler + +import scala.collection.mutable + +import org.apache.spark.Logging +import org.apache.spark.streaming.{Time, StreamingContext} + +/** To track the information of input stream at specified batch time. */ +case class InputInfo(batchTime: Time, inputStreamId: Int, numRecords: Long) + +/** + * This class manages all the input streams as well as their input data statistics. The information + * will output to StreamingListener to better monitoring. + */ +private[streaming] class InputInfoTracker(ssc: StreamingContext) extends Logging { + + /** Track all the input streams registered in DStreamGraph */ + val inputStreams = ssc.graph.getInputStreams() + /** Track all the id of input streams registered in DStreamGraph */ + val inputStreamIds = inputStreams.map(_.id) + + // Map to track all the InputInfo related to specific batch time and input stream. + private val batchTimeToInputInfos = new mutable.HashMap[Time, mutable.HashMap[Int, InputInfo]] + + /** Report the input information with batch time to the tracker */ + def reportInfo(batchTime: Time, inputInfo: InputInfo): Unit = synchronized { + val inputInfos = batchTimeToInputInfos.getOrElseUpdate(batchTime, + new mutable.HashMap[Int, InputInfo]()) + + if (inputInfos.contains(inputInfo.inputStreamId)) { + throw new IllegalStateException(s"Input stream ${inputInfo.inputStreamId}} for batch" + + s"$batchTime is already added into InputInfoTracker, this is a illegal state") + } + inputInfos += ((inputInfo.inputStreamId, inputInfo)) + } + + /** Get the all the input stream's information of specified batch time */ + def getInfo(batchTime: Time): Map[Int, InputInfo] = synchronized { + val inputInfos = batchTimeToInputInfos.get(batchTime) + // Convert mutable HashMap to immutable Map for the caller + inputInfos.map(_.toMap).getOrElse(Map[Int, InputInfo]()) + } + + /** Get the input information of specified batch time and input stream id */ + def getInfoOfBatchAndStream(batchTime: Time, inputStreamId: Int --- End diff -- This is not used anywhere other than tests, is this necessary?
--- 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