org.apache.flink.runtime.io.network.partition.consumer.InputGate Maven / Gradle / Ivy
/*
* 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.flink.runtime.io.network.partition.consumer;
import org.apache.flink.runtime.event.TaskEvent;
import java.io.IOException;
import java.util.Optional;
/**
* An input gate consumes one or more partitions of a single produced intermediate result.
*
* Each intermediate result is partitioned over its producing parallel subtasks; each of these
* partitions is furthermore partitioned into one or more subpartitions.
*
*
As an example, consider a map-reduce program, where the map operator produces data and the
* reduce operator consumes the produced data.
*
*
{@code
* +-----+ +---------------------+ +--------+
* | Map | = produce => | Intermediate Result | <= consume = | Reduce |
* +-----+ +---------------------+ +--------+
* }
*
* When deploying such a program in parallel, the intermediate result will be partitioned over its
* producing parallel subtasks; each of these partitions is furthermore partitioned into one or more
* subpartitions.
*
*
{@code
* Intermediate result
* +-----------------------------------------+
* | +----------------+ | +-----------------------+
* +-------+ | +-------------+ +=> | Subpartition 1 | | <=======+=== | Input Gate | Reduce 1 |
* | Map 1 | ==> | | Partition 1 | =| +----------------+ | | +-----------------------+
* +-------+ | +-------------+ +=> | Subpartition 2 | | <==+ |
* | +----------------+ | | | Subpartition request
* | | | |
* | +----------------+ | | |
* +-------+ | +-------------+ +=> | Subpartition 1 | | <==+====+
* | Map 2 | ==> | | Partition 2 | =| +----------------+ | | +-----------------------+
* +-------+ | +-------------+ +=> | Subpartition 2 | | <==+======== | Input Gate | Reduce 2 |
* | +----------------+ | +-----------------------+
* +-----------------------------------------+
* }
*
* In the above example, two map subtasks produce the intermediate result in parallel, resulting
* in two partitions (Partition 1 and 2). Each of these partitions is further partitioned into two
* subpartitions -- one for each parallel reduce subtask. As shown in the Figure, each reduce task
* will have an input gate attached to it. This will provide its input, which will consist of one
* subpartition from each partition of the intermediate result.
*/
public interface InputGate {
int getNumberOfInputChannels();
String getOwningTaskName();
boolean isFinished();
void requestPartitions() throws IOException, InterruptedException;
/**
* Blocking call waiting for next {@link BufferOrEvent}.
*
* @return {@code Optional.empty()} if {@link #isFinished()} returns true.
*/
Optional getNextBufferOrEvent() throws IOException, InterruptedException;
/**
* Poll the {@link BufferOrEvent}.
*
* @return {@code Optional.empty()} if there is no data to return or if {@link #isFinished()} returns true.
*/
Optional pollNextBufferOrEvent() throws IOException, InterruptedException;
void sendTaskEvent(TaskEvent event) throws IOException;
void registerListener(InputGateListener listener);
int getPageSize();
}