zhuzhurk commented on a change in pull request #11770: [FLINK-17014][runtime] Implement PipelinedRegionSchedulingStrategy URL: https://github.com/apache/flink/pull/11770#discussion_r409983090
########## File path: flink-runtime/src/main/java/org/apache/flink/runtime/scheduler/strategy/PipelinedRegionSchedulingStrategy.java ########## @@ -0,0 +1,166 @@ +/* + * 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.scheduler.strategy; + +import org.apache.flink.runtime.execution.ExecutionState; +import org.apache.flink.runtime.io.network.partition.ResultPartitionType; +import org.apache.flink.runtime.jobgraph.IntermediateDataSetID; +import org.apache.flink.runtime.jobgraph.IntermediateResultPartitionID; +import org.apache.flink.runtime.scheduler.DeploymentOption; +import org.apache.flink.runtime.scheduler.ExecutionVertexDeploymentOption; +import org.apache.flink.runtime.scheduler.SchedulerOperations; +import org.apache.flink.util.IterableUtils; + +import java.util.HashMap; +import java.util.HashSet; +import java.util.List; +import java.util.Map; +import java.util.Set; +import java.util.stream.Collectors; + +import static org.apache.flink.util.Preconditions.checkNotNull; +import static org.apache.flink.util.Preconditions.checkState; + +/** + * {@link SchedulingStrategy} instance which schedules tasks in granularity of pipelined regions. + */ +public class PipelinedRegionSchedulingStrategy implements SchedulingStrategy { + + private final SchedulerOperations schedulerOperations; + + private final SchedulingTopology<?, ?> schedulingTopology; + + private final DeploymentOption deploymentOption = new DeploymentOption(false); + + /** Result partitions are correlated if they have the same result id. */ + private final Map<IntermediateDataSetID, Set<SchedulingResultPartition<?, ?>>> correlatedResultPartitions = new HashMap<>(); + + private final Map<IntermediateResultPartitionID, Set<SchedulingPipelinedRegion<?, ?>>> partitionConsumerRegions = new HashMap<>(); + + public PipelinedRegionSchedulingStrategy( + final SchedulerOperations schedulerOperations, + final SchedulingTopology<?, ?> schedulingTopology) { + + this.schedulerOperations = checkNotNull(schedulerOperations); + this.schedulingTopology = checkNotNull(schedulingTopology); + + init(); + } + + private void init() { + for (SchedulingPipelinedRegion<?, ?> region : schedulingTopology.getAllPipelinedRegions()) { + for (SchedulingResultPartition<?, ?> partition : region.getConsumedResults()) { + // sanity check Review comment: ok. will remove it. ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services
