001/*
002 * Copyright (c) 2007-2022 The Cascading Authors. All Rights Reserved.
003 *
004 * Project and contact information: https://cascading.wensel.net/
005 *
006 * This file is part of the Cascading project.
007 *
008 * Licensed under the Apache License, Version 2.0 (the "License");
009 * you may not use this file except in compliance with the License.
010 * You may obtain a copy of the License at
011 *
012 *     http://www.apache.org/licenses/LICENSE-2.0
013 *
014 * Unless required by applicable law or agreed to in writing, software
015 * distributed under the License is distributed on an "AS IS" BASIS,
016 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
017 * See the License for the specific language governing permissions and
018 * limitations under the License.
019 */
020
021package cascading.flow.tez.planner;
022
023import cascading.flow.planner.rule.RuleRegistry;
024import cascading.flow.planner.rule.annotator.LogicalMergeAnnotator;
025import cascading.flow.planner.rule.assertion.BufferAfterEveryAssert;
026import cascading.flow.planner.rule.assertion.EveryAfterBufferAssert;
027import cascading.flow.planner.rule.assertion.LoneGroupAssert;
028import cascading.flow.planner.rule.assertion.MissingGroupAssert;
029import cascading.flow.planner.rule.assertion.SplitBeforeEveryAssert;
030import cascading.flow.planner.rule.partitioner.WholeGraphStepPartitioner;
031import cascading.flow.planner.rule.transformer.ApplyAssertionLevelTransformer;
032import cascading.flow.planner.rule.transformer.ApplyDebugLevelTransformer;
033import cascading.flow.planner.rule.transformer.RemoveNoOpPipeTransformer;
034import cascading.flow.tez.planner.rule.assertion.NoHashJoinAssert;
035import cascading.flow.tez.planner.rule.partitioner.ConsecutiveGroupOrMergesNodePartitioner;
036import cascading.flow.tez.planner.rule.partitioner.SplitJoinBoundariesNodeRePartitioner;
037import cascading.flow.tez.planner.rule.partitioner.TopDownBoundariesNodePartitioner;
038import cascading.flow.tez.planner.rule.transformer.BoundaryBalanceCheckpointTransformer;
039import cascading.flow.tez.planner.rule.transformer.BoundaryBalanceGroupSplitSpliceTransformer;
040
041/**
042 * The NoHashJoinHadoop2TezRuleRegistry assumes the plan has no {@link cascading.pipe.HashJoin} Pipes in the
043 * assembly, otherwise an planner failure will be thrown.
044 * <p>
045 * This rule registry can be used if the default registry is failing or producing less than optimal plans.
046 *
047 * @see cascading.flow.tez.planner.HashJoinHadoop2TezRuleRegistry
048 */
049public class NoHashJoinHadoop2TezRuleRegistry extends RuleRegistry
050  {
051  public NoHashJoinHadoop2TezRuleRegistry()
052    {
053//    enableDebugLogging();
054
055    // PreBalance
056    addRule( new NoHashJoinAssert() ); // fail if we encounter a HashJoin
057
058    addRule( new LoneGroupAssert() );
059    addRule( new MissingGroupAssert() );
060    addRule( new BufferAfterEveryAssert() );
061    addRule( new EveryAfterBufferAssert() );
062    addRule( new SplitBeforeEveryAssert() );
063
064    addRule( new BoundaryBalanceGroupSplitSpliceTransformer() ); // prevents AssemblyHelpersPlatformTest#testSameSourceMerge deadlock
065    addRule( new BoundaryBalanceCheckpointTransformer() );
066
067    // PreResolve
068    addRule( new RemoveNoOpPipeTransformer() );
069    addRule( new ApplyAssertionLevelTransformer() );
070    addRule( new ApplyDebugLevelTransformer() );
071    addRule( new LogicalMergeAnnotator() ); // MergePipesPlatformTest#testSameSourceMergeHashJoin
072
073    // PostResolve
074
075    // PartitionSteps
076    addRule( new WholeGraphStepPartitioner() );
077
078    // PostSteps
079
080    // PartitionNodes
081    addRule( new TopDownBoundariesNodePartitioner() );
082    addRule( new ConsecutiveGroupOrMergesNodePartitioner() );
083    addRule( new SplitJoinBoundariesNodeRePartitioner() ); // testCoGroupSelf - compensates for tez-1190
084
085    // PostNodes
086    }
087  }