001/* 002 * Copyright (c) 2016 Chris K Wensel <chris@wensel.net>. All Rights Reserved. 003 * Copyright (c) 2007-2017 Xplenty, Inc. All Rights Reserved. 004 * 005 * Project and contact information: http://www.cascading.org/ 006 * 007 * This file is part of the Cascading project. 008 * 009 * Licensed under the Apache License, Version 2.0 (the "License"); 010 * you may not use this file except in compliance with the License. 011 * You may obtain a copy of the License at 012 * 013 * http://www.apache.org/licenses/LICENSE-2.0 014 * 015 * Unless required by applicable law or agreed to in writing, software 016 * distributed under the License is distributed on an "AS IS" BASIS, 017 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 018 * See the License for the specific language governing permissions and 019 * limitations under the License. 020 */ 021 022package cascading.flow.tez.planner; 023 024import cascading.flow.planner.rule.RuleRegistry; 025import cascading.flow.planner.rule.annotator.LogicalMergeAnnotator; 026import cascading.flow.planner.rule.assertion.BufferAfterEveryAssert; 027import cascading.flow.planner.rule.assertion.EveryAfterBufferAssert; 028import cascading.flow.planner.rule.assertion.LoneGroupAssert; 029import cascading.flow.planner.rule.assertion.MissingGroupAssert; 030import cascading.flow.planner.rule.assertion.SplitBeforeEveryAssert; 031import cascading.flow.planner.rule.partitioner.WholeGraphStepPartitioner; 032import cascading.flow.planner.rule.transformer.ApplyAssertionLevelTransformer; 033import cascading.flow.planner.rule.transformer.ApplyDebugLevelTransformer; 034import cascading.flow.planner.rule.transformer.RemoveNoOpPipeTransformer; 035import cascading.flow.tez.planner.rule.assertion.NoHashJoinAssert; 036import cascading.flow.tez.planner.rule.partitioner.ConsecutiveGroupOrMergesNodePartitioner; 037import cascading.flow.tez.planner.rule.partitioner.SplitJoinBoundariesNodeRePartitioner; 038import cascading.flow.tez.planner.rule.partitioner.TopDownBoundariesNodePartitioner; 039import cascading.flow.tez.planner.rule.transformer.BoundaryBalanceCheckpointTransformer; 040import cascading.flow.tez.planner.rule.transformer.BoundaryBalanceGroupSplitSpliceTransformer; 041 042/** 043 * The NoHashJoinHadoop2TezRuleRegistry assumes the plan has no {@link cascading.pipe.HashJoin} Pipes in the 044 * assembly, otherwise an planner failure will be thrown. 045 * <p/> 046 * This rule registry can be used if the default registry is failing or producing less than optimal plans. 047 * 048 * @see cascading.flow.tez.planner.HashJoinHadoop2TezRuleRegistry 049 */ 050public class NoHashJoinHadoop2TezRuleRegistry extends RuleRegistry 051 { 052 public NoHashJoinHadoop2TezRuleRegistry() 053 { 054// enableDebugLogging(); 055 056 // PreBalance 057 addRule( new NoHashJoinAssert() ); // fail if we encounter a HashJoin 058 059 addRule( new LoneGroupAssert() ); 060 addRule( new MissingGroupAssert() ); 061 addRule( new BufferAfterEveryAssert() ); 062 addRule( new EveryAfterBufferAssert() ); 063 addRule( new SplitBeforeEveryAssert() ); 064 065 addRule( new BoundaryBalanceGroupSplitSpliceTransformer() ); // prevents AssemblyHelpersPlatformTest#testSameSourceMerge deadlock 066 addRule( new BoundaryBalanceCheckpointTransformer() ); 067 068 // PreResolve 069 addRule( new RemoveNoOpPipeTransformer() ); 070 addRule( new ApplyAssertionLevelTransformer() ); 071 addRule( new ApplyDebugLevelTransformer() ); 072 addRule( new LogicalMergeAnnotator() ); // MergePipesPlatformTest#testSameSourceMergeHashJoin 073 074 // PostResolve 075 076 // PartitionSteps 077 addRule( new WholeGraphStepPartitioner() ); 078 079 // PostSteps 080 081 // PartitionNodes 082 addRule( new TopDownBoundariesNodePartitioner() ); 083 addRule( new ConsecutiveGroupOrMergesNodePartitioner() ); 084 addRule( new SplitJoinBoundariesNodeRePartitioner() ); // testCoGroupSelf - compensates for tez-1190 085 086 // PostNodes 087 } 088 }