001/* 002 * Copyright (c) 2007-2016 Concurrent, Inc. All Rights Reserved. 003 * 004 * Project and contact information: http://www.cascading.org/ 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.assertion.BufferAfterEveryAssert; 025import cascading.flow.planner.rule.assertion.EveryAfterBufferAssert; 026import cascading.flow.planner.rule.assertion.LoneGroupAssert; 027import cascading.flow.planner.rule.assertion.MissingGroupAssert; 028import cascading.flow.planner.rule.assertion.SplitBeforeEveryAssert; 029import cascading.flow.planner.rule.partitioner.WholeGraphStepPartitioner; 030import cascading.flow.planner.rule.transformer.ApplyAssertionLevelTransformer; 031import cascading.flow.planner.rule.transformer.ApplyDebugLevelTransformer; 032import cascading.flow.planner.rule.transformer.RemoveNoOpPipeTransformer; 033import cascading.flow.tez.planner.rule.assertion.NoHashJoinAssert; 034import cascading.flow.tez.planner.rule.partitioner.ConsecutiveGroupOrMergesNodePartitioner; 035import cascading.flow.tez.planner.rule.partitioner.SplitJoinBoundariesNodeRePartitioner; 036import cascading.flow.tez.planner.rule.partitioner.TopDownBoundariesNodePartitioner; 037import cascading.flow.tez.planner.rule.transformer.BoundaryBalanceCheckpointTransformer; 038import cascading.flow.tez.planner.rule.transformer.BoundaryBalanceGroupSplitSpliceTransformer; 039 040/** 041 * The NoHashJoinHadoop2TezRuleRegistry assumes the plan has no {@link cascading.pipe.HashJoin} Pipes in the 042 * assembly, otherwise an planner failure will be thrown. 043 * <p/> 044 * This rule registry can be used if the default registry is failing or producing less than optimal plans. 045 * 046 * @see cascading.flow.tez.planner.HashJoinHadoop2TezRuleRegistry 047 */ 048public class NoHashJoinHadoop2TezRuleRegistry extends RuleRegistry 049 { 050 public NoHashJoinHadoop2TezRuleRegistry() 051 { 052// enableDebugLogging(); 053 054 // PreBalance 055 addRule( new NoHashJoinAssert() ); // fail if we encounter a HashJoin 056 057 addRule( new LoneGroupAssert() ); 058 addRule( new MissingGroupAssert() ); 059 addRule( new BufferAfterEveryAssert() ); 060 addRule( new EveryAfterBufferAssert() ); 061 addRule( new SplitBeforeEveryAssert() ); 062 063 addRule( new BoundaryBalanceGroupSplitSpliceTransformer() ); // prevents AssemblyHelpersPlatformTest#testSameSourceMerge deadlock 064 addRule( new BoundaryBalanceCheckpointTransformer() ); 065 066 // PreResolve 067 addRule( new RemoveNoOpPipeTransformer() ); 068 addRule( new ApplyAssertionLevelTransformer() ); 069 addRule( new ApplyDebugLevelTransformer() ); 070 071 // PostResolve 072 073 // PartitionSteps 074 addRule( new WholeGraphStepPartitioner() ); 075 076 // PostSteps 077 078 // PartitionNodes 079 addRule( new TopDownBoundariesNodePartitioner() ); 080 addRule( new ConsecutiveGroupOrMergesNodePartitioner() ); 081 addRule( new SplitJoinBoundariesNodeRePartitioner() ); // testCoGroupSelf - compensates for tez-1190 082 083 // PostNodes 084 } 085 }