Author: daijy
Date: Sat May 16 00:07:56 2015
New Revision: 1679663
URL: http://svn.apache.org/r1679663
Log:
PIG-4377: Skewed outer join produce wrong result if a key is oversampled
(PIG-4377-3.patch)
Modified:
pig/branches/branch-0.15/src/org/apache/pig/backend/hadoop/executionengine/tez/plan/TezCompiler.java
Modified:
pig/branches/branch-0.15/src/org/apache/pig/backend/hadoop/executionengine/tez/plan/TezCompiler.java
URL:
http://svn.apache.org/viewvc/pig/branches/branch-0.15/src/org/apache/pig/backend/hadoop/executionengine/tez/plan/TezCompiler.java?rev=1679663&r1=1679662&r2=1679663&view=diff
==============================================================================
---
pig/branches/branch-0.15/src/org/apache/pig/backend/hadoop/executionengine/tez/plan/TezCompiler.java
(original)
+++
pig/branches/branch-0.15/src/org/apache/pig/backend/hadoop/executionengine/tez/plan/TezCompiler.java
Sat May 16 00:07:56 2015
@@ -1680,7 +1680,7 @@ public class TezCompiler extends PhyPlan
TezCompilerUtil.connect(tezPlan, prevOp, sampleJobPair.first);
POValueOutputTez sampleOut = (POValueOutputTez)
sampleJobPair.first.plan.getLeaves().get(0);
- for (int i = 0; i <= 2; i++) {
+ for (int i = 0; i < 2; i++) {
joinJobs[i].setSampleOperator(sampleJobPair.first);
// Configure broadcast edges for distribution map
@@ -1689,10 +1689,8 @@ public class TezCompiler extends PhyPlan
sampleOut.addOutputKey(joinJobs[i].getOperatorKey().toString());
// Configure skewed partitioner for join
- if (i != 2) {
- edge =
joinJobs[2].inEdges.get(joinJobs[i].getOperatorKey());
- edge.partitionerClass = SkewedPartitionerTez.class;
- }
+ edge = joinJobs[2].inEdges.get(joinJobs[i].getOperatorKey());
+ edge.partitionerClass = SkewedPartitionerTez.class;
}
joinJobs[2].markSkewedJoin();