From 7d92cf2b3b90aaac615bead93267f228d762d9b1 Mon Sep 17 00:00:00 2001
From: Deepak <deepujain@gmail.com>
Date: Thu, 22 May 2014 15:08:12 +0530
Subject: [PATCH] Update IndexGeneratorJob.java

CombineTextInputFormat instead of TextInputFormat combines multiple splits for a single mapper and reduces the strain on hadoop platform. It greatly improves job completion time as there are fewer number of mappers to bookkeep.
---
 .../src/main/java/io/druid/indexer/IndexGeneratorJob.java      | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/indexing-hadoop/src/main/java/io/druid/indexer/IndexGeneratorJob.java b/indexing-hadoop/src/main/java/io/druid/indexer/IndexGeneratorJob.java
index f8633604be0..9d8a5fb6c33 100644
--- a/indexing-hadoop/src/main/java/io/druid/indexer/IndexGeneratorJob.java
+++ b/indexing-hadoop/src/main/java/io/druid/indexer/IndexGeneratorJob.java
@@ -62,6 +62,7 @@ import org.apache.hadoop.mapreduce.JobContext;
 import org.apache.hadoop.mapreduce.Partitioner;
 import org.apache.hadoop.mapreduce.Reducer;
 import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
+import org.apache.hadoop.mapreduce.lib.input.CombineTextInputFormat;
 import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
 import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
 import org.joda.time.DateTime;
@@ -146,7 +147,7 @@ public class IndexGeneratorJob implements Jobby
 
       JobHelper.injectSystemProperties(job);
 
-      job.setInputFormatClass(TextInputFormat.class);
+      job.setInputFormatClass(CombineTextInputFormat.class);
 
       job.setMapperClass(IndexGeneratorMapper.class);
       job.setMapOutputValueClass(Text.class);