From a30866438bf71c83575a3e83887bd4bf33c7cdde Mon Sep 17 00:00:00 2001
From: Alexander Pivovarov <apivovarov@gmail.com>
Date: Mon, 5 Aug 2013 21:48:43 -0700
Subject: [PATCH] SHARK-94 Log the files computed by HadoopRDD and NewHadoopRDD
---
core/src/main/scala/spark/rdd/HadoopRDD.scala | 1 +
core/src/main/scala/spark/rdd/NewHadoopRDD.scala | 1 +
2 files changed, 2 insertions(+)
diff --git a/core/src/main/scala/spark/rdd/HadoopRDD.scala b/core/src/main/scala/spark/rdd/HadoopRDD.scala
index d0fdeb741e..fd00d59c77 100644
--- a/core/src/main/scala/spark/rdd/HadoopRDD.scala
+++ b/core/src/main/scala/spark/rdd/HadoopRDD.scala
@@ -88,6 +88,7 @@ class HadoopRDD[K, V](
override def compute(theSplit: Partition, context: TaskContext) = new NextIterator[(K, V)] {
val split = theSplit.asInstanceOf[HadoopPartition]
+ logInfo("Input split: " + split.inputSplit)
var reader: RecordReader[K, V] = null
val conf = confBroadcast.value.value
diff --git a/core/src/main/scala/spark/rdd/NewHadoopRDD.scala b/core/src/main/scala/spark/rdd/NewHadoopRDD.scala
index 17fe805fd4..0b71608169 100644
--- a/core/src/main/scala/spark/rdd/NewHadoopRDD.scala
+++ b/core/src/main/scala/spark/rdd/NewHadoopRDD.scala
@@ -73,6 +73,7 @@ class NewHadoopRDD[K, V](
override def compute(theSplit: Partition, context: TaskContext) = new Iterator[(K, V)] {
val split = theSplit.asInstanceOf[NewHadoopPartition]
+ logInfo("Input split: " + split.serializableHadoopSplit)
val conf = confBroadcast.value.value
val attemptId = newTaskAttemptID(jobtrackerId, id, true, split.index, 0)
val hadoopAttemptContext = newTaskAttemptContext(conf, attemptId)
--
GitLab