From ccf48388cd8d8f4e1777be77ab30032d1b15c8c6 Mon Sep 17 00:00:00 2001
From: Matei Zaharia <matei@eecs.berkeley.edu>
Date: Thu, 14 Jul 2011 17:37:04 -0400
Subject: [PATCH] Lowered default number of splits for files
---
core/src/main/scala/spark/SparkContext.scala | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/core/src/main/scala/spark/SparkContext.scala b/core/src/main/scala/spark/SparkContext.scala
index 74e6ff1fec..18bd5c8817 100644
--- a/core/src/main/scala/spark/SparkContext.scala
+++ b/core/src/main/scala/spark/SparkContext.scala
@@ -257,7 +257,7 @@ extends Logging {
def defaultParallelism: Int = scheduler.defaultParallelism
// Default min number of splits for Hadoop RDDs when not given by user
- def defaultMinSplits: Int = Math.min(defaultParallelism, 4)
+ def defaultMinSplits: Int = Math.min(defaultParallelism, 2)
private var nextShuffleId = new AtomicInteger(0)
--
GitLab