From 173aa949c309ff7a7a03e9d762b9108542219a95 Mon Sep 17 00:00:00 2001
From: Michael Armbrust <michael@databricks.com>
Date: Mon, 22 Feb 2016 15:27:29 -0800
Subject: [PATCH] [SPARK-12546][SQL] Change default number of open parquet
files
A common problem that users encounter with Spark 1.6.0 is that writing to a partitioned parquet table OOMs. The root cause is that parquet allocates a significant amount of memory that is not accounted for by our own mechanisms. As a workaround, we can ensure that only a single file is open per task unless the user explicitly asks for more.
Author: Michael Armbrust <michael@databricks.com>
Closes #11308 from marmbrus/parquetWriteOOM.
---
sql/core/src/main/scala/org/apache/spark/sql/SQLConf.scala | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/SQLConf.scala b/sql/core/src/main/scala/org/apache/spark/sql/SQLConf.scala
index 61a7b9935a..a601c87fc9 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/SQLConf.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/SQLConf.scala
@@ -430,7 +430,7 @@ private[spark] object SQLConf {
val PARTITION_MAX_FILES =
intConf("spark.sql.sources.maxConcurrentWrites",
- defaultValue = Some(5),
+ defaultValue = Some(1),
doc = "The maximum number of concurrent files to open before falling back on sorting when " +
"writing out files using dynamic partitioning.")
--
GitLab