From 25bef7e6951301e93004567fc0cef96bf8d1a224 Mon Sep 17 00:00:00 2001 From: Michael Armbrust Date: Mon, 3 Nov 2014 14:08:27 -0800 Subject: [SQL] More aggressive defaults - Turns on compression for in-memory cached data by default - Changes the default parquet compression format back to gzip (we have seen more OOMs with production workloads due to the way Snappy allocates memory) - Ups the batch size to 10,000 rows - Increases the broadcast threshold to 10mb. - Uses our parquet implementation instead of the hive one by default. - Cache parquet metadata by default. Author: Michael Armbrust Closes #3064 from marmbrus/fasterDefaults and squashes the following commits: 97ee9f8 [Michael Armbrust] parquet codec docs e641694 [Michael Armbrust] Remote also a12866a [Michael Armbrust] Cache metadata. 2d73acc [Michael Armbrust] Update docs defaults. d63d2d5 [Michael Armbrust] document parquet option da373f9 [Michael Armbrust] More aggressive defaults --- sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveContext.scala | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'sql/hive') diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveContext.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveContext.scala index f025169ad5..e88afaaf00 100644 --- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveContext.scala +++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveContext.scala @@ -90,7 +90,7 @@ class HiveContext(sc: SparkContext) extends SQLContext(sc) { * SerDe. */ private[spark] def convertMetastoreParquet: Boolean = - getConf("spark.sql.hive.convertMetastoreParquet", "false") == "true" + getConf("spark.sql.hive.convertMetastoreParquet", "true") == "true" override protected[sql] def executePlan(plan: LogicalPlan): this.QueryExecution = new this.QueryExecution { val logical = plan } -- cgit v1.2.3