More aggressive defaults

apache · Nov 3, 2014 · da373f9 · da373f9
1 parent 06232d2
commit da373f9
Show file tree

Hide file tree

Showing 2 changed files with 5 additions and 5 deletions.
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
@@ -79,13 +79,13 @@ private[sql] trait SQLConf {
   private[spark] def dialect: String = getConf(DIALECT, "sql")
 
   /** When true tables cached using the in-memory columnar caching will be compressed. */
-  private[spark] def useCompression: Boolean = getConf(COMPRESS_CACHED, "false").toBoolean
+  private[spark] def useCompression: Boolean = getConf(COMPRESS_CACHED, "true").toBoolean
 
   /** The compression codec for writing to a Parquetfile */
-  private[spark] def parquetCompressionCodec: String = getConf(PARQUET_COMPRESSION, "snappy")
+  private[spark] def parquetCompressionCodec: String = getConf(PARQUET_COMPRESSION, "gzip")
 
   /** The number of rows that will be  */
-  private[spark] def columnBatchSize: Int = getConf(COLUMN_BATCH_SIZE, "1000").toInt
+  private[spark] def columnBatchSize: Int = getConf(COLUMN_BATCH_SIZE, "10000").toInt
 
   /** Number of partitions to use for shuffle operators. */
   private[spark] def numShufflePartitions: Int = getConf(SHUFFLE_PARTITIONS, "200").toInt
@@ -109,7 +109,7 @@ private[sql] trait SQLConf {
    * Hive setting: hive.auto.convert.join.noconditionaltask.size, whose default value is also 10000.
    */
   private[spark] def autoBroadcastJoinThreshold: Int =
-    getConf(AUTO_BROADCASTJOIN_THRESHOLD, "10000").toInt
+    getConf(AUTO_BROADCASTJOIN_THRESHOLD, (10 * 1024 * 1024).toString).toInt
 
   /**
    * The default size in bytes to assign to a logical operator's estimation statistics.  By default,

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
@@ -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 }