[SPARK-2650][SQL] More precise initial buffer size estimation for in-memory column buffer

This is a follow up of #1880.

Since the row number within a single batch is known, we can estimate a much more precise initial buffer size when building an in-memory column buffer.

Author: Cheng Lian <lian.cs.zju@gmail.com>

Closes #1901 from liancheng/precise-init-buffer-size and squashes the following commits:

d5501fa [Cheng Lian] More precise initial buffer size estimation for in-memory column buffer

sql/core/src/main/scala/org/apache/spark/sql/columnar/InMemoryColumnarTableScan.scala

@@ -20,12 +20,11 @@ package org.apache.spark.sql.columnar
 import java.nio.ByteBuffer
 
 import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.Row
 import org.apache.spark.sql.catalyst.analysis.MultiInstanceRelation
-import org.apache.spark.sql.catalyst.expressions.{GenericMutableRow, Attribute}
+import org.apache.spark.sql.catalyst.expressions.{Attribute, GenericMutableRow}
 import org.apache.spark.sql.catalyst.plans.logical.LogicalPlan
-import org.apache.spark.sql.execution.{SparkPlan, LeafNode}
-import org.apache.spark.sql.Row
-import org.apache.spark.SparkConf
+import org.apache.spark.sql.execution.{LeafNode, SparkPlan}
 
 object InMemoryRelation {
   def apply(useCompression: Boolean, batchSize: Int, child: SparkPlan): InMemoryRelation =
@@ -48,7 +47,9 @@ private[sql] case class InMemoryRelation(
       new Iterator[Array[ByteBuffer]] {
         def next() = {
           val columnBuilders = output.map { attribute =>
-            ColumnBuilder(ColumnType(attribute.dataType).typeId, 0, attribute.name, useCompression)
+            val columnType = ColumnType(attribute.dataType)
+            val initialBufferSize = columnType.defaultSize * batchSize
+            ColumnBuilder(columnType.typeId, initialBufferSize, attribute.name, useCompression)
           }.toArray
 
           var row: Row = null