ODIn/spark-instrumented-optimizer
1
0
Fork 0
Code Issues Pull requests Projects Releases Wiki Activity

[SPARK-4386] Improve performance when writing Parquet files.

Browse source 
If you profile the writing of a Parquet file, the single worst time consuming call inside of org.apache.spark.sql.parquet.MutableRowWriteSupport.write is actually in the scala.collection.AbstractSequence.size call. This is because the size call actually ends up COUNTING the elements in a scala.collection.LinearSeqOptimized.length ("optimized?").

This doesn't need to be done. "size" is called repeatedly where needed rather than called once at the top of the method and stored in a 'val'.

Author: Jim Carroll <jim@dontcallme.com>

Closes #3254 from jimfcarroll/parquet-perf and squashes the following commits:

30cc0b5 [Jim Carroll] Improve performance when writing Parquet files.
This commit is contained in:
Jim Carroll 2014-11-14 15:11:53 -08:00 committed by Michael Armbrust
parent 0c7b66bd44
commit f76b968370
1 changed files with 8 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

14
sql/core/src/main/scala/org/apache/spark/sql/parquet/ParquetTableSupport.scala
View file

@ -152,14 +152,15 @@ private[parquet] class RowWriteSupport extends WriteSupport[Row] with Logging {
}
override def write(record: Row): Unit = {
if (attributes.size > record.size) {
val attributesSize = attributes.size
if (attributesSize > record.size) {
throw new IndexOutOfBoundsException(
s"Trying to write more fields than contained in row (${attributes.size}>${record.size})")
s"Trying to write more fields than contained in row (${attributesSize}>${record.size})")
}
var index = 0
writer.startMessage()
while(index < attributes.size) {
while(index < attributesSize) {
// null values indicate optional fields but we do not check currently
if (record(index) != null) {
writer.startField(attributes(index).name, index)
@ -312,14 +313,15 @@ private[parquet] class RowWriteSupport extends WriteSupport[Row] with Logging {
// Optimized for non-nested rows
private[parquet] class MutableRowWriteSupport extends RowWriteSupport {
override def write(record: Row): Unit = {
if (attributes.size > record.size) {
val attributesSize = attributes.size
if (attributesSize > record.size) {
throw new IndexOutOfBoundsException(
s"Trying to write more fields than contained in row (${attributes.size}>${record.size})")
s"Trying to write more fields than contained in row (${attributesSize}>${record.size})")
}
var index = 0
writer.startMessage()
while(index < attributes.size) {
while(index < attributesSize) {
// null values indicate optional fields but we do not check currently
if (record(index) != null && record(index) != Nil) {
writer.startField(attributes(index).name, index)