gengliangwang commented on a change in pull request #32969:
URL: https://github.com/apache/spark/pull/32969#discussion_r655597239
##########
File path:
external/avro/src/test/scala/org/apache/spark/sql/execution/benchmark/AvroWriteBenchmark.scala
##########
@@ -31,7 +36,34 @@ package org.apache.spark.sql.execution.benchmark
* }}}
*/
object AvroWriteBenchmark extends DataSourceWriteBenchmark {
+ private def wideColumnsBenchmark: Unit = {
+ import spark.implicits._
+
+ withTempPath { dir =>
+ withTempTable("t1") {
+ val width = 1000
+ val values = 500000
+ val files = 20
+ val selectExpr = (1 to width).map(i => s"value as c$i")
+ // repartition to ensure we will write multiple files
+ val df = spark.range(values)
+ .map(_ => Random.nextInt).selectExpr(selectExpr:
_*).repartition(files)
+ .persist(StorageLevel.DISK_ONLY)
+ // cache the data to ensure we are not benchmarking range or
repartition
+ df.filter("(c1*c2) = 12").collect
Review comment:
what is this filtering for?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
