[
https://issues.apache.org/jira/browse/SPARK-40303?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17619978#comment-17619978
]
Yuming Wang commented on SPARK-40303:
-------------------------------------
How to run benchmark code:
# Download latest spark: https://spark.apache.org/downloads.html
# start spark-shell
{code:sh}
tar -zxf spark-3.3.1-bin-hadoop3.tgz
cd spark-3.3.1-bin-hadoop3
bin/spark-shell --master "local[2]"
{code}
# Run benchmark code:
{code:scala}
val dir = "/tmp/spark/benchmark"
val N = 2000000
val columns = Range(0, 100).map(i => s"id % $i AS id$i")
spark.range(N).selectExpr(columns: _*).write.mode("Overwrite").parquet(dir)
Seq(40, 60).foreach { cnt =>
val selectExps = columns.take(cnt).map(_.split(" ").last).map(c =>
s"count(distinct $c)")
val start = System.currentTimeMillis()
spark.read.parquet(dir).selectExpr(selectExps: _*).collect()
println(cnt + "|" + (System.currentTimeMillis() - start))
}
{code}
# Output:
{noformat}
Before:
40|280273
60|581743
After backport JDK-8159720 to JDK 8:
40|20582
60|49688
{noformat}
> The performance will be worse after codegen
> -------------------------------------------
>
> Key: SPARK-40303
> URL: https://issues.apache.org/jira/browse/SPARK-40303
> Project: Spark
> Issue Type: Bug
> Components: SQL
> Affects Versions: 3.4.0
> Reporter: Yuming Wang
> Priority: Major
> Attachments: TestApiBenchmark.scala, TestApis.java,
> TestParameters.java
>
>
> {code:scala}
> import org.apache.spark.benchmark.Benchmark
> val dir = "/tmp/spark/benchmark"
> val N = 2000000
> val columns = Range(0, 100).map(i => s"id % $i AS id$i")
> spark.range(N).selectExpr(columns: _*).write.mode("Overwrite").parquet(dir)
> // Seq(1, 2, 5, 10, 15, 25, 40, 60, 100)
> Seq(60).foreach{ cnt =>
> val selectExps = columns.take(cnt).map(_.split(" ").last).map(c =>
> s"count(distinct $c)")
> val benchmark = new Benchmark("Benchmark count distinct", N, minNumIters =
> 1)
> benchmark.addCase(s"$cnt count distinct with codegen") { _ =>
> withSQLConf(
> "spark.sql.codegen.wholeStage" -> "true",
> "spark.sql.codegen.factoryMode" -> "FALLBACK") {
> spark.read.parquet(dir).selectExpr(selectExps:
> _*).write.format("noop").mode("Overwrite").save()
> }
> }
> benchmark.addCase(s"$cnt count distinct without codegen") { _ =>
> withSQLConf(
> "spark.sql.codegen.wholeStage" -> "false",
> "spark.sql.codegen.factoryMode" -> "NO_CODEGEN") {
> spark.read.parquet(dir).selectExpr(selectExps:
> _*).write.format("noop").mode("Overwrite").save()
> }
> }
> benchmark.run()
> }
> {code}
> {noformat}
> Java HotSpot(TM) 64-Bit Server VM 1.8.0_281-b09 on Mac OS X 10.15.7
> Intel(R) Core(TM) i9-9980HK CPU @ 2.40GHz
> Benchmark count distinct: Best Time(ms) Avg Time(ms)
> Stdev(ms) Rate(M/s) Per Row(ns) Relative
> ------------------------------------------------------------------------------------------------------------------------
> 60 count distinct with codegen 628146 628146
> 0 0.0 314072.8 1.0X
> 60 count distinct without codegen 147635 147635
> 0 0.0 73817.5 4.3X
> {noformat}
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
