[
https://issues.apache.org/jira/browse/SPARK-36290?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17389715#comment-17389715
]
Yuming Wang commented on SPARK-36290:
-------------------------------------
{code:java}
spark.sql("create table t1 using parquet select cast(id as string) as a,
cast(id as string) as b from range(1)")
spark.sql("create table t2 using parquet select cast(id as string) as x from
range(1)")
spark.sql("set spark.sql.autoBroadcastJoinThreshold=-1")
spark.sql("SELECT t1.* FROM t1 JOIN t2 ON coalesce(t1.a, t1.b)=t2.x").show
{code}
The {{Coalesce}} evaluation:
{noformat}
at
org.apache.spark.sql.catalyst.expressions.GeneratedClass$SpecificUnsafeProjection.Pmod_0$(Unknown
Source)
at
org.apache.spark.sql.catalyst.expressions.GeneratedClass$SpecificUnsafeProjection.apply(Unknown
Source)
at
org.apache.spark.sql.execution.exchange.ShuffleExchangeExec$.$anonfun$prepareShuffleDependency$6(ShuffleExchangeExec.scala:311)
at
org.apache.spark.sql.execution.exchange.ShuffleExchangeExec$.$anonfun$prepareShuffleDependency$6$adapted(ShuffleExchangeExec.scala:311)
at
org.apache.spark.sql.execution.exchange.ShuffleExchangeExec$.$anonfun$prepareShuffleDependency$14(ShuffleExchangeExec.scala:380)
at
org.apache.spark.sql.catalyst.expressions.GeneratedClass$SpecificUnsafeProjection.apply(Unknown
Source)
at
org.apache.spark.sql.execution.SortExec$$anon$1.computePrefix(SortExec.scala:90)
at
org.apache.spark.sql.execution.UnsafeExternalRowSorter.insertRow(UnsafeExternalRowSorter.java:137)
at
org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage3.sort_addToSorter_0$(Unknown
Source)
at
org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage3.processNext(Unknown
Source)
at
org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at
org.apache.spark.sql.execution.WholeStageCodegenExec$$anon$1.hasNext(WholeStageCodegenExec.scala:759)
at
org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage5.smj_findNextJoinRows_0$(Unknown
Source)
at
org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage5.smj_findNextJoinRows_0$(Unknown
Source)
at
org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage5.processNext(Unknown
Source)
at
org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at
org.apache.spark.sql.execution.WholeStageCodegenExec$$anon$2.hasNext(WholeStageCodegenExec.scala:778)
{noformat}
> Push down join condition evaluation
> -----------------------------------
>
> Key: SPARK-36290
> URL: https://issues.apache.org/jira/browse/SPARK-36290
> Project: Spark
> Issue Type: Improvement
> Components: SQL
> Affects Versions: 3.3.0
> Reporter: Yuming Wang
> Priority: Major
>
> {code:scala}
> val numRows = 1024 * 1024 * 15
> spark.sql(s"CREATE TABLE t1 using parquet AS select id as a, id as b from
> range(${numRows}L)")
> spark.sql(s"CREATE TABLE t2 using parquet AS select id as a, id as b from
> range(${numRows}L)")
> val benchmark = new Benchmark("Benchmark push down join condition
> evaluation", numRows, minNumIters = 5)
> Seq(false, true).foreach { pushDownEnabled =>
> val name = s"Join Condition Evaluation ${if (pushDownEnabled)
> s"(Pushdown)" else ""}"
> benchmark.addCase(name) { _ =>
> withSQLConf("spark.sql.pushDownJoinConditionEvaluationevaluation" ->
> s"$pushDownEnabled") {
> spark.sql("SELECT t1.* FROM t1 JOIN t2 ON translate(t1.a, '123',
> 'abc') = translate(t2.a, '123',
> 'abc')").write.format("noop").mode("Overwrite").save()
> }
> }
> }
> benchmark.run()
> {code}
> {noformat}
> Java HotSpot(TM) 64-Bit Server VM 1.8.0_251-b08 on Mac OS X 10.15.7
> Intel(R) Core(TM) i9-9980HK CPU @ 2.40GHz
> Benchmark push down join condition evaluation: Best Time(ms) Avg Time(ms)
> Stdev(ms) Rate(M/s) Per Row(ns) Relative
> -----------------------------------------------------------------------------------------------------------------------------
> Join Condition Evaluation 32459 34521
> 1465 0.5 2063.7 1.0X
> Join Condition Evaluation (Pushdown) 19483 20350
> 812 0.8 1238.7 1.7X
> {noformat}
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
