You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Dongjoon Hyun (JIRA)" <ji...@apache.org> on 2016/12/01 21:05:58 UTC
[jira] [Commented] (SPARK-18642) Spark SQL: Catalyst is scanning
undesired columns
[ https://issues.apache.org/jira/browse/SPARK-18642?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15713081#comment-15713081 ]
Dongjoon Hyun commented on SPARK-18642:
---------------------------------------
Thank you for reporting, [~mohitgargk].
It seems to be the same with Apache Spark 1.6.3 and to be resolved since Apache Spark 2.0.0.
{code}
scala> val dfA = spark.read.parquet("/tmp/a")
scala> val dfB = spark.read.parquet("/tmp/b")
scala> dfA.createOrReplaceTempView("A")
scala> dfB.createOrReplaceTempView("B")
scala> sql("select A.*, B.* from A left join B on A.id = B.id where B.id<2").explain
== Physical Plan ==
*BroadcastHashJoin [id#0L], [id#3L], Inner, BuildRight
:- *Project [id#0L]
: +- *Filter (isnotnull(id#0L) && (id#0L < 2))
: +- *BatchedScan parquet [id#0L] Format: ParquetFormat, InputPaths: file:/tmp/a, PushedFilters: [IsNotNull(id), LessThan(id,2)], ReadSchema: struct<id:bigint>
+- BroadcastExchange HashedRelationBroadcastMode(List(input[0, bigint, true]))
+- *Project [id#3L]
+- *Filter (isnotnull(id#3L) && (id#3L < 2))
+- *BatchedScan parquet [id#3L] Format: ParquetFormat, InputPaths: file:/tmp/b, PushedFilters: [IsNotNull(id), LessThan(id,2)], ReadSchema: struct<id:bigint>
{code}
IMO, it will not be inside Spark 1.6.4 (if exist) since this is a performance issue.
> Spark SQL: Catalyst is scanning undesired columns
> -------------------------------------------------
>
> Key: SPARK-18642
> URL: https://issues.apache.org/jira/browse/SPARK-18642
> Project: Spark
> Issue Type: Bug
> Components: SQL
> Affects Versions: 1.6.2
> Environment: Ubuntu 14.04
> Spark: Local Mode
> Reporter: Mohit
> Labels: performance
>
> When doing a left-join between two tables, say A and B, Catalyst has information about the projection required for table B. Only the required columns should be scanned.
> Code snippet below explains the scenario:
> scala> val dfA = sqlContext.read.parquet("/home/mohit/ruleA")
> dfA: org.apache.spark.sql.DataFrame = [aid: int, aVal: string]
> scala> val dfB = sqlContext.read.parquet("/home/mohit/ruleB")
> dfB: org.apache.spark.sql.DataFrame = [bid: int, bVal: string]
> scala> dfA.registerTempTable("A")
> scala> dfB.registerTempTable("B")
> scala> sqlContext.sql("select A.aid, B.bid from A left join B on A.aid=B.bid where B.bid<2").explain
> == Physical Plan ==
> Project [aid#15,bid#17]
> +- Filter (bid#17 < 2)
> +- BroadcastHashOuterJoin [aid#15], [bid#17], LeftOuter, None
> :- Scan ParquetRelation[aid#15,aVal#16] InputPaths: file:/home/mohit/ruleA
> +- Scan ParquetRelation[bid#17,bVal#18] InputPaths: file:/home/mohit/ruleB
> This is a watered-down example from a production issue which has a huge performance impact.
> External reference: http://stackoverflow.com/questions/40783675/spark-sql-catalyst-is-scanning-undesired-columns
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org