Skip to content

[SPARK-32564][SQL][TEST] Inject data statistics to simulate plan generation on actual TPCDS data #29384

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 2 commits into from
Closed

[SPARK-32564][SQL][TEST] Inject data statistics to simulate plan generation on actual TPCDS data #29384

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
3b03d70
Fix
maropu Aug 7, 2020
b345248
Update stats based on SF=100
maropu Aug 7, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 8 additions & 2 deletions sql/core/src/test/scala/org/apache/spark/sql/TPCDSQuerySuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -46,11 +46,17 @@ class TPCDSQuerySuite extends BenchmarkQueryTest with TPCDSSchema {
"q81", "q82", "q83", "q84", "q85", "q86", "q87", "q88", "q89", "q90",
"q91", "q92", "q93", "q94", "q95", "q96", "q97", "q98", "q99")

val sqlConfgs = Seq(
SQLConf.CBO_ENABLED.key -> "true",
SQLConf.PLAN_STATS_ENABLED.key -> "true",
SQLConf.JOIN_REORDER_ENABLED.key -> "true"
)

tpcdsQueries.foreach { name =>
val queryString = resourceToString(s"tpcds/$name.sql",
classLoader = Thread.currentThread().getContextClassLoader)
test(name) {
withSQLConf(SQLConf.CROSS_JOINS_ENABLED.key -> "true") {
withSQLConf(sqlConfgs: _*) {
// check the plans can be properly generated
val plan = sql(queryString).queryExecution.executedPlan
checkGeneratedCode(plan)
Expand All @@ -69,7 +75,7 @@ class TPCDSQuerySuite extends BenchmarkQueryTest with TPCDSSchema {
val queryString = resourceToString(s"tpcds-v2.7.0/$name.sql",
classLoader = Thread.currentThread().getContextClassLoader)
test(s"$name-v2.7") {
withSQLConf(SQLConf.CROSS_JOINS_ENABLED.key -> "true") {
withSQLConf(sqlConfgs: _*) {
// check the plans can be properly generated
val plan = sql(queryString).queryExecution.executedPlan
checkGeneratedCode(plan)
Expand Down
6 changes: 6 additions & 0 deletions sql/core/src/test/scala/org/apache/spark/sql/TPCDSSchema.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,6 +17,8 @@

package org.apache.spark.sql

import org.apache.spark.sql.catalyst.TableIdentifier

trait TPCDSSchema {

private val tableColumns = Map(
Expand Down Expand Up @@ -255,5 +257,9 @@ trait TPCDSSchema {
|USING $format
|${options.mkString("\n")}
""".stripMargin)

// To simulate plan generation on actual TPCDS data, injects data stats here
spark.sessionState.catalog.alterTableStats(
TableIdentifier(tableName), Some(TPCDSTableStats.sf100TableStats(tableName)))
}
}
Loading