Skip to content

[SPARK-1669][SQL] Made cacheTable idempotent #1183

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-1669][SQL] Made cacheTable idempotent #1183

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
51bae90
Made cacheTable idempotent
liancheng Jun 23, 2014
68f8a20
Removed an unused import
liancheng Jun 23, 2014
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
13 changes: 9 additions & 4 deletions sql/core/src/main/scala/org/apache/spark/sql/SQLContext.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -187,10 +187,15 @@ class SQLContext(@transient val sparkContext: SparkContext)
/** Caches the specified table in-memory. */
def cacheTable(tableName: String): Unit = {
val currentTable = catalog.lookupRelation(None, tableName)
val useCompression =
sparkContext.conf.getBoolean("spark.sql.inMemoryColumnarStorage.compressed", false)
val asInMemoryRelation =
InMemoryRelation(useCompression, executePlan(currentTable).executedPlan)
val asInMemoryRelation = EliminateAnalysisOperators(currentTable.logicalPlan) match {
case _: InMemoryRelation =>
currentTable.logicalPlan

case _ =>
val useCompression =
sparkContext.conf.getBoolean("spark.sql.inMemoryColumnarStorage.compressed", false)
InMemoryRelation(useCompression, executePlan(currentTable).executedPlan)
}

catalog.registerTable(None, tableName, asInMemoryRelation)
}
Expand Down
20 changes: 20 additions & 0 deletions sql/core/src/test/scala/org/apache/spark/sql/SQLQuerySuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,9 @@

package org.apache.spark.sql

import org.apache.spark.sql.catalyst.analysis.EliminateAnalysisOperators
import org.apache.spark.sql.catalyst.expressions._
import org.apache.spark.sql.columnar.{InMemoryColumnarTableScan, InMemoryRelation}
import org.apache.spark.sql.test._

/* Implicits */
Expand Down Expand Up @@ -405,4 +407,22 @@ class SQLQuerySuite extends QueryTest {
clear()
}

test("SPARK-1669: cacheTable should be idempotent") {
assume(!table("testData").logicalPlan.isInstanceOf[InMemoryRelation])

cacheTable("testData")
EliminateAnalysisOperators(table("testData").logicalPlan) match {
case _: InMemoryRelation =>
case _ =>
fail("testData should be cached")
}

cacheTable("testData")
EliminateAnalysisOperators(table("testData").logicalPlan) match {
case InMemoryRelation(_, _, _: InMemoryColumnarTableScan) =>
fail("cacheTable is not idempotent")

case _ =>
}
}
}