ODIn/spark-instrumented-optimizer
1
0
Fork 0
Code Issues Pull requests Projects Releases Wiki Activity

[SPARK-33663][SQL] Uncaching should not be called on non-existing temp views

Browse source 
### What changes were proposed in this pull request?

This PR proposes to fix a misleading logs in the following scenario when uncaching is called on non-existing views:
```
scala> sql("CREATE TABLE table USING parquet AS SELECT 2")
res0: org.apache.spark.sql.DataFrame = []

scala> val df = spark.table("table")
df: org.apache.spark.sql.DataFrame = [2: int]

scala> df.createOrReplaceTempView("t2")
20/12/04 10:16:24 WARN CommandUtils: Exception when attempting to uncache $name
org.apache.spark.sql.AnalysisException: Table or view not found: t2;;
'UnresolvedRelation [t2], [], false

	at org.apache.spark.sql.catalyst.analysis.package$AnalysisErrorAt.failAnalysis(package.scala:42)
	at org.apache.spark.sql.catalyst.analysis.CheckAnalysis.$anonfun$checkAnalysis$1(CheckAnalysis.scala:113)
	at org.apache.spark.sql.catalyst.analysis.CheckAnalysis.$anonfun$checkAnalysis$1$adapted(CheckAnalysis.scala:93)
	at org.apache.spark.sql.catalyst.trees.TreeNode.foreachUp(TreeNode.scala:183)
	at org.apache.spark.sql.catalyst.analysis.CheckAnalysis.checkAnalysis(CheckAnalysis.scala:93)
	at org.apache.spark.sql.catalyst.analysis.CheckAnalysis.checkAnalysis$(CheckAnalysis.scala:90)
	at org.apache.spark.sql.catalyst.analysis.Analyzer.checkAnalysis(Analyzer.scala:152)
	at org.apache.spark.sql.catalyst.analysis.Analyzer.$anonfun$executeAndCheck$1(Analyzer.scala:172)
	at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.markInAnalyzer(AnalysisHelper.scala:214)
	at org.apache.spark.sql.catalyst.analysis.Analyzer.executeAndCheck(Analyzer.scala:169)
	at org.apache.spark.sql.execution.QueryExecution.$anonfun$analyzed$1(QueryExecution.scala:73)
	at org.apache.spark.sql.catalyst.QueryPlanningTracker.measurePhase(QueryPlanningTracker.scala:111)
	at org.apache.spark.sql.execution.QueryExecution.$anonfun$executePhase$1(QueryExecution.scala:138)
	at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:768)
	at org.apache.spark.sql.execution.QueryExecution.executePhase(QueryExecution.scala:138)
	at org.apache.spark.sql.execution.QueryExecution.analyzed$lzycompute(QueryExecution.scala:73)
	at org.apache.spark.sql.execution.QueryExecution.analyzed(QueryExecution.scala:71)
	at org.apache.spark.sql.execution.QueryExecution.assertAnalyzed(QueryExecution.scala:63)
	at org.apache.spark.sql.Dataset$.$anonfun$ofRows$1(Dataset.scala:90)
	at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:768)
	at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:88)
	at org.apache.spark.sql.DataFrameReader.table(DataFrameReader.scala:889)
	at org.apache.spark.sql.SparkSession.table(SparkSession.scala:589)
	at org.apache.spark.sql.internal.CatalogImpl.uncacheTable(CatalogImpl.scala:476)
	at org.apache.spark.sql.execution.command.CommandUtils$.uncacheTableOrView(CommandUtils.scala:392)
	at org.apache.spark.sql.execution.command.CreateViewCommand.run(views.scala:124)
```
Since `t2` does not exist yet, it shouldn't try to uncache.

### Why are the changes needed?

To fix misleading message.

### Does this PR introduce _any_ user-facing change?

Yes, the above message will not be displayed if the view doesn't exist yet.

### How was this patch tested?

Manually tested since this is a log message printed.

Closes #30608 from imback82/fix_cache_message.

Authored-by: Terry Kim <yuminkim@gmail.com>
Signed-off-by: HyukjinKwon <gurwls223@apache.org>
This commit is contained in:
Terry Kim 2020-12-07 09:48:16 +09:00 committed by HyukjinKwon
parent b94ecf0734
commit 119539fd49
1 changed files with 10 additions and 10 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

20
sql/core/src/main/scala/org/apache/spark/sql/execution/command/views.scala
View file

@ -113,12 +113,12 @@ case class CreateViewCommand(
verifyTemporaryObjectsNotExists(catalog, isTemporary, name, child)
if (viewType == LocalTempView) {
val samePlan = catalog.getTempView(name.table).exists {
// Don't perform sameResult check for View logical plan, since it's unresolved
case _: View => false
case other => other.sameResult(child)
val shouldUncache = replace && catalog.getTempView(name.table).exists {
// Uncache View logical plan without checking the same result check, since it's unresolved.
case _: View => true
case other => !other.sameResult(child)
}
if (replace && !samePlan) {
if (shouldUncache) {
logInfo(s"Try to uncache ${name.quotedString} before replacing.")
checkCyclicViewReference(analyzedPlan, Seq(name), name)
CommandUtils.uncacheTableOrView(sparkSession, name.quotedString)
@ -141,12 +141,12 @@ case class CreateViewCommand(
} else if (viewType == GlobalTempView) {
val db = sparkSession.sessionState.conf.getConf(StaticSQLConf.GLOBAL_TEMP_DATABASE)
val viewIdent = TableIdentifier(name.table, Option(db))
val samePlan = catalog.getGlobalTempView(name.table).exists {
// Don't perform sameResult check for View logical plan, since it's unresolved
case _: View => false
case other => other.sameResult(child)
val shouldUncache = replace && catalog.getGlobalTempView(name.table).exists {
// Uncache View logical plan without checking the same result check, since it's unresolved.
case _: View => true
case other => !other.sameResult(child)
}
if (replace && !samePlan) {
if (shouldUncache) {
logInfo(s"Try to uncache ${viewIdent.quotedString} before replacing.")
checkCyclicViewReference(analyzedPlan, Seq(viewIdent), viewIdent)
CommandUtils.uncacheTableOrView(sparkSession, viewIdent.quotedString)