cloud-fan commented on code in PR #52157:
URL: https://github.com/apache/spark/pull/52157#discussion_r2312810434
##########
sql/core/src/test/scala/org/apache/spark/sql/execution/QueryExecutionSuite.scala:
##########
@@ -327,6 +327,41 @@ class QueryExecutionSuite extends SharedSparkSession {
}
}
+ test("SPARK-53413: Cleanup shuffle dependencies for commands") {
+ Seq(true, false).foreach { adaptiveEnabled => {
+ withSQLConf((SQLConf.ADAPTIVE_EXECUTION_ENABLED.key,
adaptiveEnabled.toString),
+ (SQLConf.CLASSIC_SHUFFLE_DEPENDENCY_FILE_CLEANUP_ENABLED.key,
true.toString)) {
+ val plan = spark.range(100).repartition(10).logicalPlan
+ val df = Dataset.ofRows(spark, plan)
+ df.write.format("noop").mode(SaveMode.Overwrite).save()
+
+ val blockManager = spark.sparkContext.env.blockManager
+ assert(blockManager.migratableResolver.getStoredShuffles().isEmpty)
+ assert(blockManager.diskBlockManager.getAllBlocks().isEmpty)
+ }
+ }
+ }
+ }
+
+ test("SPARK-53413: Cleanup shuffle dependencies for DataWritingCommandExec")
{
+ withTempDir { dir =>
+ Seq(true, false).foreach { adaptiveEnabled => {
+ withSQLConf((SQLConf.ADAPTIVE_EXECUTION_ENABLED.key,
adaptiveEnabled.toString),
+ (SQLConf.CLASSIC_SHUFFLE_DEPENDENCY_FILE_CLEANUP_ENABLED.key,
true.toString)) {
+ val plan = spark.range(100).repartition(10).logicalPlan
+ val df = Dataset.ofRows(spark, plan)
+ // V1 API write
+
df.write.format("parquet").mode(SaveMode.Overwrite).save(dir.getCanonicalPath)
Review Comment:
super nit: writing JSON/CSV is faster for tests.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
