HeartSaVioR commented on a change in pull request #24154: [SPARK-27210][SS]
Cleanup incomplete output files in ManifestFileCommitProtocol if task is aborted
URL: https://github.com/apache/spark/pull/24154#discussion_r267604706
##########
File path:
sql/core/src/test/scala/org/apache/spark/sql/streaming/FileStreamSinkSuite.scala
##########
@@ -478,4 +481,48 @@ class FileStreamSinkSuite extends StreamTest {
checkDatasetUnorderly(outputDf, 1, 2, 3)
}
}
+
+ test("cleanup incomplete output for aborted task") {
+ withSQLConf(("spark.sql.streaming.commitProtocolClass",
+ classOf[TaskFailToCommitManifestFileCommitProtocol].getCanonicalName)) {
+ withTempDir { tempDir =>
+ val checkpointDir = new File(tempDir, "chk")
+ val outputDir = new File(tempDir, "output")
+ val inputData = MemoryStream[Int]
+ inputData.addData(1, 2, 3)
+ val q = inputData.toDF()
+ .writeStream
+ .option("checkpointLocation", checkpointDir.getCanonicalPath)
+ .format("parquet")
+ .start(outputDir.getCanonicalPath)
+
+ intercept[StreamingQueryException] {
+ try {
+ q.processAllAvailable()
+ } finally {
+ q.stop()
+ }
+ }
+
+ import scala.collection.JavaConverters._
+ val outputFiles = Files.walk(outputDir.toPath).iterator().asScala
+ .filter(p => Files.isRegularFile(p) && p.endsWith(".parquet"))
+ assert(outputFiles.length === 0, "Incomplete files should be cleaned
up.")
Review comment:
Ah! Nice finding. I forgot that filtered output is an iterator.
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
