cloud-fan commented on code in PR #36564:
URL: https://github.com/apache/spark/pull/36564#discussion_r894633551
##########
core/src/test/scala/org/apache/spark/scheduler/OutputCommitCoordinatorIntegrationSuite.scala:
##########
@@ -46,21 +45,21 @@ class OutputCommitCoordinatorIntegrationSuite
}
test("exception thrown in OutputCommitter.commitTask()") {
- // Regression test for SPARK-10381
- failAfter(Span(60, Seconds)) {
+ val e = intercept[SparkException] {
withTempDir { tempDir =>
sc.parallelize(1 to 4,
2).map(_.toString).saveAsTextFile(tempDir.getAbsolutePath + "/out")
}
- }
+ }.getCause.getMessage
+ assert(e.endsWith("failed; but task commit success, data duplication may
happen."))
}
}
private class ThrowExceptionOnFirstAttemptOutputCommitter extends
FileOutputCommitter {
override def commitTask(context: TaskAttemptContext): Unit = {
val ctx = TaskContext.get()
+ super.commitTask(context)
Review Comment:
why this change? I think the original test wanted to test the case that we
failed before committing in the first task attempt.
--
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
