Github user zsxwing commented on a diff in the pull request:
https://github.com/apache/spark/pull/9765#discussion_r47552258
--- Diff:
streaming/src/test/scala/org/apache/spark/streaming/CheckpointSuite.scala ---
@@ -715,6 +735,56 @@ class CheckpointSuite extends TestSuiteBase with
DStreamCheckpointTester {
}
}
+ test("DStream checkpoint invoke times") {
+ var clock: ManualClock = null
--- End diff --
I suggest writing a simpler test that only tests this issue, such as:
```
withStreamingContext(new StreamingContext(conf, batchDuration)) { ssc =>
ssc.checkpoint(checkpointDir)
val inputDStream = new CheckpointInputDStream(ssc)
val checkpointData = inputDStream.checkpointData
val mappedDStream = inputDStream.map(_ + 100)
val outputStream = new TestOutputStreamWithPartitions(mappedDStream)
outputStream.register()
/// do more two times output
mappedDStream.foreachRDD(rdd => rdd.count())
mappedDStream.foreachRDD(rdd => rdd.count())
assert(checkpointData.restoredTimes === 0)
val batchDurationMillis = ssc.progressListener.batchDuration
generateOutput(ssc, Time(batchDurationMillis * 3), checkpointDir,
stopSparkContext = false)
assert(checkpointData.restoredTimes === 0)
}
withStreamingContext(new StreamingContext(checkpointDir)) { ssc =>
val checkpointData =
ssc.graph.getInputStreams().head.asInstanceOf[CheckpointInputDStream].checkpointData
ssc.start()
ssc.stop()
assert(checkpointData.restoredTimes === 1)
}
```
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
