Github user brkyvz commented on a diff in the pull request:
https://github.com/apache/spark/pull/17467#discussion_r114856307
--- Diff:
external/kinesis-asl/src/test/scala/org/apache/spark/streaming/kinesis/KinesisStreamSuite.scala
---
@@ -234,6 +235,53 @@ abstract class KinesisStreamTests(aggregateTestData:
Boolean) extends KinesisFun
ssc.stop(stopSparkContext = false)
}
+ test("Kinesis read with custom configurations") {
+ try {
+ ssc.sc.conf.set(RETRY_WAIT_TIME_KEY, "2000ms")
+ ssc.sc.conf.set(RETRY_MAX_ATTEMPTS_KEY, "5")
+
+ val kinesisStream = KinesisInputDStream.builder.streamingContext(ssc)
+ .checkpointAppName(appName)
+ .streamName("dummyStream")
+ .endpointUrl(dummyEndpointUrl)
+ .regionName(dummyRegionName)
+ .initialPositionInStream(InitialPositionInStream.LATEST)
+ .checkpointInterval(Seconds(10))
+ .storageLevel(StorageLevel.MEMORY_ONLY)
+ .build()
+ .asInstanceOf[KinesisInputDStream[Array[Byte]]]
+
+ val time = Time(1000)
+ // Generate block info data for testing
+ val seqNumRanges1 = SequenceNumberRanges(
+ SequenceNumberRange("fakeStream", "fakeShardId", "xxx", "yyy", 67))
+ val blockId1 = StreamBlockId(kinesisStream.id, 123)
+ val blockInfo1 = ReceivedBlockInfo(
+ 0, None, Some(seqNumRanges1), new
BlockManagerBasedStoreResult(blockId1, None))
+
+ val seqNumRanges2 = SequenceNumberRanges(
+ SequenceNumberRange("fakeStream", "fakeShardId", "aaa", "bbb", 89))
+ val blockId2 = StreamBlockId(kinesisStream.id, 345)
+ val blockInfo2 = ReceivedBlockInfo(
+ 0, None, Some(seqNumRanges2), new
BlockManagerBasedStoreResult(blockId2, None))
+
+ // Verify that the generated KinesisBackedBlockRDD has the all the
right information
+ val blockInfos = Seq(blockInfo1, blockInfo2)
+
+ val kinesisRDD =
+ kinesisStream.createBlockRDD(time,
blockInfos).asInstanceOf[KinesisBackedBlockRDD[_]]
+
+ assert(kinesisRDD.kinesisReadConfigs.retryWaitTimeMs === 2000)
+ assert(kinesisRDD.kinesisReadConfigs.maxRetries === 5)
+ assert(kinesisRDD.kinesisReadConfigs.retryTimeoutMs ===
batchDuration.milliseconds)
+
+ ssc.sc.conf.remove(RETRY_WAIT_TIME_KEY)
--- End diff --
these also need to be in the `finally`
---
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 infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
