Github user budde commented on a diff in the pull request:
https://github.com/apache/spark/pull/17467#discussion_r112766633
--- Diff:
external/kinesis-asl/src/test/scala/org/apache/spark/streaming/kinesis/KinesisBackedBlockRDDSuite.scala
---
@@ -101,6 +101,37 @@ abstract class
KinesisBackedBlockRDDTests(aggregateTestData: Boolean)
}
}
+ testIfEnabled("Basic reading from Kinesis with modified configurations")
{
+ // Add Kinesis retry configurations
+ sc.conf.set("spark.streaming.kinesis.retry.waitTime", "1000ms")
+ sc.conf.set("spark.streaming.kinesis.retry.maxAttempts", "5")
+
+ // Verify all data using multiple ranges in a single RDD partition
+ val receivedData1 = new KinesisBackedBlockRDD[Array[Byte]](sc,
testUtils.regionName,
+ testUtils.endpointUrl, fakeBlockIds(1),
+ Array(SequenceNumberRanges(allRanges.toArray)),
+ sparkConf = sc.getConf).map { bytes => new String(bytes).toInt
}.collect()
+ assert(receivedData1.toSet === testData.toSet)
+
+ // Verify all data using one range in each of the multiple RDD
partitions
+ val receivedData2 = new KinesisBackedBlockRDD[Array[Byte]](sc,
testUtils.regionName,
+ testUtils.endpointUrl, fakeBlockIds(allRanges.size),
+ allRanges.map { range => SequenceNumberRanges(Array(range))
}.toArray,
+ sparkConf = sc.getConf).map { bytes => new String(bytes).toInt
}.collect()
+ assert(receivedData2.toSet === testData.toSet)
+
+ // Verify ordering within each partition
+ val receivedData3 = new KinesisBackedBlockRDD[Array[Byte]](sc,
testUtils.regionName,
+ testUtils.endpointUrl, fakeBlockIds(allRanges.size),
+ allRanges.map { range => SequenceNumberRanges(Array(range))
}.toArray,
+ sparkConf = sc.getConf
+ ).map { bytes => new String(bytes).toInt }.collectPartitions()
--- End diff --
*nit:* move this to the end of previous line
---
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]
