diff options
author | Takeshi YAMAMURO <linguin.m.s@gmail.com> | 2016-12-10 05:32:04 +0800 |
---|---|---|
committer | Sean Owen <sowen@cloudera.com> | 2016-12-10 05:32:04 +0800 |
commit | b08b5004563b28d10b07b70946a9f72408ed228a (patch) | |
tree | 74f57e536ce48227fd239f915d1e8479a5b00fe9 /external/kinesis-asl/src/main | |
parent | be5fc6ef72c7eb586b184b0f42ac50ef32843208 (diff) | |
download | spark-b08b5004563b28d10b07b70946a9f72408ed228a.tar.gz spark-b08b5004563b28d10b07b70946a9f72408ed228a.tar.bz2 spark-b08b5004563b28d10b07b70946a9f72408ed228a.zip |
[SPARK-18620][STREAMING][KINESIS] Flatten input rates in timeline for streaming + kinesis
## What changes were proposed in this pull request?
This pr is to make input rates in timeline more flat for spark streaming + kinesis.
Since kinesis workers fetch records and push them into block generators in bulk, timeline in web UI has many spikes when `maxRates` applied (See a Figure.1 below). This fix splits fetched input records into multiple `adRecords` calls.
Figure.1 Apply `maxRates=500` in vanilla Spark
<img width="1084" alt="apply_limit in_vanilla_spark" src="https://cloud.githubusercontent.com/assets/692303/20823861/4602f300-b89b-11e6-95f3-164a37061305.png">
Figure.2 Apply `maxRates=500` in Spark with my patch
<img width="1056" alt="apply_limit in_spark_with_my_patch" src="https://cloud.githubusercontent.com/assets/692303/20823882/6c46352c-b89b-11e6-81ab-afd8abfe0cfe.png">
## How was this patch tested?
Add tests to check to split input records into multiple `addRecords` calls.
Author: Takeshi YAMAMURO <linguin.m.s@gmail.com>
Closes #16114 from maropu/SPARK-18620.
Diffstat (limited to 'external/kinesis-asl/src/main')
2 files changed, 18 insertions, 2 deletions
diff --git a/external/kinesis-asl/src/main/scala/org/apache/spark/streaming/kinesis/KinesisReceiver.scala b/external/kinesis-asl/src/main/scala/org/apache/spark/streaming/kinesis/KinesisReceiver.scala index 858368d135..393e56a393 100644 --- a/external/kinesis-asl/src/main/scala/org/apache/spark/streaming/kinesis/KinesisReceiver.scala +++ b/external/kinesis-asl/src/main/scala/org/apache/spark/streaming/kinesis/KinesisReceiver.scala @@ -221,6 +221,12 @@ private[kinesis] class KinesisReceiver[T]( } } + /** Return the current rate limit defined in [[BlockGenerator]]. */ + private[kinesis] def getCurrentLimit: Int = { + assert(blockGenerator != null) + math.min(blockGenerator.getCurrentLimit, Int.MaxValue).toInt + } + /** Get the latest sequence number for the given shard that can be checkpointed through KCL */ private[kinesis] def getLatestSeqNumToCheckpoint(shardId: String): Option[String] = { Option(shardIdToLatestStoredSeqNum.get(shardId)) diff --git a/external/kinesis-asl/src/main/scala/org/apache/spark/streaming/kinesis/KinesisRecordProcessor.scala b/external/kinesis-asl/src/main/scala/org/apache/spark/streaming/kinesis/KinesisRecordProcessor.scala index a0ccd086d9..73ccc4ad23 100644 --- a/external/kinesis-asl/src/main/scala/org/apache/spark/streaming/kinesis/KinesisRecordProcessor.scala +++ b/external/kinesis-asl/src/main/scala/org/apache/spark/streaming/kinesis/KinesisRecordProcessor.scala @@ -68,8 +68,18 @@ private[kinesis] class KinesisRecordProcessor[T](receiver: KinesisReceiver[T], w override def processRecords(batch: List[Record], checkpointer: IRecordProcessorCheckpointer) { if (!receiver.isStopped()) { try { - receiver.addRecords(shardId, batch) - logDebug(s"Stored: Worker $workerId stored ${batch.size} records for shardId $shardId") + // Limit the number of processed records from Kinesis stream. This is because the KCL cannot + // control the number of aggregated records to be fetched even if we set `MaxRecords` + // in `KinesisClientLibConfiguration`. For example, if we set 10 to the number of max + // records in a worker and a producer aggregates two records into one message, the worker + // possibly 20 records every callback function called. + val maxRecords = receiver.getCurrentLimit + for (start <- 0 until batch.size by maxRecords) { + val miniBatch = batch.subList(start, math.min(start + maxRecords, batch.size)) + receiver.addRecords(shardId, miniBatch) + logDebug(s"Stored: Worker $workerId stored ${miniBatch.size} records " + + s"for shardId $shardId") + } receiver.setCheckpointer(shardId, checkpointer) } catch { case NonFatal(e) => |