[SPARK-23541][SS] Allow Kafka source to read data with greater parallelism than the number of topic-partitions #20698
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,105 @@ | ||
| /* | ||
| * Licensed to the Apache Software Foundation (ASF) under one or more | ||
| * contributor license agreements. See the NOTICE file distributed with | ||
| * this work for additional information regarding copyright ownership. | ||
| * The ASF licenses this file to You under the Apache License, Version 2.0 | ||
| * (the "License"); you may not use this file except in compliance with | ||
| * the License. You may obtain a copy of the License at | ||
| * | ||
| * http://www.apache.org/licenses/LICENSE-2.0 | ||
| * | ||
| * Unless required by applicable law or agreed to in writing, software | ||
| * distributed under the License is distributed on an "AS IS" BASIS, | ||
| * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | ||
| * See the License for the specific language governing permissions and | ||
| * limitations under the License. | ||
| */ | ||
|
|
||
| package org.apache.spark.sql.kafka010 | ||
|
|
||
| import org.apache.kafka.common.TopicPartition | ||
|
|
||
| import org.apache.spark.sql.sources.v2.DataSourceOptions | ||
|
|
||
|
|
||
| /** | ||
| * Class to calculate offset ranges to process based on the the from and until offsets, and | ||
| * the configured `minPartitions`. | ||
| */ | ||
| private[kafka010] class KafkaOffsetRangeCalculator(val minPartitions: Option[Int]) { | ||
| require(minPartitions.isEmpty || minPartitions.get > 0) | ||
|
|
||
| import KafkaOffsetRangeCalculator._ | ||
| /** | ||
| * Calculate the offset ranges that we are going to process this batch. If `minPartitions` | ||
| * is not set or is set less than or equal the number of `topicPartitions` that we're going to | ||
| * consume, then we fall back to a 1-1 mapping of Spark tasks to Kafka partitions. If | ||
| * `numPartitions` is set higher than the number of our `topicPartitions`, then we will split up | ||
| * the read tasks of the skewed partitions to multiple Spark tasks. | ||
| * The number of Spark tasks will be *approximately* `numPartitions`. It can be less or more | ||
| * depending on rounding errors or Kafka partitions that didn't receive any new data. | ||
| */ | ||
| def getRanges( | ||
| fromOffsets: PartitionOffsetMap, | ||
| untilOffsets: PartitionOffsetMap, | ||
| executorLocations: Seq[String] = Seq.empty): Seq[KafkaOffsetRange] = { | ||
| val partitionsToRead = untilOffsets.keySet.intersect(fromOffsets.keySet) | ||
|
|
||
| val offsetRanges = partitionsToRead.toSeq.map { tp => | ||
| KafkaOffsetRange(tp, fromOffsets(tp), untilOffsets(tp), preferredLoc = None) | ||
| }.filter(_.size > 0) | ||
|
|
||
| // If minPartitions not set or there are enough partitions to satisfy minPartitions | ||
| if (minPartitions.isEmpty || offsetRanges.size > minPartitions.get) { | ||
| // Assign preferred executor locations to each range such that the same topic-partition is | ||
| // preferentially read from the same executor and the KafkaConsumer can be reused. | ||
| offsetRanges.map { range => | ||
| range.copy(preferredLoc = getLocation(range.topicPartition, executorLocations)) | ||
| } | ||
| } else { | ||
|
|
||
| // Splits offset ranges with relatively large amount of data to smaller ones. | ||
| val totalSize = offsetRanges.map(_.size).sum | ||
| val idealRangeSize = totalSize.toDouble / minPartitions.get | ||
|
|
||
| offsetRanges.flatMap { range => | ||
| // Split the current range into subranges as close to the ideal range size | ||
| val numSplitsInRange = math.round(range.size.toDouble / idealRangeSize).toInt | ||
|
|
||
| (0 until numSplitsInRange).map { i => | ||
| val splitStart = range.fromOffset + range.size * (i.toDouble / numSplitsInRange) | ||
| val splitEnd = range.fromOffset + range.size * ((i.toDouble + 1) / numSplitsInRange) | ||
| KafkaOffsetRange( | ||
| range.topicPartition, splitStart.toLong, splitEnd.toLong, preferredLoc = None) | ||
| } | ||
| } | ||
| } | ||
| } | ||
|
|
||
| private def getLocation(tp: TopicPartition, executorLocations: Seq[String]): Option[String] = { | ||
| def floorMod(a: Long, b: Int): Int = ((a % b).toInt + b) % b | ||
|
|
||
| val numExecutors = executorLocations.length | ||
| if (numExecutors > 0) { | ||
| // This allows cached KafkaConsumers in the executors to be re-used to read the same | ||
| // partition in every batch. | ||
| Some(executorLocations(floorMod(tp.hashCode, numExecutors))) | ||
| } else None | ||
| } | ||
| } | ||
|
|
||
| private[kafka010] object KafkaOffsetRangeCalculator { | ||
|
|
||
| def apply(options: DataSourceOptions): KafkaOffsetRangeCalculator = { | ||
| val optionalValue = Option(options.get("minPartitions").orElse(null)).map(_.toInt) | ||
|
Contributor
There was a problem hiding this comment. nit:
Contributor
Author
There was a problem hiding this comment. Because it returns java Optional and not scala Option. |
||
| new KafkaOffsetRangeCalculator(optionalValue) | ||
| } | ||
| } | ||
|
|
||
| private[kafka010] case class KafkaOffsetRange( | ||
| topicPartition: TopicPartition, | ||
| fromOffset: Long, | ||
| untilOffset: Long, | ||
| preferredLoc: Option[String]) { | ||
| lazy val size: Long = untilOffset - fromOffset | ||
| } | ||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,24 @@ | ||
| /* | ||
| * Licensed to the Apache Software Foundation (ASF) under one or more | ||
| * contributor license agreements. See the NOTICE file distributed with | ||
| * this work for additional information regarding copyright ownership. | ||
| * The ASF licenses this file to You under the Apache License, Version 2.0 | ||
| * (the "License"); you may not use this file except in compliance with | ||
| * the License. You may obtain a copy of the License at | ||
| * | ||
| * http://www.apache.org/licenses/LICENSE-2.0 | ||
| * | ||
| * Unless required by applicable law or agreed to in writing, software | ||
| * distributed under the License is distributed on an "AS IS" BASIS, | ||
| * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | ||
| * See the License for the specific language governing permissions and | ||
| * limitations under the License. | ||
| */ | ||
| package org.apache.spark.sql | ||
|
|
||
| import org.apache.kafka.common.TopicPartition | ||
|
|
||
| package object kafka010 { // scalastyle:ignore | ||
| // ^^ scalastyle:ignore is for ignoring warnings about digits in package name | ||
| type PartitionOffsetMap = Map[TopicPartition, Long] | ||
| } |
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
was this check here before? What if there are new topic partitions? Are we missing those, because they may not exist in fromOffsets?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
fromOffsetshere will contain the initial offsets of new partitions. See the how fromOffsets is set withstartOffsets + newPartitionInitialOffsets.