[SPARK-18682][SS] Batch Source for Kafka #16686
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 +1,83 @@ | ||
| /* | ||
| * 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 java.{util => ju} | ||
|
|
||
| import scala.collection.JavaConverters._ | ||
|
|
||
| import org.apache.kafka.clients.consumer.{Consumer, KafkaConsumer} | ||
| import org.apache.kafka.clients.consumer.internals.NoOpConsumerRebalanceListener | ||
| import org.apache.kafka.common.TopicPartition | ||
|
|
||
| /** | ||
| * Subscribe allows you to subscribe to a fixed collection of topics. | ||
| * SubscribePattern allows you to use a regex to specify topics of interest. | ||
| * Note that unlike the 0.8 integration, * using Subscribe or SubscribePattern | ||
| * should respond to adding partitions during a running stream. | ||
| * Finally, Assign allows you to specify a fixed collection of partitions. | ||
| * All three strategies have overloaded constructors that allow you to specify | ||
| * the starting offset for a particular partition. | ||
| */ | ||
| sealed trait ConsumerStrategy { | ||
| def createConsumer(kafkaParams: ju.Map[String, Object]): Consumer[Array[Byte], Array[Byte]] | ||
| } | ||
|
|
||
| /** | ||
|
Contributor
There was a problem hiding this comment. nit: short docs can be put in a single line |
||
| * Specify a fixed collection of partitions. | ||
| */ | ||
| case class AssignStrategy(partitions: Array[TopicPartition]) extends ConsumerStrategy { | ||
| override def createConsumer( | ||
| kafkaParams: ju.Map[String, Object]): Consumer[Array[Byte], Array[Byte]] = { | ||
| val consumer = new KafkaConsumer[Array[Byte], Array[Byte]](kafkaParams) | ||
| consumer.assign(ju.Arrays.asList(partitions: _*)) | ||
| consumer | ||
| } | ||
|
|
||
| override def toString: String = s"Assign[${partitions.mkString(", ")}]" | ||
| } | ||
|
|
||
| /** | ||
| * Subscribe to a fixed collection of topics. | ||
| */ | ||
| case class SubscribeStrategy(topics: Seq[String]) extends ConsumerStrategy { | ||
| override def createConsumer( | ||
| kafkaParams: ju.Map[String, Object]): Consumer[Array[Byte], Array[Byte]] = { | ||
| val consumer = new KafkaConsumer[Array[Byte], Array[Byte]](kafkaParams) | ||
| consumer.subscribe(topics.asJava) | ||
| consumer | ||
| } | ||
|
|
||
| override def toString: String = s"Subscribe[${topics.mkString(", ")}]" | ||
| } | ||
|
|
||
| /** | ||
| * Use a regex to specify topics of interest. | ||
| */ | ||
| case class SubscribePatternStrategy(topicPattern: String) extends ConsumerStrategy { | ||
| override def createConsumer( | ||
| kafkaParams: ju.Map[String, Object]): Consumer[Array[Byte], Array[Byte]] = { | ||
| val consumer = new KafkaConsumer[Array[Byte], Array[Byte]](kafkaParams) | ||
| consumer.subscribe( | ||
| ju.regex.Pattern.compile(topicPattern), | ||
| new NoOpConsumerRebalanceListener()) | ||
| consumer | ||
| } | ||
|
|
||
| override def toString: String = s"SubscribePattern[$topicPattern]" | ||
| } | ||
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 +1,123 @@ | ||
| /* | ||
| * 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 java.{util => ju} | ||
|
|
||
| import org.apache.kafka.common.TopicPartition | ||
|
|
||
| import org.apache.spark.internal.Logging | ||
| import org.apache.spark.rdd.RDD | ||
| import org.apache.spark.sql.{Row, SQLContext} | ||
| import org.apache.spark.sql.catalyst.InternalRow | ||
| import org.apache.spark.sql.catalyst.util.DateTimeUtils | ||
| import org.apache.spark.sql.sources.{BaseRelation, TableScan} | ||
| import org.apache.spark.sql.types.StructType | ||
| import org.apache.spark.unsafe.types.UTF8String | ||
|
|
||
|
|
||
| private[kafka010] class KafkaRelation( | ||
| override val sqlContext: SQLContext, | ||
|
|
||
| kafkaReader: KafkaTopicPartitionOffsetReader, | ||
| executorKafkaParams: ju.Map[String, Object], | ||
| sourceOptions: Map[String, String], | ||
| failOnDataLoss: Boolean, | ||
| startingOffsets: KafkaOffsets, | ||
| endingOffsets: KafkaOffsets) | ||
| extends BaseRelation with TableScan with Logging { | ||
|
|
||
| assert(startingOffsets != LatestOffsets, | ||
| "Starting offset not allowed to be set to latest offsets.") | ||
| assert(endingOffsets != EarliestOffsets, | ||
| "Ending offset not allowed to be set to earliest offsets.") | ||
|
|
||
| private val pollTimeoutMs = sourceOptions.getOrElse( | ||
| "kafkaConsumer.pollTimeoutMs", | ||
| sqlContext.sparkContext.conf.getTimeAsMs("spark.network.timeout", "120s").toString | ||
| ).toLong | ||
|
|
||
| override def schema: StructType = KafkaTopicPartitionOffsetReader.kafkaSchema | ||
|
|
||
| override def buildScan(): RDD[Row] = { | ||
| // Leverage the KafkaReader to obtain the relevant partition offsets | ||
| val fromPartitionOffsets = getPartitionOffsets(startingOffsets) | ||
| val untilPartitionOffsets = getPartitionOffsets(endingOffsets) | ||
| // Obtain topicPartitions in both from and until partition offset, ignoring | ||
| // topic partitions that were added and/or deleted between the two above calls. | ||
| if (fromPartitionOffsets.keySet != untilPartitionOffsets.keySet) { | ||
| implicit val topicOrdering: Ordering[TopicPartition] = Ordering.by(t => t.topic()) | ||
| val fromTopics = fromPartitionOffsets.keySet.toList.sorted.mkString(",") | ||
| val untilTopics = untilPartitionOffsets.keySet.toList.sorted.mkString(",") | ||
| throw new IllegalStateException("different topic partitions " + | ||
| s"for starting offsets topics[${fromTopics}] and " + | ||
| s"ending offsets topics[${untilTopics}]") | ||
| } | ||
|
|
||
| // Calculate offset ranges | ||
| val offsetRanges = untilPartitionOffsets.keySet.map { tp => | ||
| val fromOffset = fromPartitionOffsets.get(tp).getOrElse { | ||
| // This should not happen since topicPartitions contains all partitions not in | ||
| // fromPartitionOffsets | ||
| throw new IllegalStateException(s"$tp doesn't have a from offset") | ||
| } | ||
| val untilOffset = untilPartitionOffsets(tp) | ||
| KafkaSourceRDDOffsetRange(tp, fromOffset, untilOffset, None) | ||
| }.toArray | ||
|
|
||
| logInfo("GetBatch generating RDD of offset range: " + | ||
| offsetRanges.sortBy(_.topicPartition.toString).mkString(", ")) | ||
|
|
||
| // Create an RDD that reads from Kafka and get the (key, value) pair as byte arrays. | ||
| val rdd = new KafkaSourceRDD( | ||
|
Member
There was a problem hiding this comment. I found |
||
| sqlContext.sparkContext, executorKafkaParams, offsetRanges, | ||
| pollTimeoutMs, failOnDataLoss, reuseKafkaConsumer = false).map { cr => | ||
| InternalRow( | ||
| cr.key, | ||
| cr.value, | ||
| UTF8String.fromString(cr.topic), | ||
| cr.partition, | ||
| cr.offset, | ||
| DateTimeUtils.fromJavaTimestamp(new java.sql.Timestamp(cr.timestamp)), | ||
| cr.timestampType.id) | ||
| } | ||
| sqlContext.internalCreateDataFrame(rdd, schema).rdd | ||
| } | ||
|
|
||
| private def getPartitionOffsets(kafkaOffsets: KafkaOffsets): Map[TopicPartition, Long] = { | ||
| def validateTopicPartitions(partitions: Set[TopicPartition], | ||
| partitionOffsets: Map[TopicPartition, Long]): Map[TopicPartition, Long] = { | ||
| assert(partitions == partitionOffsets.keySet, | ||
| "If startingOffsets contains specific offsets, you must specify all TopicPartitions.\n" + | ||
| "Use -1 for latest, -2 for earliest, if you don't care.\n" + | ||
| s"Specified: ${partitionOffsets.keySet} Assigned: ${partitions}") | ||
| logDebug(s"Partitions assigned to consumer: $partitions. Seeking to $partitionOffsets") | ||
| partitionOffsets | ||
| } | ||
| val partitions = kafkaReader.fetchTopicPartitions() | ||
| // Obtain TopicPartition offsets with late binding support | ||
| kafkaOffsets match { | ||
| case EarliestOffsets => partitions.map { | ||
| case tp => tp -> KafkaOffsets.EARLIEST | ||
| }.toMap | ||
| case LatestOffsets => partitions.map { | ||
| case tp => tp -> KafkaOffsets.LATEST | ||
| }.toMap | ||
| case SpecificOffsets(partitionOffsets) => | ||
| validateTopicPartitions(partitions, partitionOffsets) | ||
| } | ||
| } | ||
| } | ||
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.
nit: offset range is $range