Github user tdas commented on a diff in the pull request:
https://github.com/apache/spark/pull/11863#discussion_r68529586
--- Diff:
external/kafka-0-10/src/main/scala/org/apache/spark/streaming/kafka/DirectKafkaInputDStream.scala
---
@@ -0,0 +1,318 @@
+/*
+ * 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.streaming.kafka
+
+import java.{ util => ju }
+import java.util.concurrent.ConcurrentLinkedQueue
+import java.util.concurrent.atomic.AtomicReference
+
+import scala.annotation.tailrec
+import scala.collection.JavaConverters._
+import scala.collection.mutable
+import scala.reflect.ClassTag
+
+import org.apache.kafka.clients.consumer._
+import org.apache.kafka.common.{ PartitionInfo, TopicPartition }
+
+import org.apache.spark.annotation.Experimental
+import org.apache.spark.SparkException
+import org.apache.spark.internal.Logging
+import org.apache.spark.storage.StorageLevel
+import org.apache.spark.streaming.{StreamingContext, Time}
+import org.apache.spark.streaming.dstream._
+import org.apache.spark.streaming.scheduler.{RateController,
StreamInputInfo}
+import org.apache.spark.streaming.scheduler.rate.RateEstimator
+
+/**
+ * A stream of [[KafkaRDD]] where
+ * each given Kafka topic/partition corresponds to an RDD partition.
+ * The spark configuration spark.streaming.kafka.maxRatePerPartition gives
the maximum number
+ * of messages
+ * per second that each '''partition''' will accept.
+ * @param locationStrategy In most cases, pass in [[PreferConsistent]],
+ * see [[LocationStrategy]] for more details.
+ * @param executorKafkaParams Kafka
+ * <a href="http://kafka.apache.org/documentation.html#newconsumerconfigs";>
+ * configuration parameters</a>.
+ * Requires "bootstrap.servers" to be set with Kafka broker(s),
+ * NOT zookeeper servers, specified in host1:port1,host2:port2 form.
+ * @param driverConsumer zero-argument function for you to construct a
Kafka Consumer,
+ * and subscribe topics or assign partitions.
+ * This consumer will be used on the driver to query for offsets only,
not messages.
+ * See <a
href="http://kafka.apache.org/documentation.html#newconsumerapi";>Consumer
doc</a>
+ * @tparam K type of Kafka message key
+ * @tparam V type of Kafka message value
+ */
+@Experimental
+private[spark] class DirectKafkaInputDStream[K: ClassTag, V: ClassTag](
+ _ssc: StreamingContext,
+ locationStrategy: LocationStrategy,
+ consumerStrategy: ConsumerStrategy[K, V]
+ ) extends InputDStream[ConsumerRecord[K, V]](_ssc) with Logging with
CanCommitOffsets {
+
+ val executorKafkaParams = {
+ val ekp = new ju.HashMap[String,
Object](consumerStrategy.executorKafkaParams)
+ KafkaUtils.fixKafkaParams(ekp)
+ ekp
+ }
+
+ protected var currentOffsets = Map[TopicPartition, Long]()
+
+ @transient private var kc: Consumer[K, V] = null
+ def consumer(): Consumer[K, V] = this.synchronized {
+ if (null == kc) {
+ kc = consumerStrategy.onStart(currentOffsets)
+ }
+ kc
+ }
+
+ override def persist(newLevel: StorageLevel): DStream[ConsumerRecord[K,
V]] = {
+ logError("Kafka ConsumerRecord is not serializable. " +
+ "Use .map to extract fields before calling .persist or .window")
+ super.persist(newLevel)
+ }
+
+ protected def getBrokers = {
+ val c = consumer
+ val result = new ju.HashMap[TopicPartition, String]()
+ val hosts = new ju.HashMap[TopicPartition, String]()
+ val assignments = c.assignment().iterator()
+ while (assignments.hasNext()) {
+ val tp: TopicPartition = assignments.next()
+ if (null == hosts.get(tp)) {
+ val infos = c.partitionsFor(tp.topic).iterator()
+ while (infos.hasNext()) {
+ val i = infos.next()
+ hosts.put(new TopicPartition(i.topic(), i.partition()),
i.leader.host())
+ }
+ }
+ result.put(tp, hosts.get(tp))
+ }
+ result
+ }
+
+ protected def getPreferredHosts: ju.Map[TopicPartition, String] = {
+ locationStrategy match {
+ case PreferBrokers => getBrokers
+ case PreferConsistent => ju.Collections.emptyMap[TopicPartition,
String]()
+ case PreferFixed(hostMap) => hostMap
+ }
+ }
+
+ // Keep this consistent with how other streams are named (e.g. "Flume
polling stream [2]")
+ private[streaming] override def name: String = s"Kafka 0.10 direct
stream [$id]"
+
+ protected[streaming] override val checkpointData =
+ new DirectKafkaInputDStreamCheckpointData
+
+
+ /**
+ * Asynchronously maintains & sends new rate limits to the receiver
through the receiver tracker.
+ */
+ override protected[streaming] val rateController: Option[RateController]
= {
+ if (RateController.isBackPressureEnabled(ssc.conf)) {
+ Some(new DirectKafkaRateController(id,
+ RateEstimator.create(ssc.conf, context.graph.batchDuration)))
+ } else {
+ None
+ }
+ }
+
+ private val maxRateLimitPerPartition: Int =
context.sparkContext.getConf.getInt(
+ "spark.streaming.kafka.maxRatePerPartition", 0)
+
+ protected[streaming] def maxMessagesPerPartition(
+ offsets: Map[TopicPartition, Long]): Option[Map[TopicPartition, Long]]
= {
+ val estimatedRateLimit = rateController.map(_.getLatestRate().toInt)
+
+ // calculate a per-partition rate limit based on current lag
+ val effectiveRateLimitPerPartition = estimatedRateLimit.filter(_ > 0)
match {
+ case Some(rate) =>
+ val lagPerPartition = offsets.map { case (tp, offset) =>
+ tp -> Math.max(offset - currentOffsets(tp), 0)
+ }
+ val totalLag = lagPerPartition.values.sum
+
+ lagPerPartition.map { case (tp, lag) =>
+ val backpressureRate = Math.round(lag / totalLag.toFloat * rate)
+ tp -> (if (maxRateLimitPerPartition > 0) {
+ Math.min(backpressureRate, maxRateLimitPerPartition)} else
backpressureRate)
+ }
+ case None => offsets.map { case (tp, offset) => tp ->
maxRateLimitPerPartition }
+ }
+
+ if (effectiveRateLimitPerPartition.values.sum > 0) {
+ val secsPerBatch = context.graph.batchDuration.milliseconds.toDouble
/ 1000
+ Some(effectiveRateLimitPerPartition.map {
+ case (tp, limit) => tp -> (secsPerBatch * limit).toLong
+ })
+ } else {
+ None
+ }
+ }
+
+ protected def latestOffsets(): Map[TopicPartition, Long] = {
--- End diff --
Can add explain (and add them as docs) on what this does for the
`newPartitions`? And what does `c.pause` and `c.seektoEnd` do in this context?
---
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]
