1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
|
/*
* 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 scala.annotation.tailrec
import scala.collection.mutable
import scala.reflect.ClassTag
import kafka.common.TopicAndPartition
import kafka.message.MessageAndMetadata
import kafka.serializer.Decoder
import org.apache.spark.SparkException
import org.apache.spark.internal.Logging
import org.apache.spark.streaming.{StreamingContext, Time}
import org.apache.spark.streaming.dstream._
import org.apache.spark.streaming.kafka.KafkaCluster.LeaderOffset
import org.apache.spark.streaming.scheduler.{RateController, StreamInputInfo}
import org.apache.spark.streaming.scheduler.rate.RateEstimator
/**
* A stream of {@link org.apache.spark.streaming.kafka.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.
* Starting offsets are specified in advance,
* and this DStream is not responsible for committing offsets,
* so that you can control exactly-once semantics.
* For an easy interface to Kafka-managed offsets,
* see {@link org.apache.spark.streaming.kafka.KafkaCluster}
* @param kafkaParams Kafka <a href="http://kafka.apache.org/documentation.html#configuration">
* configuration parameters</a>.
* Requires "metadata.broker.list" or "bootstrap.servers" to be set with Kafka broker(s),
* NOT zookeeper servers, specified in host1:port1,host2:port2 form.
* @param fromOffsets per-topic/partition Kafka offsets defining the (inclusive)
* starting point of the stream
* @param messageHandler function for translating each message into the desired type
*/
private[streaming]
class DirectKafkaInputDStream[
K: ClassTag,
V: ClassTag,
U <: Decoder[K]: ClassTag,
T <: Decoder[V]: ClassTag,
R: ClassTag](
_ssc: StreamingContext,
val kafkaParams: Map[String, String],
val fromOffsets: Map[TopicAndPartition, Long],
messageHandler: MessageAndMetadata[K, V] => R
) extends InputDStream[R](_ssc) with Logging {
val maxRetries = context.sparkContext.getConf.getInt(
"spark.streaming.kafka.maxRetries", 1)
// Keep this consistent with how other streams are named (e.g. "Flume polling stream [2]")
private[streaming] override def name: String = s"Kafka 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
}
}
protected val kc = new KafkaCluster(kafkaParams)
private val maxRateLimitPerPartition: Int = context.sparkContext.getConf.getInt(
"spark.streaming.kafka.maxRatePerPartition", 0)
protected[streaming] def maxMessagesPerPartition(
offsets: Map[TopicAndPartition, Long]): Option[Map[TopicAndPartition, 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 var currentOffsets = fromOffsets
@tailrec
protected final def latestLeaderOffsets(retries: Int): Map[TopicAndPartition, LeaderOffset] = {
val o = kc.getLatestLeaderOffsets(currentOffsets.keySet)
// Either.fold would confuse @tailrec, do it manually
if (o.isLeft) {
val err = o.left.get.toString
if (retries <= 0) {
throw new SparkException(err)
} else {
log.error(err)
Thread.sleep(kc.config.refreshLeaderBackoffMs)
latestLeaderOffsets(retries - 1)
}
} else {
o.right.get
}
}
// limits the maximum number of messages per partition
protected def clamp(
leaderOffsets: Map[TopicAndPartition, LeaderOffset]): Map[TopicAndPartition, LeaderOffset] = {
val offsets = leaderOffsets.mapValues(lo => lo.offset)
maxMessagesPerPartition(offsets).map { mmp =>
mmp.map { case (tp, messages) =>
val lo = leaderOffsets(tp)
tp -> lo.copy(offset = Math.min(currentOffsets(tp) + messages, lo.offset))
}
}.getOrElse(leaderOffsets)
}
override def compute(validTime: Time): Option[KafkaRDD[K, V, U, T, R]] = {
val untilOffsets = clamp(latestLeaderOffsets(maxRetries))
val rdd = KafkaRDD[K, V, U, T, R](
context.sparkContext, kafkaParams, currentOffsets, untilOffsets, messageHandler)
// Report the record number and metadata of this batch interval to InputInfoTracker.
val offsetRanges = currentOffsets.map { case (tp, fo) =>
val uo = untilOffsets(tp)
OffsetRange(tp.topic, tp.partition, fo, uo.offset)
}
val description = offsetRanges.filter { offsetRange =>
// Don't display empty ranges.
offsetRange.fromOffset != offsetRange.untilOffset
}.map { offsetRange =>
s"topic: ${offsetRange.topic}\tpartition: ${offsetRange.partition}\t" +
s"offsets: ${offsetRange.fromOffset} to ${offsetRange.untilOffset}"
}.mkString("\n")
// Copy offsetRanges to immutable.List to prevent from being modified by the user
val metadata = Map(
"offsets" -> offsetRanges.toList,
StreamInputInfo.METADATA_KEY_DESCRIPTION -> description)
val inputInfo = StreamInputInfo(id, rdd.count, metadata)
ssc.scheduler.inputInfoTracker.reportInfo(validTime, inputInfo)
currentOffsets = untilOffsets.map(kv => kv._1 -> kv._2.offset)
Some(rdd)
}
override def start(): Unit = {
}
def stop(): Unit = {
}
private[streaming]
class DirectKafkaInputDStreamCheckpointData extends DStreamCheckpointData(this) {
def batchForTime: mutable.HashMap[Time, Array[(String, Int, Long, Long)]] = {
data.asInstanceOf[mutable.HashMap[Time, Array[OffsetRange.OffsetRangeTuple]]]
}
override def update(time: Time) {
batchForTime.clear()
generatedRDDs.foreach { kv =>
val a = kv._2.asInstanceOf[KafkaRDD[K, V, U, T, R]].offsetRanges.map(_.toTuple).toArray
batchForTime += kv._1 -> a
}
}
override def cleanup(time: Time) { }
override def restore() {
// this is assuming that the topics don't change during execution, which is true currently
val topics = fromOffsets.keySet
val leaders = KafkaCluster.checkErrors(kc.findLeaders(topics))
batchForTime.toSeq.sortBy(_._1)(Time.ordering).foreach { case (t, b) =>
logInfo(s"Restoring KafkaRDD for time $t ${b.mkString("[", ", ", "]")}")
generatedRDDs += t -> new KafkaRDD[K, V, U, T, R](
context.sparkContext, kafkaParams, b.map(OffsetRange(_)), leaders, messageHandler)
}
}
}
/**
* A RateController to retrieve the rate from RateEstimator.
*/
private[streaming] class DirectKafkaRateController(id: Int, estimator: RateEstimator)
extends RateController(id, estimator) {
override def publish(rate: Long): Unit = ()
}
}
|
