Github user harishreedharan commented on a diff in the pull request:
https://github.com/apache/spark/pull/10953#discussion_r51799340
--- Diff:
external/kafka-newapi/src/main/scala/org/apache/spark/streaming/kafka/newapi/DirectKafkaInputDStream.scala
---
@@ -0,0 +1,208 @@
+/*
+ * 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.newapi
+
+import scala.collection.mutable
+import scala.reflect.ClassTag
+
+import org.apache.kafka.clients.consumer.ConsumerRecord
+import org.apache.kafka.common.TopicPartition
+
+import org.apache.spark.Logging
+import org.apache.spark.streaming.{StreamingContext, Time}
+import org.apache.spark.streaming.dstream._
+import org.apache.spark.streaming.kafka.newapi.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.
+ *
+ * @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
+ */
+private[streaming]
+class DirectKafkaInputDStream[
+ K: ClassTag,
+ V: ClassTag,
+ R: ClassTag](
+ @transient ssc_ : StreamingContext,
+ val kafkaParams: Map[String, String],
+ @transient val fromOffsets: Map[TopicPartition, Long],
+ messageHandler: ConsumerRecord[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 0.9 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, ssc_.graph.batchDuration)))
--- End diff --
Why use both `ssc` and `ssc_`?
---
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]
