gaborgsomogyi commented on a change in pull request #19096: [SPARK-21869][SS] A
cached Kafka producer should not be closed if any task is using it - adds inuse
tracking.
URL: https://github.com/apache/spark/pull/19096#discussion_r264179052
##########
File path:
external/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/CachedKafkaProducer.scala
##########
@@ -18,103 +18,180 @@
package org.apache.spark.sql.kafka010
import java.{util => ju}
-import java.util.concurrent.{ConcurrentMap, ExecutionException, TimeUnit}
+import java.util.concurrent.{ConcurrentLinkedQueue, ConcurrentMap,
ExecutionException, TimeUnit}
+import java.util.concurrent.atomic.AtomicInteger
+
+import scala.collection.JavaConverters._
+import scala.util.control.NonFatal
import com.google.common.cache._
import com.google.common.util.concurrent.{ExecutionError,
UncheckedExecutionException}
import org.apache.kafka.clients.producer.KafkaProducer
-import scala.collection.JavaConverters._
-import scala.util.control.NonFatal
import org.apache.spark.SparkEnv
import org.apache.spark.internal.Logging
-private[kafka010] object CachedKafkaProducer extends Logging {
+private[kafka010] case class CachedKafkaProducer(
+ private val id: String = ju.UUID.randomUUID().toString,
+ private val inUseCount: AtomicInteger = new AtomicInteger(0),
+ private val kafkaParams: Seq[(String, Object)]) extends Logging {
- private type Producer = KafkaProducer[Array[Byte], Array[Byte]]
+ private val configMap = kafkaParams.map(x => x._1 -> x._2).toMap.asJava
+
+ lazy val kafkaProducer: KafkaProducer[Array[Byte], Array[Byte]] = {
+ val producer = new KafkaProducer[Array[Byte], Array[Byte]](configMap)
+ logDebug(s"Created a new instance of KafkaProducer for " +
+ s"$kafkaParams with Id: $id")
+ closed = false
+ producer
+ }
+ private var isCached: Boolean = true
+ private var closed: Boolean = true
+ private def close(): Unit = {
+ try {
+ this.synchronized {
+ if (!closed) {
+ closed = true
+ kafkaProducer.close()
+ logInfo(s"Closed kafka producer: $kafkaProducer")
Review comment:
As a general comment I would write out the kafka params all the time which
would make it easier to follow the lifecycle of a producer. (Maybe instance is
also useful but the kafka params needed from my perspective).
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
