viirya commented on code in PR #55420: URL: https://github.com/apache/spark/pull/55420#discussion_r3228430377
########## connector/kafka-0-10-sql/src/test/scala/org/apache/spark/sql/kafka010/RTMKafkaKafkaBenchmark.scala: ########## @@ -0,0 +1,327 @@ +/* + * 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.nio.file.Files +import java.util.{Properties, Timer, TimerTask} +import java.util.concurrent.{CountDownLatch, TimeUnit} +import java.util.concurrent.atomic.{AtomicInteger, AtomicLong} + +import scala.concurrent.duration._ + +import org.apache.kafka.clients.producer.{Callback, KafkaProducer, Producer, ProducerRecord, RecordMetadata} + +import org.apache.spark.benchmark.BenchmarkBase +import org.apache.spark.internal.Logging +import org.apache.spark.sql.{Column, SparkSession} +import org.apache.spark.sql.execution.streaming.RealTimeTrigger +import org.apache.spark.sql.functions._ +import org.apache.spark.sql.internal.SQLConf +import org.apache.spark.sql.streaming.StreamingQueryListener + +/** + * Stateless Kafka-to-Kafka RTM benchmark. Reads from an input Kafka topic, applies a + * stateless transformation, and writes results to an output Kafka topic using + * [[RealTimeTrigger]]. After the run it reports e2e latency percentiles. + * + * The benchmark spins up a real local-cluster Spark context and a live embedded Kafka + * broker, so a single run takes several minutes. + * + * To run this benchmark: + * {{{ + * 1. without sbt: + * bin/spark-submit --class <this class> + * --jars <spark core test jar>,<spark sql test jar> <spark sql kafka 0-10 test jar> + * 2. build/sbt "sql-kafka-0-10/Test/runMain <this class>" + * 3. generate result: + * SPARK_GENERATE_BENCHMARK_FILES=1 build/sbt "sql-kafka-0-10/Test/runMain <this class>" + * Results will be written to: + * "connector/kafka-0-10-sql/benchmarks/RTMKafkaKafkaBenchmark-results.txt". + * }}} + */ +object RTMKafkaKafkaBenchmark extends BenchmarkBase with Logging { + + private val topicId = new AtomicInteger(0) + private var spark: SparkSession = _ + private var testUtils: KafkaTestUtils = _ + + override def runBenchmarkSuite(mainArgs: Array[String]): Unit = { Review Comment: BenchmarkBase.main calls runBenchmarkSuite(args) and only calls afterAll() afterwards; it does not wrap runBenchmarkSuite in try/finally. This benchmark starts embedded Kafka and a local-cluster Spark session in runBenchmarkSuite, then relies on afterAll() for teardown. If benchmark(...) times out, the query fails, getLatencies throws, or setup partially fails after Kafka starts, afterAll() will not run, leaving Kafka/Spark resources behind. Since this benchmark intentionally runs heavyweight local resources, it should handle its own exception path, e.g. wrap setup/run in try/finally or call an idempotent cleanup method on failure. -- 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. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
