linhongliu-db commented on a change in pull request #35856: URL: https://github.com/apache/spark/pull/35856#discussion_r839169074
########## File path: sql/core/src/main/scala/org/apache/spark/sql/diagnostic/DiagnosticListener.scala ########## @@ -0,0 +1,104 @@ +/* + * 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.diagnostic + +import org.apache.spark.SparkConf +import org.apache.spark.scheduler.{SparkListener, SparkListenerEvent} +import org.apache.spark.sql.execution.ExplainMode +import org.apache.spark.sql.execution.ui.{SparkListenerSQLAdaptiveExecutionUpdate, SparkListenerSQLExecutionEnd, SparkListenerSQLExecutionStart} +import org.apache.spark.sql.internal.SQLConf +import org.apache.spark.sql.internal.StaticSQLConf.UI_RETAINED_EXECUTIONS +import org.apache.spark.status.{ElementTrackingStore, KVUtils} + +class DiagnosticListener( + conf: SparkConf, + kvStore: ElementTrackingStore) extends SparkListener { + + kvStore.addTrigger( + classOf[ExecutionDiagnosticData], + conf.get(UI_RETAINED_EXECUTIONS)) { count => + cleanupExecutions(count) + } + + override def onOtherEvent(event: SparkListenerEvent): Unit = event match { + case e: SparkListenerSQLExecutionStart => onExecutionStart(e) + case e: SparkListenerSQLExecutionEnd => onExecutionEnd(e) + case e: SparkListenerSQLAdaptiveExecutionUpdate => onAdaptiveExecutionUpdate(e) + case _ => // Ignore + } + + private def onAdaptiveExecutionUpdate(event: SparkListenerSQLAdaptiveExecutionUpdate): Unit = { + val data = new AdaptiveExecutionUpdate( + event.executionId, + System.currentTimeMillis(), + event.physicalPlanDescription Review comment: I'm not worried about the cost too much because a separate listener with a separate event queue won't slow down other listeners. But I do want to make sure everything we added is necessary. I mean, usually, it's enough to only output full fields in the final plan, and plan change history can keep a truncated plan. Because, IIUC, the AQE aims to change the operators and expressions usually unchanged. -- 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]
