i7xh commented on a change in pull request #1085: URL: https://github.com/apache/incubator-kyuubi/pull/1085#discussion_r710855635
########## File path: dev/kyuubi-extension-spark-3-1/src/main/scala/org/apache/kyuubi/sql/watchdog/MaxOutputRowsRule.scala ########## @@ -0,0 +1,73 @@ +/* + * 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.kyuubi.sql.watchdog + +import org.apache.spark.sql.SparkSession +import org.apache.spark.sql.catalyst.dsl.expressions._ +import org.apache.spark.sql.catalyst.plans.logical.{GlobalLimit, LogicalPlan, Project} +import org.apache.spark.sql.catalyst.rules.Rule +import org.apache.spark.sql.catalyst.trees.Origin +import org.apache.spark.sql.execution.command.InsertIntoDataSourceDirCommand + +import org.apache.kyuubi.sql.KyuubiSQLConf + +/* +* Add MaxOutputRows rule for output rows limitation to avoid huge output rows of query unexpectedly +* mainly applied to cases as below: +* case 1: +* {{{ +* INSERT OVERWRITE DIRECTORY (path=STRING)? +* USING format OPTIONS ([option1_name "option1_value", option2_name "option2_value", ...]) +* SELECT ... +* }}} +* +* case 2: +* {{{ +* SELECT [c1, c2, ...] +* }}} +* +* case 3: +* {{{ +* WITH CTE AS ( +* ...) +* SELECT [c1, c2, ...] FROM CTE ... +* }}} +* +* The Logical Rule add a GlobalLimit node before root project +* */ +case class MaxOutputRowsRule(session: SparkSession) extends Rule[LogicalPlan] { + override def apply(plan: LogicalPlan): LogicalPlan = { + if (!plan.resolved) { + plan + } else { + conf.getConf(KyuubiSQLConf.WATCHDOG_MAX_OUTPUTROWS) match { + case Some(maxOutputRows) => plan match { Review comment: > Do you mean if user's query limit 100 and the config is 10 then we can't add the limit ? Yes. > I think we should add limit as long as `plan.maxRows is none` or `plan.maxRows.get > maxOutputRows`. Otherwise it's hard to say which limit is added by us. Do you mean using maxOutputRows as final limit cover user limit setting if plan.maxRows.get > maxOutputRows？ -- 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]
