i7xh commented on a change in pull request #1085:
URL: https://github.com/apache/incubator-kyuubi/pull/1085#discussion_r711452357
##########
File path:
dev/kyuubi-extension-spark-3-1/src/test/scala/org/apache/spark/sql/KyuubiExtensionSuite.scala
##########
@@ -1303,4 +1303,96 @@ class KyuubiExtensionSuite extends
KyuubiSparkSQLExtensionTest {
}
}
}
+
+ test("test watchdog with query forceMaxOutputRows") {
+
+ withSQLConf(KyuubiSQLConf.WATCHDOG_FORCED_MAXOUTPUTROWS.key -> "10") {
+
+ assert(sql("SELECT * FROM VALUES(1, 'a'),(2, 'b') AS t(c1, c2)")
+ .queryExecution.analyzed.isInstanceOf[GlobalLimit])
+
+ assert(sql("SELECT * FROM VALUES(1, 'a'),(2, 'b') AS t(c1, c2) LIMIT 1")
+ .queryExecution.analyzed.asInstanceOf[GlobalLimit].maxRows.contains(1))
+
+ assert(sql("SELECT * FROM VALUES(1, 'a'),(2, 'b') AS t(c1, c2) LIMIT 11")
+
.queryExecution.analyzed.asInstanceOf[GlobalLimit].maxRows.contains(10))
+
+ assert(!sql("SELECT count(*) FROM VALUES(1, 'a'),(2, 'b') AS t(c1, c2)")
+ .queryExecution.analyzed.isInstanceOf[GlobalLimit])
+
+ assert(sql(
+ """
+ |SELECT c1, COUNT(*)
+ |FROM VALUES(1, 'a'), (2, 'b') AS t(c1, c2)
+ |GROUP BY c1
+ |""".stripMargin).queryExecution.analyzed.isInstanceOf[GlobalLimit])
Review comment:
> > It's flaky with Spark3.2.0 that the issue of some logical plan has
not overridden maxRows is fixed. see
[apache/spark#30443](https://github.com/apache/spark/pull/30443).
> > We can use the test table, see `KyuubiExtensionSuite.setupData`.
>
> _见贤思齐_
> I read the
[apache/spark#30443](https://github.com/apache/spark/pull/30443). It seems to
get more exactly maxRows in Optimizer? I don't understand how affect the test
case changed yet, as `VALUES(1, 'a'), (2, 'b') AS t(c1, c2)`?
##########
File path:
dev/kyuubi-extension-spark-3-1/src/main/scala/org/apache/kyuubi/sql/watchdog/ForcedMaxOutputRowsRule.scala
##########
@@ -0,0 +1,71 @@
+/*
+ * 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.{Aggregate, Limit,
LogicalPlan, Project}
+import org.apache.spark.sql.catalyst.rules.Rule
+
+import org.apache.kyuubi.sql.KyuubiSQLConf
+
+/*
+* Add ForcedMaxOutputRows rule for output rows limitation
+* to avoid huge output rows of non_limit query unexpectedly
+* mainly applied to cases as below:
+*
+* case 1:
+* {{{
+* SELECT [c1, c2, ...]
+* }}}
+*
+* case 2:
+* {{{
+* WITH CTE AS (
+* ...)
+* SELECT [c1, c2, ...] FROM CTE ...
+* }}}
+*
+* The Logical Rule add a GlobalLimit node before root project
+* */
+case class ForcedMaxOutputRowsRule(session: SparkSession) extends
Rule[LogicalPlan] {
+
+ private def canInsertLimit(p: LogicalPlan): Boolean = {
Review comment:
> can we put it as parameter `maxOutputRows: Option[Int]` ?
OK, I unified the maxOutputRows quote
--
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]
