Github user JoshRosen commented on a diff in the pull request:
https://github.com/apache/spark/pull/6810#discussion_r33523518
--- Diff:
sql/core/src/test/scala/org/apache/spark/sql/execution/AggregateSuite.scala ---
@@ -0,0 +1,59 @@
+/*
+ * 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.execution
+
+import org.apache.spark.sql.SQLConf
+import org.apache.spark.sql.catalyst.expressions._
+import org.apache.spark.sql.test.TestSQLContext
+import org.apache.spark.sql.types.DataTypes._
+
+class AggregateSuite extends SparkPlanTest {
+
+ test("SPARK-8357 Memory leakage on unsafe aggregation path with empty
input") {
+
+ val input0 = Seq.empty[(String, Int, Double)]
+ val input1 = Seq(("Hello", 4, 2.0))
+
+ // hack : current default parallelism of test local backend is two
+ val x0 = Seq(Tuple1(0L), Tuple1(0L))
+ val y0 = Seq.empty[Tuple1[Long]]
+
+ val x1 = Seq(Tuple1(0L), Tuple1(1L))
+ val y1 = Seq(Tuple1(1L))
+
+ val codegenDefault = TestSQLContext.getConf(SQLConf.CODEGEN_ENABLED)
+ try {
+ for ((input, x, y) <- Seq((input0, x0, y0), (input1, x1, y1))) {
+ val df = input.toDF("a", "b", "c")
+ val colB = df.col("b").expr
+ val colC = df.col("c").expr
+ val aggrExpr = Alias(Count(Cast(colC, LongType)), "Count")()
+
+ for ((codegen, unsafe) <- Seq((false, false), (true, false),
(true, true));
+ partial <- Seq(false, true); groupExpr <- Seq(colB :: Nil,
Seq.empty)) {
--- End diff --
Style nit: put each nested loop on its own line (e.g. one <- per line,
since that's easier to read). Also, I think `Seq(Seq(colB), Seq.empty)` is a
bit more readable.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
