You are viewing a plain text version of this content. The canonical link for it is here.
Posted to reviews@spark.apache.org by GitBox <gi...@apache.org> on 2021/08/11 07:43:18 UTC

[GitHub] [spark] cloud-fan commented on a change in pull request #33698: [SPARK-32986][SQL] Add bucketed scan info in query plan of data source v1

cloud-fan commented on a change in pull request #33698:
URL: https://github.com/apache/spark/pull/33698#discussion_r686580428



##########
File path: sql/core/src/test/scala/org/apache/spark/sql/ExplainSuite.scala
##########
@@ -677,6 +677,33 @@ class ExplainSuiteAE extends ExplainSuiteHelper with EnableAdaptiveExecutionSuit
       }
     }
   }
+
+  test("SPARK-32986: Bucketed scan info should be a part of explain string") {
+    withTable("t1", "t2") {
+      Seq((1, 2), (2, 3)).toDF("i", "j").write.bucketBy(8, "i").saveAsTable("t1")
+      Seq(2, 3).toDF("i").write.bucketBy(8, "i").saveAsTable("t2")
+      val df1 = spark.table("t1")
+      val df2 = spark.table("t2")
+
+      withSQLConf(SQLConf.AUTO_BROADCASTJOIN_THRESHOLD.key -> "0") {
+        checkKeywordsExistsInExplain(
+          df1.join(df2, df1("i") === df2("i")),
+          "Bucketed: true" :: Nil: _*)

Review comment:
       nit: `"Bucketed: true" :: Nil: _*` -> `"Bucketed: true"`?

##########
File path: sql/core/src/test/scala/org/apache/spark/sql/ExplainSuite.scala
##########
@@ -677,6 +677,33 @@ class ExplainSuiteAE extends ExplainSuiteHelper with EnableAdaptiveExecutionSuit
       }
     }
   }
+
+  test("SPARK-32986: Bucketed scan info should be a part of explain string") {
+    withTable("t1", "t2") {
+      Seq((1, 2), (2, 3)).toDF("i", "j").write.bucketBy(8, "i").saveAsTable("t1")
+      Seq(2, 3).toDF("i").write.bucketBy(8, "i").saveAsTable("t2")
+      val df1 = spark.table("t1")
+      val df2 = spark.table("t2")
+
+      withSQLConf(SQLConf.AUTO_BROADCASTJOIN_THRESHOLD.key -> "0") {
+        checkKeywordsExistsInExplain(
+          df1.join(df2, df1("i") === df2("i")),
+          "Bucketed: true" :: Nil: _*)
+      }
+
+      withSQLConf(SQLConf.BUCKETING_ENABLED.key -> "false") {
+        checkKeywordsExistsInExplain(
+          df1.join(df2, df1("i") === df2("i")),
+          "Bucketed: false (disabled by configuration)" :: Nil: _*)

Review comment:
       ditto

##########
File path: sql/core/src/test/scala/org/apache/spark/sql/ExplainSuite.scala
##########
@@ -677,6 +677,33 @@ class ExplainSuiteAE extends ExplainSuiteHelper with EnableAdaptiveExecutionSuit
       }
     }
   }
+
+  test("SPARK-32986: Bucketed scan info should be a part of explain string") {
+    withTable("t1", "t2") {
+      Seq((1, 2), (2, 3)).toDF("i", "j").write.bucketBy(8, "i").saveAsTable("t1")
+      Seq(2, 3).toDF("i").write.bucketBy(8, "i").saveAsTable("t2")
+      val df1 = spark.table("t1")
+      val df2 = spark.table("t2")
+
+      withSQLConf(SQLConf.AUTO_BROADCASTJOIN_THRESHOLD.key -> "0") {
+        checkKeywordsExistsInExplain(
+          df1.join(df2, df1("i") === df2("i")),
+          "Bucketed: true" :: Nil: _*)
+      }
+
+      withSQLConf(SQLConf.BUCKETING_ENABLED.key -> "false") {
+        checkKeywordsExistsInExplain(
+          df1.join(df2, df1("i") === df2("i")),
+          "Bucketed: false (disabled by configuration)" :: Nil: _*)
+      }
+
+      checkKeywordsExistsInExplain(df1, "Bucketed: false (disabled by query planner)" :: Nil: _*)

Review comment:
       ditto




-- 
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: reviews-unsubscribe@spark.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org



---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org