Made cacheTable idempotent

Author: liancheng

sql/core/src/main/scala/org/apache/spark/sql/SQLContext.scala

@@ -32,7 +32,7 @@ import org.apache.spark.sql.catalyst.types._
 import org.apache.spark.sql.catalyst.optimizer.Optimizer
 import org.apache.spark.sql.catalyst.plans.logical.LogicalPlan
 import org.apache.spark.sql.catalyst.rules.RuleExecutor
-import org.apache.spark.sql.columnar.InMemoryRelation
+import org.apache.spark.sql.columnar.{InMemoryColumnarTableScan, InMemoryRelation}
 import org.apache.spark.sql.execution._
 import org.apache.spark.sql.execution.SparkStrategies
 import org.apache.spark.sql.json._
@@ -187,10 +187,15 @@ class SQLContext(@transient val sparkContext: SparkContext)
   /** Caches the specified table in-memory. */
   def cacheTable(tableName: String): Unit = {
     val currentTable = catalog.lookupRelation(None, tableName)
-    val useCompression =
-      sparkContext.conf.getBoolean("spark.sql.inMemoryColumnarStorage.compressed", false)
-    val asInMemoryRelation =
-      InMemoryRelation(useCompression, executePlan(currentTable).executedPlan)
+    val asInMemoryRelation = EliminateAnalysisOperators(currentTable.logicalPlan) match {
+      case _: InMemoryRelation =>
+        currentTable.logicalPlan
+
+      case _ =>
+        val useCompression =
+          sparkContext.conf.getBoolean("spark.sql.inMemoryColumnarStorage.compressed", false)
+        InMemoryRelation(useCompression, executePlan(currentTable).executedPlan)
+    }
 
     catalog.registerTable(None, tableName, asInMemoryRelation)
   }

sql/core/src/test/scala/org/apache/spark/sql/SQLQuerySuite.scala

@@ -17,7 +17,9 @@
 
 package org.apache.spark.sql
 
+import org.apache.spark.sql.catalyst.analysis.EliminateAnalysisOperators
 import org.apache.spark.sql.catalyst.expressions._
+import org.apache.spark.sql.columnar.{InMemoryColumnarTableScan, InMemoryRelation}
 import org.apache.spark.sql.test._
 
 /* Implicits */
@@ -405,4 +407,22 @@ class SQLQuerySuite extends QueryTest {
     clear()
   }
 
+  test("SPARK-1669: cacheTable should be idempotent") {
+    assume(!table("testData").logicalPlan.isInstanceOf[InMemoryRelation])
+
+    cacheTable("testData")
+    EliminateAnalysisOperators(table("testData").logicalPlan) match {
+      case _: InMemoryRelation =>
+      case _ =>
+        fail("testData should be cached")
+    }
+
+    cacheTable("testData")
+    EliminateAnalysisOperators(table("testData").logicalPlan) match {
+      case InMemoryRelation(_, _, _: InMemoryColumnarTableScan) =>
+        fail("cacheTable is not idempotent")
+
+      case _ =>
+    }
+  }
 }