[SPARK-20594][SQL] The staging directory should be a child directory …

…starts with "." to avoid being deleted if we set hive.exec.stagingdir under the table directory. JIRA Issue: https://issues.apache.org/jira/browse/SPARK-20594 ## What changes were proposed in this pull request? The staging directory should be a child directory starts with "." to avoid being deleted before moving staging directory to table directory if we set hive.exec.stagingdir under the table directory. ## How was this patch tested? Added unit tests Author: zuotingbing <[email protected]> Closes apache#17858 from zuotingbing/spark-stagingdir.
liyichao · May 24, 2017 · 130cc78 · 130cc78
1 parent 6b8fc88
commit 130cc78
Show file tree

Hide file tree

Showing 2 changed files with 25 additions and 2 deletions.
diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/InsertIntoHiveTable.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/InsertIntoHiveTable.scala
@@ -17,7 +17,7 @@
 
 package org.apache.spark.sql.hive.execution
 
-import java.io.IOException
+import java.io.{File, IOException}
 import java.net.URI
 import java.text.SimpleDateFormat
 import java.util.{Date, Locale, Random}
@@ -97,12 +97,24 @@ case class InsertIntoHiveTable(
     val inputPathUri: URI = inputPath.toUri
     val inputPathName: String = inputPathUri.getPath
     val fs: FileSystem = inputPath.getFileSystem(hadoopConf)
-    val stagingPathName: String =
+    var stagingPathName: String =
       if (inputPathName.indexOf(stagingDir) == -1) {
         new Path(inputPathName, stagingDir).toString
       } else {
         inputPathName.substring(0, inputPathName.indexOf(stagingDir) + stagingDir.length)
       }
+
+    // SPARK-20594: This is a walk-around fix to resolve a Hive bug. Hive requires that the
+    // staging directory needs to avoid being deleted when users set hive.exec.stagingdir
+    // under the table directory.
+    if (FileUtils.isSubDir(new Path(stagingPathName), inputPath, fs) &&
+      !stagingPathName.stripPrefix(inputPathName).stripPrefix(File.separator).startsWith(".")) {
+      logDebug(s"The staging dir '$stagingPathName' should be a child directory starts " +
+        "with '.' to avoid being deleted if we set hive.exec.stagingdir under the table " +
+        "directory.")
+      stagingPathName = new Path(inputPathName, ".hive-staging").toString
+    }
+
     val dir: Path =
       fs.makeQualified(
         new Path(stagingPathName + "_" + executionId + "-" + TaskRunner.getTaskRunnerID))

diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/InsertIntoHiveTableSuite.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/InsertIntoHiveTableSuite.scala
@@ -494,4 +494,15 @@ class InsertIntoHiveTableSuite extends QueryTest with TestHiveSingleton with Bef
         spark.table("t").write.insertInto(tableName)
       }
   }
+
+  test("SPARK-20594: hive.exec.stagingdir was deleted by Hive") {
+    // Set hive.exec.stagingdir under the table directory without start with ".".
+    withSQLConf("hive.exec.stagingdir" -> "./test") {
+      withTable("test_table") {
+        sql("CREATE TABLE test_table (key int)")
+        sql("INSERT OVERWRITE TABLE test_table SELECT 1")
+        checkAnswer(sql("SELECT * FROM test_table"), Row(1))
+      }
+    }
+  }
 }