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 2020/07/17 05:50:12 UTC

[GitHub] [spark] moomindani commented on a change in pull request #27690: [SPARK-21514][SQL] Added a new option to use non-blobstore storage when writing into blobstore storage

moomindani commented on a change in pull request #27690:
URL: https://github.com/apache/spark/pull/27690#discussion_r456231877



##########
File path: sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/SaveAsHiveFile.scala
##########
@@ -97,12 +99,46 @@ private[hive] trait SaveAsHiveFile extends DataWritingCommand {
       options = Map.empty)
   }
 
-  protected def getExternalTmpPath(
+  // Mostly copied from Context.java#getMRTmpPath of Hive 2.3.
+  // Visible for testing.
+  private[execution] def getNonBlobTmpPath(
+      hadoopConf: Configuration,
+      sessionScratchDir: String,
+      scratchDir: String): Path = {
+
+    // Hive's getMRTmpPath uses nonLocalScratchPath + '-mr-10000',
+    // which is ruled by 'hive.exec.scratchdir' including file system.
+    // This is the same as Spark's #oldVersionExternalTempPath.
+    // Only difference between #oldVersionExternalTempPath and Hive 2.3.0's is HIVE-7090.
+    // HIVE-7090 added user_name/session_id on top of 'hive.exec.scratchdir'
+    // Here it uses session_path unless it's emtpy, otherwise uses scratchDir.
+    val sessionPath = if (!sessionScratchDir.isEmpty) sessionScratchDir else scratchDir
+    val mrScratchDir = oldVersionExternalTempPath(new Path(sessionPath), hadoopConf, sessionPath)
+    logDebug(s"MR scratch dir '$mrScratchDir/-mr-10000' is used")
+    val path = new Path(mrScratchDir, "-mr-10000")
+    val scheme = Option(path.toUri.getScheme).getOrElse("")
+    if (scheme.equals("file")) {
+      logWarning(s"Temporary data will be written into a local file system " +
+        s"(scheme: '$scheme', path: '$mrScratchDir'). If your Spark is not in local mode, " +
+        s"you might need to configure 'hive.exec.scratchdir' " +
+        s"to use accessible file system (e.g. HDFS path) from any executors in the cluster.")
+    }
+    path
+  }
+
+  private def supportSchemeToUseNonBlobStore(path: Path): Boolean = {
+    path != null && {
+      val supportedBlobSchemes = SQLConf.get.supportedSchemesToUseNonBlobstore
+      val scheme = Option(path.toUri.getScheme).getOrElse("")
+      Utils.stringToSeq(supportedBlobSchemes).contains(scheme.toLowerCase(Locale.ROOT))
+    }
+  }
+
+  def getExternalTmpPath(
       sparkSession: SparkSession,
       hadoopConf: Configuration,
       path: Path): Path = {
     import org.apache.spark.sql.hive.client.hive._
-

Review comment:
       Thanks for pointing it. Reverted.




----------------------------------------------------------------
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.

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