From 3e48f3b9ee7645e4218ad3ff7559e578d4bd9667 Mon Sep 17 00:00:00 2001
From: Dongjoon Hyun <dongjoon@apache.org>
Date: Tue, 20 Feb 2018 16:02:44 -0800
Subject: [PATCH] [SPARK-23434][SQL] Spark should not warn `metadata directory`
for a HDFS file path
## What changes were proposed in this pull request?
In a kerberized cluster, when Spark reads a file path (e.g. `people.json`), it warns with a wrong warning message during looking up `people.json/_spark_metadata`. The root cause of this situation is the difference between `LocalFileSystem` and `DistributedFileSystem`. `LocalFileSystem.exists()` returns `false`, but `DistributedFileSystem.exists` raises `org.apache.hadoop.security.AccessControlException`.
```scala
scala> spark.version
res0: String = 2.4.0-SNAPSHOT
scala> spark.read.json("file:///usr/hdp/current/spark-client/examples/src/main/resources/people.json").show
+----+-------+
| age| name|
+----+-------+
|null|Michael|
| 30| Andy|
| 19| Justin|
+----+-------+
scala> spark.read.json("hdfs:///tmp/people.json")
18/02/15 05:00:48 WARN streaming.FileStreamSink: Error while looking for metadata directory.
18/02/15 05:00:48 WARN streaming.FileStreamSink: Error while looking for metadata directory.
```
After this PR,
```scala
scala> spark.read.json("hdfs:///tmp/people.json").show
+----+-------+
| age| name|
+----+-------+
|null|Michael|
| 30| Andy|
| 19| Justin|
+----+-------+
```
## How was this patch tested?
Manual.
Author: Dongjoon Hyun <dongjoon@apache.org>
Closes #20616 from dongjoon-hyun/SPARK-23434.
---
.../spark/sql/execution/streaming/FileStreamSink.scala | 8 +++++---
1 file changed, 5 insertions(+), 3 deletions(-)
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/FileStreamSink.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/FileStreamSink.scala
index 2715fa93d0..87a17cebdc 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/FileStreamSink.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/FileStreamSink.scala
@@ -42,9 +42,11 @@ object FileStreamSink extends Logging {
try {
val hdfsPath = new Path(singlePath)
val fs = hdfsPath.getFileSystem(hadoopConf)
- val metadataPath = new Path(hdfsPath, metadataDir)
- val res = fs.exists(metadataPath)
- res
+ if (fs.isDirectory(hdfsPath)) {
+ fs.exists(new Path(hdfsPath, metadataDir))
+ } else {
+ false
+ }
} catch {
case NonFatal(e) =>
logWarning(s"Error while looking for metadata directory.")
--
GitLab