zsxwing commented on a change in pull request #23733: [SPARK-26824][SS]Fix the
checkpoint location and _spark_metadata when it contains special chars
URL: https://github.com/apache/spark/pull/23733#discussion_r258191434
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/FileStreamSink.scala
##########
@@ -37,23 +39,47 @@ object FileStreamSink extends Logging {
* Returns true if there is a single path that has a metadata log indicating
which files should
* be read.
*/
- def hasMetadata(path: Seq[String], hadoopConf: Configuration): Boolean = {
+ def hasMetadata(path: Seq[String], hadoopConf: Configuration, sqlConf:
SQLConf): Boolean = {
path match {
case Seq(singlePath) =>
+ val hdfsPath = new Path(singlePath)
+ val fs = hdfsPath.getFileSystem(hadoopConf)
+ if (fs.isDirectory(hdfsPath)) {
+ val metadataPath = new Path(hdfsPath, metadataDir)
+ checkEscapedMetadataPath(fs, metadataPath, sqlConf)
+ fs.exists(metadataPath)
+ } else {
+ false
+ }
+ case _ => false
+ }
+ }
+
+ def checkEscapedMetadataPath(fs: FileSystem, metadataPath: Path, sqlConf:
SQLConf): Unit = {
+ if
(sqlConf.getConf(SQLConf.STREAMING_CHECKPOINT_ESCAPED_PATH_CHECK_ENABLED)
+ && StreamExecution.containsSpecialCharsInPath(metadataPath)) {
+ val legacyMetadataPath = new Path(metadataPath.toUri.toString)
+ val legacyMetadataPathExists =
try {
- val hdfsPath = new Path(singlePath)
- val fs = hdfsPath.getFileSystem(hadoopConf)
- if (fs.isDirectory(hdfsPath)) {
- fs.exists(new Path(hdfsPath, metadataDir))
- } else {
- false
- }
+ fs.exists(legacyMetadataPath)
} catch {
case NonFatal(e) =>
- logWarning(s"Error while looking for metadata directory.")
+ // We may not have access to this directory. Don't fail the query
if that happens.
+ logWarning(e.getMessage, e)
Review comment:
@gaborgsomogyi Making this check best effort is safer. I don't want to force
people that don't hit this issue to use the config until we remove this check
in future.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
