Github user tdas commented on a diff in the pull request:
https://github.com/apache/spark/pull/11897#discussion_r57102528
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/FileStreamSource.scala
---
@@ -114,18 +114,24 @@ class FileStreamSource(
val endId = end.asInstanceOf[LongOffset].offset
assert(startId <= endId)
- val files = metadataLog.get(Some(startId + 1), endId).map(_._2).flatten
- logDebug(s"Return files from batches ${startId + 1}:$endId")
+ val files = metadataLog.get(Some(startId + 1),
Some(endId)).map(_._2).flatten
+ logInfo(s"Processing ${files.length} files from ${startId + 1}:$endId")
logDebug(s"Streaming ${files.mkString(", ")}")
dataFrameBuilder(files)
}
private def fetchAllFiles(): Seq[String] = {
- fs.listStatus(new Path(path))
+ val startTime = System.nanoTime()
+ val files = fs.listStatus(new Path(path))
.filterNot(_.getPath.getName.startsWith("_"))
.map(_.getPath.toUri.toString)
+ val endTime = System.nanoTime()
+ logDebug(s"Listed ${files.size} in ${(endTime.toDouble - startTime) /
1000000}ms")
+ files
}
override def getOffset: Option[Offset] =
Some(fetchMaxOffset()).filterNot(_.offset == -1)
+
+ override def toString: String = s"FileSink[$path]"
--- End diff --
This is the file source :D
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
