dongjoon-hyun commented on code in PR #44636:
URL: https://github.com/apache/spark/pull/44636#discussion_r1448087582
##########
sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/FileStreamSource.scala:
##########
@@ -113,16 +117,32 @@ class FileStreamSource(
// Visible for testing and debugging in production.
val seenFiles = new SeenFilesMap(maxFileAgeMs, fileNameOnly)
- private var allFilesForTriggerAvailableNow: Seq[(SparkPath, Long)] = _
+ private var allFilesForTriggerAvailableNow: Seq[NewFileEntry] = _
metadataLog.restore().foreach { entry =>
seenFiles.add(entry.sparkPath, entry.timestamp)
}
seenFiles.purge()
- logInfo(s"maxFilesPerBatch = $maxFilesPerBatch, maxFileAgeMs =
$maxFileAgeMs")
+ logInfo(s"maxFilesPerBatch = $maxFilesPerBatch, " +
+ s"maxBytesPerBatch = $maxBytesPerBatch, maxFileAgeMs = $maxFileAgeMs")
+
+ private var unreadFiles: Seq[NewFileEntry] = _
- private var unreadFiles: Seq[(SparkPath, Long)] = _
+ /**
+ * Split files into a selected/unselected pair according to a total size
threshold.
+ */
+ private def takeFilesUntilMax(files: Seq[NewFileEntry], maxSize: Long):
+ (Seq[NewFileEntry], Seq[NewFileEntry]) = {
+ var idx = 0
+ var totalSize = 0L
+ val (bFiles, usFiles) = files.span { case NewFileEntry(_, size, _) =>
+ idx += 1
+ totalSize += size
+ idx == 1 || totalSize <= maxSize
Review Comment:
If we change the type of `maxSize` from `Int` to `Long`, line 141 and 142
should be revised in order to avoid overflow.
--
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.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
