xuanyuanking commented on a change in pull request #32767:
URL: https://github.com/apache/spark/pull/32767#discussion_r656929673
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBFileManager.scala
##########
@@ -200,6 +246,55 @@ class RocksDBFileManager(
immutableFiles
}
+ /**
+ * Copy files from DFS directory to a local directory. It will figure out
which
+ * existing files are needed, and accordingly, unnecessary SST files are
deleted while
+ * necessary and non-existing files are copied from DFS.
+ */
+ private def loadImmutableFilesFromDfs(
+ immutableFiles: Seq[RocksDBImmutableFile], localDir: File): Unit = {
+ val requiredFileNameToFileDetails = immutableFiles.map(f =>
f.localFileName -> f).toMap
+ // Delete unnecessary local immutable files
+ listRocksDBFiles(localDir)._1
+ .foreach { existingFile =>
+ val isSameFile =
+
requiredFileNameToFileDetails.get(existingFile.getName).exists(_.isSameFile(existingFile))
+ if (!isSameFile) {
+ existingFile.delete()
+ logInfo(s"Deleted local file $existingFile")
+ }
Review comment:
A safer guard for checking both file names and file size.
--
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:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
