[GitHub] [spark] vanzin commented on a change in pull request #26502: [SPARK-29876][SS] Delete/archive file source completed files in separate thread

[GitBox <gi...@apache.org>]

vanzin commented on a change in pull request #26502: [SPARK-29876][SS] Delete/archive file source completed files in separate thread
URL: https://github.com/apache/spark/pull/26502#discussion_r353497386
 
 

 ##########
 File path: sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/FileStreamSource.scala
 ##########
 @@ -342,8 +345,34 @@ object FileStreamSource {
     def size: Int = map.size()
   }
 
-  private[sql] trait FileStreamSourceCleaner {
-    def clean(entry: FileEntry): Unit
+  private[sql] abstract class FileStreamSourceCleaner extends Logging {
+    private val numThreads = SQLConf.get.getConf(SQLConf.FILE_SOURCE_CLEANER_NUM_THREADS)
+
+    private val cleanThreadPool: Option[ThreadPoolExecutor] = if (numThreads > 0) {
+      logDebug(s"Cleaning file source on $numThreads separate thread(s)")
+      Some(ThreadUtils.newDaemonCachedThreadPool("file-source-cleaner-threadpool", numThreads))
+    } else {
+      logDebug("Cleaning file source on main thread")
+      None
+    }
+
+    def stop(): Unit = cleanThreadPool.foreach(ThreadUtils.shutdown(_))
+
+    def clean(entry: FileEntry): Unit = {
+      cleanThreadPool match {
+        case Some(p) =>
+          p.submit(new Runnable {
+            override def run(): Unit = {
+              cleanTask(entry)
+            }
+          })
+
+        case None =>
+          cleanTask(entry)
+      }
+    }
+
+    def cleanTask(entry: FileEntry): Unit
 
 Review comment:
   protected

----------------------------------------------------------------
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:
users@infra.apache.org


With regards,
Apache Git Services

---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org