QiangCai commented on a change in pull request #3842:
URL: https://github.com/apache/carbondata/pull/3842#discussion_r454233869
##########
File path:
integration/spark/src/main/scala/org/apache/spark/rdd/CarbonMergeFilesRDD.scala
##########
@@ -157,21 +157,21 @@ object CarbonMergeFilesRDD {
if (carbonTable.isHivePartitionTable &&
!StringUtils.isEmpty(tempFolderPath)) {
// remove all tmp folder of index files
val startDelete = System.currentTimeMillis()
- val numThreads = Math.min(Math.max(partitionInfo.size(), 1), 10)
- val executorService = Executors.newFixedThreadPool(numThreads)
- val carbonSessionInfo = ThreadLocalSessionInfo.getCarbonSessionInfo
- partitionInfo
- .asScala
- .map { partitionPath =>
- executorService.submit(new Runnable {
- override def run(): Unit = {
- ThreadLocalSessionInfo.setCarbonSessionInfo(carbonSessionInfo)
- FileFactory.deleteAllCarbonFilesOfDir(
- FileFactory.getCarbonFile(partitionPath + "/" +
tempFolderPath))
- }
- })
+ val allTmpDirs = partitionInfo
+ .asScala.map { partitionPath =>
+ partitionPath + CarbonCommonConstants.FILE_SEPARATOR + tempFolderPath
}
- .map(_.get())
+ val allTmpFiles = allTmpDirs.map { partitionDir =>
+ FileFactory.getCarbonFile(partitionDir).listFiles()
+ }.flatten.map(_.getAbsolutePath)
+ // delete tmp files in parallel
+ sparkSession.sparkContext.parallelize(allTmpFiles).map {
+ FileFactory.getCarbonFile(_).delete()
+ }.collect()
+ // delete tmp dir in parallel
+ sparkSession.sparkContext.parallelize(allTmpDirs).map {
+ FileFactory.getCarbonFile(_).delete()
+ }.collect()
Review comment:
You can just use job to replace multi-threads, one task delete one dir
with files.
----------------------------------------------------------------
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:
us...@infra.apache.org
