turboFei commented on a change in pull request #25797: [SPARK-29043][Core]
Improve the concurrent performance of History Server
URL: https://github.com/apache/spark/pull/25797#discussion_r343571354
##########
File path:
core/src/main/scala/org/apache/spark/deploy/history/FsHistoryProvider.scala
##########
@@ -664,10 +659,42 @@ private[history] class FsHistoryProvider(conf:
SparkConf, clock: Clock)
}
}
+ private def mergeApplicationListing(
+ reader: EventLogFileReader,
+ scanTime: Long,
+ enableOptimizations: Boolean): Unit = {
+ try {
+ pendingReplayTasksCount.incrementAndGet()
+ doMergeApplicationListing(reader, scanTime, enableOptimizations)
+ } catch {
+ case e: InterruptedException =>
+ throw e
+ case e: AccessControlException =>
+ // We don't have read permissions on the log file
+ logWarning(s"Unable to read log ${reader.rootPath}", e)
+ blacklist(reader.rootPath)
+ // SPARK-28157 We should remove this blacklisted entry from the KVStore
+ // to handle permission-only changes with the same file sizes later.
+ listing.delete(classOf[LogInfo], reader.rootPath.toString)
+ case e: Exception =>
+ logError("Exception while merging application listings", e)
+ } finally {
+ endProcessing(reader.rootPath)
+ pendingReplayTasksCount.decrementAndGet()
+
+ val isExpired = scanTime + conf.get(MAX_LOG_AGE_S) * 1000 <
clock.getTimeMillis()
+ if (isExpired) {
+ listing.delete(classOf[LogInfo], reader.rootPath.toString)
Review comment:
done.
----------------------------------------------------------------
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]
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
