HeartSaVioR commented on a change in pull request #26416: [SPARK-29779][CORE] Compact old event log files and cleanup URL: https://github.com/apache/spark/pull/26416#discussion_r360788851
########## File path: core/src/main/scala/org/apache/spark/deploy/history/FsHistoryProvider.scala ########## @@ -663,13 +670,49 @@ private[history] class FsHistoryProvider(conf: SparkConf, clock: Clock) } } + private[spark] def getOrUpdateCompactible(reader: EventLogFileReader): Option[Boolean] = { + try { + val info = listing.read(classOf[LogInfo], reader.rootPath.toString) + val compactible = checkEligibilityForCompaction(info, reader) + if (info.compactible != compactible) { + listing.write(info.copy(compactible = compactible)) + } + compactible + } catch { + case _: NoSuchElementException => None + } + } + + protected def checkEligibilityForCompaction( + info: LogInfo, + reader: EventLogFileReader): Option[Boolean] = { + info.compactible.orElse { + // This is not applied to single event log file. + if (reader.lastIndex.isEmpty) { + Some(false) + } else { + if (reader.listEventLogFiles.length > 1) { + // We have at least one 'complete' file to check whether the event log is eligible to + // compact further. + val rate = eventFilterRateCalculator.calculate( Review comment: Changed to update EventFilterBuilder incrementally; the result should be same as reading from the start, as EventFilterBuilder just processes the events flowing through replay listener bus. If we memorize how far we replayed, we can continue replaying from (latest replayed + 1). It will be done per log file, as the unit of compaction is file. ---------------------------------------------------------------- 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 With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org