[SPARK-55998][SHS] Synchronize more places on accessing SHS listing.db #54817
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -584,7 +584,9 @@ private[history] class FsHistoryProvider(conf: SparkConf, clock: Clock) | |
| .foreach { log => | ||
| log.appId.foreach { appId => | ||
| cleanAppData(appId, log.attemptId, log.logPath) | ||
| listing.synchronized { | ||
| listing.delete(classOf[LogInfo], log.logPath) | ||
| } | ||
| } | ||
| } | ||
|
|
||
|
|
@@ -698,7 +700,9 @@ private[history] class FsHistoryProvider(conf: SparkConf, clock: Clock) | |
| // If the LogInfo read had succeeded, but the ApplicationInafoWrapper | ||
| // read failure and throw the exception, we should also cleanup the log | ||
| // info from listing db. | ||
| listing.synchronized { | ||
| listing.delete(classOf[LogInfo], reader.rootPath.toString) | ||
| } | ||
| false | ||
| } else if (count < conf.get(UPDATE_BATCHSIZE)) { | ||
| listing.write(LogInfo(reader.rootPath.toString(), newLastScanTime, | ||
|
|
@@ -1194,7 +1198,9 @@ private[history] class FsHistoryProvider(conf: SparkConf, clock: Clock) | |
| logInfo(log"Deleting invalid / corrupt event log ${MDC(PATH, log.logPath)}") | ||
| val logPath = new Path(log.logPath) | ||
| deleteLog(fsForPath(logPath), logPath) | ||
| listing.synchronized { | ||
| listing.delete(classOf[LogInfo], log.logPath) | ||
| } | ||
| } | ||
|
|
||
| log.appId.foreach { appId => | ||
|
|
@@ -1228,22 +1234,28 @@ private[history] class FsHistoryProvider(conf: SparkConf, clock: Clock) | |
| } | ||
|
|
||
| // Delete log files that don't have a valid application and exceed the configured max age. | ||
| val stale = listing.synchronized { | ||
| KVUtils.viewToSeq(listing.view(classOf[LogInfo]) | ||
| .index("lastProcessed") | ||
| .reverse() | ||
| .first(maxTime), Int.MaxValue) { l => l.logType == null || l.logType == LogType.EventLogs } | ||
| } | ||
| stale.filterNot(isProcessing).foreach { log => | ||
| if (log.appId.isEmpty) { | ||
| logInfo(log"Deleting invalid / corrupt event log ${MDC(PATH, log.logPath)}") | ||
| val logPath = new Path(log.logPath) | ||
| deleteLog(fsForPath(logPath), logPath) | ||
| listing.synchronized { | ||
| listing.delete(classOf[LogInfo], log.logPath) | ||
| } | ||
| } | ||
| } | ||
|
|
||
| // If the number of files is bigger than MAX_LOG_NUM, | ||
| // clean up all completed attempts per application one by one. | ||
| val num = listing.synchronized { | ||
| KVUtils.size(listing.view(classOf[LogInfo]).index("lastProcessed")) | ||
|
Member
Author
There was a problem hiding this comment. @sarutak, it seems I can not jump to the line in my browser, could you please provide the line number instead?
Member
There was a problem hiding this comment. Oh, it's L1348. |
||
| } | ||
| var count = num - maxNum | ||
| if (count > 0) { | ||
| logInfo(log"Try to delete ${MDC(NUM_FILES, count)} old event logs" + | ||
|
|
@@ -1324,20 +1336,28 @@ private[history] class FsHistoryProvider(conf: SparkConf, clock: Clock) | |
| } | ||
| if (deleteFile) { | ||
| logInfo(log"Deleting expired driver log for: ${MDC(PATH, logFileStr)}") | ||
| listing.synchronized { | ||
| listing.delete(classOf[LogInfo], logFileStr) | ||
| } | ||
| deleteLog(driverLogFs, f.getPath()) | ||
| } | ||
| } | ||
|
|
||
| // Delete driver log file entries that exceed the configured max age and | ||
| // may have been deleted on filesystem externally. | ||
| val stale = listing.synchronized { | ||
| KVUtils.viewToSeq(listing.view(classOf[LogInfo]) | ||
| .index("lastProcessed") | ||
| .reverse() | ||
| .first(maxTime), Int.MaxValue) { l => | ||
| l.logType != null && l.logType == LogType.DriverLogs | ||
| } | ||
| } | ||
| stale.filterNot(isProcessing).foreach { log => | ||
| logInfo(log"Deleting invalid driver log ${MDC(PATH, log.logPath)}") | ||
| listing.synchronized { | ||
| listing.delete(classOf[LogInfo], log.logPath) | ||
| } | ||
| deleteLog(driverLogFs, new Path(log.logPath)) | ||
| } | ||
| } | ||
|
|
||
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Uh oh!
There was an error while loading. Please reload this page.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
NoSuchElementExceptionis thrown from here, because the LevelDB/RocksDB-based KVStore does not support MVCC, we must use a relatively heavysynchronizedto fix the concurrency issue.