Github user vanzin commented on a diff in the pull request:
https://github.com/apache/spark/pull/2471#discussion_r18782185
--- Diff:
core/src/main/scala/org/apache/spark/deploy/history/FsHistoryProvider.scala ---
@@ -195,22 +241,68 @@ private[history] class FsHistoryProvider(conf:
SparkConf) extends ApplicationHis
}
}
- val newIterator = logInfos.iterator.buffered
- val oldIterator = applications.values.iterator.buffered
- while (newIterator.hasNext && oldIterator.hasNext) {
- if (newIterator.head.endTime > oldIterator.head.endTime) {
- addIfAbsent(newIterator.next)
- } else {
- addIfAbsent(oldIterator.next)
+ applications.synchronized {
+ val newIterator = logInfos.iterator.buffered
+ val oldIterator = applications.values.iterator.buffered
+ while (newIterator.hasNext && oldIterator.hasNext) {
+ if (newIterator.head.endTime > oldIterator.head.endTime) {
+ addIfAbsent(newIterator.next)
+ } else {
+ addIfAbsent(oldIterator.next)
+ }
}
+ newIterator.foreach(addIfAbsent)
+ oldIterator.foreach(addIfAbsent)
+
+ applications = newApps
}
- newIterator.foreach(addIfAbsent)
- oldIterator.foreach(addIfAbsent)
+ }
+ } catch {
+ case t: Throwable => logError("Exception in checking for event log
updates", t)
+ }
+ }
+
+ /**
+ * Deleting apps if setting cleaner.
+ */
+ private def cleanLogs() = {
+ lastLogCleanTimeMs = getMonotonicTimeMs()
+ logDebug("Cleaning logs. Time is now %d.".format(lastLogCleanTimeMs))
+ try {
+ val logStatus = fs.listStatus(new Path(resolvedLogDir))
+ val logDirs = if (logStatus != null) logStatus.filter(_.isDir).toSeq
else Seq[FileStatus]()
+ val maxAge = conf.getLong("spark.history.fs.maxAge.seconds",
+ DEFAULT_SPARK_HISTORY_FS_MAXAGE_S) * 1000
+
+ val now = System.currentTimeMillis()
+ fs.synchronized {
+ // scan all logs from the log directory.
+ // Only directories older than this many seconds will be deleted .
+ logDirs.foreach { dir =>
+ // history file older than this many seconds will be deleted
+ // when the history cleaner runs.
+ if (now - getModificationTime(dir) > maxAge) {
+ fs.delete(dir.getPath, true)
--- End diff --
Because the existing `try..catch` means that if you fail to delete a
directory, you'll stop trying to delete others. So if a directory in the middle
of the list has wrong permissions, you'll never clean up any directory that is
more recent than it is (well, depending on the ordering HDFS returns the file
list).
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
