Github user vanzin commented on a diff in the pull request:
https://github.com/apache/spark/pull/2471#discussion_r19179055
--- Diff:
core/src/main/scala/org/apache/spark/deploy/history/FsHistoryProvider.scala ---
@@ -210,7 +226,46 @@ private[history] class FsHistoryProvider(conf:
SparkConf) extends ApplicationHis
applications = newApps
}
} catch {
- case t: Throwable => logError("Exception in checking for event log
updates", t)
+ case t: Exception => logError("Exception in checking for event log
updates", t)
+ }
+ }
+
+ /**
+ * Delete event logs from the log directory according to the clean
policy defined by the user.
+ */
+ private def cleanLogs() = {
+ 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()
+ val newApps = new mutable.LinkedHashMap[String,
FsApplicationHistoryInfo]()
+ def addIfNotExpire(info: FsApplicationHistoryInfo) = {
+ if (now - info.lastUpdated <= maxAge) {
+ newApps += (info.id -> info)
+ }
+ }
+
+ val oldIterator = applications.values.iterator.buffered
+ oldIterator.foreach(addIfNotExpire)
+
+ applications = newApps
+
+ // Scan all logs from the log directory.
+ // Only directories older than now maxAge milliseconds mill will be
deleted
+ logDirs.foreach { dir =>
+ try{
+ if (now - getModificationTime(dir) > maxAge) {
+ fs.delete(dir.getPath, true)
+ }
+ } catch {
+ case t: IOException => logError("IOException in cleaning logs",
t)
--- End diff --
nit: add `$dir` to the log message, in case it does not show up in the
exception.
---
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
