[GitHub] spark pull request #22504: [SPARK-25118][Submit] Persist Driver Logs in Clie...

[ankuriitg <gi...@git.apache.org>]

Github user ankuriitg commented on a diff in the pull request:

    https://github.com/apache/spark/pull/22504#discussion_r223859868
  
    --- Diff: core/src/main/scala/org/apache/spark/deploy/history/FsHistoryProvider.scala ---
    @@ -806,6 +806,22 @@ private[history] class FsHistoryProvider(conf: SparkConf, clock: Clock)
         }
         // Clean the blacklist from the expired entries.
         clearBlacklist(CLEAN_INTERVAL_S)
    +
    +    // Delete driver logs from the configured spark dfs dir that exceed the configured max age
    +    try {
    +      val hdfsDir = conf.get("spark.driver.log.dfsDir")
    +      val appDirs = fs.listLocatedStatus(new Path(hdfsDir))
    +      while (appDirs.hasNext()) {
    +        val appDirStatus = appDirs.next()
    +        if (appDirStatus.getModificationTime() < maxTime) {
    +          logInfo(s"Deleting expired driver log for: ${appDirStatus.getPath().getName()}")
    +          deleteLog(appDirStatus.getPath())
    +        }
    +      }
    +    } catch {
    +      case nse: NoSuchElementException => // no-op
    --- End diff --
    
    conf.get("spark.driver.log.dfsDir")


---

---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org