Uploaded image for project: 'Hadoop Map/Reduce'
  1. Hadoop Map/Reduce
  2. MAPREDUCE-4604

In mapred-default, mapreduce.map.maxattempts & mapreduce.reduce.maxattempts defaults are set to 4 as well as mapreduce.job.maxtaskfailures.per.tracker.

    XMLWordPrintableJSON

Details

    • Bug
    • Status: Closed
    • Critical
    • Resolution: Fixed
    • 0.23.3, 2.0.0-alpha
    • 0.23.3, 2.0.2-alpha
    • mrv2
    • None

    Description

      This causes the AM to fail the job at the same time as it blacklists a node, thus never actually trying another node.

      Marking as critical because we need this in 0.23.3 before it releases.

      Attachments

        1. MAPREDUCE-4604.patch
          4 kB
          Ravi Prakash
        2. MAPREDUCE-4604.patch
          4 kB
          Ravi Prakash

        Activity

          People

            raviprak Ravi Prakash
            raviprak Ravi Prakash
            Votes:
            0 Vote for this issue
            Watchers:
            7 Start watching this issue

            Dates

              Created:
              Updated:
              Resolved: