Uploaded image for project: 'Cassandra'
  1. Cassandra
  2. CASSANDRA-8193

Multi-DC parallel snapshot repair

    XMLWordPrintableJSON

Details

    • Improvement
    • Status: Resolved
    • Low
    • Resolution: Fixed
    • 2.0.12, 2.1.3
    • None
    • None

    Description

      The current behaviour of snapshot repair is to let one node at a time calculate a merkle tree. This is to ensure only one node at a time is doing the expensive calculation. The drawback is that it takes even longer time to do the merkle tree calculation.

      In a multi-DC setup, I think it would make more sense to have one node in each DC calculate the merkle tree at the same time. This would yield a significant improvement when you have many data centers.

      I'm not sure how relevant this is in 2.1, but I don't see us upgrading to 2.1 any time soon. Unless there is an obvious drawback that I'm missing, I'd like to implement this in the 2.0 branch.

      Attachments

        1. 8193-followup.txt
          9 kB
          Yuki Morishita
        2. cassandra-2.0-8193-1.txt
          20 kB
          Jimmy Mårdell
        3. cassandra-2.0-8193-2.txt
          54 kB
          Jimmy Mårdell

        Activity

          People

            yarin Jimmy Mårdell
            yarin Jimmy Mårdell
            Jimmy Mårdell
            Yuki Morishita
            Votes:
            0 Vote for this issue
            Watchers:
            5 Start watching this issue

            Dates

              Created:
              Updated:
              Resolved: