Uploaded image for project: 'Apache Cassandra'
  1. Apache Cassandra
  2. CASSANDRA-8497

Do not replay commit log records for tables that have been repaired since

    XMLWordPrintableJSON

Details

    • Improvement
    • Status: Resolved
    • Low
    • Resolution: Duplicate
    • None
    • None
    • None

    Description

      If somehow we have commit log records around since prior to a repair was completed, and we have repair-aware tombstone collection, then we could potentially reintroduce deleted data. Since we consider repaired data to be completely up-to-date, unless there has been a cross-cluster failure where data only ended up in the commit log, the commit log records will by now be superfluous. Some grace period may be necessary, as with CASSANDRA-6434.

      Attachments

        Issue Links

          duplicates

          Improvement - An improvement or enhancement to an existing feature or task. CASSANDRA-8498 Replaying commit log records that are older than gc_grace is dangerous

          • Normal -
          • Open
          is part of

          New Feature - A new feature of the product, which has yet to be developed. CASSANDRA-6434 Repair-aware gc grace period

          • Normal -
          • Resolved
          is related to

          Bug - A problem which impairs or prevents the functions of the product. CASSANDRA-7275 Errors in FlushRunnable may leave threads hung

          • Low -
          • Resolved

          Activity

            People

              Unassigned Unassigned
              benedict Benedict Elliott Smith
              Votes:
              0 Vote for this issue
              Watchers:
              4 Start watching this issue

              Dates

                Created:
                Updated:
                Resolved: