Uploaded image for project: 'Cassandra'
  1. Cassandra
  2. CASSANDRA-6109

Consider coldness in STCS compaction

    XMLWordPrintableJSON

    Details

    • Type: New Feature
    • Status: Resolved
    • Priority: Normal
    • Resolution: Fixed
    • Fix Version/s: 2.0.3
    • Component/s: None
    • Labels:
      None

      Description

      I see two options:

      1. Don't compact cold sstables at all
      2. Compact cold sstables only if there is nothing more important to compact

      The latter is better if you have cold data that may become hot again... but it's confusing if you have a workload such that you can't keep up with all compaction, but you can keep up with hot sstable. (Compaction backlog stat becomes useless since we fall increasingly behind.)

        Attachments

        1. 6109-v3.patch
          26 kB
          Tom Hobbs
        2. 6109-v2.patch
          21 kB
          Tom Hobbs
        3. 6109-v1.patch
          7 kB
          Tom Hobbs

          Issue Links

            Activity

              People

              • Assignee:
                thobbs Tom Hobbs
                Reporter:
                jbellis Jonathan Ellis
                Authors:
                Tom Hobbs
                Reviewers:
                Jonathan Ellis
              • Votes:
                0 Vote for this issue
                Watchers:
                3 Start watching this issue

                Dates

                • Created:
                  Updated:
                  Resolved: