Uploaded image for project: 'Core Server'
  1. Core Server
  2. SERVER-21129

Allow pipelining of applier work before updating-position/reporting

    XMLWordPrintable

Details

    • Improvement
    • Status: Closed
    • Major - P3
    • Resolution: Fixed
    • None
    • 3.2.0-rc2
    • Replication
    • None
    • Fully Compatible
    • Repl C (11/20/15)

    Description

      Currently the applier must (sequentially) do the following in a loop:

      1. batch oplog entries
      2. apply and record in local oplog
      3. journal, including minvalid
      4. report/update-position

      The task here is to break the last two steps (journal + reporting) into a separate process which doesn't block the next batch from starting/applying. This should allow higher throughput on the replicas without adversely affecting latency.

      Attachments

        Issue Links

          Activity

            People

              matt.dannenberg Matt Dannenberg
              scotthernandez Scott Hernandez
              Votes:
              0 Vote for this issue
              Watchers:
              7 Start watching this issue

              Dates

                Created:
                Updated:
                Resolved: