Uploaded image for project: 'Cassandra'
  1. Cassandra
  2. CASSANDRA-1954

Double-check or replace RRW memtable lock

    XMLWordPrintableJSON

Details

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

    Description

      ...when a Memtable reaches its threshold, up to (all) N write threads will often notice, and race to acquire the writeLock in order to freeze the memtable. This means that we do way more writeLock acquisitions than we need to...

      See CASSANDRA-1930 for backstory, but adding double checking inside a read lock before trying to re-entrantly acquire the writelock would eliminate most of these excess writelock acquisitions.

      Alternatively, we should explore removing locking from these structures entirely, and replacing the writeLock acquisition with a per-memtable counter of active threads.

      Attachments

        1. 0001-Double-check-in-maybeSwitchMemtable-to-minimize-writeL.txt
          2 kB
          Stu Hood
        2. 0001-Remove-flusherLock-readLock.patch
          24 kB
          Sylvain Lebresne
        3. 1954_trunk.patch
          20 kB
          Sylvain Lebresne
        4. 1954-0.7-v2.txt
          2 kB
          Jonathan Ellis
        5. 1954-v2.txt
          23 kB
          Jonathan Ellis

        Issue Links

          Activity

            People

              Unassigned Unassigned
              stuhood Stu Hood
              Jonathan Ellis
              Votes:
              0 Vote for this issue
              Watchers:
              3 Start watching this issue

              Dates

                Created:
                Updated:
                Resolved:

                Time Tracking

                  Estimated:
                  Original Estimate - 8h
                  8h
                  Remaining:
                  Remaining Estimate - 8h
                  8h
                  Logged:
                  Time Spent - Not Specified
                  Not Specified