Uploaded image for project: 'JDK'
  1. JDK
  2. JDK-8327042

G1: Parallelism used for redirty logged cards needs better control.

XMLWordPrintable

    • Icon: Enhancement Enhancement
    • Resolution: Fixed
    • Icon: P4 P4
    • 23
    • 23
    • hotspot
    • gc
    • b13

      Investigate the scaling of the RedirtyLoggedCardsTask with number of worker threads. In the current implementation, the threads contend for access to the Log Buffers through a single BufferNode resulting in a bottleneck as we increase the threads. The cost per card is pretty low, thus the work distribution overhead dominates the task. Increasing the number of threads just increases contention overheads leading to regression in the task execution time.

      Please see the images attached where TX_ refers to T[no of threads] run on a 20G heap with BigRamTester microbenchmark.

        1. concurrent_start.png
          concurrent_start.png
          79 kB
        2. Mixed.png
          Mixed.png
          76 kB
        3. Normal.png
          Normal.png
          73 kB
        4. Prepare_mixed.png
          Prepare_mixed.png
          74 kB

            iwalulya Ivan Walulya
            iwalulya Ivan Walulya
            Votes:
            0 Vote for this issue
            Watchers:
            3 Start watching this issue

              Created:
              Updated:
              Resolved: