Parallel: Use per-marker cache for marking stats during Full GC

XMLWordPrintable

    • gc
    • b12

      In `PSParallelCompact::mark_obj`, `_summary_data.add_obj` uses atomic-operation to record live bytes info, which hinders scalability during Full GC.

      One can take some inspiration from `G1RegionMarkStatsCache` to address this issue.

        1. fullgc.java
          0.3 kB

            Assignee:
            Albert Yang
            Reporter:
            Albert Yang
            Votes:
            0 Vote for this issue
            Watchers:
            4 Start watching this issue

              Created:
              Updated:
              Resolved: