Memory serialization page can become a bottleneck

XMLWordPrintable

    • Type: Enhancement
    • Resolution: Won't Fix
    • Priority: P4
    • 13
    • Affects Version/s: 9
    • Component/s: hotspot

      When threads transition state to/from native code they use the memory_serialization_page as a means of performing memory synchronization. Due to the use of a single 4K page, and the requirement for 128byte alignment this is limited to 32 distinct slots. Combined with a poor hashing function we can get excessive contention on these slots and encounter a performance bottleneck.

        1.
        		 UseMembar should not be obsoleted yet Sub-task Resolved Robbin Ehn  

            Assignee:
            Robbin Ehn
            Reporter:
            David Holmes
            Votes:
            0 Vote for this issue
            Watchers:
            10 Start watching this issue

              Created:
              Updated:
              Resolved: