Uploaded image for project: 'JDK'
  1. JDK
  2. JDK-8180932

Parallelize safepoint cleanup

    XMLWordPrintable

Details

    • Enhancement
    • Resolution: Fixed
    • P3
    • 10
    • 10
    • hotspot
    • b21
    • generic
    • generic

    Description

      Some operations in safepoint cleanup have been observed to (sometimes) take significant time. Most notably, idle monitor deflation and nmethod marking stick out in some popular applications and benchmarks.

      I propose to:
      - parallelize safepoint cleanup processing
      - enable to hook up idle monitor deflation and nmethod marking to GC VM ops, if GC can support it (resulting in even more efficient deflation/nmethod marking)

      Attachments

        Issue Links

          relates to

          Bug - A problem which impairs or prevents the functions of the product. JDK-8132849 Increased stop time in cleanup phase because of single-threaded walk of thread stacks in NMethodSweeper::mark_active_nmethods()

          • P2 - Crashes, loss of data, severe memory leak.
          • Resolved

          Enhancement - null JDK-8184751 Provide thread pool for parallel safepoint cleanup

          • P4 - Minor loss of function, or other problem where easy workaround is present.
          • Resolved

          Bug - A problem which impairs or prevents the functions of the product. JDK-8186837 Memory ordering nmethod, _state and _stack_traversal_mark

          • P4 - Minor loss of function, or other problem where easy workaround is present.
          • Resolved

          Bug - A problem which impairs or prevents the functions of the product. JDK-8185273 Test8004741.java crashes with SIGSEGV in JDK10-hs nightly

          • P1 - Blocks development and/or testing work, production could not run.
          • Closed

          Bug - A problem which impairs or prevents the functions of the product. JDK-8185102 TestSAServer.java fails due to "sun.jvm.hotspot.types.WrongTypeException: field "_stack_traversal_mark"

          • P2 - Crashes, loss of data, severe memory leak.
          • Closed

          Enhancement - null JDK-8153224 Monitor deflation prolong safepoints

          • P3 - Major loss of function.
          • Resolved

          Enhancement - null JDK-8185580 Refactor Threads::possibly_parallel_oops_do() to use Threads::parallel_java_threads_do()

          • P4 - Minor loss of function, or other problem where easy workaround is present.
          • Resolved

          Activity

            People

              rkennke Roman Kennke
              rkennke Roman Kennke
              Votes:
              0 Vote for this issue
              Watchers:
              3 Start watching this issue

              Dates

                Created:
                Updated:
                Resolved: