* world. Figure out what sort of space-time tradeoff we're actually going to get here with the
   * *Map variants. This class is particularly hard to benchmark, because the benefit is not only in
   * less allocation, but also having the GC do less work to scan the heap because of fewer
   * references, which is particularly hard to quantify.
   */

    // the monitor with the guard satisfied. Therefore as soon as tearDownLatch is triggered, we
    // should be able to enter the monitor, and then we set the guard to satisfied for the benefit
    // of any remaining waiting threads.

    tearDownLatch.countDown();
    assertTrue(
        "Monitor still occupied in tearDown()",
        monitor.enter(UNEXPECTED_HANG_DELAY_MILLIS, TimeUnit.MILLISECONDS));

        // run() on the same thread that called execute() - such as in a thread pool, and think
        // that it was happening inline. As a side benefit, avoids holding on to the Thread object
        // longer than necessary.
        submitting = null;
      }
    }

    @SuppressWarnings("ShortCircuitBoolean")
    @Override
    public void run() {

    /*
     * Padding from 40 into 64 bytes, same size as cache line. Might be beneficial to add a fourth
     * long here, to minimize chance of interference between consecutive locks, but I couldn't
     * observe any benefit from that.
     */
    long unused1;
    long unused2;
    long unused3;

    PaddedLock() {
      super(false);
    }
  }

  private static class PaddedSemaphore extends Semaphore {