src/share/vm/runtime/thread.cpp

rev 12508 : 8166944: Hanging Error Reporting steps may lead to torn error logs.
Reviewed-by: cjplummer, dholmes
Summary: Interupt error reporting if reporting steps hang to enable subsequent reporting steps to run.

*** 1287,1318 ****
      int time_waited = sleep();
  
      if (is_error_reported()) {
        // A fatal error has happened, the error handler(VMError::report_and_die)
        // should abort JVM after creating an error log file. However in some
!       // rare cases, the error handler itself might deadlock. Here we try to
!       // kill JVM if the fatal error handler fails to abort in 2 minutes.
!       //
        // This code is in WatcherThread because WatcherThread wakes up
        // periodically so the fatal error handler doesn't need to do anything;
        // also because the WatcherThread is less likely to crash than other
        // threads.
  
        for (;;) {
!         if (!ShowMessageBoxOnError
!             && (OnError == NULL || OnError[0] == '\0')
!             && Arguments::abort_hook() == NULL) {
!           os::sleep(this, (jlong)ErrorLogTimeout * 1000, false); // in seconds
            fdStream err(defaultStream::output_fd());
            err.print_raw_cr("# [ timer expired, abort... ]");
            // skip atexit/vm_exit/vm_abort hooks
            os::die();
          }
  
!         // Wake up 5 seconds later, the fatal handler may reset OnError or
!         // ShowMessageBoxOnError when it is ready to abort.
!         os::sleep(this, 5 * 1000, false);
        }
      }
  
      if (_should_terminate) {
        // check for termination before posting the next tick
--- 1287,1322 ----
      int time_waited = sleep();
  
      if (is_error_reported()) {
        // A fatal error has happened, the error handler(VMError::report_and_die)
        // should abort JVM after creating an error log file. However in some
!       // rare cases, the error handler itself might deadlock. Here periodically
!       // check for error reporting timeouts, and if it happens, just proceed to
!       // abort the VM.
! 
        // This code is in WatcherThread because WatcherThread wakes up
        // periodically so the fatal error handler doesn't need to do anything;
        // also because the WatcherThread is less likely to crash than other
        // threads.
  
        for (;;) {
!         // Note: we use naked sleep in this loop because we want to avoid using
!         // any kind of VM infrastructure which may be broken at this point.
!         if (VMError::check_timeout()) {
!           // We hit error reporting timeout. Error reporting was interrupted and
!           // will be wrapping things up now (closing files etc). Give it some more
!           // time, then quit the VM.
!           os::naked_short_sleep(200);
!           // Print a message to stderr.
            fdStream err(defaultStream::output_fd());
            err.print_raw_cr("# [ timer expired, abort... ]");
            // skip atexit/vm_exit/vm_abort hooks
            os::die();
          }
  
!         // Wait a second, then recheck for timeout.
!         os::naked_short_sleep(999);
        }
      }
  
      if (_should_terminate) {
        // check for termination before posting the next tick