[Bug libgcj/16662] IllegalMonitorStateException in EventQueue.getNextEvent(): possible hash synchronization bug?

mckinlay at redhat dot com gcc-bugzilla@gcc.gnu.org
Tue Aug 10 18:02:00 GMT 2004


------- Additional Comments From mckinlay at redhat dot com  2004-08-10 18:02 -------
Thanks for investigating this, Hans. Perhaps it is more difficult to reproduce
the bug on slower hardware - with the LockTest.java test case it always seems to
happen within 1 second or so on the 4-way PPC and HT P4 hardware I've tried. It
sometimes takes longer on a 4-way AMD opteron system but the longest I've had to
wait was 30 seconds or so. Let me know if you'd like me to test any patches.

Here's another thing - when running LockTest, I've occasionally seen the
exception come from Object.wait() rather than _Jv_MonitorExit:

$ ./a.out 
java.lang.IllegalMonitorStateException: current thread not owner
   at java.lang.Object.wait (natObject.cc:1215)
   at LockTest$Queue.pop (LockTest.java:59)
   at LockTest$PopThread.run (LockTest.java:39)
java.lang.IllegalMonitorStateException: current thread not owner
   at LockTest$Queue.pop (LockTest.java:50)
   at LockTest$PopThread.run (LockTest.java:39)



-- 


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=16662



More information about the Java-prs mailing list