From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (qmail 21646 invoked by alias); 10 Aug 2004 18:02:26 -0000 Mailing-List: contact java-prs-help@gcc.gnu.org; run by ezmlm Precedence: bulk List-Subscribe: List-Archive: List-Post: List-Help: , Sender: java-prs-owner@gcc.gnu.org Received: (qmail 21626 invoked by uid 48); 10 Aug 2004 18:02:25 -0000 Date: Tue, 10 Aug 2004 18:02:00 -0000 Message-ID: <20040810180225.21624.qmail@sourceware.org> From: "mckinlay at redhat dot com" To: java-prs@gcc.gnu.org In-Reply-To: <20040721214713.16662.mckinlay@redhat.com> References: <20040721214713.16662.mckinlay@redhat.com> Reply-To: gcc-bugzilla@gcc.gnu.org Subject: [Bug libgcj/16662] IllegalMonitorStateException in EventQueue.getNextEvent(): possible hash synchronization bug? X-Bugzilla-Reason: CC X-SW-Source: 2004-q3/txt/msg00206.txt.bz2 List-Id: ------- 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