>In 2.2.10 it could. The IPI timeout occurs when we get a
deadlock across
>CPU's. One cpu is waiting for a lock and not listening to the
interrupts
>the other one is asking it to handle and reply to.
so then someone calling a syncoronized java method could
possibly cause a dead lock which could then cause the IPI
timout? Since the original question was about Kaffe, it is
possible that the single threaded app still had a syncronized
method that was causing the deadlock situation. In Java if you
do not tell you threads to listen to interrupts they
don't.(AFAIK)
__________________________________________________
Do You Yahoo!?
Bid and sell for free at http://auctions.yahoo.com
-
Linux SMP list: FIRST see FAQ at http://www.irisa.fr/prive/mentre/smp-faq/
To Unsubscribe: send "unsubscribe linux-smp" to [EMAIL PROTECTED]
