[Gc] Removal of mark lock spinning for Win32

Boehm, Hans hans.boehm at hp.com
Wed Nov 12 17:13:00 PST 2008



> -----Original Message-----
> From:  Ivan Maidanski
> "Boehm, Hans" <hans.boehm at hp.com> wrote:
> > ...
> > Your performance test had the other app (separate process?)
> using up cpu time during the GC?  So the processors were
> over-committed?  In that case, the results don't seem
> surprising.  Maybe I'm misunderstanding something.
>
> Yes. Two separate processes (with 4 never-sleep threads
> allocating many normally-small and short-lived objects)
> parallelly plus a number OS processes (out of my control). I
> couldn't manage to get stable measurements when I launch the
> processes sequentially.
> To my opinion, PARALLEL_MARK could be considered as just an
> optimization (eg., to get shorter stop-the-world delays) for
> real apps running on real busy systems, so my performance
> test may have some sense.
Thanks.  That makes sense, though with overcommitted processors latencies will always be hard to predict.

Hans



More information about the Gc mailing list