Re: [Gc] Removal of mark lock spinning for Win32
ivmai at mail.ru
Wed Nov 12 15:15:50 PST 2008
"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.
> > -----Original Message-----
> > From: gc-bounces at napali.hpl.hp.com
> > [mailto:gc-bounces at napali.hpl.hp.com] On Behalf Of Ivan Maidanski
> > Sent: Saturday, November 01, 2008 3:47 AM
> > To: gc at napali.hpl.hp.com
> > Subject: [Gc] Removal of mark lock spinning for Win32
> > Hi!
> > ...
> > Several words about performance gain with parallel markers (Win32).
> > I ran two instances (in parallel) of a long running demo GUI
> > app with several active threads (one without PARALLEL_MARK
> > and other with GC_markers=2, both in non-incremental mode,
> > all optimizations on, no assertions, heapsize=35M). It gives
> > me in average about 25% shorter world-stopped delays (no
> > more) after 1500 collections. In the incremental mode (both,
> > no time limit) I haven't noticed any performance gain at all.
> > Bye.
More information about the Gc