Hi Alex, I have been planning to make the processor affinity configurable, but just haven't had a chance to do this yet.
This certainly isn't a feature for 2.8.1 as the minor point releases are contain just bug fixes. This feature will have to wait till the 2.9.x dev series and the final 2.10. This does assume that I or other get on to tackling this task before 2.10... Robert. On Thu, Feb 19, 2009 at 2:16 AM, Pecoraro, Alexander N <[email protected]> wrote: > I think it would be nice if the processor chosen for the draw thread by > the osgViewer was somehow configurable instead of it just defaulting to > starting at processor number 1 and going up from there. I, like Todd, > seem to have found that running the draw thread on my second processor > (on any of the four cores on my second processor) produces better > performance than running it on any of the cores of my first processor. I > can't explain why I get better performance on my second processor, but > the only way I was able to make the draw thread run on my second > processor was by modifying the osgViewer::startThreading() function > because I found that calling the draw thread's setProcessorAffinity() > function had no effect after the thread started running. > > Perhaps something for 2.8.1? > > Alex > > -----Original Message----- > From: [email protected] > [mailto:[email protected]] On Behalf Of Robert > Osfield > Sent: Monday, September 01, 2008 8:34 AM > To: OpenSceneGraph Users > Subject: Re: [osg-users] Draw threads serialized by default? > > HI Todd. > > osgViewer already sets the affinity, and indeed this makes a big > difference to performance when running multi-threaded, > mult-context/mulit-gpu work. The draw dispatch serialization that > osgViewer::Renderer does on top of this makes even more difference on > PCs I've tested. I would guess that a decent multi-processing > architecture like the Onyx would scale much better, it might be that > some very high PC hardware set ups would also scale much better (the > AMD 4x4 motherboards spring to mind as a potential candidate for this > better scaling). > > Robert. > > On Mon, Sep 1, 2008 at 4:22 PM, Todd J. Furlong <[email protected]> > wrote: >> Robert, >> >> The post of yours that Paul linked to sounds very similar to something > we >> saw with VR Juggler & OSG a while back: terrible performance with OSG > apps >> that had parallel draw threads. In our case, VR Juggler manages > threading, >> but the same may apply to OSG with osgViewer. >> >> For us, it turned out that we had to set the threads' affinity to lock > them >> to a particular CPU/core. The Linux scheduler moved the threads > around and >> thrashed the cache, I believe. Setting the affinity boosted the > parallel >> draw performance back up. >> >> The solution we ended up with is twofold: >> 1. Add a default behavior that sequentially locks draw threads to CPU > cores >> (0,1,2,etc. & repeat) >> 2. Use an environment variable to override the default behavior >> (VJ_DRAW_THREAD_AFFINITY, a space-delimited list of integers). >> >> The default behavior is good for most users, but we can squeeze out a > little >> more performance by tweaking the environment variable. For a system > with >> two draw threads and two dual-core CPUs, the default behavior locks > the draw >> threads to CPUs 0 & 1, but we get slightly better performance if we > set >> VJ_DRAW_THREAD_AFFINITY="2 3". >> >> Regards, >> Todd >> >> Robert Osfield wrote: >>> >>> Hi Paul, >>> >>> On Sat, Aug 30, 2008 at 10:19 PM, Paul Martz <[email protected]> >>> wrote: >>>> >>>> Hi Robert -- Prior to the 2.2 release, code was added to serialize > the >>>> draw >>>> dispatch. Is there a reason that this behavior defaults to ON? (See >>>> DisplaySettings.cpp line 135.) I have somehow incorrectly documented > this >>>> as >>>> defaulting to OFF in the ref man. Now that I see it's ON by default, > I >>>> half >>>> wonder if this is a bug. Wanted to check with you: should I change > the >>>> documentation, or the code? Which is right? >>> >>> The settings has been ON since I introduced the option to serialize >>> the draw dispatch. >>> >>> Just before the 2.6 release I did testing at my end and still found >>> serializing the draw dispatch to be far more effiecent on my >>> Linux/NVidia drivers so I left the option on. >>> >>> In the original thread when I introduced the optional draw mutex into >>> the draw dispatch I did call for testing on the performance impact > but >>> I didn't get sufficient feedback to make a more informed decision > than >>> just basing it on my own testing. I would still appreciate more >>> testing, as I'd expect that best default setting to vary on different >>> hardware and drivers - I for one would love to see better scalability >>> in driver/hardware. >>> >>> Robert. >>> _______________________________________________ >>> osg-users mailing list >>> [email protected] >>> > http://lists.openscenegraph.org/listinfo.cgi/osg-users-openscenegraph.or > g >> >> _______________________________________________ >> osg-users mailing list >> [email protected] >> > http://lists.openscenegraph.org/listinfo.cgi/osg-users-openscenegraph.or > g >> > _______________________________________________ > osg-users mailing list > [email protected] > http://lists.openscenegraph.org/listinfo.cgi/osg-users-openscenegraph.or > g > _______________________________________________ > osg-users mailing list > [email protected] > http://lists.openscenegraph.org/listinfo.cgi/osg-users-openscenegraph.org > _______________________________________________ osg-users mailing list [email protected] http://lists.openscenegraph.org/listinfo.cgi/osg-users-openscenegraph.org
