Messages in this thread | | | Subject | Re: hackbench regression with kernel 2.6.32-rc1 | From | "Zhang, Yanmin" <> | Date | Tue, 13 Oct 2009 11:12:02 +0800 |
| |
On Mon, 2009-10-12 at 16:21 +0200, Peter Zijlstra wrote: > On Mon, 2009-10-12 at 15:05 +0800, Zhang, Yanmin wrote: > > > > So hackbench is a multi-cast, with one sender spraying multiple > > > receivers, who in their turn don't spray back, right? > > > Right. volanoMark has about 9% regression on stoakley and 50% regression > > on tigerton. If I revert the original patches, volanoMark regression on stoakley > > disappears, but still has about 45% on tigerton. > > > > /me ponders a bit > > > > > > Does this make it any better? > > > I apply this patch and another one you sent on tbench email thread. > > On stoakley, hackbench is recovered. If reverting the original 2 patches, > > we get 8% improvement. > > On tigerton, with your 2 patches, there is still about 45% regression. > > [ and here I got confused because this 45% seemed to match the 45% > above, but then I saw it was hackbench vs volano ] Sorry for mentioning some data about multiple benchmarks in one email.
> > > As for volanoMark, with your 2 patches, regression disappears on staokley > > and it becomes about 35% on tigerton. > > So hackbench on tigerton is worse, but volano on tigerton is better with > this patch vs reverting bits? Right with your 2 new patches vs reverting the 2 original patches.
> > > The good news is only tbench has about 6% regression on Nehalem machines. > > Other regressions such like hackbench/aim7/volanoMark is not clear/big on > > Nehalem. But reverting the original 2 patches don't fix the tbench regression > > on Nehalem machines. > > Right, so Mike's suggestion of doing: > echo NEXT_BUDDY > /debug/sched_features With your 2 new patches plus NEXT_BUDDY configuration, hackbench has some improvement instead of regression on tigerton now. So it does work.
NEXT_BUDDY has no help on volanoMark and tbench.
> > Seems like the next thing to try.. > > Mike, did we ever figure out _why_ NEXT_BUDDY introduced latencies? > > Buddies shouldn't make latencies worse than regular while(1); loops > would. >
| |