Messages in this thread | | | Date | Thu, 1 Dec 2005 02:11:52 +0100 | From | Antonio Vargas <> | Subject | Re: [PATCH 1/1] elevator: indirect function calls reducing |
| |
On 11/30/05, Ananiev, Leonid I <leonid.i.ananiev@intel.com> wrote: > Christoph, > During that function calls 3 memory ridings are performed under > spin_lock and having cache miss/conflict problem; > and 2 only main memory ridings after patching. > > In a source a[b][c][d](arg); > after patching number of memory ridings less by 1: > a[c][d](arg); > Do you agree with it? > Have you other explanation of performance degradation 2.6.9 -> 2.6.10? > > Leonid >
Leonid, you are "just" removing a memory fetch by embeding the struct instead of pointing to it, not removing a whole indirect jump... granted it's good to remove innecesary mem-fetchs, but then please call the patch that, a removal of not-necessary mem-fetches.
> > -----Original Message----- > From: Christoph Hellwig [mailto:hch@infradead.org] > Sent: Wednesday, November 30, 2005 7:26 PM > To: Ananiev, Leonid I > Cc: linux-kernel@vger.kernel.org; axboe@suse.de > Subject: Re: [PATCH 1/1] elevator: indirect function calls reducing > > > this _still_ isn't an indirect function call reduction and people > have told you N times. Please get your basics right first, to start > with the patch description. > - > To unsubscribe from this list: send the line "unsubscribe linux-kernel" in > the body of a message to majordomo@vger.kernel.org > More majordomo info at http://vger.kernel.org/majordomo-info.html > Please read the FAQ at http://www.tux.org/lkml/ >
-- Greetz, Antonio Vargas aka winden of network
http://wind.codepixel.com/ windNOenSPAMntw@gmail.com thesameasabove@amigascne.org
Every day, every year you have to work you have to study you have to scene. - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
| |