From mboxrd@z Thu Jan 1 00:00:00 1970 From: Pekka Enberg Subject: Re: Mainline kernel OLTP performance update Date: Thu, 12 Feb 2009 18:03:32 +0200 Message-ID: <1234454612.28812.181.camel@penberg-laptop> References: <1232616517.11429.129.camel@ymzhang> <1232617672.14549.25.camel@penberg-laptop> <1232679773.11429.155.camel@ymzhang> <4979692B.3050703@cs.helsinki.fi> <1232697998.6094.17.camel@penberg-laptop> <1232699401.11429.163.camel@ymzhang> <1232703989.6094.29.camel@penberg-laptop> <1232765728.11429.193.camel@ymzhang> <84144f020901232336v71687223y2fb21ee081c7517f@mail.gmail.com> <1234416153.2604.387.camel@ymzhang> <1234417660.2604.391.camel@ymzhang> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: QUOTED-PRINTABLE Return-path: In-Reply-To: <1234417660.2604.391.camel@ymzhang> Sender: linux-kernel-owner@vger.kernel.org To: "Zhang, Yanmin" Cc: Christoph Lameter , Andi Kleen , Matthew Wilcox , Nick Piggin , Andrew Morton , netdev@vger.kernel.org, Stephen Rothwell , matthew.r.wilcox@intel.com, chinang.ma@intel.com, linux-kernel@vger.kernel.org, sharad.c.tripathi@intel.com, arjan@linux.intel.com, suresh.b.siddha@intel.com, harita.chilukuri@intel.com, douglas.w.styner@intel.com, peter.xihong.wang@intel.com, hubert.nueckel@intel.com, chris.mason@oracle.com, srostedt@redhat.com, linux-scsi@vger.kernel.org, andrew.vasquez@qlogic.com, anirban.chakraborty@qlogic.com, Ingo Molnar List-Id: linux-scsi@vger.kernel.org On Sat, 2009-01-24 at 09:36 +0200, Pekka Enberg wrote: > > > On Fri, 2009-01-23 at 10:22 -0500, Christoph Lameter wrote: > > > >> No there is another way. Increase the allocator order to 3 for= the > > > >> kmalloc-8192 slab then multiple 8k blocks can be allocated fro= m one of the > > > >> larger chunks of data gotten from the page allocator. That wil= l allow slub > > > >> to do fast allocs. > > >=20 > > > On Sat, Jan 24, 2009 at 4:55 AM, Zhang, Yanmin > > > wrote: > > > > After I change kmalloc-8192/order to 3, the result(pinned netpe= rf UDP-U-4k) > > > > difference between SLUB and SLQB becomes 1% which can be consid= ered as fluctuation. > > >=20 > > > Great. We should fix calculate_order() to be order 3 for kmalloc-= 8192. > > > Are you interested in doing that? On Thu, 2009-02-12 at 13:22 +0800, Zhang, Yanmin wrote: > > Pekka, > >=20 > > Sorry for the late update. > > The default order of =EF=BB=BFkmalloc-8192 on 2*4 stoakley is reall= y an issue of calculate_order. On Thu, 2009-02-12 at 13:47 +0800, Zhang, Yanmin wrote: > Oh, previous patch has a compiling warning. Pls. use below patch. >=20 > From: =EF=BB=BFZhang Yanmin >=20 > =EF=BB=BFThe default order of =EF=BB=BFkmalloc-8192 on 2*4 stoakley i= s an issue of calculate_order. Applied to the 'topic/slub/perf' branch. Thanks! Pekka