From mboxrd@z Thu Jan 1 00:00:00 1970 From: Rahul Lakkireddy Subject: Re: [RFC PATCH 2/3] x86/io: implement 256-bit IO read and write Date: Wed, 21 Mar 2018 17:57:09 +0530 Message-ID: <20180321122708.GA3245@chelsio.com> References: <6ec3e7e0c70e85a804933f27bb4275d5363c044b.1521469118.git.rahul.lakkireddy@chelsio.com> <20180320133206.GB25574@chelsio.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Thomas Gleixner , "x86@kernel.org" , "linux-kernel@vger.kernel.org" , "netdev@vger.kernel.org" , "mingo@redhat.com" , "hpa@zytor.com" , "davem@davemloft.net" , "akpm@linux-foundation.org" , "torvalds@linux-foundation.org" , Ganesh GR , Nirranjan Kirubaharan , Indranil Choudhury To: Andy Shevchenko Return-path: Content-Disposition: inline In-Reply-To: Sender: linux-kernel-owner@vger.kernel.org List-Id: netdev.vger.kernel.org On Tuesday, March 03/20/18, 2018 at 19:14:46 +0530, Andy Shevchenko wrote: > On Tue, Mar 20, 2018 at 3:32 PM, Rahul Lakkireddy > wrote: > > On Monday, March 03/19/18, 2018 at 20:13:10 +0530, Thomas Gleixner wrote: > >> On Mon, 19 Mar 2018, Rahul Lakkireddy wrote: > > >> Aside of that I very much doubt that this is faster than 4 consecutive > >> 64bit reads/writes as you have the full overhead of > >> kernel_fpu_begin()/end() for each access. > >> > >> You did not provide any numbers for this so its even harder to > >> determine. > >> > > > > Sorry about that. Here are the numbers with and without this series. > > > > When reading up to 2 GB on-chip memory via MMIO, the time taken: > > > > Without Series With Series > > (64-bit read) (256-bit read) > > > > 52 seconds 26 seconds > > > > As can be seen, we see good improvement with doing 256-bits at a > > time. > > But this is kinda synthetic test, right? > If you run in a normal use case where kernel not only collecting logs, > but doing something else, especially with frequent userspace > interaction, would be trend the same? > We see same improvement when collecting logs while running heavy IO with iozone. Thanks, Rahul