From mboxrd@z Thu Jan 1 00:00:00 1970 From: Keld =?iso-8859-1?Q?J=F8rn?= Simonsen Subject: Re: Faster read performance DURING (?) resync on raid10 Date: Sun, 28 Sep 2008 19:35:12 +0200 Message-ID: <20080928173512.GA28823@rap.rap.dk> References: <19666016.post@talk.nabble.com> <18652.25227.7530.435789@notabene.brown> <104f2a240809261619m2512bddem11ea7960d86df2ff@mail.gmail.com> <20080928022318.GA5634@rap.rap.dk> <104f2a240809280345i74ddc8dej462a33383082dfe8@mail.gmail.com> <104f2a240809280406q22ab748s3dca796e70e63ec3@mail.gmail.com> Mime-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: QUOTED-PRINTABLE Return-path: Content-Disposition: inline In-Reply-To: <104f2a240809280406q22ab748s3dca796e70e63ec3@mail.gmail.com> Sender: linux-raid-owner@vger.kernel.org To: Daniel Zetterman Cc: Neil Brown , linux-raid@vger.kernel.org List-Id: linux-raid.ids On Sun, Sep 28, 2008 at 01:06:09PM +0200, Daniel Zetterman wrote: > Sorry guys, the offset is if course as stated near=3D2, far=3D1 >=20 > Isn't near=3D2, far=3D2 better for raid10? >=20 a number of people say that near=3D1, far=3D2 is better. you could try it out and see if there is any difference. best regards keld >=20 > On Sun, Sep 28, 2008 at 12:45 PM, Daniel Zetterman > wrote: > > I'm using near=3D2, far=3D1, superblock version=3D00.90.03 > > > > I'm not sure about offset, but its the default. > > > > I wan't to clearify one thing about the data, its not only a proble= m > > with encryption over raid, you get the same drop without encryption= =2E.. > > but you can remedy it by setting up the readahead, which gives no > > effect when using encryption. > > > > > > On Sun, Sep 28, 2008 at 4:23 AM, Keld J=F8rn Simonsen wrote: > >> On Sat, Sep 27, 2008 at 01:19:50AM +0200, Daniel Zetterman wrote: > >>> I've done some more tests and here are the results: > >>> > >>> # bonnie++ during resync with readahead set to 512 (encrypted rai= d10) > >>> kpax,4G,,,77308,21,34585,17,,,82073,33,384.8,1,,,,,,,,,,,,, > >> > >> It would be nice to know which layout (near,far,offset) > >> that you are using for the test. The expected results are quite > >> dependent on this. > >> > >> best regards > >> keld > >> > > > -- > To unsubscribe from this list: send the line "unsubscribe linux-raid"= in > the body of a message to majordomo@vger.kernel.org > More majordomo info at http://vger.kernel.org/majordomo-info.html -- To unsubscribe from this list: send the line "unsubscribe linux-raid" i= n the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html