From mboxrd@z Thu Jan 1 00:00:00 1970 From: Keld =?iso-8859-1?Q?J=F8rn?= Simonsen Subject: Re: Linux MD RAID 1 read performance tunning Date: Tue, 22 Dec 2009 20:22:49 +0200 Message-ID: <20091222182248.GA5719@rap.rap.dk> References: <8e04b5820912220834m595f1aa6sf0071f99b4a5a144@mail.gmail.com> <20091222165225.GA2684@rap.rap.dk> <8e04b5820912220908s233c3bf9yf0fa9ba8deda693b@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: <8e04b5820912220908s233c3bf9yf0fa9ba8deda693b@mail.gmail.com> Sender: linux-raid-owner@vger.kernel.org To: "Ciprian Dorin, Craciun" Cc: linux-raid@vger.kernel.org List-Id: linux-raid.ids On Tue, Dec 22, 2009 at 07:08:25PM +0200, Ciprian Dorin, Craciun wrote: > 2009/12/22 Keld J=F8rn Simonsen : > > On Tue, Dec 22, 2009 at 06:34:55PM +0200, Ciprian Dorin, Craciun wr= ote: > >> =A0 =A0 Hello all! > >> > >> =A0 =A0 I've created a 64G RAID 1 matrix from 3 real disks. (I int= end to > >> use this as a target for backups.) > >> =A0 =A0 Now while playing around with this array, I've observed th= at the > >> read performance is quite low because it always reads from the dis= k in > >> the first slot (which happens to be the slowest...) > >> > >> =A0 =A0 So my questions are: > >> =A0 =A0 * is there any way to tell the MD driver to load-balance t= he reads > >> between the three disks? > > > > It does not make sense to do distributed reading in raid1 for seque= ntial > > files. This is because it will not be faster to read from more driv= es, > > as this will only make the reading from one drive skipping blocks o= n > > that drive. In other words, in the time you use for skipping blocks= on > > one drive, you could just as well have read the blocks. So then bet= ter > > just read all the blocks off one drive, and then do other possible = IO > > from other drives. >=20 > Aha. It makes sens now. But, does it mean that if I have parallel > IO's (from different read operations) they are going to be distribute= d > between the disks? It should, but I am not fully sure it does. But try it out with two concurrent reads of two big files, and then watch it with iostat=20 Best regards keld -- 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