From mboxrd@z Thu Jan 1 00:00:00 1970 From: Wolfgang Denk Subject: Re: Optimize RAID0 for max IOPS? Date: Wed, 19 Jan 2011 08:10:06 +0100 Message-ID: <20110119071006.C05B12FC@gemini.denx.de> References: <20110118210112.D13A236C@gemini.denx.de> <4D361F26.3060507@stud.tu-ilmenau.de> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: QUOTED-PRINTABLE Return-path: In-reply-to: <4D361F26.3060507@stud.tu-ilmenau.de> Sender: linux-raid-owner@vger.kernel.org To: stefan.huebner@stud.tu-ilmenau.de Cc: linux-raid@vger.kernel.org List-Id: linux-raid.ids Dear =3D?ISO-8859-15?Q?Stefan_/*St0fF*/_H=3DFCbner?=3D, In message <4D361F26.3060507@stud.tu-ilmenau.de> you wrote: >=20 > [in German:] Sch=E4tzelein, Dein Problem sind die Platten, nicht der > Controller. Irrtum. > [in English:] Dude, the disks are your bottleneck. Wrong. Testing the same workload with soft RAID versus the h/w RAID solution gives a _significant_ performance difference. I happen to know which benchmarks 3ware (and other RAID controller manufacturers) are optimizing their firmware for - IOPS is not even mentioned there. > On a 4-disk RAID0 software RAID can only outspeed this 3ware Controll= er > with a really really fast processor. The limiting factor is the disk= 's > access time. If SSDs are too expensive, then your actual performance= is > the max you'll get (maybe to replace the HWRAID controller might give= a > little speed-up, but not very much). =46rom some tests done before I expect to see a speed increase of >10. Hey, even a single disk is performing better under this work load. And fast processor? Yes, I have it, but what for? It spends most of it's time (>90%, usually more) in iowait. Best regards, Wolfgang Denk --=20 DENX Software Engineering GmbH, MD: Wolfgang Denk & Detlev Zundel HRB 165235 Munich, Office: Kirchenstr.5, D-82194 Groebenzell, Germany Phone: (+49)-8142-66989-10 Fax: (+49)-8142-66989-80 Email: wd@denx.de "To IBM, 'open' means there is a modicum of interoperability among some of their equipment." - Harv Masterson -- 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