From mboxrd@z Thu Jan 1 00:00:00 1970 From: Roberto Spadim Subject: Re: Optimize RAID0 for max IOPS? Date: Fri, 21 Jan 2011 18:03:52 -0200 Message-ID: References: <20110118210112.D13A236C@gemini.denx.de> <4D361F26.3060507@stud.tu-ilmenau.de> <20110119192104.1FA92D30267@gemini.denx.de> <4D37677D.9010108@stud.tu-ilmenau.de> <20110121193457.C7719D30268@gemini.denx.de> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: QUOTED-PRINTABLE Return-path: In-Reply-To: <20110121193457.C7719D30268@gemini.denx.de> Sender: linux-raid-owner@vger.kernel.org To: Wolfgang Denk Cc: stefan.huebner@stud.tu-ilmenau.de, linux-raid@vger.kernel.org List-Id: linux-raid.ids =3D) i know but, every body tell software is slower, the solution - use hardware ok there=B4s no opensource firmware for raid hardware i preffer a good software/hardware solution, linux raid is a good software solution for me =3D) but, why not try a opensource project? hehe what we could do.... a virtual machine :P with only raid and nfs, or make a dedicated cpu for raid (cpu affinity) and a portion of memory only for raid cache (today i think raid software don=B4t have cache, it shoudn=B4t, cache is done by linux at filesystem level, i=B4m right?) 2011/1/21 Wolfgang Denk : > Dear Roberto, > > In message you wrote: >> a good idea.... >> why not start a opensource raid controller? >> what we need? a cpu, memory, power supply with battery or capacitor, >> sas/sata (disk interfaces), pci-express or another (computer >> interface) >> it don=B4t need a operational system, since it will only run one pro= gram >> with some threads (ok a small operational system to implement thread= s >> easly) >> >> we could use arm, fpga, intel core2duo, atlhon, xeon, or another sys= tem... > > You could evenuse a processor dedicated for such a job, like a > PPC440SPe or PPC460SX or similar, which provide hardware-offload > capabilities for the RAID calculations. =A0These are even supported b= y > drivers in mainline Linux. > > But again, thee would not helpo to maximize IOPS - goal for > optimization has always been maximum sequential troughput only > (and yes, I know exactly what I'm talking about; guess where the > aforementioned drivers are coming from). > > Best regards, > > Wolfgang Denk > > -- > DENX Software Engineering GmbH, =A0 =A0 MD: Wolfgang Denk & Detlev Zu= ndel > HRB 165235 Munich, Office: Kirchenstr.5, D-82194 Groebenzell, Germany > Phone: (+49)-8142-66989-10 Fax: (+49)-8142-66989-80 Email: wd@denx.de > I don't see any direct evidence ... =A0but, then, my crystal ball is = in > dire need of an ectoplasmic upgrade. :-) =A0 =A0 =A0 =A0 =A0 =A0 =A0-= - Howard Smith > -- > 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 =A0http://vger.kernel.org/majordomo-info.html > --=20 Roberto Spadim Spadim Technology / SPAEmpresarial -- 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