thanks, i never used a PPC440SPe, i will buy one for hobby =) 2011/1/21 Roberto Spadim <roberto@xxxxxxxxxxxxx>: > =) i know > but, every body tell software is slower, the solution - use hardware > ok > there´s no opensource firmware for raid hardware > > i preffer a good software/hardware solution, linux raid is a good > software solution for me =) > 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´t have cache, it > shoudn´t, cache is done by linux at filesystem level, i´m right?) > > > 2011/1/21 Wolfgang Denk <wd@xxxxxxx>: >> Dear Roberto, >> >> In message <AANLkTiki_FfRrLtL3dMsrDLXeT8jNO0ndnTNpXk1OXMW@xxxxxxxxxxxxxx> 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´t need a operational system, since it will only run one program >>> with some threads (ok a small operational system to implement threads >>> easly) >>> >>> we could use arm, fpga, intel core2duo, atlhon, xeon, or another system... >> >> 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. These are even supported by >> 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, 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@xxxxxxx >> I don't see any direct evidence ... but, then, my crystal ball is in >> dire need of an ectoplasmic upgrade. :-) -- Howard Smith >> -- >> To unsubscribe from this list: send the line "unsubscribe linux-raid" in >> the body of a message to majordomo@xxxxxxxxxxxxxxx >> More majordomo info at http://vger.kernel.org/majordomo-info.html >> > > > > -- > Roberto Spadim > Spadim Technology / SPAEmpresarial > -- Roberto Spadim Spadim Technology / SPAEmpresarial -- To unsubscribe from this list: send the line "unsubscribe linux-raid" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html