From mboxrd@z Thu Jan 1 00:00:00 1970 From: John Robinson Subject: Re: [Slightly OT] Cheap 4-port PCI-E SATA card? Date: Mon, 03 Jan 2011 16:00:59 +0000 Message-ID: <4D21F2BB.3020905@anonymous.org.uk> References: <4D20E9F7.2080800@anonymous.org.uk> <4D216FA1.5010502@hardwarefreak.com> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: QUOTED-PRINTABLE Return-path: In-Reply-To: <4D216FA1.5010502@hardwarefreak.com> Sender: linux-raid-owner@vger.kernel.org To: Linux RAID List-Id: linux-raid.ids On 03/01/2011 06:41, Stan Hoeppner wrote: [...] > Go with one or two of these SATA II port multipliers with 1 host > interface and 5 drive interfaces--perfect for a 10 drive setup with t= wo > 5 drive cages. > > http://www.addonics.com/products/host_controller/ad5sapm.asp > > http://www.buy.com/prod/addonics-ad5sapm-serial-ata-controller-5-x-7-= pin-serial-ata-300-serial/q/loc/101/213272437.html > > http://www.siliconimage.com/products/product.aspx?pid=3D32 > > If your mobo SATA ports support FIS based switching, this PMP will gi= ve > you 5 SATA II drive ports. It doesn't use a PCI slot of any kind. N= o > additional software required. No kernel driver issues. 300MB/s is > sufficient for 5 drives in an mdraid setup isn't it? =46or a backup array, yes, but I'm not sure it is for online storage.=20 300MB/s is an absolute max and there's protocol overhead etc, but even=20 if it's minimal we're still looking at no better than 50MB/s per drive,= =20 while the drives can manage 125MB/s these days. I doubt my motherboard supports FIS PMPs. It's an Asus P5Q Pro, Intel=20 P45+ICH10R, and I'm pretty sure the ICH10R doesn't support PMPs even if= =20 the original spec said it would. There is a Marvell 88SE6121 SATA+IDE chip on there but it's currently i= n=20 IDE-only mode for the DVD drive and even if I switched over to SATA mod= e=20 and a SATA DVD drive that'd only give me one more SATA port. But it=20 might work with a FIS PMP, I suppose. > When I use these I remove the slot bracket and mount the PCB directly= to > my server chassis side wall using mobo type standoffs. You may need = to > drill a couple of holes in the chassis depending on where you decide = to > mount it. If you're not a mechanically inclined DIY type person, jus= t > use the supplied mounting bracket. This may deny access to an > underlying PCI slot though. I prefer the more solid mount and having > all slots available. I'd do that too - no problems doing case mods here. I suppose it's=20 possible the mounting holes might be able to be made to line up with=20 some of the mounting holes on the side of the hot-swap chassis. On the=20 other hand I might cheat and use the little plastic mounts with=20 double-sided tape on their feet. [...] > The driver for the Marvell chip is present in kernel > 2.6.19 and later. Considering that 2.6.19 is like 6 years old, I'd h= ope > your kernel is newer. It's kernel-2.6.18-194.26.1.el5 so it's stuffed full of backports and=20 security updates, it's less than two months old. Yes, I have sata_mv,=20 but several people have reported data corruption issues with some=20 Marvell controllers - a bad interaction with SMART I think. > It may be a little more money than you were planning on spending, but > for little more than the cost of one hard drive In this case I'm using consumer-level drives so they're about =C2=A340 = ($60),=20 so $165 is a bit rich for me, especially since it's potentially limited= =20 for throughput. Nevertheless, thank you very much for taking the time for such a=20 considered reply. Cheers, John. -- 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