From owner-freebsd-scsi@FreeBSD.ORG Thu Nov 8 15:18:17 2007 Return-Path: Delivered-To: freebsd-scsi@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 12BD516A46C for ; Thu, 8 Nov 2007 15:18:17 +0000 (UTC) (envelope-from ambrisko@ambrisko.com) Received: from mail.ambrisko.com (mail.ambrisko.com [64.174.51.43]) by mx1.freebsd.org (Postfix) with ESMTP id C76DF13C4B2 for ; Thu, 8 Nov 2007 15:18:11 +0000 (UTC) (envelope-from ambrisko@ambrisko.com) Received: from server2.ambrisko.com (HELO www.ambrisko.com) ([192.168.1.2]) by ironport2.ambrisko.com with ESMTP; 08 Nov 2007 07:12:05 -0800 Received: from ambrisko.com (localhost [127.0.0.1]) by www.ambrisko.com (8.14.1/8.12.11) with ESMTP id lA8FI3kw057304; Thu, 8 Nov 2007 07:18:03 -0800 (PST) (envelope-from ambrisko@ambrisko.com) Received: (from ambrisko@localhost) by ambrisko.com (8.14.1/8.13.1/Submit) id lA8FI2O2057303; Thu, 8 Nov 2007 07:18:02 -0800 (PST) (envelope-from ambrisko) From: Doug Ambrisko Message-Id: <200711081518.lA8FI2O2057303@ambrisko.com> In-Reply-To: <4732C443.1070100@samsco.org> To: Scott Long Date: Thu, 8 Nov 2007 07:18:02 -0800 (PST) X-Mailer: ELM [version 2.4ME+ PL94b (25)] MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Content-Type: text/plain; charset=US-ASCII Cc: freebsd-scsi@freebsd.org Subject: Re: MFI and passthrough X-BeenThere: freebsd-scsi@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: SCSI subsystem List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 08 Nov 2007 15:18:17 -0000 Scott Long writes: | Borja Marcos wrote: | > On Nov 6, 2007, at 4:02 PM, Scott Long wrote: | > | >> Doug Ambrisko wrote: | >>> BTW, it works great in this mode if you know what you are doing :-) | >> | >> Can you explain what that means? I recommend against it because it's | >> not a well-tested configuration either in FreeBSD or in Dell. It's not | >> clear, at least to me, how basic things like i/o errors get handled; | >> does SCSI sense data get consumed by the controller firmware, or is it | >> passed through to the OS without problem? | > | > Aha, I see. I assumed that the controller would pass the sense data, | > etc, without problems. | > | >>> | I do believe that Dell does sell a direct attached disk option for | >>> | the 2950/1950 called the PERC5/e. It's essentially an LSI MPT-SAS | >>> | controller that directly replaces the PERC5/i card that you have now. | >>> | It should be able to control all 6 disk slots, and can do both SAS | >>> | and SATA. | >>> I've been told the PERC5/e and PERC5/i are the same except for PCI | >>> sub-device ID and are both the mfi(4) RAID controllers. They do | >>> have a mpt(4) based card but it only supports 4 bays. I'm not sure | >>> what it's real name is but we have some lying around for random | >>> testing. I don't leave them in machines. | >> | >> We should get a definitive answer on this. | > | > We asked our Dell salesman and he confirmed that there's a non disk | > array card for this machine, | > but it only supports 4 disks, not 6. | | Ok, I thought that the 4 disk option just routed the motherboard SATA | connectors to the backplane, and that there was a 6 disk SAS+SATA option | that put an MPT card into the slot behind the backplane. Oh well. The Dell storage cards are interesting now. The built-in cards are a PCIe card on a horizontal tray the plug in a special PCIe slot by the front. You can take it off the tray, screw on a PC slot bracket then plug it into a PCIe slot. So the same cards can be used for either in the special slot in the PE2950 or in the other Dell machines via a generic PCIe slot. The mpt(4) card only has on SAS connector on that can only plug into one of the SAS back-planes connector. So you are limited to 4 SAS bays. The mfi(4) cards have 2 so you can use all drive bays. Dell's current mpt(4) and mfi(4) cards have been layed out so they can be interchanged with their mounting HW. The only this I don't know is their naming since PERC is for "built-in" and CERC is external. Also I'm not sure what they do for the battery if in generic PCIe mode. They could make a battery that bolts on or piggy back the DIMM like LSI does. I don't know all of the specifics since we order random things that I just make work. It's a fairly smart move since they can offer the same RAID/SAS stuff across their product line and only use 2 cards. Since they share the SAS card and some platforms don't have the space for a lot of drives they probably cost reduced it to one connector versus the 2. Note moving cards around like this is probably not supported but I do things like this to test out things. Doug A.