Date: Thu, 12 Oct 2000 17:33:47 -0700 From: Leonard Chung <leonard@ssl.berkeley.edu> To: Carroll Kong <damascus@home.com>, "Jeffrey J. Mountin" <jeff-ml@mountin.net> Cc: Warner Losh <imp@village.org>, kline@tao.thought.org, freebsd-stable@FreeBSD.ORG Subject: Re: Bad IDE Drive Message-ID: <4.3.2.7.2.20001012171658.02704b28@yikes.com> In-Reply-To: <4.2.2.20001012192324.00c0de90@email.eden.rutgers.edu> References: <4.3.2.20001010190749.00c5cf00@207.227.119.2> <4.3.2.7.2.20001010124858.026637c0@yikes.com> <200010100509.XAA18135@harmony.village.org> <Your message of "Mon, 09 Oct 2000 19:06:31 PDT." <4.3.2.7.2.20001009190324.028c6d58@yikes.com> <4.3.2.7.2.20001009190324.028c6d58@yikes.com>
next in thread | previous in thread | raw e-mail | index | archive | help
At 05:58 PM 10/12/2000, Carroll Kong wrote: >The Scsi bus is far superior to the Ide bus, overlapping queue commands, etc. Yes, to get the speeds that I was talking about, you need to have master-only on each string which is what you get using IDE RAID cards. In addition, they add only a nominal cost to the already cheap IDE drives. With good IDE RAID cards, you'll get the n-deep outstanding IOs, hot swap, and hardware RAID. Plus, it has the added benefit that the drives aren't sharing the bus, rather each IDE drive gets the full IDE channel to itself, so essentially where SCSI is a bus, the IDE RAID acts more like a switch. The other nice thing is that SCSI is notorious for being flaky sometimes, so you have to perform a little bit of SCSI voodoo. Getting the full 160MBps performance sometimes takes a bit of work, even with the LVD interfaces. IDE on the other hand doesn't require the expensive cables and is more reliable since each drive is on its own channel and the clock rate on each cable is slower. Someone could open the case and a cable could get cut, and only that one drive would go down. >Some reasons why scsi is more expensive, >They are giving you a longer warranty on average, more liability. >Scsi is harder to debug (the controllers), testing is a larger % of cost >in all hardware. (this is a hard fact, the testing adding a large % of >the cost that is). >The entire "it's cheaper since i dont' need a scsi controller" bit. >The controller on the drive itself probably costs a bit more due to >economies of scale. >You can argue researching for the fastest known drive at the time is >expensive too. > >And the ever popular "It's a conspiracy by the harddrive makers!" (ok.. I >do not vouch for this, as I strongly feel the former possibilities are the >harder reason why). Another big reason that you should add to the list is that SCSI is marketed as a high end premium product. Where IDE is aimed and and generally bought by OEMs moving drives at huge volumes, SCSI is a much higher margin, lower volume product, which is more likely to be sold through middlemen (i.e VARs who resell SUN relabeled SCSI drives, or maybe they're in an EMC, etc.). These middlemen really help to increase the cost of the drive. The cost of the controller itself is relatively cheap, adding only about $15/drive. >Finally, I am neither an IDE fan nor SCSI fan in all situations. They >have their places in different areas. For Dollar per Megabytes, you >really win with IDE. For performance, you might even say so >(economically). For the absolute best... SCSI wins out. As for the raid >situation, you'd need a dedicated channel for each IDE drive... good lord, >does that thing take up IRQs per channel? If so, cannot possibly scale to >match up to a good scsi raid. IDE RAID cards actually do all the heavy lifting themselves, and masquerade as SCSI controllers to the OS. So there's no IRQ problem there. The main difficult with IDE RAID is that most commodity boxes don't make it easy to get lots of IDE cables to drive bays from your PCI card. Especially with IDE's 18" limitation and fat cables, it's difficult to pull off correctly. There are cases out there that do make it easy, but you have to look around. You can also get ones specifically made for use with IDE RAID, but you can't just pop into your local Fry's to pick one up (yet!). Leonard -- Leonard Chung - <leonard@ssl.berkeley.edu> SETI@home - The Search for Extraterrestrial Intelligence @ home http://www.setiathome.ssl.berkeley.edu To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-stable" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?4.3.2.7.2.20001012171658.02704b28>