begin quoting Gregory K. Ruiz-Ade as of Fri, Mar 17, 2006 at 07:53:31PM -0800: > On Mar 17, 2006, at 10:09 AM, Dexter Filmore wrote: > > >If affordable, I go for SCSI. > >sATA = consumer cruft. > > SATA is actually pretty good in terms of reliability. WD and > Seagate, I think, offer "server-class" SATA drives (which just means > they have a lower MTBF and cost more). Poking around at Wikipedia, I get the impression that SATA requires one controller per disk (but it's only seven wires, so adding another controller to the ASIC is fairly trivial), with no daisy-chaining.
Somewhere I found an assertion that SATA-II will support up to 15 devices per controller, but it also talked about SATA port replication. > Besides, with modern SATA drives, price/performance-wise, you can buy > much more capacity in hot-spares than you can with SCSI. How much CPU time does a SATA disk require? SCSI can do device-to-device transfers with comparatively little CPU involvement; that, plus the number of devices you could hang off of a controller, makes SCSI much more attractive to me than IDE/ATA/PATA. I'm not finding a lot of information about this so far tonight. > Six 300GB SATA drives (four in raid 5, two hot spare (is that raid6 > with a hot spare?)) will likely be significantly cheaper than the > amount for SCSI drives you'd need to get a 900GB array with two hot > spares. Are these for comparable hardware? Another one of the web-pages asserted that (Enterprise-class? Server-class?) SCSI drives have stronger arms and better motors and suchlike, to better handle server-class loads. That's the problem with the web... what can you believe? -- _ |\_ \| -- [email protected] http://www.kernel-panic.org/cgi-bin/mailman/listinfo/kplug-list
