On Mon, Dec 29, 2003 at 10:53:11AM -0800, Marc Wilson wrote: > On Mon, Dec 29, 2003 at 11:39:52AM -0500, Bijan Soleymani wrote: > > This is no longer true. Most current IDE controllers support various > > DMA schemes. Like ATA-100, ATA-133, etc. So with IDE the controller > > now bypasses the CPU too. > > DMA isn't the issue. Bandwidth is. As long as only one IDE device on a > chain can be performing a command at a given moment, SCSI will always win. This is true. I get around it by having my hard disks on their own channel. > Whether the *battle* is something you care about... that's for you to > decide. I was simply disputing the fact that the problem with IDE was that it used CPU while SCSI used the controller to do the work. I was just trying to show that current IDE controllers also do the work. Bijan -- Bijan Soleymani <bijan@psq.com> http://www.crasseux.com
Attachment:
signature.asc
Description: Digital signature