Messages in this thread | | | From | Oliver Xymoron <> | Subject | Re: Scheduled Transfer Protocol on Linux | Date | Sun, 13 Feb 2000 23:10:53 -0600 |
| |
On Sun, 13 Feb 2000, Larry McVoy wrote:
> : Again, I'm not talking about protocols. I'm addressing the argument that an > : STP-capable drive is somehow fundamentally different from a SCSI-capable > : one, since that's the argument that keeps being raised against this idea. > : I'm talking about the controller board, not the details of communication. > > OK, I think I get it. Your point is that SCSI is similar in complexity > to STP so the fact that SCSI exists says that drives with STP (and > perhaps Linux) are pretty much a done deal. Is that it? If so, excuse > my slow brain, it takes me a while sometimes. > > It's a good point, the only flaw is that SCSI drives are way more expensive > than IDE drives. The question is if that is inherent or just mark up...
Markup. At one point, just before the introduction of DMA IDE chipsets, the price differential was closing in on $30 or so - the ratio of people buying new SCSI drives to IDE was climbing rapidly and for a brief while it looked like the PC industry might actually end up going the SCSI route.
Now UDMA 66 drives have more than enough performance for just about anything you'd want to do on a typical PC and SCSI is relegated to the price inelastic server domain. The only thing that will change that dynamic in favor of SCSI or other new technology is changing peoples' expectations of what you can do with a desktop machine. That could mean everyone running Unix-like systems and wanting good I/O or it could mean things like hotplugging. I suspect that IDE will be marginally extended to make that happen rather than everyone jumping over to a completely different interface though.
-- "Love the dolphins," she advised him. "Write by W.A.S.T.E.."
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/
| |