Re: Dumb question: Which is "better" SCSI or IDE disks?
kwrohrer@ce.mediaone.net
Sat, 5 Dec 1998 23:57:15 -0600 (EST)
And lo, Rik van Riel saith unto me:
> On Sat, 5 Dec 1998, Meelis Roos wrote:
> > RvR> When there are not too many processes accessing the disk at
> > RvR> the same time, IDE is cheaper and thus to be preferred.
> >
> > And swapping is a big disk-intensive task in addition to normal
> > tasks when you are short of memory...
>
> You can put swap space on IDE disks without performance loss,
> however. The trick is to make sure that the disk head doesn't
> have to go out of it's way. You can do this by only using the
> rest of the disk for streamed data (which is read in large
> chunks) and storage.
If swap access is as random as I think it is, a good SCSI disk should
be able to manage a fairly big win if it can reorder the accesses
taking rotational latency into account. Just because the next lowest
block number in the batch is on the current track, doesn't mean the
disk can't handle another request on a different track more quickly.
> This isn't as bad as it sounds since systems where MP3s take
> up more than 50% of all space are becoming more and more
> common each day :)
Actually, I think the people complaining about MP3s and the people
complaining about porn on the internet are both fronts for someone
who doesn't like hard disk manufacturers. :-) Maybe Iomega is trying
to keep 100 MB seeming big for as long as it can?
Keith
--
"Well, look at that. The sun's | Linux: http://www.linuxhq.com |"Zooty,
coming up." -- John Sheridan, | KDE: http://www.kde.org | zoot
"Sleeping in Light", Babylon 5 | Keith: kwrohrer@enteract.com | zoot!"
www.midwinter.com/lurk/lurker.html | http://www.enteract.com/~kwrohrer | --Rebo
-
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/