On Sun, 19 May 2002, Rick Moen wrote:
> Quoting Ian C. Sison ([EMAIL PROTECTED]):
>
> > First of all, please understand my replies in the context of my original
> > posting:
>
> Naturally.
>
> But I was responding to _one specific comment_ you made about UDMA 133.
Ok lets concentrate on that, if you must insist. \8)
> > The advantage of disconnected operation only comes in when you have more
> > than one scsi device in the chain. IDE RAID solves this problem by having
> > multiple IDE channels, with only one device connected to each channel.
>
> That is true, but irrelevant to your earlier statement, and to my
> critique of it. A point we will return to.
Ok
> > Also, By faster access i meant to compare to previous IDE technology,
> > which did not support RAID, and was contrained to dismal data transfer
> > rates on the wire.
>
> But that is precisely where your assertion was misleading: In previous
> IDE technology (such as the ATA/66 and ATA/100 bus-transfer specs),
> there was absolutely no way to ever saturate the bus, because only one
> drive on the chain could be active at a time, and no single hard drive
> of current or recent production can read data quickly enough to saturate
> those buses even under ideal conditions, let alone with any significant
> frequency. And of course the same is true of ATA/133 ("UDMA 133"), for
> the exact same reason.
>
> Thus, claims that ATA/133 (or predecessors) yields "faster access" are
> rubbish. Inherently.
Ok. Let's use some facts:
According to this URL:
http://www.oreilly.com/reference/dictionary/terms/E/Enhanced_IDE.htm
"old style" DMA/PIO access speed tops out at: 16.6 Mbytes/s
And according to the latest specs from Maxtor:
http://www.maxtor.com/Maxtorhome.htm [specs are in an embedded PDF]
A D740X can transfer data *To/From Media* at 54 MBytes/sec.
[Note the numbers are To/From Media, not To/From Interface]
Are you telling me now that the D740X model hard disk will not saturate
the IDE channel running at PIO/DMA speeds?
> > I get your point that SCSI allows you to aggregate the bandwidth
> > consumption on a single bus. I hope you get mine when i said the latest
> > ATA is "faster" then its previous incarnations, when the wire speed was
> > the limiting factor.
>
> No, that is rubbish. There isn't a hard drive that can put out even
> ideal-case disk reads that quickly. (I'm not counting reads from
> cache.)
Ok it's rubbish then. Maybe the manufacturers lie when they give out specs
of their hard disk capabilities. You think so?
> > Again, I'm merely pointing out (as in my original post) that IDE RAID
> > solutions approach the speed and reliability of SCSI based systems for a
> > fraction of the cost.
>
> Here, you are changing the subject. I was addressing the merits of your
> (quite wrong) assertion that UDMA 133 yields "faster access".
Actually i was maintaining the original premise by which i posted my
comments on SCSI vs IDE RAID. Since you want to nitpick on one point i
mentioned, then let's do just that.
> And I am declining to change the subject as long as efforts to obscure
> my point continue.
Ok so be it!
_
Philippine Linux Users Group. Web site and archives at http://plug.linux.org.ph
To leave: send "unsubscribe" in the body to [EMAIL PROTECTED]
To subscribe to the Linux Newbies' List: send "subscribe" in the body to
[EMAIL PROTECTED]
