[ILUG] Mandrake 10

[Rick Moen]

Quoting Paul Jakma (paul at clubi.ie):

> Not in SATA 1.0a, no, that intentionally specified physical layer
> only, simply carrying ATA and ATAPI commands. But SATA 1.1 (aka SATA
> II) adds command queueing, SAF-TE, signal recovery / hot-swap (device
> quiescence, comms state (stop/start/reset - whole state machine)),
> async notification, etc.

Don't forget additional ports to support up to 15 drives per host,
failover switches, external connectors, and doubling of the theoretical
bus bandwidth.  But the drives themselves seem, even then, likely to
remain underdesigned windup toys heavily reliant on write-back caching
to maintain even a semblance of reasonable performance -- which is
especially damning in environments with significant multitasking,
multithreading, or multiuser access.  Like, say, Unix.

See previously cited article.

Of course, when and if all of that starts getting fixed, I'll be glad to
take another look at the revised standard.  But we've been told _before_
"See!  We've just fixed all the problems of ATA and it's better than ice
water on a hot day, now."  And, lo!  It was not so, nor am I holding my
breath waiting now, either.

Now, I certainly don't mind ATA.  I'm typing this on a 1999 laptop with
a nice, quiet, small, low-power IBM ATA hard drive.  But that's just my
console, and this mail is actually coming from the SCSI-based VA Linux
2U in my living room, which does most of my real computing.

> The host controller interfaces tend to be far far nicer and more
> modern too, from what i gather from Jeff Garzik's posts.

Speaking of interfaces, I wonder how many of the excited early adopters
were aware that almost all so-called SATA drives for the first year were
literally the same old ATA/133 models with Marvell Technology Group
PATA-to-SATA bridge chips tacked on?

And oh, look!  Here's Jeff Garzik's latest update about libata support
for the wildly popular Silicon Image 3112/3114 SATA host adapter
(http://www.kerneltraffic.org/kernel-traffic/kt20040418_258.html#9):
"limit SII to UDMA5 (reading info on FreeBSD lists and source code
scared me about chip errata), mainly related to PATA->SATA bridges."

Yeah, that's quality.

-- 
Cheers,                 "Heedless of grammar, they all cried 'It's him!'"
Rick Moen                       -- R.H. Barham, _Misadventure at Margate_
rick at linuxmafia.com