Serial ATA Technology Explained

Mike Parsons writes "Explosive Labs has an interesting article on Serial ATA . Here is a quote: 'In the rapidly moving computer industry, there are rarely the kinds of revolutionary changes like what is about to take place in secondary storage segment. Soon the hard drives and configuration methods that have existed since the origins of the personal computer will change forever. The basic IDE technology has been around for nearly twenty years. When the lifetimes of other computer components like CPUs and video are measured in months, twenty years ago seems like prehistory.'"

Comments

Prehistory? Depends on context

[Hentai]

Think about this - how long has RS232 been defined? How long has the PC's parallel (i.e., LPT1) pin-out been defined? How long has the VGA pin-out been defined? How long has the PC keyboard pin-out and protocol been defined? A lot of things change pretty fast; a lot of things stay around forever. It all depends on whether upgrading them is worth the cost in the long run.

Re:Prehistory? Depends on context

[Thurn und Taxis]

For that matter, how long has the x86 architecture been defined? How many /. readers were even alive when the 8086 was released? I know I felt a few grey hairs pop out when a co-worker told me his first computer was a 286. Only superficial changes in computer architecture have happened during our lifetimes. The way we interact with computers is totally archaic, just like the way we interact with banks, cars, washing machines, and televisions is archaic. The world is dying for some clever person to come up with a way to make it just as easy to ask a machine to do something as it is to ask a person to do something.

Re:Prehistory? Depends on context

[sjbrown]

• RS232:
  Three modifications. Most recent in 1991
• Parallel port:
  Does anyone still use this? In the past 6 years, any printing I've done has either been off a network printer or at Kinko's
• VGA pin-out:
  Here comes DVI!
• keyboard pin-out:
  USB!

But yes, I acknowledge your point.

Re:Prehistory? Depends on context

[Anonymous Coward]

>For that matter, how long has the x86 architecture been defined?

Amazingly, I'm told it has roots in the 4004, the first processor ever. And not just history roots. Roots like "easy to port code".

Re:Prehistory? Depends on context

[dutky]

With one exception, none of the "standards" you mention are either very old or very standard. The exception is, of course, RS-232, which was defined in 1969 by the Electronic Industries Association of Washington D.C. (my home town). All of the others are relative infants:

• The PC parallel port was defined, in a very loose manner, by IBM when the IBM-PC was introduced in the early 1980s. The original PC parallel port was unidirectional and good for little else than driving a printer. While a number of manufacturers offered bi-directional versions of the PC parallel port (including IBM, in the late 1980s, with the IBM-PS/2) no actual standard existed until the release of IEEE-1284, in the mid-1990s, which gives us the modern ECP/EPP option.
• The VGA pin-out dates from the introduction of the IBM-PS/2 in 1988/1989.
• The PC keyboard pin-out and protocol have only been around since the introduction of the IBM-PC, and have undergone at least two revisions, first for the IBM-AT keyboard, and second for the IBM-PS/2.

The reference to IDE having been around for 20 years is a pretty dubious one, unless you count IDE as just a variation on the vernerable IBM-PC expansion bus. (commonly known as the ISA bus) Still, 20 years ago, there was no such thing as IDE, even as a glimmer of a hope in anyone's eye.

Re:Prehistory? Depends on context

[Call Me Black Cloud]

You're correct. Consider the length of time the original male-female coupling system has been around...

Re:Prehistory? Depends on context

[shepd]

>RS232:
>Three modifications. Most recent in 1991

Like what?

RS232 still seems to be the same as day one to me, other than changing the size/pinout of the connector. I suppose the chipset could support more features, but that's no difference in the specs of what goes down the wire.

>Here comes DVI!

And there it goes! At 165 Mhz, none-the-less! That used to be fast (in 1995).

>USB!

I hope you never have to access the BIOS.

Re:Prehistory? Depends on context

[chemmathguy]

I think that this "standard" will be around for a very long time...(andd I have no complaints about that =:p

Re:Prehistory? Depends on context

[Wesley Felter]

I don't have any of those ports on my computer; it's got USB and DVI instead.

Re:Prehistory? Depends on context

[Arandir]

My first computer was an 8086. And yes, I said 8086, and not 8088.

Re:Prehistory? Depends on context

[Toraz Chryx]

FYI, most modern bioses recognise USB keyboards and can be accessed from them.

Re:Prehistory? Depends on context

[shepd]

>FYI, most modern bioses recognise USB keyboards and can be accessed from them.

Oh, I know that.

I also know its an option I disable on all my boards, and an option that isn't always the default.

This means that if you only have a USB keyboard and buy/receive a motherboard with USB disabled by default, you just bought a heap of trash.

Re:Prehistory? Depends on context

[Anonymous Coward]

At least on the pcs I have used a USB keyboard (2 or 3 of them), even with the USB disabled, you can still access the BIOS with them

Re:Prehistory? Depends on context

[mehfu]

Well, there are other standards available, which aren't as functual when it comes to the result, but enthusiasts say that the procedure is just as good, or better.

Re:Prehistory? Depends on context

[BWJones]

Well, the Macintosh boxes and laptops I use have none of those protocols. I use USB, Firewire, and ADC protocols. However, the desktop machines do use SCSI hard drive protocols.

There are reasons that older standards have been supplanted for bandwidth, convenience (hot plug and play is sweet), and useability and I would certainly argue that upgrading from all of these older protocols is certainly worth it. With USB I get decent bandwidth for tasks that require it (synching PDA, downloading digital camera images, hot plug and play of trackball and keyboard use). With Firewire I get hot plug and play 80 GB backups in under an hour and a half and very fast transfer of larger image datasets. Oh, and very fast iPod synching). With ADC I get an uncluttered single cable going from my flat panel to my computer that carries power, pure digital video signal and USB.

Re:Prehistory? Depends on context

[horse]

Since buying a new keyboard costs $20-30 (U.S.), who cares? You can easily buy a new keyboard if you need one.

Re:Prehistory? Depends on context

[civilizedINTENSITY]

But did you ever see a 4004?

Re:Prehistory? Depends on context

[bobv-pillars-net]

Yeah, my Casio EC4004 calculator was based on a 4004.

Re:Prehistory? Depends on context

[sconeu]

The IDE I/O register mapping/interface dates to the ST-506 interface (early '80s), defined by Shugart Technologies.

The (16-bit) IDE physical interface is an extension of the AT bus (1984).

Re:Prehistory? Depends on context

[sconeu]

I was in college. I got my first 8086 manual (original Intel, onionskin) as a college text.

Re:Prehistory? Depends on context

[Anonymous Coward]

First off, the original PC was introduced 20 years ago... that's ages in computer land.

The reference to IDE having been around for 20 years is a pretty dubious one, unless you count IDE as just a variation on the vernerable IBM-PC expansion bus. (commonly known as the ISA bus) Still, 20 years ago, there was no such thing as IDE, even as a glimmer of a hope in anyone's eye.

Second, this is very wrong. IDE is a close sibling of MFM, which was one of the original PC hard drive interconnects, so the claim of 20 years isn't all that far fetched.

Re:Prehistory? Depends on context

[pyrrho]

mine was 6502.

I like the guy that says how the grey hairs pop out... ping. poing.

Hmmm. do people port linux to emulators?

Re:Prehistory? Depends on context

[Anonymous Coward]

Yeah, like it's ever done you any good.

Re:Prehistory? Depends on context

[Oggust]

The PC keyboard interface has seen three revs, the original one was for the IBM PC RT and it had a lot of cool features that they removed for the XT. (Along with a lot of other stuff. Both the PC and the POWER-based RS/6000 architecture stems from it. It used a short-lived (but pretty cool) RISC CPU of a family called ROMP, and it ran AIX 2.XX)

It had a different physical connector too, most connectors on the RT was in the same style, kind of like a ribbon cable connector, but with a housing that prevented you from connecting stuff upside down.

The physical interface for RS-232 has changed quite a lot, too. Back in the olden days (terminal nets), 15-pin D-subs were very common, and you NEVER see those today. People would think it was a game port I guess. But you can sometimes see that there's one of those push-out D-sub blanks on the back side of a PC box that is too big for a 9-pin and to small for a 23-pin connector. That's what that's for.

Of course, the RT had the flat, small (8-pin IIRC) connectors for that too. It was pretty handy, you could get a 4-port serial card that didn't need octopus cables or external connector boxes or anything.

/August, got rid of my last 6150 a little over a year ago, but still has a few IBM 9332/400 disks.

Re:Prehistory? Depends on context

[Jamie Craig]

That's nonsense, almost every BIOS in the world turns on USB keyboard support at least long enough for you to hit Delete or whatever to enable it. (and yes, the BIOS leaves the support on while you're actually changing the settings. :)
)

Re:Prehistory? Depends on context

[Ed Avis]

I think that although the PS/2 keyboard connector is a different size to the AT's, it is exactly the same interface (you can buy simple adaptors). OTOH, the AT and XT keyboards have the same plug but incompatible interfaces (which is annoying to those of us who have some of the lovely old XT keyboards but no machine to use them with). They are both some kind of serial port though. I wonder if it would be possible to hook up the keyboard to some kind of analogue sampler and decode the keypress messages in software.

Re:Prehistory? Depends on context

[SpaceJunkie]

Mine was a z80 - in fact the zx80..Although I had a periphery keyboard.Does any else here own an RML 380z? Or even a 480z? Better still does it work and do you have software for it?

Re:Prehistory? Depends on context

[TheBeck]

My keyboart was US $7.99 :)

Re:Prehistory? Depends on context

[greed]

23-pin D-sub? Amiga floppy and video; very unstandard size connector. Hacksaw and a D-25 was my usual solution....

Don't forget 15-pin D-subs are (OK, were) also used for Ethernet AUI connectors; also hardly ever seen these days. I would expect some cases built to support on-board networking to have these.

Those RT connectors carried over into the early RS/6000s, which meant every machine came with a "book" containing 1' long cables with the weird connector on one side and the standard connector on the other. (Plus the wrap plugs for self-diagnosis.)

Re:Prehistory? Depends on context

[Oggust]

23-pin D-sub? Amiga floppy and video;

Ah, yes, thinko...

Don't forget 15-pin D-subs are (OK, were) also used for Ethernet AUI connectors; also hardly ever seen these days. I would expect some cases built to support on-board networking to have these.

Yeah, but those always* came with the (weirdo) sliding thingy instead of screws, so you can tell those apart pretty easily. Also, those were only for reasonably high-end 10 Mb ethernet, for 100 they used (the even less common) MII interface.

Those RT connectors carried over into the early RS/6000s, which meant every machine came with a "book" containing 1' long cables with the weird connector on one side and the standard connector on the other. (Plus the wrap plugs for self-diagnosis.)

They were a bit longer than 1" for the RT, more like a foot, but yeah. I still have the RT manuals though - they are by far the best manuals for any computer I have ever had. I swear my mom could get an RT up and running using those, and that's saying something.

* Well, I have seen one really old ungermann-bass card (I think it was a UB card at least) that had screws, but pretty much always

/August.

Re:Prehistory? Depends on context

[bunicula]

But Serial and Parallel are gradually fading away (some PCs don't have them, others are calling them "legacy devices", macs don't use them).

DVI is becoming more common. USB keyboards and mice more common.

IDE really hasn't had much other than speed boosts.

Re:Prehistory? Depends on context

[MojoRilla]

The way you interact with televisions may be archaic. But I have a TiVO!

Re:Prehistory? Depends on context

[slipgun]

Mine was a z80 - in fact the zx80

If you've still got a ZX80, I believe they're quite valuable these days... in the order of 250ukp.

Re:Prehistory? Depends on context

[hpa]

The PS/2 bidirectional serial port was all but 100% standard ever since the early 1990s. ECP/EPP came before IEEE-1284 (which was the standardization of these options); they were already ubiquitous when the first SuperIO chips came out

Furthermore, the electrical interface of the parallel port was defined by Centronics some time in the mid-1970s, and significantly predates the IBM PC -- IBM used it because it (and RS 232) exactly because it was *already* a standard!

Note also that on the original IBM PC all of these came on separate boards that you had to buy extra. Noone bought an "IBM Personal Computer Asynchronous Communication Adapter" (serial port) unless they had a modem to plug into, and noone bought a parallel port unless they had a printer.

Re:Prehistory? Depends on context

[shepd]

>Since buying a new keyboard costs $20-30 (U.S.), who cares?

Yeah, but why not just use a PS/2 keyboard to start with?

USB keyboards add nothing but trouble.

Re:Prehistory? Depends on context

[Anonymous Coward]

"I don't have any of those ports on my computer"

And what kind of computer is that?

Unless you're using something really shady & obscure, I'm pretty certain you have at least a keyboard port. I've never seen a motherboard without one.

Doesn't mean you're using it of course, but you still have it

Re:Prehistory? Depends on context

[shepd]

>That's nonsense, almost every BIOS in the world turns on USB keyboard support at least long enough for you to hit Delete or whatever to enable it.

Integrated Peripherals->USB Keyboard support->Disabled.

You just haven't fixed enough comptuer yet to come across a crappy one that has this set as default.

Re:Prehistory? Depends on context

[ka9dgx]

Let's see...
Commodore PET - 6502
Cosmac ELF - 1802
Heathkit Trainer - 6800
Radio Shack CoCo II - 6809 (OS-9 Rules!)
Custom built project - 8088 and glue logic
First computer repair - PDP11/34 with bad RAM
Got into it just after they phased out punch cards.

I have many friends who were there before CP/M, Xmodem, etc.

--Mike--

Re:Prehistory? Depends on context

[StillaCoward]

I think the idea was that USB would replace PS/2 (IE no more PS/2 connectors). In which case you can go out and purchase all the PS/2 keyboards you like, but in preschool they taught me the circle does not go in the rectangle....

Re:Prehistory? Depends on context

[Anonymous Coward]

What the fuck are you talking about you dammed homo hippie?

Re:Prehistory? Depends on context

[StillaCoward]

I don't know what standard hardware a MAC has, but maybe he has one of those....

Re:Prehistory? Depends on context

[Wesley Felter]

We have a winner. Macs use USB for keyboards and mice.

Re:Prehistory? Depends on context

[japhmi]

My family had an Osbourne 1s, which we later stoped using when we got a brand new IBM PC (8088, dual floppies, yeah baby!)

Re:Prehistory? Depends on context

[mehfu]

Hah! Did that upset you? I feel sorry for you ;)

Re:Prehistory? Depends on context

[Hans Lehmann]

First computer I actually laid my hands on? A DEC PDP-8, precursor to the more famous PDP-11. The PDP-8 was a 12-bit machine (forget hexadecimal, we're talking octal here.) After powering it up you had to hand enter your code using a row of 12 toggle switches on the front panel, entering one word at a time. The current memory contents were read out with a corresponding row of 12 light bulbs, any 1 or 2 of which were burnt out at any given time (LEDs?, not invented yet.) Had to keep the lab windows open, even in the winter time, to keep the beast from crashing.

First Computer I actually owned? A 1MHz 8080, wire-wrapped by hand on an S100 board in my last year of college (Z80's were stilly pretty pricey at that time.) 1Kbyte EPROM, just barely enough to hold a simple monitor program to be able to connect to the remote terminal. 1Kbyte RAM, using 8 2102 static RAM chips (1000 *bits* each). Your entire application had to fit into that 1Kbyte space. The "remote terminal" was a ASR33 teletype (no electronics, entirely mechanical), running at 110 baud through a current loop interface (RS-232 was just too new-fangled.) Later we started doing code development with a real Intel in-circuit emulator that had an actual CRT terminal and a 8-inch floppy drive to store your code.

My first PC wasn't until 1986. An 8MHz 8086, complete with a 20MByte hard drive, 25x80 character VGA display, and an Epson 9-pin dot matrix printer. I think I was running DOS 3.0 at the time, spending most of my time playing Infocom games.

I also had to walk to school through the snow, up hill both ways.

Re:Prehistory? Depends on context

[some guy I know]

The PC parallel port was defined, in a very loose manner, by IBM when the IBM-PC was introduced in the early 1980s. The original PC parallel port was unidirectional and good for little else than driving a printer.

Actually, the parallel port was defined by Centronics before 1980.
(I remember using a Centronics D.M. printer with this interface around 1974 or so, connected to a PDP-11.)
The connector was different, using a 36-pin plug with flat blades.
I think that IBM introduced the D-15 connector, but I'm not certain.
I still have two printers that use the 36-pin connector.
The cable has a D-15 connector on one end, and a 36-pin Centronics connector on the other.

The advantage of the parallel port is that you can directly drive TTL logic, without having to build any interface circuitry.
You can also drive a printer directly from TTL.
(I did this on my KIM-II (6502 with 2K ROM, 1K RAM, and several TTL outputs).)

It is also possible to use the parallel port as an input device, by "misusing" the paper-out and fault lines, although this is slow.

Re:Prehistory? Depends on context

[Anonymous Coward]

Sorry, D-25.

Re:Prehistory? Depends on context

[SpaceJunkie]

I knew that- but sadly I didnt when I opened it up, modded it, and when I finished with it used the z80 chip somewhere else.... Oh well...
If I had left the RML 380z unmodded it would be worth something as well... Sad really... I cant leave a machines innards alone...

Re:Prehistory? Depends on context

[Eil]

I agree to a certain extent. But follow me for a moment. Remember that just because something is old doesn't mean it's obsolete. The idea of using a machine or system to carry out lots and lots of trivial calculations in a short period of time goes back longer than most of us can trace our family tree. Yet today that idea is more important and ultimately more useful than it has ever been and things are only going to improve.

If we improve upon the technology and methods that exist today, there's simply nowhere to go but up. If we just scrap what we have and try to think up something better everytime a piece of technology seems old-school, we waste a lot of time sitting around and thinking.

Only superficial changes in computer architecture have happened during our lifetimes.

The first microprocessor had 2000 transistors. The Pentium 4 has 55 million. Modern processors also have features like optimizing cache logic, special-purpose instructions, and mechanisms to accelerate throughput. I'd call that more than a superficial change. Of course, the concepts of accumulators, registers, instructions, interrupts, stacks, and etc have been around for a long time, but like I mentioned above, that doesn't make them obsolete. If you took them out of the machine, you no longer have what anyone could call a microprocessor.

The way we interact with computers is totally archaic, just like the way we interact with banks, cars, washing machines, and televisions is archaic.

Er, they seem to work well enough for billions of people. My keyboard and mouse, for instance. I'm sure there are quicker ways to enter data and I'm sure there are more accurate ways. But not both. The keyboard and mouse are the best balance of speed and accuracy we have. Technology has not advanced enough to give us an increase in both, but I am confident that it will someday.

The world is dying for some clever person to come up with a way to make it just as easy to ask a machine to do something as it is to ask a person to do something.

I don't think I can speak for the rest of the world, but I personally agree. I hope to own, within my lifetime, a house with a computer that you can literally talk to and have it respond and perform actions based on your requests. It would be quite similar to ship-wide computers on Star Trek where you could tell it to adjust the room temperature, dim the lights, put on some Beethoven, give you the proper spelling for a word, list hibachi dealers in the area, record Enterprise at 9 o'clock on Friday, quiz my daughter on fractions, and compile a brief history of the Intel 4004 microprocessor from available sources.

Today's computers are capable of all of these functions (with the exception of the last one), just one key element is missing: artificial intelligence. Yes, computers can recognize speech, but the accuracy is horrible and they lack any way to figure out what you actually mean and neither can they recognize when you're talking to them or when you're talking to yourself or someone else.

However, it's not as simple as just waiting for some genius to come along and bestow AI upon the world. People used to believe that computers would never be able to spot patterns in a suitably complex set of data, but now we have a number of algorithms that do a sufficient job. It's going to be a constant evolution, but I'm confident that we'll get there. We probably won't ever see a "sentient" computer, (which is what most people think of when they think of AI) but someday we'll all be rambling off instructions and requests to our computers.

And then someone will make the comment on Slashdot that speech interfaces are archaic.

Re:Prehistory? Depends on context

[tgrigsby]

Wait... you can couple with them?

SCSI?

[GreyWolf3000]

Soon the hard drives and configuration methods that have existed since the origins of the personal computer will change forever.

All of IDE's shortcomings are fixed by SCSI (except for a small degree of added complexity). SCSI hardware is more expensive, and rarely does it come built-in to motherboards.

If more people used it, it would be a cheaper solution, and would fix all of IDE's problems without re-inventing the wheel--it's a solution that, right now, works.

15k rpm scsi drives get seek times in the low three range--that's three times faster than your average 5400 rpm ide hdd.

Re:SCSI?

[stratjakt]

> All of IDE's shortcomings are fixed by SCSI

You mean the oversized 40-conductor ribbon cables are solved by 68 conductor ones?

> If more people used it, it would be a cheaper solution

Heh, sure it would.

> 15k rpm scsi drives get seek times in the low three range--that's three times faster than your average 5400 rpm ide hdd.

And 10x more expensive.

You are the first SCSI fanboy I've ever seen.

Now bring on the cheap!

Re:SCSI?

[pretoris]

Um, Mac's havn't shipped with SCSI standard for quite some time now, and since when did a server using SCSI become "obscure"?

Re:SCSI?

[jandrese]

SCSI is largely expensive because it is sold to the server market. It would not be impossible to make a SCSI drive only a few dollars more than the comparable ATA drive, but why bother when you can sell it for twice the price of the comperable ATA drives. SCSI drives will stay expensive until people are no longer willing to pay the huge markup for them.

Re:SCSI?

[shepd]

>You mean the oversized 40-conductor ribbon cables are solved by 68 conductor ones?

Nope, they're solved by using high-density cable connectors, which IDE still hasn't figured out with 80-pin cables (instead IDE just cheats).

>And 10x more expensive.

Because... why?

Nobody is buying, that's why. Lower speed SCSI drives are still available, but are still expensive because IDE is stuck in everyone's heads as the only storage method for a PC.

>You are the first SCSI fanboy I've ever seen.

You haven't been here very long. Let me be the first to say welcome! :-)

Re:SCSI?

[Stigmata669]

"All of IDE's shortcomings are fixed by SCSI (except for a small degree of added complexity)."

Yeah, even if your statement were true. Price is a huge shortcoming in technology today, especialy when most people can't use the preformance hardware that they own.

I strongly support the development of IDE standards. There are many situations when you need lots of hard drive space without bleeding edge preformance. Try to find a solution for doing a small (350GB) backup server to add to a tape backup system, you find 200GB IDE drives for the price of a 18GB SCSI drive. A thousand people will try and explain why the SCSI is a better deal because its more reliable and faster, but backing up 350 gb on IDE costs about $650, and on SCSI costs aboyt $4000. I don't believe the demand is the reason for the premium price for SCSI, but the hardware... It's just more expencive to make.

Re:SCSI?

[puppetman]

Lots of motherboards come with SCSI. Most Intel server boards do, as do boards from SuperMicro (P3TDE6-G, S370DL3, P3TDDR), Tyan (S2721, S2720), etc, etc. I've been looking into them for server upgrades (I just don't have time to track down a few dozen model numbers).

SCSI does have a faster spin time, and is in general much faster, but for small, random chunks of data, it can be slower (but it's a small penalty in a rare case). The width of the SCSI bus is much better (320 MB/s for SCSI 320), assuming you have alot of drives in big striped arrays.

Don't forget - most IDE drives (except for a few premium models) just had their warranty chopped from 3-years to 1-year. Not a reflection on declining quality of IDE drives, but rather the economics of the market place. SCSI still has decent warranties, and they last longer regardless.

SCSI is (much) better; could they be as cheap as IDE if everyone used them? Probably pretty close. But it's a chicken and an egg thing. Home-users don't buy them because they are expensive, and they are expensive because consumers won't buy them.

Ironically, SCSI stands for Small Computer Standard Interface, but SCSI is most frequently found in Servers (large, not small computers), in large RAID arrays. And more ironically, the SCSI drives usually used in RAID (Redundant Array of Inexpensive Disks) usually are not that inexpensive at 3x the cost of IDE.

Re:SCSI?

[Enry]

> You mean the oversized 40-conductor ribbon cables are solved by 68 conductor ones?

No, I'd guess the 80 pin ones that include power and configure the drive's ID, and allow you to just slap the drive in and let it go. IDE has NOTHING with that configurability.

> You are the first SCSI fanboy I've ever seen.

Now you've seen two.

Don't get me wrong - for home use, SCSI is overpowered. But if you're talking anything bigger than a desktop, make mine SCSI.

Re:SCSI?

[km790816]

Read the article.

The problem with SCSI is heat and noise, things that work fine in a server room, but are bad for the home user.

I had SCSI for a while in college. It was cool to show off, but having to turn up my TV to hear over the jet engine in my PC was annoying.

Re:SCSI?

[Stigmata669]

>Nobody is buying, that's why. Lower speed SCSI drives are still available, but are still expensive because IDE is stuck in everyone's heads as the only storage method for a PC.

I have to say that all of my computers up until my most recent have been SCSI, and I am glad that I stuck to IDE this time.

Firstly the price to preformance ratio is dismal. Twice the preformance for 10x the price is not worth it.

I would like to say that the price of SCSI drives is not 10x more because nobody wants a SCSI drive, but because they are simply more complicated to manufacture and interface. Attributing cost comparison between two different technologies solely to suply and demand is a very very basic understanding of the way the economy works.

Also, the preformance hit you take going from 7200rpm SCSI to 7200rpm IDE is not noticable at most times, but I suppose i am tolerant because i can wait more than 3 ms seek.

SCSI is loud and hot and expencive, just like all preformance computing componants, and thus will never be a consumer standard.

Re:SCSI?

[stratjakt]

Well, yeah, SCSI will always have a place in high end workstations and servers.

But my new desktop (as I've already posted) has an onboard SATA RAID controller.

Personally I cant wait to get some workstation-level performance at desktop-level prices.

And no more big ugly cables uglying up my side window. These little cables that came in the mobo box are going to look pretty good in there.

It's an improvement over PATA no matter how you slice it. It promises to be cheaper, faster, easier, hot-swappable, self-powered.

I dunno why people are complaining. Well, yes I do. This is slashdot, and any new technology is equated with a bid for world dominance from [CORPORATION].

Re:SCSI?

[megaduck]

Actually, even Macs don't use SCSI anymore. SCSI is strictly a "build-to-order" option on their PowerMac line. Even their Xserve server and storage products use multiple IDE channels instead of a SCSI bus.
</nitpicking>

You're right, though. SCSI only really survives in servers because it's just too darn expensive for everything else. Shame.

Re:SCSI?

[Sneftel]

Err... since when did a communications bus generatte any appreciable noise or sound? Nothing distinguishes the dynamics of hard drive operation between IDE and SCSI. SCSI hard drives tend to be faster, since people who buy them tend to want to attach them to servers, but if pushed into the home consumer arena you'd see SCSI drives with exactly the same noise/heat output as IDE drives. This is an example of market-driven, not technology-driven.

Re:SCSI?

[larry bagina]

15k rpm scsi drives get seek times in the low three range--that's three times faster than your average 5400 rpm ide hdd

Wow. 15k = 3 x 5k. Thanks for the math lesson.

Re:SCSI?

[shepd]

>I would like to say that the price of SCSI drives is not 10x more because nobody wants a SCSI drive, but because they are simply more complicated to manufacture and interface.

That was true in 1980. It isn't now. I mean, it costs no more to build a RAID card (witness Promise Ultra Hack) than it does to build an IDE card, and that's massively more complicated than SCSI.

In fact, since all the smarts are moved onto the controller (which is dead simple to make today -- I bought a cheap one for $35 CDN two years ago -- it was cheaper than a cheap IDE card!) the drive itself is less complicated.

>Also, the preformance hit you take going from 7200rpm SCSI to 7200rpm IDE is not noticable at most times, but I suppose i am tolerant because i can wait more than 3 ms seek.

Agreed, but there's more to it than that. IDE requires new interfaces every drive (unless you want to take the horrible performance hit master/slave arrangements incurr). SCSI doesn't. IDE cables can only be 18". SCSI can be quite a bit longer. IDE only works for hard drives and CD-ROMS (and one or two other things). SCSI is for anything. There's more reasons than this to support SCSI over IDE (at the same price), but I think these three would be enough to sway users at the right price.

>SCSI is loud and hot and expencive, just like all preformance computing componants, and thus will never be a consumer standard.

Only because no manufacturer thinks there's a good market if they slap a SCSI controller on their current consumer hard drives. I think there is, and I'd be game to buy one, if they existed, for my next upgrade.

Re:SCSI?

[GreyWolf3000]

Yeah, even if your statement were true. Price is a huge shortcoming in technology today, especialy when most people can't use the preformance hardware that they own.

Here's why your point is moot: First, IDE drives are only cheaper because it's more widely used. Secondly, SCSI can scale to low end needs--you're not locked into having to be fast. What has happened is that SCSI has found its nitch in the server market. SCSI could downscale very well

I don't believe the demand is the reason for the premium price for SCSI, but the hardware... It's just more expencive to make.

That's only true because SCSI hard drive makers have to make fast server-oriented drives. If they had a desktop nitch, they could sell slower drives for similar prices--as it stands they couldn't compete.

SCSI can serve both low-end and high-end needs, if folks would give it a chance. The article's mentioning of SCSI being too loud is ridiculous--internally they all work the same. 15k rpm hard drives by nature make a lot of noise.

Re:SCSI?

[GreyWolf3000]

SCSI could scale down to fit desktop needs, but it wouldn't since IDE has such a high market share, it would start out more expensive. SCSI is expandable and scaleable (in both directions).

Re:SCSI?

[Anonymous Coward]

Rpm and seek time don't always correlate.

Thanks for the idiot post.

Re:SCSI?

[G-funk]

it's got nothing to do with how common it is, scsi is expensive because it raises the percieved value of the product, and it's common knowledge that this "elite"ness of more expensive alternatives to a product aid sales.

In short, it's expensive because they like it that way. There's no shortage of scsi drives, they're not particularly more expensive to produce.

Re:SCSI?

[mindstrm]

Scsi drive price has nothing to do with the fact that it's scsi, technically.

It's only because of the market segment that's interested in it.

The only reason ide drives aren't built to the same standards as scsi drives is the market isn't interested in it.

For the same reason, that relatively cheap unreliable scsi drives are not made.. because nobody is interested in them.

Re:SCSI?

[PotatoHead]

Now you have seen three!

Scsi is fast and reliable. Notice that the price premium gives you a warranty these days where IDE does not. (Cheap has to come from somewhere, looks like it will be the IDE drives :)

SCSI devices last forever, or until they break, which is a long time. Move them from machine to machine, OS to OS as much as you want. They are almost all cross-platform and compatable. Just can't say that for IDE in general.

SCSI is really pretty easy. Where IDE can be a mess sometimes. Want to share a CD-ROM and DISK on same controller, want speed also? Not likely to happen unless you have a higher end IDE controller, but if you are going to go to this trouble, why not just get a SCSI one and be done with it?

Your 10X more expensive is packing a lot less punch these days and it's not true anymore. If you want the very high end SCSI devices you will pay a premium, but choose one notch down and the prices are fair. 3-5x maybe, not 10x but that does include nicely supported devices.

Most of the hard work has been done for SCSI, this new standard will cost all of us who depend on IDE. I would much rather keep my investment in SCSI hardware rolling rather than start paying again for another standard that is supposed to fix the broken IDE standard I have to live with now.

So, I may just do that. You see with SCSI, I have that choice, have always had it. Given a longer term useful life, it is fair to say that SCSI has saved me money! IDE? Not!

Re:SCSI?

[GooberToo]

Someone mod this guy up. He, "gets it!" SCSI is expensive because it's the premium, top-shelf product. Period. SCSI is expensive for the same reason that diamonds are. Both are highly desired but have no more value than the next drive (be it IDE or rock).

In other words, they are expensive because people want to keep them that way!

Re:SCSI?

[dan the person]

"Ironically, SCSI stands for Small Computer Standard Interface, but SCSI is most frequently found in Servers (large, not small computers), in large RAID arrays. And more ironically, the SCSI drives usually used in RAID (Redundant Array of Inexpensive Disks) usually are not that inexpensive at 3x the cost of IDE. "

You have to look at when these terms where invented.

The following definitions applied back then:
Small Computer = a computer that did not require an entire building to house it.
Inexpensive = cheaper than solid state.

Re:SCSI?

[Thaelon]

It depends on the drive.

For example the Quantum Atlas 10k's were NOISY, they sound like a ratchet being wielded by an overzealous mechanic.

The 10k II's were considerably better.

Last but not least the 10K III's....I've got (4) four of them operating in a RAID 0 array and combined they're considerably quieter than my 7200RPM IDE drive. Virtually silent in fact.

Re:SCSI?

[fava]

I quote:
SCSI devices last forever, or until they break,

I can top that:
I will live forever, until I die.

What was your point again?

Re:SCSI?

[Anonymous Coward]

You are the first SCSI fanboy I've ever seen.

Go hang out on messageboards with lots of older mac users on them. You'll see lots. Why? Because apple used to use nothing but SCSI, and now they use nothing but IDE (unless you get the special-ordered version, which no one realizes you can), and for various mac-user-y reasons (including speed.. mac users get kind of miserly about what speed boosts they get..) pretty much everyone liked it better when they used SCSI.

Of course, they'll all be even more fanboyish about firewire, but that is neither here nor there.

Re:SCSI?

[egarland]

> All of IDE's shortcomings are fixed by SCSI.

Heh. Here's a list of IDE's shortcomings SCSI makes worse:

• cable size
  
• interoperability issues caused by multiple drives per cable
  
• bandwidth per drive
  
• cost of the controllers
  
• cost of the cables
  
• cost of the drives
  
• Low reliability caused by multiple devices physically attached to the same cable that can bring parts of the bus or the whole bus down
  

The bandwidth per drive thing is one of the great things that SATA brings to the table. With a modern large SCSI setup it seems like you have a lot of bandwidth but on a per drive basis you really don't. 160MB/s divided by 12 drives = 13MB/s (1980's speed). To contrast that look at a 12 drive 3Ware SATA controller. That has a full 150 MBytes/Sec to each of the 12 drives.

To see the usefulness of this take the example of a 12 drive RAID 5 array doing a rebuild while the server is trying to read from the drives. The controller has at it's disposal 1800 MB/s worth of bandwidth that it can use. It can run those drives as fast as they can go keeping the write buffer full on the drive it's rebuilding and using the leftover bandwidth to service the server's requests. Modern ATA drives can read at up to 56 MB/s. With 12 drives you get a total of 672 MB/s throughput which is far more than even the new Ultra320 SCSI is capable of. With newer faster drives and 16 drive RAID controllers this problem gets even worse.

> If more people used it, it would be a cheaper solution

SCSI is quite widely used. There is a lot more SCSI out there than SATA and yet a motherboard with a SATA raid controller costs about the same as one without it whereas a motherboard with a SCSI raid controller on it costs about 3 times as much. SCSI is simply an expensive, complicated technology to implement.

>15k rpm scsi drives get seek times in the low three range--that's three times faster than your average 5400 rpm ide hdd.

The low seek times are a result of expensive server class drive technology, not of the interface. Seagate could just as easily drop a SATA interface on those 15K Cheetah drives and I suspect in the near future they will because:

All of SCSI's shortcomings are fixed by Serial ATA

Yea, I know, it's a cheap shot but really SATA is poised to replace SCSI in most of the markets SCSI still occupies. SCSI was mostly popular in server systems because of it's hot swapablility and plug and play operation (no jumpers to set on 80 pin sca drives.) These are advantages that Serial ATA shares. Motherboard integrated SATA RAID will take over for SCSI RAID in server class systems because of cost, size, power and bandwidth issues. 8 - 16 drive SATA RAID arrays will take over the low to mid-size storage array market. (If you can count 4.8 Terabytes as mid size.) Fiber channel will be left for SANs and large storage arrays. SCSI will be relegated to connecting external drive systems but I imagine fiber channel will eventually take most of that market.

People who like SCSI will probably like SATA even more. It will be faster, much cheaper, more reliable, more compatible, and easier to maintain and troubleshoot. True, you won't be able to run a printer or scanner off it but I doubt there will be a lot of people missing that particular piece of SCSI functionality.

Re:SCSI?

[emmons]

I don't believe the demand is the reason for the premium price for SCSI, but the hardware... It's just more expencive to make.

Actually, many companies make identical ide and scsi versions of the same hard drive- identical except the controller. The only thing that makes the scsi controller on the drive more expensive than its ide counterpart is that *far* frewer are made, which drives up production costs and ultimatly the cost of the drive it's put onto. If the volume of scsi hardware reached that of ide, it would be just as cheap to produce and sell.

Re:SCSI?

[Shwag]

It is called Market Segmentation, and another example is when products first hit the market, there is always that group of people who are willing to pay top prices because something is new ... despite that it will cost way less in just a couple of weeks.

Re:SCSI?

[Anonymous Coward]

...but why bother when you can sell it for twice the price of the comperable ATA drives.

Twice!??! Holy shit, where you getting your drives from?!?! Come on! There's money to be made here! If SCSI cost ony 2x of ATA drives, I'd been all over it ages ago.

Re:SCSI?

[Anonymous Coward]

For the love of god, man, it's performance. Performance. Preformance is like, they haven't made it yet.

Re:SCSI?

[Have Blue]

That's not counting the FC RAID add-on unit that should be released Real Soon Now(tm).

Re:SCSI?

[gad_zuki!]

> SCSI is expensive for the same reason that diamonds are.

Not at all. Diamonds are a controlled cartel and price-fixing is par for the course. SCSI in mass production anywhere near how much IDE stuff gets made will drop the price to the point where it would be affordable to sell it to the home market. Or so the theory goes.

If diamonds weren't price-controled they would be incredibly cheap. Read about it here: http://www.professionaljeweler.com/archives/news/2 000/020300story.html

Re:SCSI?

[PotatoHead]

You know there is *always* someone....

Well, if you take the rest of the sentence, which you left out, in context with the rest of what was written, it is not much of a stretch to understand that SCSI devices last longer in general than IDE ones.

This general idea expressed in the first paragraph nicely ties in with the part you left out; namely, ", which is a long time." Maybe that has just a little to do with why exactly you left it out, or could it be that you just knee jerked a smart ass response?

If you consider the entire first sentence, then you will come to realize that it sort of hangs at the end. You might wonder how long of a time after reading it? Well how long? Compared to what? Why so?

All three questions are answered in the first paragraph. Compared to what refers to IDE devices in a negative way. (Intended!)

Why so is answered by a little critical thought surrounding the warranty part of that paragraph combined with the cheap part of it. Why would one cut the term of their warranty? Could product failure costs have anything to do with it? Maybe, but if that fails then cheap is there to back things up. Taking the cost out of things often means cutting a few corners. Well IDE drives are cheap right? Must have cut a few corners. Maybe those that affect lifespan?

Given this, how long is pretty easy. Longer than IDE devices in general.

There you go.

If that does not do it for you, then know it's late, and I'm done with this.

Re:SCSI?

[adolf]

There is a certain elegance to such things as SCA backplanes which ATA (in any incarnation) will never achieve.

Which is another point:

They botched SATA by not including power on the bus, having no standardized connector locations, and (at least so far) having no facility for connection of external devices.

The 1-device-per-wire rule of SATA is another detriment: Sure, the cables are fairly small, but can you imagine the rats nest that would be a 12-device SATA system?

SCSI daisychaining is an easy fix for that, and now-common LVD SCSI is quite able to support this number of devices with a single ribbon. And LVD, by its differential nature, is quite resistant to the electrical problems introduced by slice-and-jacket cable rounding techniques that are all the rage these days..

Oh. And you've got your math wrong, Son:

It doesn't matter if 3ware makes a controller with 12 150MBps ports. The 12-port Escalade 8500 you speak of has a 64-bit 33MHz PCI interface, topping out at no more than a paltry 264MBps to be shared by all connected devices.

If you're serious about throughput, try something like this: Two 320MBps channels on a 64-bit, 133MHz PCI bus. Good for real-world transfer rates in the realm of 640MBps, more than twice that of the 3ware product, while keeping a good portion of the PCI bus free the -other- 30 SCSI devices you've got plugged into it.

And none of this says anything about the benefit of SCSI for the home user:

Just bought a new DVD-R, but don't want to toss your old but dead-solid Plextor? SATA requires you to buy another port. SCSI just requires you to plug it in.

Re:SCSI?

[Anonymous Coward]

"the preformance hit you take going from 7200rpm SCSI to 7200rpm IDE is not noticable at most times"

Is this your best argument? The perfomance hit you take going from the slowest SCSI drive available (7200 rpm) to fthe fastest IDE drive available (7200 rpm) is not noticable at most times...

Re:SCSI?

[AlecC]

The cost difference between a Scsi interface and a Parallell ATA interface is negligible. At the worst it was only ever about $10, ten years ago, and now it is probably about $0.01. Manufacturers just use the Scsi interface as a way of separating "professional" grade drives from "consumer" grade drives. Scsi drives go up to 15,000 rpm, seek times of 4.5msec, five year warranty. IDE drives go to 7200rpm, 9 msec seek times, one year warranty. Scsi is not intended to be a consumer standard, it is intended to be a "hot rod".

On a single user computer, you will be unusual if you need the performance of a scsi disk. You may like the reliability (but there is always IDE based raid). For a central server, however, the scsi difference matters.

Re:SCSI?

[Sneftel]

Erm... heehee... noise or heat that is.

Friends don't let friends post drunk!

Re:SCSI?

[Lumpy]

Ok I know you were trying to be funny... but here you go...

I am a HUGE scsi fanboy... My Dual processor lowly P-III866 still smokes the pants off of anything you can buy in the stores just because I have Ultra 160 SCSI drives in a raid 5 arrangement.. my linux and W2K boot times on this box make even a 2.4Ghz P4 machine look like a downright dog. why? because the hard drive is STILL the major bottleneck in a PC.. I do tons of video editing here so I need this mad-insane hdd access speed. (It also helps to have a fast-as-hell older machine at the lanparty's to knock the show-off's down a step... I really do love that! no winstone crap.... let's time out boot, ok let's time the start of UT2K3, ok why does UT2k3 look smoother on my machine? I only have a geforce2... hmmmm.. your' computer sucks if it cant outperform a P-III..... that is a blast!)

Cheap is good for low performance... and it has it's place.. SCSI is for those of us looking for reliability and speed... I will use NOTHING but scsi in servers, anything else is asking for trouble. and I only use SCSI for my perfoemance items... because I demand it.

Re:SCSI?

[Jedi Alec]

Scsi is clearly superior. Can you imagine doing This with IDE?

Re:SCSI?

[hatchet]

Much nicer with SATA.

Re:SCSI?

[MrFredBloggs]

Part of the article says are the HD is the main bottleneck on a fast pc, then later it says:

Serial ATA will be introduced at a bandwidth of 150MB/s. This is a seemingly disappointing 13% improvement over Ultra/ATA 133. However, today's hard drives rarely ever use that much bandwidth, so 150MB/s is more than enough.

If that's true, why is a HD a bottleneck?

Re:SCSI?

[Anonymous Coward]

Serial ATA can have 1m (~3 feet) cable...

Both SCSI & ATA have smarts in the drives.

Haven't seen a whole lot of inexpensive SCSI network, processor, printers nor scanner.

On the other hand, the Compact Flash is a scaled down PCMCIA that is essentially an ATA bus.
There are all kinds of things for that.

Re:SCSI?

[Spoing]

If more people used [SCSI devices], [SCSI] would be a cheaper solution, and would fix all of IDE's problems without re-inventing the wheel--it's a solution that, right now, works.

All my systems are SCSI-based, usually with one or two IDE devices added as adjuncts. While it is true that many of IDE's failings could be solved by using SCSI instead, the focus of each interface is entirely different. Both SCSI and IDE are valuable on thier own merits;

1. SCSI: A complex protocol to control propriatory and diverse devices transfered on standardized cables and handled by propriatory controllers. Hardware control of the device is handled by the protocol layer that is supported by a propriatory hardware and software layer plus the electronics on the device. These added layers are required because SCSI devices are so diverse and the controller-to-system interface is not standardized. SCSI devices can be any type of data storage unit (from simple hard drives to chained optical juke boxes), all types of scanners, network interfaces, and other standard and custom devices. The SCSI protocol allows extentions on a per-device basis. SCSI controlers require a chipset-specific software layer to link them to the rest of the system.

   IDE: A single physical and protocol interface located primarily on the drive itself. IDE was designed to be a cheap and simple extention of x86 chipsets for specific data storage devices; hard drives. CD, DVD, and enhancements to the IDE chipsets were added later. Because the drive electronics masks the true nature of the drive attached, and the system-side IDE support is generic, no chipset-specific drivers are required. (Yes, some IDE chipsets are garbage and require special support to prevent data loss. Most of these defects occured because the testing done was limited to "does it work with Windows 3.x/9x?" and things like DMA were largely ignored. Oops!)

All things considered SCSI would probably be cheaper now if it were used as the standard interface on x86 systems back before IDE, though it's impossible that it could underprice IDE just because of the propriatory nature of the hardware-heavy controller chipsets -- each flavor with it's own unique set of features. Keep in mind that Apple used SCSI as it's standard till reciently and switched to IDE mainly because of cost.

That said, I wish both IDE and SCSI devices a heart felt and fond "get lost". Newer device interfaces are cheap, fairly generic, fast, and allow arbitrary devices to be attached.

I don't expect a complete switch to happen soon, though fiber channel has replaced some of the functions that SCSI devices used to perform on the high end, and IDE is too cheap to pass up on the low end.

Re:SCSI?

[Zathrus]

IDE has NOTHING with that configurability.

Uh... yes it does. It's called SATA. See the article.

And, frankly, configuring IDE drives isn't the nightmare it used to be. As long as the jumpers are set right then the BIOS will usually auto detect and setup the drive properly. Only time I've had problems with that is jumper issues or having explicitly set the location to "disabled".

Don't get me wrong - for home use, SCSI is overpowered. But if you're talking anything bigger than a desktop, make mine SCSI.

That I can certainly agree with you on.

Re:SCSI?

[Anonymous Coward]

that is funny!

go and use a machine with U160 SCSI drives and then one that has IDE... there is a SIGNIFICANT difference in speed, it's snappier, and even the transfer rate measuring software will show it..

remember it's an article... and articles are RARELY accurate and are based on other opinions and not actual tests..

Re:SCSI?

[Anonymous Coward]

I believe he said as much...

Both are highly desired but have no more value than the next drive (be it IDE or rock).

In other words, they are expensive because people want to keep them that way!

Re:SCSI?

[TheWickedKingJeremy]

... without re-inventing the wheel

How is Serial ATA re-inventing the wheel? It is not that complex - and in fact, seems to me to be a natural progression... Faster speeds, and much more importantly, gets rid of those ribbon cables. Everytime I see one of those stupid cables I cant help but think this is one piece of technology we will be laughing at in 10 years (and if not, we *should* be)

Yes, SCSI is a better solution available "right now" - but this article isnt recommending us to go buy Serial ATA now... It is a simple explanation, a heads-up, concerning technology looming on the short-term horizon.

Re:SCSI?

[GooberToo]

If diamonds weren't price-controled they would be incredibly cheap.

And if you substitute SCSI drive for diamond, your original statement is also true! I'm fully aware of what the situation is with diamonds. Obviously. If I had not been, I wouldn't of made the reference. Because of the fact that it's controlled by cartels, that's the reason why diamonds sale for 1000x or more its actual value. Since SCSI is mearly a top shelf product, you don't see such extreme differences but the market mechanics are the same.

If SCSI weren't price-controled they would be incredibly cheap. See how the same is true? SCSI is expensive because they want it to be. Period. It's artificially inflated in place. This is VERY COMMON for ANY premium product! Argue all you want, this is how the real world works!

Re:SCSI?

[Anonymous Coward]

Like cars, realestate, insurance, stocks, etc.

Re:SCSI?

[LookSharp]

SCSI in mass production anywhere near how much IDE stuff gets made will drop the price to the point where it would be affordable to sell it to the home market. Or so the theory goes.

As I sit here in the datacenter, surrounded by (and overwhelmed by the noise of) twelve hundred rackmount servers, each containing between 3 and 15 SCSI Ultra3 (and up) hard drives, 10 to 15 thousand RPMs... and realize that corporations have been buying these things for years...

I am STILL trying to understand why we pay $500 for a 36 GB 15k SCSI drive (40 gig 7200RPM IDE, $77) and over $800 for a 72 GB 10k SCSI drive (80 gig 7200 RPM IDE, $105).

Yes, the IDE drives are more mass-produced, have shorter warranties, and are slower. But the "make more and they'll go down in price" thing just doesn't seem to make sense. And I've been doing this for a few years; long enough to tell you that when you deal with thousands of drives, a couple a dozen per year are still going to fail within the first 6 months. The data density is well below par, even if the drive reliability is comparable. (Thank God for RAID.)

Re:SCSI?

[rsatter]

> go and use a machine with U160 SCSI drives and
> then one that has IDE... there is a
> SIGNIFICANT difference in speed,

Really. I have machines that have Ultra160 and IDE. The only advantage that SCSI has is the multiple I/O requests it can handle. And I have seen absolutely no preceived difference in performance in the normal use of the computers ie. I use them as workstations. In fact I challenge your remark that 2+ ghz machine using IDE boots slower than you Dual P3.

I have a dual Xenon with Ulta160 at home and a 2ghz using IDE133 at work. Both with 512mb memory. The machine at work boots much faster than my home machine even excluding the POST time to find the SCSI drives. And I have seen no difference in preceived performance.

SCSI is only worth anything when you start talking about I/O intensive applications like housing a database. And most desktop users almost never require anything more from there drive than reading and writing a single file at a time.

Thus the reason for SCSI being expensive is because it is for corporations and backend servers that are a shared resource and so the cost per user is cheaper than IDE.

Re:SCSI?

[Null PTR for Lunch]

And whats wrong with that ribbon cable? It gets my data from my drive just fine, and if i feel like soldering stuff on there... :)

Re:SCSI?

[greed]

You can't get the same density at higher rotational speeds; it requires more "design" in the heads and sense amps to read the signals reliably enough. So you have to trade capacity for high RPM... and you have to hope the density is _enough_ better that you still get a transfer-rate advantage with the higher RPM.

Since they don't even make SCSI drives with the same rotational speed as IDE these days, you can't compare, there are too many differences. So you get the "new research" model with SCSI, and once they have it figured out, the IDE versions come out.

So you've got more than just www.scsita.org putting up the prices, you've also got the bleeding-edge factor too.

I used to like SCSI. I still like the command set, and since FireWire supports serial SCSI (SBP-2), I get the best of both: cheap IDE drives in a FireWire box and I can use SCSI drivers to control them.

Re:SCSI?

[Anonymous Coward]

And that is why people use SCSI/FC in a data centre. The ability to scale in performance, and handle many requests is far greater in SCSI than IDE/ATA. I do agree that Desktop users have (generally) no need for this level of performance. Although when doing audio related work, I prefer the performance of SCSI, but then how many people are doing that with their home PC/Mac?

Re:SCSI?

[Anonymous Coward]

C'mon-which SCSI? There's plenty of variants there as well, and they can cause even more headaches.

Re:SCSI?

[shepd]

>Haven't seen a whole lot of inexpensive SCSI network, processor, printers nor scanner.

I bought a SCSI scanner 5 years ago for $99 CDN. Unfortunately, the consumer standard is now USB, which is FAR slower.

My 5 year old scanner beats the pants off any new USB scanner, except for the colours being off (Hey, it's an Acer, whaddaya expect, perfection? ;-)

Oh well.

Re:SCSI?

[druxton]

Ironically, SCSI stands for Small Computer Standard Interface

Ironically, it does not. Try Small Computer System Interface. Or, in early days System Can't See It.

Re:SCSI?

[Anonymous Coward]

I remember buying a CDR with an UltraSCSI interface in Taiwan and I went to get a card for it at a shop in California and they tried to sell me this card for six hundred dollars with a hundred dollar cable. I was like, hey you've got to be kidding, this CDR was only a few hundred to begin with. They found a reasonably priced one somehow after they realized I wasn't expecting such a high price. Rather suspicious.

Re:SCSI?

[Anonymous Coward]

I would like to say that the price of SCSI drives is not 10x more because nobody wants a SCSI drive, but because they are simply more complicated to manufacture and interface.
SCSI and IDE disks are vitually the same, but IDE has the added complexity of having the drive electronics as well. From a manufacturing standpoint SCSI should be cheaper.

Re:SCSI?

[Anonymous Coward]

"not that complex"

Don't understate the complexity: serial adds complexity you don't have in a parallel interface. Encoding and decoding, high-speed serdes (very challenging beyond 1 or 2 Gb/s), and clock extraction with a PLL or DLL on the receive side. Of course, those things already exist for serial interfaces such as Fibre Channel, USB, and 1394, so SATA is just an adaptation (reinvention, if you will) of existing elements.

Not that parallel SCSI hasn't become complex. To the original async and sync SCSI protocols, the last few years have added double-transition and paced transfers, along with precompensation and equalization strategies and deskew training, all in the quest for higher performance. Serial eliminates all of those things except precomp and equalization (and deskewing, in the case of multi-lane serial). Interestingly, SAS (serial attached SCSI) will be based on the SATA infrastructure.

I don't expect to see any new generations of parallel SCSI after 640 MB/s, if it even reaches that. The future is serial.

Re:SCSI?

[TheWickedKingJeremy]

Ahh I love replying to ACs ;)

By "not that complex" I meant in terms of the end-user experience... The original post had mentioned that going with a Serial-ATA solution is like "reinventing the wheel" -- I simply meant to say as far as the end-user is concerned, Serial ATA is not any more complex, and in fact might be simpler to setup than IDE or SCSI.

I am sure the inner workings are very complex and I respect that - I just am not particularly concerned with it as I am not an engineer.

Re:SCSI?

[sfgoth]

15k rpm scsi drives get seek times in the low three range--that's three times faster than your average 5400 rpm ide hdd.

Mostly because they're spinning three times faster. It has nothing to do with IDE or SCSI.

-pmb

Re:SCSI?

[egarland]

From what I understand SATA will get SCA style backplanes.

The 3ware card's bandwith limitation is a property of that card, not of the SATA bus.

I've been working with IDE RAID for a few years now and I have to say, I grimmace whenever I see someone throwing buckets of money down the drain by putting together a SCSI system. I've seen IDE RAID machines performing 3+ times as fast for less money and then had to build one of the old SCSI style because we coudln't buy IDE RAID from one of the big server makers who provides global support. I personally have a 480GB array at home that cost me under $1000 to put together 6 months ago.

Soon, with the 320GB maxtors you will be able to create a 3.5 TB array in 3U using off the shelf hardware and $350 drives for under $10K. Spend that on a SCSI array and you get about 1/5th as much space.

SATA has a long way to go but SCSI is dying. The newest technology is no-longer introduced into the SCSI drive lines first. ATA drive lines are usually many months ahead of their SCSI counterparts.

Karma: Instant (Mostly the sum of being smacked for making stupid puns)

Re:SCSI?

[pls]

SCSI drives are not 10 times more expensive, it's more like $10 CHANGING THE INTERFACE ONLY.

There is a lot more difference between the common SCSI and ATA drives than the interface. SCSI drives are usually built for server duty, use a much heavier duty mechanism that will operate for several years working 24X7, and are usually faster and rely on external cooling. ATA drives are light duty drives built for price, suited only for lightly used workstations, and will probaly die after 1.5 years in that service.

Given the coming serial SCSI, it is my considered opinion that serial ATA has no reason to exist. Manufacturers should produce server-duty SCSI drives and workstation-duty SCSI drives with the appropriate difference in mechanical quality and effective life. They'y probably save more money from increased commonality of parts than the trivial extra cost of the SCSI interface chip.

++PLS

Re:SCSI?

[Wolfrider]

Sure you can make an IDE RAID setup, but with most manufacturers going with a 1-year warranty how long do you expect an "average" single IDE drive to last?
.

Re:SCSI?

[egarland]

Not all IDE drives are shipping with a 1 year warranty.

Maxtor's Enterprise Class IDE Drives for example still cary a 3 year warranty.

drives and natalie

[Anonymous Coward]

I'm quite happy with my 7200 8meg cache drives...better than spending that money on scsi. I wonder what size drives natalie portman has on her?

SCSI?

[lpret]

Couldn't the same arguments be made for SCSI? And where is it now? Relegated to obscure servers and macs. It has to do with the price -- when will anyone ever realise that?

Only if...

[SirKron]

Serial ATA will only take off if it is not more expensive than parallel ATA. If we (meant users) want to spend more we would buy SCSI. What I want is a low cost way to stipe 4+ drives at home.

Re:Only if...

[jkfresh]

Its going to be coming standard on lots of new motherboards.. its not going to cost you anything.. well outside the cost of the board and the drives..

Re:Only if...

[stratjakt]

It should be at least a bit cheaper, the logic for a serial circuit is much simpler than for a parallel one. (less wires = less logic).

Re:Only if...

[rodgerd]

This gives it to you. The main problem with IDE-RAID is fucking around with cables and a standard that doesn't support hot-swap.

yeah, yeah, yeah enough with the sales pitch

[stratjakt]

Where are my drives?

I got a shiny new SATA RAID controller on my new motherboard, now when the hell am I gonna get a couple of 80 gig cheap, fast SATA drives to put into a striped set?

huh? huh?

Re:yeah, yeah, yeah enough with the sales pitch

[Anonymous Coward]

Seagate Barracuda V Serial ATA drives will be available mid November.

Re:yeah, yeah, yeah enough with the sales pitch

[Hadlock]

IIRC, you only get one controller per port for SATA. you'd have to do software, or build your own striping solution. (with several add-in boards to support 4 more HD's)

Re:yeah, yeah, yeah enough with the sales pitch

[bjschrock]

Well... Seagate has announced their first SATA drives, the Cuda ATA V, but they haven't hit the shelves yet as far as I can tell. It is supposed to be available this fall... so they should be out soon. Also, the Cuda V is a true SATA drive, not just an IDE drive with a bridge slapped on it.

Re:yeah, yeah, yeah enough with the sales pitch

[Anonymous Coward]

Just get the PATA to SATA converters - they're only $50 each ;-)

FIREWIRE?

[cybercomm]

So...why don't we use firewire? Isn't it faster than SATA? And the upcomming Firewire IEE 1394b should double the firewire speed to ~800mb/s. And let's not forget the fact that there are firewire HDD-s and other perhipeals on the market (though they are generaly external) or maybe, could this have anything to do with INTEL's desire to controll all components? I don't see the price as a limiting factor either.

Re:FIREWIRE?

[cheezedawg]

Um, no. Gen 1 SATA is 1.5 Gb/s. Firewire is not faster.

Re:FIREWIRE?

[Anonymous Coward]

Yeah i have a RAID 2 connected to my mac i i have never experienced any problems with it.

Re:FIREWIRE?

[Anonymous Coward]

That is because the cheese in that mac is providing insulation from the outside world. Just wait until you get hungry...then you'll see what I'm talking about.

Re:FIREWIRE?

[ArsonPerBuilding]

Regardless of what the speeds for various standards are, it is futile to argue which standard is superior. Why argue if SATA or Fireware is faster when current storage technolagies availible to mass consumers can not provide throughput on the level of the maximum bandwith?

Re:FIREWIRE?

[Salamander]

Actually SATA is 1.2Gb/s, but that doesn't change your point.

Re:FIREWIRE?

[cheezedawg]

Actually, it is 1.5 Gb/s. There is a 8b/10b encoding at the link layer.

Re:FIREWIRE?

[Salamander]

Bits that the signalling throws away don't count.

Re:FIREWIRE?

[cheezedawg]

Well, I'm not the only one that calls it 1.5 Gb/s. The serial ATA website often refers to it as 1.5 Gb/s.

Also, signalling bits that are thrown away are often counted. Otherwise we would have 98 Mb/s ethernet instead of 100 :)

Re:FIREWIRE?

[Anonymous Coward]

Excuse me... FireWire is 400 MBps (B as in Bytes) or 2.4 Gbps, which is TWICE the speed of SATA.

Re:FIREWIRE?

[Anonymous Coward]

http://www.firewire.org/firewire/

Dipshit.

Re:FIREWIRE?

[alue]

You're kidding me, right?

800mb/s? Do you think that means 800 megabytes per second? Try 800mbps, as in megabits per second, which is 100 megabytes per second. I think ATA133 beats that.

I don't even know where you're getting this 800 figure; last I heard it was 400.

Re:FIREWIRE?

[Anonymous Coward]

Yes. I do not understand why we need another "new" set of connectors, cables and so on. HDDs with native firewire support should do the work (why not?).

Re:FIREWIRE?

[Anonymous Coward]

Well, actually you are wrong because SATA only supports one hard drive. FireWire supports multiple hard drives (up to about 60) . So, even though theoretical maximum thorough-fair is higher on SATA, FIreWire is actually capable of the higher speed, while, with current technology, SATA is not. I love my 3-drive FireWire RAID setup (striped) & I know GEN-1 SATA will never touch it.

Re:FIREWIRE?

[Anonymous Coward]

Let me get this straight:

SATA has a dedicated 150 MB/sec to each drive, and Firewire has a shared 50 MB/sec for all drives, and somehow that makes Firewire faster?

Re:FIREWIRE?

[Wesley Felter]

Well, I'm not the only one that calls it 1.5 Gb/s. The serial ATA website [serialata.org] often refers to it as 1.5 Gb/s.

That's what you get when you don't keep a tight leash on the marketing folks. InfiniBand is guilty of the same thing.

Also, signalling bits that are thrown away are often counted. Otherwise we would have 98 Mb/s ethernet instead of 100 :)

No, you've got it backwards. Fast Ethernet runs at 125MHz, so it would be 125Mbps if you count overhead and 100Mbps if you don't count the overhead. Guess which number people use.

This just looks expensive.

[jericho4.0]

The first generation doesn't look that impressive, as shown by the selling points given by the author. Thinner cables, up to a meter long?? Ok, sounds nice, but not worth paying extra for, for my needs. Serial ATA wil debut at 150 mb/s, not really an improvment at all.

The author then goes on to note that the 'roadmap' calls for the 2006 version to run at 600mb/s, which fits nicely with my roadmap to world domination in 2005. ...Ummmm, yeah, we'll see.

Although looking at the list of upcoming products and the manufactures making them, I don't doubt we'll all be useing this in a few years.

Re:This just looks expensive.

[pope nihil]

Actually they said SATA 3 (600 MB/sec) will debut in 2007.

I was a bit confused by this article. They talk as if this thing is the Second Coming of Christ, but then they talk about how desktop pcs are just going to keep taking baby steps. Also at the beginning of the article they say that serial seems to be a step back from parallel (ya think?) but it is faster and better and Oh! Look! An elephant!

Re:This just looks expensive.

[photon317]

The battle between serial and parallel communications is neverending. Show me a Serial WAN connection like a DS3, and I can say "Well, since you never send partial bytes, we could strap 8 of these side by side, send one byte at a time with the bits split up over the 8 DS3s in parallel frames, and we get an 8x speed improvement that's usable by a single connection and no additional latency".

Or show me a parallel bus like IDE, and I can say "Look, having all those data lines next to each other causes additional interference we have to account for, and they're bulky, cost more, overly complex, blah blah. If we just put a serial bitstream on a pair of wires, it would be so much simpler that for the same cost we can turn up the bitrate more than enough to make up for the lost parallelism."

It's all the same. Various communication technologies tend to rise and fall, serial replacing parallel replacing serial replacing parallel ad infinitum. In some cases (like PCI busses) parallel just makes a lot more sense, but in a lot of cases (network stuff, storage stuff especially) there's a tradeoff where both are better and worse than the other in different ways. You could just pick one and stick with it and do you incremental improvements, but the occasional switcheroo provides upgrade revenues and more user "wow" factor and buzzwords.

Re:This just looks expensive.

[Magila]

Eh, parallel is on the way out for good. You've obviously never heard of a little thing called clock skew. It's what makes your DS3 example impractical since the bits won't all arive at the same time, with the run lengths you're talking about with a DS3 the potential difference would be too large to effectivly compensate for.

Re:This just looks expensive.

[bjschrock]

It is an impressive jump ahead, and it's not going to be much more expensive. It's estimated that Serial ATA interfaces will be less than $10 more expensive than their parallel counterparts, and that will go down once it becomes more popular. Also, it's not 150 M-bits/sec, it's 150 M-Bytes/sec. Another big advantage is that Serial ATA is that the drives will be hot-swapable. The new power connectors have extended ground plugs so that the grounds contact before power... also drives will get to use a new voltage line (+3.3V) that they didn't get before.

Another interesting thing about the technology is that drives that are currently using the parallel SCSI interface will be moving to either SAS (Serial-Attached-SCSI) or Fibre Channel. SAS will use the SCSI protocol over the Serial ATA cables, so you can get rid of those nice giant ribbons.

Re:This just looks expensive.

[mosch]

Let's repeat that one more time for the Google archive. Magila has said that "parallel is on the way out for good."

As Will Rogers once said, "It's always risky to make predictions, especially about the future."

Re:This just looks expensive.

[alsta]

I doubt it will cost a lot extra. Perhaps initially in the order of $50 on a $200 disk, but I doubt it will go further.

The roadmap is interesting, but it's pointless to assume that the 600MB/s version would have surpassed SCSI in 2006. SCSI is today at 320MB/s levels and come very close to those transfer rates. Where SCSI will be in 2006 is something none of us know. In fact, we don't know if SATA will be a success at all at this point. Neither do we know that either of the two will still exist in 2006. Perhaps FCAL-3 would be cheap enough at that point and with idiot-proof connectors, that nobody would look back...

Where are we today?

* SCSI has much better seek times than IDE disks.
* IDE can transfer huge files at decent speeds, but CPU usage goes up significantly and doesn't come close to concurrent SCSI gear.
* IDE is cheap for storage, but if you're looking for performance, a nice IDE RAID card (3WARE Escalade 8500-4) and disks (Western Digital Caviar Special Edition) is expensive compared to an Adaptec 39320 and a Seagate Ultra320 disk. The IDE variant would require at least two, but probably four disks in a RAID 0 configuration to even come close to the SCSI performance.
* IDE is terrible at simultaneous access to lots of small files, compared to SCSI.
* While to some degree also true about SCSI, IDE disks use large caches to compensate for slow write speeds to the platter. IDE disks "cheat" and report back that the file has been written, when it may partly or entirely exist in cache at that moment. Hence unsuitable for reliable storage.

If SATA or any other standard produces a better performing product than today's SCSI, I will gladly switch. But as of right now, there is no such alternative. And for all intents and purposes, SATA is still not widely tested which SCSI is. In the case of several hundreds of dollars, I'd rather spend money on a devil I know than a devil I don't.

Re:This just looks expensive.

[Anonymous Coward]

No, the cycle will happen over. They'll start simple (1 byte at a time) after they master 1 byte at a high number of clock cycles, they'll look at trade offs and it'll get wide (say 2 to 4 bytes per cycle) then they'll notice their design running into a brick wall (although expect some signalling improvements--transmission line improvements, pulse shaping, new modulation technologies, etc). At this point, someone will come up with another faster serial transmission method and it'll all start again.

Re:This just looks expensive.

[Magila]

You want to come up with a real argument or just make stupid quips and quote people? Parallel interfaces are limited by well eshablished physical properies of electricity traveling through a conductor, thoes properties arn't going away any time soon and pretty much every known method of transmitting 1s and 0s has similar properties. Parallel interfaces came along because signal processors of the time were slow enough that these physical properties weren't a problem. Now that we can send signals of high enough frequency that things like clock skew do become a problem it makes sense that we abandon the parallel interface and never look back.

Re:This just looks expensive.

[bryan1945]

Interesting that no one else caught the one flaw in the serial/parallel debate- optics. Not quite price feasible now, but maybe 5 years or so(?), but run X number of single-mode fibers and you have X parallel bits with zero interference. It has its pros and cons, but nice performance!

Re:This just looks expensive.

[rodgerd]

Thinner cables are very impressive for those who like to stuff drives in boxes. In fact, thinner cables sell me on the standard - I don't care about the speed.

Re:This just looks expensive.

[jericho4.0]

What!?!?!?!?! Thats crazy. Oh, and btw, I have a nive Vax for sale, $20 + shipping. Obviously a great deal for the likes of you.

Re:This just looks expensive.

[Zeio]

I have to agree with alsta here and vehemently disagree with the moderation "flamebait."

Lets got over this supposed flamebait.
* SCSI has much better seek times than IDE disks
This is irrefutable. This is in industry rule. I refer people to the fastest hard drive I could think off the top of my head here: http://www.storage.ibm.com/hdd/desk/ds180gxp.htm Deskstar 180GXP - Average seek time - 8.5 ms
and to here: http://www.seagate.com/cda/products/discsales/mark eting/detail/0,1081,549,00.html 15K.3 Model Number: ST373453LC Seek time: 3.6 ms avg

Now, I don't know about you people but an increase in seek performance that is easily 2.4 times better that the best IDE for something that occurs that many times a second, well, I'm convinced that the drive is considerably faster. Think of any "worst case" scenarios, and this extra speed is likely never to go un-wasted on a computer.

I am also in accord with alsta's skepticism that SATA will be anything but a consumer grade technology. I am an ardent supporter of Firewire and SCSI, and it clear the SCSI standard has much to offer because implementations of SCSI over IP are planned to deprecate FC in favor of iSCSI over 10GE. To me this SATA is a day late and performance short. I think it is nice we can now clean up the crap connectors, but I will not be deluded into believing that SATA has a prayer in terms of beating SCSI.

I also have seen many reviews on IDE RAID and must concur that it is nearly impossible to IDE up to single drive SCSI performance without doing some hardcore RAID-ing. I cannot provide links to support this statement, but peruse through a site like Storage Review and you can see clearly where and why and how SCSI drives cremate their IDE counterparts.

I have IDE and would buy SATA for mass cheap storage at home, but it was a sad day when PC vendors stopped offerering SCSI upgrades from the factory on their cheesier machines and Apple stopped using them by default. This essentially was the advent of the "Geo" or "Kia" of the computer world. I hate hackneyed car analogies, but in this case, as I have seen in acerbic reviews of the said cars, "Why buy this cars where there are better used ones around?", directly applies. I can think of many "used" scsi drives and how badly they destroy consumer grade stuff with ease. This is both from L&F and measure performance metrics.

IDE does not support tagged commands, and it is still unclear if SATA's implementation will be as robust as SCSI. This alsta's statement is again correct with regards to terrible simultaneous access. Try running a busy Unix box with 100s of people copying files and doing this or that, compiling crap, etc. The disk needs to be serious about handling jumpy situations. Seek time and command tagging comes in handy here.

Unfortunately larger buffers can only mask problems. There are many situations where consistency is not guaranteed, and where the cache can easily be blown. I like buffers to be there to make an already fast situations move along more regularly, like a capacitor helps regulate power. I don't like an already bad situations being masked by case specific buffering optimizations.

I will ,as alsta indicates he will, continue to use SCSI as my most preferred storage bus. I cannot think of reasons not to, if I have an dumping ground for "crap" in my IDE large capacity hard drives. Also suspect is the standard being ratified over a year ago and nothing materializing yet. Also, I think the SMART works better in SCSI, I think sector sparing is essential and IDE and apparently SATA wont do that, and I like 5 year drive warranties not ONE like most IDE drives moved to now, and I liked support, and I like knowing that the company I bought the device from made an okay profit so I can get amenities like advanced replacement. It's a preferred choice, and if you can afford it, so it.

Just because you may not be able to afford it or don't think storage is not the way you should spend your hard earned money, don't knock SCSI. And certainly don't come to Slashdot and suppress other people's views on the subject.

Re:This just looks expensive.

[Ed Avis]

In the future couldn't there be two SATA connectors on a single device? Not running in lockstep like a parallel interface, but two separate connectors with data being sent along both. That sounds like an easy way to increase bandwidth without the syncronization problems of having parallel wires at the hardware level. But I don't know if the SATA standard supports this.

Re:This just looks expensive.

[Ed Avis]

SCSI has much better seek times than IDE disks

No, the interface makes no difference to the seek time. What you mean is that fast, high-end disks are typically sold with a SCSI interface, while slower models get IDE.

Re:This just looks expensive.

[photon317]

Of course you still have synchronization problems. Over an appreciable length, each fiber will be slightly different internally (and probably in path shape as well), which leads to the actual photons paths being significantly shorter or longer than each other.

Re:This just looks expensive.

[photon317]

Well, the DS3 example is of course crazy or people would be doing it. Over long wide area links serial tends to win, just like parallel wins on expansion card busses. However clock skew can be mitigated with buffering. However by eating the potential buffer time you increase the latency, which makes the tradeoff imperfect. YOu might gain 8x the bandwidth but double your latency or more. It would come down to actually measuring how things work out in a particular technology you're building to decide whether the amount of gained latency versus gained bandwidth paid off.

Re:This just looks expensive.

[Zathrus]

ATA wil debut at 150 mb/s, not really an improvment at all.

Does it matter? At all? No.

Frankly it could be 150 GB/s and it wouldn't matter in the least.

Go look at the manufacturer specs. Read the line that says "drive to host, sustained throughput". Note that no manufacturer claims more than 52 MB/s. Reality is closer to 48 MB/s for the fastest IDE drive. That's right! We're not even exceeding ATA/66 bandwidth yet. And still people are talking about 600 MB/s in a few years. Who cares? You can't reach that throughput anyway. Not to mention that the PCI bus is limited to 133 MB/s.

Ok, the bus speed does make a bit of difference. If the data you need is in cache then you can use the maximum theoretical bandwidth while reading from cache. So dumping a 8 MB cache via ATA-133 saves you about half a millisecond over ATA-66. You noticed that, right?

The advantages of SATA have nothing to do with the bus speed. The longer cable is useful in a select few tower cases. The hot swap will be nice for a small percentage of enthusiasts and idiot admins (I'm not a SCSI fan boy, but if you're running a server you really should be running SCSI). The small, thin cable is useful for everyone though -- the air traps created by ribbon cables are causing more and more problems as everything runs hotter. Most drives fail due to poor cooling. Want to bet that SATA drives have a significantly lower failure rate?

Re:This just looks expensive.

[mejh]

"IDE is cheap for storage, but if you're looking for performance, a nice IDE RAID card (3WARE Escalade 8500-4) and disks (Western Digital Caviar Special Edition) is expensive compared to an Adaptec 39320 and a Seagate Ultra320 disk. The IDE variant would require at least two, but probably four disks in a RAID 0 configuration to even come close to the SCSI performance."

Did you see this, posted here a few days ago?

It mentions their choice of storage being a RAID0+1 of four IDE disks, and it beating SCSI in both price and performance by some considerable margin.

Cheers,
Mark.

Re:This just looks expensive.

[clarkc3]

The author then goes on to note that the 'roadmap' calls for the 2006 version to run at 600mb/s, which fits nicely with my roadmap to world domination in 2005.

He obviously never read a hard drive manufacturer's webage about their plans for developing them - check out seagate's page on ata and notice that their planned releases for 150/300/600 mb/s drives are all behind the 160/320/640 scsi ones planned for development/release

Re:This just looks expensive.

[jpc]

hmm, no in a few years time, the scsi roadmap says they are going to serial scsi. Curiously this is exactly the same as serial ata except:

1. max cable length is officially 3m, sata officically 1m, though in fact 3m should work on both.

2. the command set is scsi not ata6: irrlevent as ata6 was tcq etc.

3. there was going to be multiple devoces on serial scsi I think but they scrapped this as the termination didnt work.

4. er thats it.

So scsi will go anyway.

Re:This just looks expensive.

[Dastardly]

http://www.storage.ibm.com/hdd/desk/ds180gxp.htm [ibm.com] Deskstar 180GXP - Average seek time - 8.5 ms
and to here: http://www.seagate.com/cda/products/discsales/mark eting/detail/0,1081,549,00.html [seagate.com] 15K.3 Model Number: ST373453LC Seek time: 3.6 ms avg

Do you really expect people to take this sentence seriously!! You are comparing a 7200RPM drive to a 15000RPM drive and claiming SCSI is faster. You obviously have no idea what seek time is. Average seek time is solely a factor of platter size, rotational speed, and speed of the read/write actuators. The interface is insignificant. Slap a SCSI interface on the IBM drive and the seek time would be identical, slap an IDE interface on the Seagate drive and the seek time would be the same. You shoto down your own argument before it even gets started.

Don

Re:This just looks expensive.

[mosch]

clock skew, a problem which we get better and better at handling, and which isn't particulary difficult to solve if the application allows for the addition of a small amount of latancy.

To use the DS3 example that somebody mentioned previously, it's entirely possible to create hardware on each side of the link that would send simultaneously over each link, and on the other side the bits would be reassembled, with some small reassembly delay.

Using this method you could greatly outstrip the bandwidth available from the current top of the line serial link, at the cost of a small amount of latency. And yes, I understand that 8 lines wouldn't get you 8 times the speed, because there'd need to be protocol overhead.

That being said, this is slashdot, so I tend to avoid real debate. Very few people have the capability to thoughtfully discuss technical topics, and those that do are often unreasonable, unable to recognize humor and generally unwilling to engage in anything interesting or useful. Thus, it's far easier to just use a quip and a quote to imply that your statement is clearly wrong than it is to explain why you're wrong.

Re:This just looks expensive.

[alsta]

Nonwithstanding, the comparison is the fastest disks from both camps. Thus it is valid.

Re:This just looks expensive.

[Anonymous Coward]

Show me a single drive soem IDE-land that beats any current one one generation old SCSI.

15K.3, 15K.2, and 10K.6 and 10K.5 will all easily beat IDE drives.

Sorry pal. If they could strap an IDE connector on a 15K drive and make money doing it it would have been done.

You cheap fucks wont pay for it, so you get slow shit.

And I laugh. Every metric of performance tell me I'm right to be choosing SCSI for performance.

Enjoy your cheesy IDE shit, with no sector sparing. Oh, SATA drives dont have sparing, oh, well you sound so fucking dumb that I doubt your computer has anything worth saving on it anyway.

Re:This just looks expensive.

[Anonymous Coward]

If that was the case, why hasn't it been done? You are a fool. Yeah, slap it on there. Sure thing. You obviously use a mop more than a keyboard to trivialize drive ASICS like that. Sure, just sping that shit a bit fast and slap that on there. Right-o.


ST1181677LWV Barracuda 180 181.6 GB Ultra160 SCSI 7200 RPM 7.4 ms avg MSS&W

ST318418N Barracuda 36ES2 18.4 GB Ultra SCSI 7200 RPM 7 ms avg ELS&W


Looks like your fucking mouth is spouting drivel again. Gigantic and old SCSI drives at 7200 RPM are still faster, and, oh, well better.

Please, you fucking dumpster diving piece of shit, shut your fucking cheap ass mouth. Please. Yeah, im sure your Honda Civic can beat my SC400 off the line too.

Re:This just looks expensive.

[Anonymous Coward]

Hey asshole.... you just shot yourself in the foot.... ITS THE WHOLE FUCKING POINT.

IDE IS SLOWER, notwithstanding all other bullshit reasons... such as being too much of a kyke to buy fast storage.

Re:This just looks expensive.

[Anonymous Coward]

and you work for a hard drive company and deal with signalling and drive asics and are and expert on the issue too right? sure thing pal. next you'll be telling us to get an IDE to SCSI converter so we can use the bad ass zero CPU usage SCSI cards instead of the IDE CPU eating shit controllers. And because there is no difference, we will see godly performance right. Shithead.

Re:This just looks expensive.

[Anonymous Coward]

That being said, this is slashdot, so I tend to avoid real debate. Very few people have the capability to thoughtfully discuss technical topics, and those that do are often unreasonable, unable to recognize humor and generally unwilling to engage in anything interesting or useful. Thus, it's far easier to just use a quip and a quote to imply that your statement is clearly wrong than it is to explain why you're wrong.

this from a gentleman whose chief claim to fame is that his perceived importance : slashdot id ratio score is more than three standard deviations above average

Re:This just looks expensive.

[Ed Avis]

The seek time of a hard disk is a physical property of the head, how fast it can move to a particular track. You could buy one of those slow parallel port disk attachments and the seek time would be just the same as with IDE or SCSI or Fibre Channel or whatever. It doesn't mean that the system's performance will be the same whatever the interface, but I didn't say that. I was talking about the seek time.

Re:This just looks expensive.

[Anonymous Coward]

So, How you move the head doesn't play a role? PLEASE. PLEASE. You know what, I actually know a guy who worked for lucent making ASICS for these things. We laugh at this. The physical design plays a role. Vibration, spindle speed, etc. How fast a head can flutter is a physical property. But when you have a stack of information to look for or write, you can do it out of order to save movements. There is vast amounts of intelligence that goes into avoiding moving the heads more than necessary. It also happens to be that SCSI drives are able to do this better.

You think that you can't improve a drive's seeking ability with a firmware change? If you think not, think again. In fact, try THINKING.

There is the theoretical maximum, and then there is the reality, that going to a random point on a disk is very much dependant on where you just were and where you need to be next.

The fact is most kiddies here don't know 1's and 0's aren't written on the disk, there is huge amounts of signal processing and other things that go on to make a 1 or 0 apparent. I've seen the signals, they are unreadable without transformations. The intelligence on higher end devices, SCSI in particular, allows for the processing of signals at a furious pace, with faster spindles for less latency and also the superior electronics and firmware are able to be proactive and intelligent about moving the heads.

I know fro experience, that when things in an OS get to the point of thrashing, which drive randomly seek better [SCSI]. And how bad ass or fast the heads are in this situation don't save you. Its how well your drive firmware handles the deluge while finding it [easy/difficult] to read the signals coming off the disk.

Your statement is like saying; "We have nuclear weapons, so aiming it isn't important." Its probably even more ridiculous than that.

Re:This just looks expensive.

[alsta]

I read the review and it speaks loads about how fast IDE is versus SCSI and how much cheaper it is and blah blah blah. But NOT ONE WORD about what made it faster or even how the test was performed to make the ruling.

Hence it is hearsay at best and a pointless comparison. Did you know that a Yugo is better than a Porsche? Because you get a lot farther on a tank of gas and it costs considerably less.

See? Now I made a comparison. All I have to do now is say that the Yugo is faster and puts the Porsche to shame. Now I made a ruling. What do I base this on? If I don't tell anybody how I came to that conclusion, it is a rather pointless thing to say, no?

Re:This just looks expensive.

[Ed Avis]

You're right, the way you order the disk seeks (elevator algorithm or whatever) can make a huge difference to the disk's performance. But I thought that average seek time was a purely physical measurement of how long it takes to do a single seek, from one part of the disk to another. Are you saying that average seek time is in fact computed by sending lots and lots of commands to the drive, letting it reorder them how it wishes, and seeing how long it takes until the last one is completed?

I'm pretty sure it's done by taking two spots on the disk, moving the head to one, and timing how long it takes to get to the next. This is certainly how ye olde disk benchmarks (Norton etc) used to compute the 'average' and 'maximum' seek time figures. The disk and controller did not have any scope to reorder the head movements because each test was done individually, after waiting for the previous one to finish.

Again, I didn't say seek performance, I said seek time. The performance you get in practice will depend both on the physical seek time and on how intelligent the software and firmware is in ordering reads/writes, as you mentioned.

Re:This just looks expensive.

[Wakko Warner]

Clearly, you're jealous.

- A.P.

Personally, I can't wait until it comes out...

[HoneyBunchesOfGoats]

...'cause that means prices will drop on hard disks that I can use.

Re:Personally, I can't wait until it comes out...

[Null PTR for Lunch]

Huzzah! Then I'll be able to buy that 200GB drive for peanuts!!! PEANUTS!!! MWAHAHHAHAHAHAHAHA

ide is great

[Anonymous Coward]

I'd like to eat an apple (no pun intended) rather than pay for scsi. This is a good thing to happen for ide.

Parallel vs Serial?

[Phoex]

Forgive me if I sound a bit naive but wouldn't parallel be faster than serial? Higher bandwidth, no need for data caching, and no need to convert back to parallel...

Also did anyone pick up more than 2 pieces of relavent info in the hype? I saw 150Mb/sec as a speed but other than that I saw no real information.

Re:Parallel vs Serial?

[stratjakt]

> Forgive me if I sound a bit naive but wouldn't parallel be faster than serial?

No. It's much harder to keep 10, 20, 30, 40 lines in sync at higher clock speeds than it is 1. There's a ton of crosstalk, which is why the cables are limited to about 18" right now.

Parallel is pretty crude. This is why your ethernet cable has 4 wires (that it uses).

Re:Parallel vs Serial?

[shepd]

>Forgive me if I sound a bit naive but wouldn't parallel be faster than serial?

Yes, but just like with memory, serial is cheap, parallel costs. Those extra wires just ain't free.

Re:Parallel vs Serial?

[sunspot55]

Forgive me if I sound a bit naive but wouldn't parallel be faster than serial? Higher bandwidth

It depends. It depends on the several things. Note that when I talk about bandwidth here, I'm talking about the non-bastardized version of bandwidth, in FREQUENCY terms. (Sorry it's a pet peeve of mine and everyone abuses the term.) If you have a higher bandwidth (frequency here) available to you, or a high signal-to-noise available to you, you can possibly transmit more bits than parallel, especially with more complex line codes and modulation/demodulation schemes. With modern VLSI the added costs of more complicated mod/demod schemes are quickly becoming less of a factor. It depends on the frequency bandwidth that are specified in the specs. I have no clue what the attenuation specs are on vanilla IDE, but I would imagine that it has much lower passband than Serial ATA. Now I could be way off base on that, and would love for someone to correct me on that, but I am fairly confident in my assumption. Therefore, if regular parallel ATA had the same bandwidth (frequency, remember) available to it that serial ATA had, than yes, parallel would be faster. It just gets trickier when you consider non-ON/OFF line codes.

Re:Parallel vs Serial?

[CMiYC]

Forgive me if I sound a bit naive but wouldn't parallel be faster than serial?

On paper, parellel can be made to be faster than serial. However, in the practical world it is very difficult to make a high bandwidth parallel bus. It is even more difficult to run that bus any considerable amount of length. By using a serial bus with embedded clock you only need 2 signal wires. If those signal wires are a differential pair (perferrable Low-Voltage) then you can run them a considerable length at an extremely fast rate. If you have a parallel bus, you don't have the option of embedding the clock. If you are running with out an embedded clock you must send a clock syhncronous with the data. Now you have to deal with skew issues between each individual channel as well as all channels relative to the clock. Not to mention other aspects such as crosstalk between the channels. If all you have to worry about is two signals (which if are differential can be considered 1) then many of those issues ago away.

There's a lot of physical behind why its extremely difficult to run long lengths of parallel lines. Yes a parallel bus is faster, but it is almost impossible to implement a reliable parellel bus running at 1.5Gb/s, through cables, and with connectors. Take a look at a bus like hypertransport. It can be up to 16bit wide and run 1.6Gb/s. However, it is a point to point protocol, is run over a control impendance, and is run over very short distances.

I hope that helps.

Re:Parallel vs Serial?

[Anonymous Coward]

Do you have over 1600 comments? Why not?

Because I have a job.

Re:Parallel vs Serial?

[shepd]

>Because I have a job.

So do I, but unlike yourself, I actually have a name.

Must be hard having the same name as a few thousand other people.

even cheaper

[lseltzer]

The whole point of it is to be at least as cheap as parallel ATA, even cheaper. The connectors will be smaller and cheaper for example. It should also make system design more flexible since you won't have parallel ATA's infuriating cable length limits.

Re:even cheaper

[rodgerd]

Indeed - it'll be a blessing for system builders.

Give me Firewire!

[xixax]

So what does SerialATA offer that a Firewire connector on my hard-drive won't?

And haven't we discussed this before?

Xix.

Re:Give me Firewire!

[cheezedawg]

So what does SerialATA offer that a Firewire connector on my hard-drive won't?

150 MB/sec?

Re:Give me Firewire!

[Com2Kid]

• So what does SerialATA offer that a Firewire connector on my hard-drive won't?

Bingo, it is exactly what Serial ATA does not have over firewire that makes it so desirable.

Namely the $50 or so price premium. . . .

too bad that

[LuckyJ]

All data goes through the PCI bus...and it's bandwidth is only 133MB/sec theoretical. So, what does 400/800/anything else greater than about 100MB/sec in a media interface get you? Not much!

Ever read the actual throughput specs on a drive? The media throughput is not much more than 40MB/sec!!! Read the data sheets, people!

Add this all up and what do you get? Ripped off is about it!

Re:too bad that

[Enry]

Haven't seen 64bit PCI busses running at 66 or 133 Mhz, have you?

Re:too bad that

[stratjakt]

> All data goes through the PCI bus...and it's bandwidth is only 133MB/sec theoretical

PCI-X?

> Ever read the actual throughput specs on a drive? The media throughput is not much more than 40MB/sec!!!

4 of them in RAID 0?

> Add this all up and what do you get?

150Mb/s peak bandwidth to and from my drives.

Re:too bad that

[Magila]

1. The "PCI problem" is going to get fixed next year when the next gen busses (Hypertansport, PCI-X, etc.) start appearing on motherboards.

2. That 40MB/s is sustained throughput, HDs can burst from cache much faster than that. This is going to become more of an issue as HD manufactures have finally started putting more cache on their drives.

Re:too bad that

[cheezedawg]

All data goes through the PCI bus

No it doesnt. Data goes through the PCI bus if the address is not claimed by something else along the way. That means that everything from the southbridge up is not limited by the PCI bus bandwidth. That means that integrated SATA controllers (not available until next year) are only limited by the bandwidth between the northbridge and southbridge.

Ever read the actual throughput specs on a drive?

Drive throughput has been steadily increasing, and it is predicted to pass up PATA within a few years, and that is not counting RAID striping or the 8 MB drive caches. Its always desirable for the bottleneck to be the drive rather than the controller.

Re:too bad that

[LuckyJ]

Sure, but how many systems are sold with them? Not many. How many people buy motherboards with 64-bit 66MHz PCI buses? Not many. Even if they were, the drive cannot physically spit out that much data anyway. Check out http://www.maxtor.com/en/documentation/data_sheets /diamondmax_D740X_datasheet.pdf and look at the data transfer speed. Notice now sustained transfers are pretty low! Now check out http://www.seagate.com/cda/products/discsales/ente rprise/family/0,1086,345,00.html. Look at the internet formatted transfer rates...nothing above 50MB/sec there.

Re:too bad that

[LuckyJ]

Eh, that nothing abot 50 should have been 80. Doh.

Re:too bad that

[Magila]

4 of them in RAID 0?

This won't be an issue since SATA is strictly point-to-point, every drive gets it's own 150MB/s link.

Re:too bad that

[ltwally]

For starters, the PCI spec isn't limited to 133 MB/s. PCI 2.1 specs allow for 66 MHz 64-bit transfers, which equals 528 MB/s. PCI 2.2 specs allow for PCI-X mode, which adds 133 MHz 64-bit transfers: 1056 MB/s.

That being said, it is entirely possible to reach throughputs in excess of 133 MB/s using a PCI bus... though currently most desktop motherboards do not support anything faster than 133 MB/s. In time this will change as NICs, hard disks, and other gear requires it.

And your hard disk performance is barely par by today's standards. IDE drives are currently topping 50MB/s, while SCSI gear is hittin > 70MB/s. Though I am a SCSI man, i can see the future need for SATA. Right now it may be mainly a marketing ploy... But in a couple years it will be a necessity. Parallel cabling is nearing the end of the road.. all those wires in a cable allow for too much signal interference. Serial is the answer. Though it has less wires, the dramatic increase in signal strength allows for insane transfer rates.

Anyhoo.. personally I don't see any reason to go out and buy a new system just to have SATA. At the current it offers few advantages.. but in the not so distant future it will be a necessity for desktop systems. As for me, i plan on going Fibre-Channel SCSI :)

Re:too bad that

[Toraz Chryx]

" All data goes through the PCI bus...and it's bandwidth is only 133MB/sec theoretical."

Except of course on boards that have dedicated interlinks between the northbridge and southbridge for IDE/legacy/integrated sound etc.. (VIA KT266 onwards, SiS's recent chipsets, Intel i810 onwards, nForce etc.)

Re:too bad that

[adrenalinerush]

All data goes through the PCI bus...and it's bandwidth is only 133MB/sec theoretical. So, what does 400/800/anything else greater than about 100MB/sec in a media interface get you? Not much!

64-bit PCI buses are being phased in, which have data rates of around 250MB/s.

Ever read the actual throughput specs on a drive? The media throughput is not much more than 40MB/sec!!! Read the data sheets, people!

For typical home use, the data being read is often cached in internal RAM on the drive. When this data is requested, the transfer speed is well above 40MB/s.

Add this all up and what do you get? Ripped off is about it!

What do you get? No more dealing with unwieldly ribbon cables. No more separate power cables. More efficient airflow inside your computer. Faster interface.

Re:too bad that

[runderwo]

Though I am a SCSI man, i can see the future need for SATA. Right now it may be mainly a marketing ploy... But in a couple years it will be a necessity. Parallel cabling is nearing the end of the road..

Then maybe Serial-attached SCSI is the answer.

http://www.intel.com/pressroom/archive/releases/20 020610corp_a.htm

Re:too bad that

[rodgerd]

The media throughput is, yes. At the moment (I remember when my old 4 MB/s Seagate Barracuda were considered quite fast; that was only oin the mid-90s), which will doubtless change as densities and rotational speed increases.

But a large chunk of the performance in a moden drive isn't the platter to interface performance, it's the cache to interface. Adding RAM to a drive is a relatively inexpensive way to improve performance.

Re:too bad that

[Anonymous Coward]

That means that integrated SATA controllers (not available until next year)

Available right now, by the way. I just installed one yesterday.

Too bad they didn't include SATA adapters so that I can actually use the SATA ports with my ATA133 drives.

Re:too bad that

[Anonymous Coward]

Actually thats not an integrated controller. The promise SATA controller is an extra chip soldered to the board that probably does sit off of the PCI bus. SATA controllers that are integrated into the chipset will not be on the market until next year.

More Information

[leibnizme]

Since the site is slashdotted, here are further links about Serial ATA:

Cnet

SATA and ISCSI

Intel Dev Paper

Maxtor White Paper

Re:More Information

[Salamander]

I really love how the Maxtor paper compares SATA to parallel ATA, USB (?!) and Firewire...but not to SCSI or FC. I wonder why that is. Actually, no I don't. ;-)

i dont see a huge rush for people to upgrade

[jkfresh]

I dont think that there is going to be a real reason for people to upgrade their setups just for this new interface. Most new computers are coming standard with at least 60 gig drives. For my mom, who only looks at her email every once in a while, transfer speed is really not that important. Current drives are already plenty fast.

Re:i dont see a huge rush for people to upgrade

[Anonymous Coward]

Psst.

Don't look now, but you're momma dont drive the hi-tech industry.

I do.

Re:i dont see a huge rush for people to upgrade

[Hadlock]

i think the idea is savings on the hardware manufacturer's end, not the consumer.

serial cables are infintely cheaper than parelell cables. there's less chance of not connecting them properly, or breaking them as there is with parelell cables (don't tell me you've never heard of someone bending a pin on a hard drive before). USB, firewire & others don't have this problem, as they're single orientation (or at least more obvious than parelell). this increases the productivity of assembly workers and thus cheapens the process.

it's more expensive in the short term, but since the technology is inherently cheaper, the initial costs balance the long term savings. computers should start shipping with serial ATA as soon as the next chipsets come out for intel/amd. your mom (or mother in law, as your mom already has a computer) may have serial ATA before you do, and not even know about it.

Re:i dont see a huge rush for people to upgrade

[rodgerd]

s/hardware manufacturer/OEM/

Dell will be drooling. Cheaper cables that are easier to install will be a big win for them.

Not important yet

[thetzar]

I can't wait to get my hands on some SATA devices. However, we're still stuck with PCI, here on the desktop end. WHEN will we finally start seeing the old original PCI spec phased out on the desktop end? Not until then will new technologies like SATA be able to shine. Bus bandwidth is everything these days.

Re:Not important yet

[Anonymous Coward]

Gee, where have you been? The latest chipsets on the PC market skip the PCI bus for a lot of things. The latest offering from SIS has a south bridge with a 1 GB/s max bandwidth, and if it had a Serial ATA controller on it.. Well, I don't think I need to go on.

Re:Not important yet

[Cyno01]

hopefully soon we'll be seeing AGP8 mobos w/ multiple agp slots and then finally agp cards, then SATA will get a foothold

Re:Not important yet

[illumin8]

Infiniband will be the replacement for the PCI bus. For more information, see the Infiniband Trade Association. It offers speeds of 2.5 Gbps, 10 Gbps, and 30 Gbps. It also allows multiple hosts to connect to an "Infiniband Fabric", where they can share I/O devices. Don't expect to see desktop implementations for 5 years or so, but server implementations will be out in the next few months in the form of a PCI-to-Infiniband adapter.

RDRAM Redux

[grendelkhan]

This sounds remarkably like the plugs we got for Rambus RDRAM: serial interface is better than parallel, first gen won't see real performance gains, stick with us kids, this is gonna be really good.

I see a decided lack of Sun, IBM, AMD, or HP listed in the adopters, which leads me to believe that this is much like the above. Sorry guys, I'm not riding the first wave of any new tech on my salary. I'll sit on the sidelines for awhile and see how this pans out.

Re:RDRAM Redux

[Magila]

Excpect SerialATA is actualy cheaper to implement than ParallelATA and there's no latency issues like those that killed RDRAM, SATA is unquestionably faster than ATA100. SATA will be taking over in place of parallel, it's only a matter of time.

Re:RDRAM Redux

[MtViewGuy]

This is NOT RDRAM redux.

For one thing, both the Intel and AMD camps are heavily supporting Serial ATA, with the first motherboards that have Serial ATA connectors starting to appear on the market as I type this. Not only is the throughput going to be way higher than standard dual-conductor IDE cable connections for ATA-33/66/100/133, but because Serial ATA cable is a small rounded cable this means there are no wide flat ribbon cable connections; this makes for a much neater-looking system case interior and also means better system case cooling as a side benefit.

I expect the first CD-R/RW and DVD-R/RW drives with Serial ATA connectors to hit the market any time now.

Re:RDRAM Redux

[vnsnes]

IBM's name is on the front page of the SATA specification.

I want a

[edbarrett]

Serial ATA Network.

Re:I want a

[Hadlock]

i'll second that. until then, windows XP has TCP/IP drivers for firewire, which is 400mbps, and just around the corner, 800mbps. firewire can also go longer distances than SATA

what the fuck?

[Anonymous Coward]

basic IDE technology has been around for nearly twenty years. When the lifetimes of other computer components like CPUs and video are measured in months, twenty years ago seems like prehistory.

Would someone buy this fuck-tard a clue? Your top of the line P4 xeon is, when powered on, a fast 8086! Your Keyboard will plug into an IBM PC from the early 80s. The only difference is the windows key and maybe some "internet" keys. VGA is 15+ years old, and SVGA 10+. The only thing that's been retired in the x86 pc world is the 5.25" drive. Almost all consumer sound cards include sound-blaster 16 emulation.

Re:what the fuck?

[Anonymous Coward]

The point is that cpus and video become outdated very quickly as the technology grows. IDE has "just been there." It doesn't seem to get much attention.

Re:what the fuck?

[Anonymous Coward]

> Your top of the line P4 xeon is, when powered on, a fast 8086

No, but it's backwards compatible. I don't remember 8086 being highly pipelined, having an integrated FPU, and MMX and SSE/2 instructions.

> Your Keyboard will plug into an IBM PC from the early 80s

They had USB in the early 80s?

> VGA is 15+ years old, and SVGA 10+.

Thats close to true, but irrelevant

>Almost all consumer sound cards include sound-blaster 16 emulation

That would be a software emulation - they aren't register compatible.

The common thread? That they're all backwards compatible. As will be PATA.

If I wanted my next computer to be incompatible with this wall of media behind me, I'd buy a mac. (Not an anti-mac troll, just saying)

Re:what the fuck?

[Cyno01]

i wish i could find a USB 5.25" drive, i dunno why, but that'd be cool

Re:what the fuck?

[dan the person]

IDE also becomes outdated very quickly.

Try plugging your 7200RPM 120Gb IDE drive into a 386 era IDE controller and see what sort of performance you get. You'll probably only be able to access 8Gb of its capacity also.

IDE hasn't "just been there" it has been constantly evolving.

I'm waiting....

[Audacious]

I'm waiting until the Nth revision comes out on the SATA drives. ;-)

SCSI TROLLS: READ THIS

[Vengie]

For all of you waxing locquatious on the merits of scsi....please read the article, noticeably:

SCSI drives are notorious for their noise, heat and vibration levels. These low points are not acceptable at the consumer level. Noise and heat don't matter too much in huge server rooms, but they can quickly become a problem in desktops. Unfortunately, this means that the extremely low seek times and high spindle speeds that make SCSI drives so fast are not available in consumer market. Basically until cooler, quieter, smoother drives can be manufactured in high volume, desktop hard drives will continue to make baby steps in speed.

For the time being, IDE isn't going anywhere.
NOISE & HEAT will tend to outweigh (relatively) minor performance gains in consumer systems. (Enterprise hardware is another matter entirely)
sigh....we need to start using those annoying javascripts that make people read the article BEFORE posting.

Re:SCSI TROLLS: READ THIS

[Drogo Knotwise]

Not to mention the #1 stumbling block for most people: price. SCSI costs significantly more for comparatively little actual performance benefit. On a server, which is hard-drive intensive, this performance difference is big enough to make SCSI worthwhile. On the desktop, on the other hand, it costs more, allows smaller sizes, and apparently makes more noise and heat. No wonder IDE is here to stay...

Re:SCSI TROLLS: READ THIS

[helzerr]

SCSI is a bus, IDE is a bus. Usually busses (as found in PC's) don't make noise or heat.

There is no reason a cool quiet IDE drive couldn't also be sold with SCSI interface electronics.

Re:SCSI TROLLS: READ THIS

[Anonymous Coward]

Before using a word like loquacious you should be sure that you know how to spell it.

Re:SCSI TROLLS: READ THIS

[mosch]

That has nothing to do with SCSI. The only reason it's even remotely related is because people have a tendancy to buy SCSI drives like this one, which is a 15K RPM drive with a 3.2ms seek, and the ability to sustain a 75MB/sec data throughput rate, whereas high-end ATA drives like this one spin at 7200 RPM, have a 9ms seek, and don't list their maximum sustained data throughput rate on the data sheet.

Is IDE appropriate for the desktop? absolutely.

Will retards continue using IDE in applications where SCSI is far more appropriate? definitely.

Does your post make any fucking sense at all? nope.

Re:SCSI TROLLS: READ THIS

[colenski]

Depends how you use the workstation. Ever try to burn a CD, rawrite a floppy, and do heavy HD copying at the same time on IDE? Painful. Sometimes seems like the workstation is hung. I've seen and configured myself P-II's w/ AHA-2940's and Plextor CD burners / Micropolis (ah, the olden days!) hard drives that subjectively ran rings around P4's w/ ATA-100 when the system is under disk load. Response time is a zillion times better, seems to me, with SCSI than with IDE. Granny may not notice the difference downloading Klez, but every goddamn Slashdot reader is gonna know the difference.

Re:SCSI TROLLS: READ THIS

[dubiousmike]

zing

Re:SCSI TROLLS: READ THIS

[Anonymous Coward]

Does your post make any fucking sense at all? nope.

I'm not so sure about that.. think about it.

He says "SCSI TROLLS: READ THIS"..

Then proceeds to write a SCSI-related troll.

Makes perfect sense to *me*.. i mean, think about it, the BSD trolls weren't pro-BSD either .. :)

Re:SCSI TROLLS: READ THIS

[Ed Avis]

I'm surprised disks aren't sold with both interfaces, SCSI and IDE (perhaps using a small external dongle to make the plugs fit). It sounds like it would be cheaper to have a single production line for both.

Re:SCSI TROLLS: READ THIS

[Null PTR for Lunch]

I happen to find that characteristic roar of my computer's SCSI drives lends a soothing aspect to the environment of my room :) Who cares if the machine sounds like a starship :P

command queueing

[Tester]

I think I read in somewhere that SATA could do command queueing. Does that mean that it will allow the driver to re-order them like SCSI drives? That was, I think, one of the main advantage of SCSI over IDE/ATA drives.. That they could re-order the commands and send answers in a different order to maximize performance.

Re:command queueing

[cheezedawg]

Yes- but AFAIK command queuing is not implemented in a lot of the 1st generation controllers because it can break backwards compatibility with PATA software. Most vendors went for an easy upgrade path instead. Look for command queuing in the next generation of controllers.

Re:command queueing

[bjschrock]

Most of the command queueing and multi-threaded operation in SCSI devices is implemented in the device. I think the protocol can handle re-ordering, but it's up to the device to figure out what order it wants it's data in... It is a bit interesting to send some write commands to a hard drive and then have it come back and ask you for the data in a different order that it decided was best.

whats new?

[nonane]

narrower flexible cables is all the SATA has to offer? its like switching from a two-headed screw driver standard to a philips one. the heads are different but the screw gose in the same way. give me a few features of SCSI in an affordable package and then your talking.

on the other hand: installing more ram/new-cpu wouldn't be such a pain .. 2 hard disks, a dvd and cd writer later your computer would have enough ribbons to host a toddlers birthday party. and to get rid of the freaking master/slave shite ... ahhh. damn it I want SATA!

Re:whats new?

[Anonymous Coward]

what's new you say?

That you actually got a 1 mod instead of the usual -1. j/k

It's not like "switching from a two-headed screw driver." It is more like asking the marketing department: what can we do to increase revenue, use existing parts and stay lazy?

The answer in one part was round cables... Come on, are you going to buy that sales phrase "increases air flow?" :P

Re:whats new?

[Cyno01]

round cables do help, when u've got 6 drives in a case (dvd, cd-r/rw, floppy, zip and 2 HDs, it can get pretty crowded, round cables do help airflow quite a bit, and every few degrees helps

Re:whats new?

[Hadlock]

not to mention SATA cables are cheaper for the manufacturer, & they increase air flow

Re:whats new?

[Noehre]

You have an IDE floppy? Impressive.

Re:whats new?

[Cyno01]

round floppy cables

Re:whats new?

[Anonymous Coward]

If you plan the design of a case well, you shouldn't need round cables for better air flow on a smaller system. But if you have 4+ drives, it may get a bit crowded, so I can understand that.

I want the connector!

[aronc]

Personally, I could give a rats butt about the speed. I don't want SATA so my drives go faster. I want it so I'm not having to spend twenty minutes doing finger gymnastics everytime I need to do _anything_ in my case.

Is it worth upgrading for? No, probably not. But id damn sure is worth waiting an extra few months for that next machine to save the hassel of those f'ing ribbon cables.

Re:I want the connector!

[HoneyBunchesOfGoats]

From the Cnet article: Parallel ATA ribbon cable is about two inches wide and can be only 18 inches long. The Serial ATA cables can be made up to three feet long, allowing for more elaborate routing, which would aid in creating cooler-running PCs. This just isn't true. For those who want narrower, longer cables, there are solutions available. I am currently using 36 inch long ATA/133 rounded cables, which I bought from Cable and Connector Technologies for $5 each. Yes, rounded cables to hurt the performace a *tiny* bit, but what drives run at 100% of their peak capable performance anyway? It is more than worth the extra length/reduced hassle that the rounded cables provide.

Re:I want the connector!

[Anonymous Coward]

What!? Only 20 minutes? Those f'ing ribbon cables kept me going for 2 hours straight once!

Re:I want the connector!

[Null PTR for Lunch]

Can i say.... Waah? I've been working on these things for 9 years and it sounds to me like you're just whining. Ribbon cables are not hard to remove or re-attach. Dexterity: 3 ;)

Re:I want the connector!

[aronc]

Can i say.... Waah? I've been working on these things for 9 years and it sounds to me like you're just whining.

I've been working on them for 12.. but anyway. It's hardly 'whining'. Those cables are a true pain and if I can get rid of them at no extra cost, why not? It's not like I'm blindly bitching about the current standard just to hear myself complain. Just voicing a positive (the best one, imho) of a new standard that's about to become available.

Re:I want the connector!

[aronc]

I am currently using 36 inch long ATA/133 rounded cables, which I bought from Cable and Connector Technologies [callcct.com] for $5 each. Yes, rounded cables to hurt the performace a *tiny* bit, but what drives run at 100% of their peak capable performance anyway? It is more than worth the extra length/reduced hassle that the rounded cables provide.

Having used rounded cables before (not currently, but before) and having messed with the SATA connectors on a product demo I can say that SATA beats them hands down, no contest. Did we really need a new standard for this? Nope. But they did it anyway. Would I pay extra for it? Maybe a few bucks.. say like the 5 or so the rounded cables would cost me.

Re:More "standards"

[billd]

I hope the connectors are keyed properly. It looks like a pin is offset, so that's good. I always hated when the key block is missing or shaved off the old IDE cable and you had to figure (guess) which way round it goes. This new system looks good. Bring it on.

ridiculous

[tps12]

Why are they wasting their time on this ancient technology? Serial is too slow to sync my damn Palm Pilot. I can't even imagine what it would be like to try and transfer 60GB of media files over it. These companies should just accept that USB is the way of the future (no extra power required either!) and get to work on something that stands a chance of selling.

Re:ridiculous

[Anonymous Coward]

Just checking, but you are joking, right? You didn't lay the sarcasm on thick enough for it to be obvious.

Re:ridiculous

[Jerf]

I especially enjoyed the hidden joke about U S B.... (hint: what does the S stand for?)

Cute!

Re:ridiculous

[LS]

Easily categorizable "humor" is a waste of time for those who's age is in the double digits. The category for your humor would be "misinterpreting a word to be that of an inferior sort, and responding with a straight face". Next time, review your jokes before you post them. Now move on, son...

Re:ridiculous

[Goalie_Ca]

Hey, that's what i was thinking. Very subtle humour, or a totally large moron!

Re:ridiculous

[chrisvdp74656]

You may want to check your acronyms before you spout off about serial interfaces' downfalls.

USB == Universal Serial Bus.

Chris

Re:ridiculous

[Anonymous Coward]

thankfully, your post was easily categorizable "unhumor"

Re:ridiculous

[Anonymous Coward]

You may want to check your acronyms before you spout off about serial interfaces' downfalls.

No mystery as to why you are not posting at +1.

This is a GOOD thing. FINALLY

[krray]

I've been waiting for Serial-ATA ever since reading about it. Faster speeds/bandwidth - which is actually finally needed in the IDE type world.

NO MORE RIBBON CABLE. My favorite Linux configuration is 1 whatever IDE drive for the OS, 1 IDE CDROM, and two (RAID-1) large IDE's for data and configurations. Quick and cheap for non-critical type functions/services. I rolled through a complete failure on the core OS drive, CD died -- while trying to roll up in size on the RAID-1 and hit *FOUR* defective WD drives...while never losing data _and_ configurations. IBM sits in there right now... :)

High end servers and workstations? Yeah, Serial-ATA is nice with the coming 40M/sec IDE type drives...but I'm also going to go after that 320M/sec SCSI technology too. Same IDE game, just a different connector basically.

NO MORE RIBBON CABLE.

Try stuffing four drives in a case. Not only is the IDE chain full, but cabling is a complete joke. Not anymore. Kind of like Firewire in the box, if you will. Except I think their screwing it up and keeping power separate where Firewire _can_ cary power to the devices.

So instead of tiny IDE connectors in the current Firewire and external type drives there will be tiny Serial-ATA hookups. So what. Now get inside a PC (and/or Mac) and do a little work.

With this and pricing for LARGE amounts of data ... I could see easily wanting a tall tower (remember those?) and building a rock and roll back end storage system for personal use. Quick and cheap ... and now VERY EASY to do. Personal RAID-50 500G personal array anybody?

I could record so many hours of anything I wanted and never worry about losing it ... even with el'crap-ola IDE no-warranty technology.

Of course when I have a few extra thousand lying around (not likely any time soon with the current economy outlook) I'd love to try SCSI-320.

Now, IDE is rolling into ~40M/sec. Firewire *has* been ready for those speeds for a while. At least USB2 can keep up for a bit as well. Even faster drives is a must though. Firewire-2 is just around the corner (either 800 or 1.6Gbit's).

It's sad that your typical/standard Mac type network (1Gbit) is faster than the typical drive being hosted. Your typical Windows network at 100Mbit is pretty muched caqpped by the current typical drives top performance at 10M/sec.

Serial-ATA, oh yeah. One card (1Gbit) in the Linux box and I could saturate their bandwidth. Why not?

Microwho?

Re:This is a GOOD thing. FINALLY

[NineNine]

This post is an *excellent* example of what watching too much super-fast cutting TV (like MTV) can do to you.

Re:This is a GOOD thing. FINALLY

[chez69]

perhaps it is the markov bot back in action

see this guy's posts

Re:This is a GOOD thing. FINALLY

[kentborg]

> My favorite Linux configuration is 1 whatever IDE
> drive for the OS, 1 IDE CDROM, and two (RAID-1)
> large IDE's for data and configurations.

Why not put Linux on the raid 1? Bootable software raid 1 works. You can have your OS be redundant. You also would need fewer IDE controllers. Assuming the CD use is relatively infrequent, two ide controllers will do you well with each drive effectively getting its own controller, and that means speed.

-kb, the Kent who has become a software raid 1 fan.

Re:More "standards"

[billd]

Oh yeah, and I hope this will lead to a STANDARD for removeable drive cannisters too!

Huh?

[WD]

What on earth does the type of interface have to do with heat or noise?

Re:Huh?

[hatchet]

What good is SCSI interface without GOOD scsi drive?!
In order to use SCSI in it's full potential.. you need 10k or 15k RPM drive.. and those things are loud.

Re:Huh?

[trevinofunk]

You see,

The interface and the heat/noise form a symbiote circle. You must realize that.

SATA Linux Support

[yamcha666]

I noticed this little remark:

... although it wont officially be supported until Microsoft's Longhorn OS, Serial ATA devices will work with all versions of Windows.

And this made me wonder... how long will it take until Linux (and the *BSDs) support this new standard? Will it happen after Longhorn's release? Or has it already been done?

Re:SATA Linux Support

[stratjakt]

It's completely transparent to the OS. So far as linux is concerned, it's just the same as parallel.

Re:SATA Linux Support

[jensend]

Serial ATA support is in Linux 2.5.35 and up, as noted here.

Re:SATA Linux Support

[Anonymous Coward]

all versions of Windows

Including 3.1?

Bandwidth

[vlad_petric]

Serial is the wave of the future, and it will give ATA hard drives the bandwidth and features to compete with SCSI.

I don't get it ... I quite agree that, as a serial bus, it'll be clocked a lot faster than IDE ... but a simple back-of-the-envelope calculation tells us that it has to be at least 8 times as fast as the current devices (it'd have to be 533 MHz to be on par with ATA-66)

It looks like a technology whose main purpose is to make things incompatible, and thus require people upgrade more stuff. And anyway, it's not the speed of the bus the limiting factor (for the vast majority of users), but the mechanics of the harddrive (SCSI hardrives are faster than IDEs because they almost always are top-of-the-line products with higher rotational speeds - anybody saw a 15000 RPM IDE ?)

The Raven

Re:Bandwidth

[TheGratefulNet]

scsi drives share the same rotational stuff as ide cousins. just translate different host language to the disk itself.

I'm a big believer in scsi, don't get me wrong. but its only the controller that's different (the one on the drive itself).

there's no technical reason for why ide can't be 15krpm. its pure marketing.

and besides, thinner cables that can run longer are MUCH nicer than fat parallel ones (like scsi and current ata).

Re:Bandwidth

[Francis Avila]

It looks like a technology whose main purpose is to make things incompatible, and thus require people upgrade more stuff.

I was under the impression that it was possible to connect a P-ATA drive to a S-ATA controller using a physical adaptor--i.e., that it was fully backward-compatable. Is this no longer the case?

Re:Bandwidth

[rweir]

a simple back-of-the-envelope calculation tells us that it has to be at least 8 times as fast as the current devices

You needed an envelope to calculate 8x=8x? Geez, schools these days. Back in my day...:)

Re:Bandwidth

[vnsnes]

Data transfer rate of SATA physical layer is 1.5Gb/s. See page 37 of the SATA spec.

SATA Optical Drives?

[OutRigged]

I've seen SATA hard drives from a bunch of companies, but where are the SATA Optical drives? I know they wouldn't exactly benefit from the added bandwidth, but I'd rather have all my devices on a SATA controller, with it's thin cables, then my hard drives on SATA, and my optical drives on PATA.

Re:More "standards"

[Wesley Felter]

Serial ATA connectors are keyed and designed for hot-swap.

IDE TROLLS: READ THIS

[darkwiz]

SCSI drives are notorious for their noise, heat and vibration levels. These low points are not acceptable at the consumer level. Noise and heat don't matter too much in huge server rooms, but they can quickly become a problem in desktops.

For the time being, IDE isn't going anywhere.
NOISE & HEAT will tend to outweigh (relatively) minor performance gains in consumer systems. (Enterprise hardware is another matter entirely)
sigh....we need to start using those annoying javascripts that make people read the article BEFORE posting.

Absolutely. But this has nothing to do with SCSI, it has to do with the high spindle speeds at the bleeding edge. The card on the underside of the drive is not making that ear shattering racket. They even acknowledge that in your quote.

SCSI is better than ATA. Even SATA. ATA has been trying to catch up by stealing some of the best parts of SCSI (like TCQ). But it just isn't quite as good yet. Quite frankly, I agree with the majority of SCSI zealots: if the damn PC makers would embrace SCSI, then the cost of SCSI would come down to near parity from the volume of sales.

Now, is SCSI better for your average Joe? Maybe not significantly. Neither is 7200 vs 5400, 2MB vs 8MB buffers, or 8.9 vs 9.1 ms access times.

However, if they could use one cable to connect 15 devices in their tower, they'd be alot happier than having the 8 cables they'd need to do it with current IDE tech (let alone IDE's relative inability to be used externally).

Re:IDE TROLLS: READ THIS

[figa]

> if the damn PC makers would embrace SCSI, then the cost of SCSI would come down to near parity from the volume of sales.

This just isn't the case. Apple products used SCSI exclusively for at least a decade and sold a pretty high volume of them. There were even SCSI scanners and a whole slew of SCSI external drives before USB. I still have an Adaptec SCSI card that came free with a scanner. All this never made a dent in SCSI prices.

SCSI had its chance on the desktop and blew it.

I'm writing this on a SCSI-based box, so I know how smooth-n-creamy the SCSI experience is. The problem was, SCSI had to be cheap before it would be adopted over IDE, not the other way around. Now more than ever the performance doesn't justify the price, unless you have an IT budget.

This is the one to watch

[Gerry Gleason]

It looks like it is designed correctly from a physical standpoint. Hot swap should and blind mating should be part of the program. I looked at it in some detail a while back. They even planned for progressive mating of the ground first. All the big drive manufacturers seem to be behind it.

The only thing I haven't seen is any noise about chip sets that support in on the system side. As soon as these are available, you'll see MBs and systems. SCSI will probably stay important for larger faster arrays, but scaling bandwidth seems to look pretty good for this as well.

As soon as mainstream MBs are there, these will quickly become the commodity drives for all the manufacturers, and they will phase out Parallel ATA stuff.

Obligatory crazy conspiracy theory

[spun]

They are implementing this new standard rather than utilizing firewire so They can create a whole new generation of "trusted devices" and make us all buy them.

Those are already obsolete

[Anonymous Coward]

You didn't think much before you wrote that, did you? SATA isn't going to render all parallel ATA devices obsolete overnight, but this is the introduction of what will replace them. Just like USB's introduction was the dawn of the death of the parallel, serial (RS232), keyboard (as well as floppy) ports on PCs, and the introduction of DVI was the eventual death knell of the VGA port.

This will be a big deal for SoC (system on a chip) development, since finally it will be cost effective to put all the stuff on a PC motherboard onto a single chip for low end boxes, that chip need only have a board large enough to interface with a power supply and provide some USB ports, SATA ports, enet, and DVI. In two years you'll see complete PCs (sans LCD) the size of a CD-ROM drive sold for $100 due to this, which will further aid the spread of technology into less affluent countries.

Portable storage potential?

[djkitsch]

Since this seems to support hot-swapping, how about adopting it as a standard for portable storage devices? A few SATA ports on the back of my laptop wouldn't go amiss, and you could use drives either internally or externally.

On top of that, it's faster than Firewire/i.Link and USB2.0. Sort out power supply and it'd be invaluable.

Dunno about anyone else, but I'll be VERY glad to see the back of all that master/slave crap, twisted ribbon cables and so on.

Re:More "standards"

[cscx]

The red stripe points towards the power supply connector, or marked pin 1 on the mobo. That's SOOO difficult. 8-)

Firewire Drive != Pure Firewire

[nuxx]

Note that almost all the Firewire hard drives that you see on the market are ATA hard drives with FirewireATA hardware in the enclosures. As far as I'm aware, the only disks that you can readily get your hands on will have interfaces of IDE/ATA, SATA, SCSI (of various connectors), and FC-AL. That's why you can't use Firewire inside a PC. Using SATA makes far more sense, especially for migrating to a new standard, as it's most likely easier to make a SATAATA adapter since the protocol is very similar.

Re:Firewire Drive != Pure Firewire

[Random Data]

it's most likely easier to make a SATAATA

Isn't that a cracker?

Logic?

[wyrmBait]

> (less wires = less logic).

If you've ever looked at the circuit diagram for a simple multiplexer, you'd take that back. Really, how complex the is logic depends on what you want to do with the data off of those wires. To really simplify the idea: if you use serial, you've got to have a muxer/demuxer on the end of that line, and if you use parallel you need to have a clock to syncronise communications on those lines.

In any case, the difference in circuit complexity due to parallel vs. serial, even if one required less than the other, would be a few orders of magnitude less than the complexity of the circuits required to manage the disk itself.

SATA == Future

[nuxx]

Note that Sun, IBM, AMD, nor HP are disk manufacturers. (Well, IBM might still be, my memory is being bad tonight, but I digress...) Some AMD and Intel motherboards are already coming with SATA RAID interfaces. Intel is right behind the technology, as they are a chipset manufacturer. AMD isn't. VIA, a chipset manufacturer is, along with a ton of other manufacturers who are core to desktop/workstation storage. Just because the big power houses that you name aren't on board doesn't mean anything. Most of these places leave their disk interfaces up to someone else. And those companies *are* adopters.

Re:SATA == Future

[Noehre]

Funny, I have an AMD 760MPX chipset on my motherboard.

How could they possibly do such a thing as you say they don't make chipsets!

My world is on end!

Oh btw, AMD's Hammer chipset is one of the few first-generation Hammer chipsets that will support onboard SATA.

Re:SATA == Future

[nuxx]

Doh. Sorry. My bad. When I think of AMD boards I generally think of VIA (or SiS, ick) stuff. I guess I'm forgetting the wonderful AMD PCnet32 chip that's powered so many different workstations and servers without a hitch. I shouldn't forget all their other semiconductors, either...

Re:Give me Firewire!-here we go again!

[Anonymous Coward]

http://www.adaptec.com/worldwide/product/markedito rial.html?sess=no&cat=%2fTechnology%2fFireWire-139 4&prodkey=1394_summary&type=Technology

# Data transfer rates of up to 400 Mb/sec with 1.2 Gb/sec speeds in development

Serial *is* better given todays technology

[egarland]

It's not about "wow" factor or buzzwords. Serial ATA is better. They can transmit 150 MB/sec over a single pair whereas PATA's 80 wire cables can only transmit 133 MB/s which is split between 2 drives. Now, with SerialATA, instead of having 66 MBytes/Sec/Drive you have more than double the bandwidth per drive and the cabling is smaller even with a separate cable for each drive.

I'm no communications expert but I believe most modern high speed serial connections could not be economically put in parallel since in parallel, all the bits need to be clocked together and the modern serial protocols are not designed to coordinate with anything but the other side of the connection. Instead you would need to multiplex the connections on a much higher level and that becomes difficult and expensive (ALA equal cost multipath routers).

I think what is happening is they are figuring out that it's cheaper to put seriously complicated technology on either end of a single pair of wires and keep the cabling small and simple.

SATA saves money in a bunch of ways:
o It keeps the pin count low on the chips
o It keeps the motherboard real estate down
o It keeps the cabling cost down.

It also has better features:
o It's faster
o It can be made hot-swappable
o Cables are smaller and can be longer and will be cheaper
o It has a more reliable hub and spoke architecture which should eliminate most interoperability issues.

Not with 3ware's solution

[Anonymous Coward]

Look at the 3ware website and check out the Escalade 8500 series SerialATA controllers. Up to 12 drives in a RAID5 set, or JBOD, WITH hot swap and removable tray configurations (from some VARs). Yeah, they're brilliant to be sure.

Command Queuing in SerialATA-II

[Anonymous Coward]

Click here for the full spec. SATA-II will likely usurp SCSI for all enterprise applications that don't require low random-access latencies (which is nearly nothing these days, comparatively speaking).

Am I missing something here???

[Lobsang]

I think I am. Really.

The article seems immensely biased and lacking in technical detail. It also raises some "dubious" points IMHO. Let's see:

- P-ATA cables cannot be longer than 40cm. S-ATA cables can be up to 1m long:

Granted, those cables are annoying. But really, how many times have you felt the need for a cable much longer than 40cm? People with full-sized cases may benefit, but then the author says that the current trend is "small footprint machines". So, why do I need a cable that is bigger than my server?

Also, if you dislike flat cables, buy "rounded" P-ATA cables (available today, just google for it).

- P-ATA connectors are big!

Yes, they are! But you'll require at least twice as many S-ATA connectors, as only one device is supported... In the end, the real state on the mobo is going to be similar.

- One device per controller is an "Advantage".

C'mon... This guy must be joking. I couldn't believe my eyes when I read it! One device per controller is an *advantage*???? Why??? I wish I could add more devices (like SCSI and Firewire) to my curreny P-ATA technology. And then he says ONE is good for me? Don't think so...

- High transfer rates are useful for multi-disk RAIDS.

What kind of RAID? RAID 5 is slow in writes due to the computational power needed to calculate the XOR. Adding bandwidth won't help. And I can't see why or how only RAIDs will benefit from higher throughput.

- Speed:

Granted. It may be faster than P-ATA. But what about established technologies like SCSI and Firewire? I *think* (not sure) Firewire can go much faster than S-ATA in its initial version.

I'm disappointed...

Re:Am I missing something here???

[Kevin Stevens]

Longer, thinner cables are a huge advantage. As processors start catching up to space heaters in the amount of heat they throw off, airflow is ever more critical in a case. Ribbon cables can really screw up the flow in a case. In the case of meter long cables, they could even be ran along the side of the case. And do you honestly like ribbon cables? serial ata will have a keyed connector... no more guessing as to which way it should plug in. Similarly, one device per header should reduce aggravation between master and slave drives. Have you seen the size of the new headers? They are smaller than half the size of the ribbon connectors, and also, since there are fewer data lines, there is alot less space needed on the mobo for connections. And yeah the speed will be faster. Serial ATA was never intended to be a major milestone in computing like the article hypes it up to be. However, it IS an improvement, and a step in the right direction. I personally can not wait until I build a system without those dreaded annoying ribbon cables. Its nice, its better, it IS backward compatible (they will sell adapters to convert the two connections). You are not losing anything here, but you are gaining some nice advantages.

Re:Am I missing something here???

[helzerr]

As processor's catch up with space heaters, I doubt they'll be as likely to be air cooled.

P-ATA connectors are keyed. There is a mechanism called "cable select" that essentially auto-configures IDE chains.

Re:Am I missing something here???

[Anonymous Coward]

Rounded PATA cables have problems with data corruption. Normally they're stretching the limits of signal shielding in a standard cable, when you pick them apart like that and bind them up; they WILL interfere with each other as each signalling cable is shielded by the cable next to it (as opposed to having lots of signalling cables surrounding it).

SATA is faster then firewire by a factor of at least 3 (SATA will initially be 1.5 Gbit/s vs Firewire's 400 Mbit/s).

Also, with a little thought, I can see how SATA cabling can be used for LVD daisy chaining as long as there's sufficient power and there's signal termination. Undoubtedly this will take a change in SATA, but not an impossibility. ^_^ Might be worth a Ph.D project.

Re:Am I missing something here???

[Anonymous Coward]

- Granted, those cables are annoying. But really, how many times have you felt the need for a cable much longer than 40cm? People with full-sized cases may benefit, but then the author says that the current trend is "small footprint machines". So, why do I need a cable that is bigger than my server?

Quite a lot of people have been bitten by the IDE cable length restriction. The only way to use the top drive bay in a full tower case is to use an out of spec case, or use an PCI IDE controller in the closest PCI slot. Besides the SATA cables are much smaller, they are also much more flexible so they are useful for lots of reasons: eg:

a) Route the cables out of the way, no longer do you have to remove drive cables to access poorly positioned RAM, etc

b) Smaller thiner cable, make for better ventalation which is desirable in both cutting edge gamer boxes and in mini PCs.

c) You no longer have to worry about multiple drives on the one cable, each cable is independent, useful for either neatness, or for cable patterns in show boxes (gamer, with neons, etc).

-Yes, they are! But you'll require at least twice as many S-ATA connectors, as only one device is supported... In the end, the real state on the mobo is going to be similar.

RTFA! I mean they had pretty pictures and everything. 2 SATA = 25% area of one PATA connector. Obviously a plus for either miniturising the motherboard, or for making room for more features (Dual ethernet).

-C'mon... This guy must be joking. I couldn't believe my eyes when I read it! One device per controller is an *advantage*???? Why??? I wish I could add more devices (like SCSI and Firewire) to my curreny P-ATA technology. And then he says ONE is good for me? Don't think so...

I have not yet seen a single controller where you end up with less useable drives than a traditional IDE setup (2 channels, 4 drives). And this is an advantage. Why? A Master/Slave arrangement is horribly inefficient, it causes not only bandwidth sharing but also latency issues. Not a problem on a 4 channel SATA solution, and with no useable loss.

-What kind of RAID? RAID 5 is slow in writes due to the computational power needed to calculate the XOR. Adding bandwidth won't help. And I can't see why or how only RAIDs will benefit from higher throughput.

Depends have the RAID controller is implemented, it can be either integrated so that it communicates directly with the south bridge (SATA no advantage), or it can appear as a logical drive over a normal IDE channel (advantage). However the former is the most common method.

As for your comments on RAID, don't confuse a RAID methodology (1,2,3,4,5,50,etc) with the number of drives. You can have 20 disk RAID 1 sets if you like , which would definately overload a single SATA channel iff using the latter method in the above paragraph. RAID 5 write speed is not _slow_, It would only be a problem, if the drives were being continuously written to, in which case RAID 3 is a better idea. Burst writes are handled by both the controller's and the drive's cache.

RAID 5 controllers have their own dedicated CPU's (commonly i960s) to do the relevant calculations. The speed penalty is very tiny, and the difference from a single non-RAID drives performance is slight. Remember the controllers are spec'd to be able to reconstruck data on the fly, and practically all drives read faster then they write.

-Granted. It may be faster than P-ATA. But what about established technologies like SCSI and Firewire? I *think* (not sure) Firewire can go much faster than S-ATA in its initial version.

SATA is really IDE over SATA, IDE is emulated on a different faster data link. There is in fact a SCSI over SATA standard proposed as a cheaper alternative to Fibre Channel (Another SCSI emulated over a serial data link standard). SCSI theoretically already has a faster standard (Ultra 160 and Ultra 320) but these are buses, that is all 7 (or 14 for wide) devices must share that bandwidth, wheras SATA is a peer to peer technology, one device only. The difference will only be usefull with integrated RAID controllers and/or when you have the money to buy enough drives to saturate a PCI-X bus.

Firewire (1st gen) has 400Mb/sec, SATA 1.5Gb/sec
Firewire (2nd gen) has 800Mb/sec, SATA (II) 3.0Gb/sec (Faster than the current AMD platforms FSB at 2.4Gb/sec)

Road map also includes SATA (II) at 6.0Gb/sec

-I'm disappointed...

You need to do research...

Re:Am I missing something here???

[Anonymous Coward]

1 device per interface is the way to go for high speed interfaces - you don't have signal reflections limiting the speed of the interface. It is like having multitaps on the cable TV - the more you have, the poorer pictures you'll get. Remember 1.5Gbps is the first stop. Having multiple drives with multiple 1.5Gbps links are nice.

1m is about the right length to go outside the white box PC into an external case for external drives. I would love to put all the drives in a well cooled case for extra reliability.

Re:Am I missing something here???

[CharlieO]

Cable Select essentially auto-configures non disk devices

So your hard drive still needs to be flagged master if you want your OS to boot.

But it does mean newbies can plug a CD-ROM device in thats been delivered in CS mode, and its controller will be slave if its bundled next to a drive, master if its got the cable to itself

Why not firewire?

[splorf]

Unlike some here, I'm not fond of SCSI (obnoxious cabling and termination issues even worse than ATA). But Firewire seems to have every advantage claimed for SATA and then some. Why not just put firewire on motherboards and in disk drives? Then we can finally ditch ATA in all its incarnations.

Re:Why not firewire?

[chez69]

Could it be that it is both slower and more expensive?

Be a SCSI fanboy too

[Lobsang]

SCSI is full of annoyances. Price, incompatibility between controllers, etc.

However, if you're using linux, try this on both IDE and SCSI:

time dd if=/dev/your_disk_device_here of=/dev/null bs=1k count=100000

Then compare the CPU used for IDE and SCSI.

You might too become a SCSI fanboy. :)

Re:Be a SCSI fanboy too

[drsmithy]

Just for the hell of it, I did:

SCSI first (Quantum Atlas II on a 2940U2W):
[root@big-kahuna root]# time dd if=/dev/sda
of=/dev/null bs=1k count=100000
100000+0 records in
100000+0 records out
real 0m2.340s
user 0m0.057s
sys 0m0.887s

Now a software IDE RAID1 (2xIBM-DTLA-307030 on a CMD 649 chipset card) and one of its component drives:
[root@big-kahuna root]# time dd if=/dev/md0
of=/dev/null bs=1k count=100000
100000+0 records in
100000+0 records out
real 0m1.301s
user 0m0.074s
sys 0m0.650s
[root@big-kahuna root]# time dd if=/dev/hda
of=/dev/null bs=1k count=100000
100000+0 records in
100000+0 records out
real 0m2.793s
user 0m0.063s
sys 0m0.887s

Now a software IDE RAID5 (4xMaxtor D740X on 2x
Promise TX2 controllers) and one of its component drives:
[root@big-kahuna root]# time dd if=/dev/md1
of=/dev/null bs=1k count=100000
100000+0 records in
100000+0 records out
real 0m2.833s
user 0m0.076s
sys 0m0.676s
[root@big-kahuna root]# time dd if=/dev/hdi
of=/dev/null bs=1k count=100000
100000+0 records in
100000+0 records out
real 0m4.495s
user 0m0.084s
sys 0m0.811s

SCSI is definitely somewhat faster at some things, but having to spend 3x - 5x as money to get there, and have less space to boot, is means it simply ain't worth it for 99.9% of people.

Re:Be a SCSI fanboy too

[Lobsang]

SCSI is definitely somewhat faster at some things, but having to spend 3x - 5x as money to get there, and have less space to boot, is means it simply ain't worth it for 99.9% of people.

Yes, yes! We agree 100% on that. I don't have SCSI on my home desktop. But I wouldn't have a Data Warehouse server running on IDE. To each tool, its use...

Re:Be a SCSI fanboy too

[Anonymous Coward]

Interesting the comparison between the single drive performance versus a logical volume (ie md0 and md1). The LV should offer better read performance over the single drive because of the multiple concurrent streams. However, the single SCSI disk performed better in all but one case. The difference in write performance ought to be even greater.

I have yet to see IDE/ATA outperform SCSI in any of the applications I run, and I'll take the reliability any day...

Re:Be a SCSI fanboy too

[drsmithy]

"But I wouldn't have a Data Warehouse server running on IDE."

If you can't see a place for lower-speed, high density, dirt cheap storage in the enterprise, then your company has too much money.

The only advantages SCSI retains, assuming a sane hardware setup, are a higher top speed and drives manufactured to last longer. The former is only of interest for storing data that is frequently accessed in such a way that the disk is actually the bottleneck, and the latter can be largely circumvented with appropriate RAID configurations.

A never-ending game of leapfrog

[Salamander]

Of course, no discussion of Serial ATA would be complete without mentioning the answer from the SCSI camp - Serial Attached SCSI. SAS will use the same connector as SATA, but will support longer cable lengths, multiple initiators (if you don't know what an initiator is you don't even belong in this discussion), full SCSI semantics instead of lame-o ATA semantics, etc. Even so, the SAS folks are still ceding the high end to Fibre Channel and talking about three coexisting technologies for the low-end/midrange/enterprise market segments. Sorry, kiddies, but SATA is still low-end.

If there's one mistake you should try not to make more than once in this business, it's that competitors have been standing still since their previous generation. Announcing something brand new and having it be less than half a generation ahead of the competitor's last version is a failure.

Re:More "standards"

[bongholio]

did you mean ATRAC or 8-Track ;)

argueing with everyone

[squarefish]

ok, SCSI is cool and fast- however it is not marketed to general pulic. *** It's a higher standard who's taget is the server market where it can draw a more technical user base willing to pay the higher prices. I *** IDE is very limited, but also easier to use and way cheaper. *** Serial ATA is an itelligent combination of both that targets the way even new users would like to equip their machines to do more and be more flexible. It will be marketed to the general public and at a much cheaper price because of the collaboration of so many different companies that will mutally benefit from it's popularity. *** In the end it will be better for everyone (the companies and the users) *** It will also help drive a hurting industry if it ever actually becomes available!

Re:argueing with everyone

[GreyWolf3000]

SCSI is not an interface limited to the server by any physical means--merely marketing means. SCSI drives are built almost identically to IDE hard drives. They are usually faster, but you could make a SCSI hard drive of any speed/noise level you damn well pleased. SCSI is a superior interface to SATA. Period.

Re:argueing with everyone

[AlecC]

> SCSI drives are built almost identically to IDE hard drives.

Not according to the presentations I have had from the manufacturers. And, puttint their money where their mouth is, compare warranties (5 yrs vs 1 year), seek times (4 msc vs 9). They put better bearings in - one mfr claimes that bearings in their scsi drives cost him twice what the bearings in teh IDE drive cost.

Re:argueing with everyone

[Zathrus]

Compare apples to apples.

Take a 7200 RPM IDE drive. Take a 7200 RPM SCSI drive (ok, these are rather hard to find now). Rip off the electronics boards.

Now try to find a difference. You won't find one.

The physical drives are identical, at least as long as they have the same performance criteria.

Seek times? Bearing costs? You're comparing a 7200 RPM IDE drive to a 15,000 RPM SCSI drive. Amazing how the seek time is lower and the bearing costs are higher. It's simple math.

Re:argueing with everyone

[Anonymous Coward]

The parts may be higher quality, but the same overall design in the same. There is no reason why they can't make a SCSI disk of the quality that IDE is and sell it much cheaper. Then you wouldn't even need the drive electronics that IDE has which should make it even cheaper!

Re:argueing with everyone

[Wolfrider]

Why the hell would you want to REDUCE the quality of a SCSI drive, you moron??
.

Re:SCSI?-Deja Vu

[Anonymous Coward]

http://www.driveservice.com/bestwrst.htm

Excerpt:
"There is one more very important item I need to mention to you all. Very recently, an IBM engineer let slip, a white paper on one of their drives that actually told the truth about how long an IDE drive should last and under what conditions. In this paper, it said that current IDE drives are really only designed to be in operation from 6-8 hours per day! I have always known this to be true! IBM very quickly changed the white paper, and also stated that they stand behind their drives whether it is on for 8 hours or 24 hours per day. Do you want to take the chance? Most if not all of the current large capacity IDE drives, no matter who makes it, are not meant to be left on 24 hours a day. I am sure that none of you reading this are aware of that and may be quite shocked to hear this. These drives should not be put into servers, or be assigned any other industrial use duty! But, you might ask, "What am I supposed to use for heavy duty business use?". The answer is, use what we have used for years in server applications and that is SCSI! SCSI drives are meant to run and run and run without a hiccup. They are made much better than IDE, using better liquid-cooled motors, better parts, and usually better everything! So, the next time you are deciding what to use in a server that you are building, think twice about it. These days, IDE drives are consumer drives at best, and should be used for no other reason. If this list helps one person avoid troubles, I am happy I made it for you."

For those with short memories.
http://slashdot.org/article.pl?sid=02/1 0/17/135324 6&mode=thread&tid=137
"Tom's Hardware recently ran a story about major hard drive manufacturers drastically reducing their warranties on many of their products. "

SCSI isn't standing still
http://www.serialattachedscsi.com/

BTW Will serialATA still have the IRQ limitation of it's parallel cousin?

SATA propagates all the crap of PATA

[mnemotronic]

Serial ATA has kept all the truely horrible, obscure, and performance limiting features of parallel ATA (which was originally designed for 40 Mbyte drives), and shoves it down a thin cable. A course in ATA protocols will leave anyone who is computer literate going : You have got to be kidding!! What were they smoking????? The Serial spec has to maintain all kinds of bizarre, obsolete behavior just so that a SATA drive is backwards compatible with old software (i.e. that WfWG 3.11 system you've got tucked away in the closet). Throughout the history of ATA, when drive capacities climb towards the addressable limit of the spec, the protocol is kludged by a team of drunken baboons to extend it for another generation. The SATA committee munched an opportunity to drill a much-needed stake through the heart of ATA and give us a new interface for the next 20 years. Instead we get a change in connectors for a protocol with it's feet firmly encased in the concrete of MS-DOS 2.

Firewire (1394) was killed by Apple's licensing fees and Intel's sudden backstabbing policy change on building it into south-bridge, along with their NIH attitude. There existed working 1394 Device Bay drives over 6 years ago, with OS support from m-soft. 1394 was an attempt to keep the good parts of SCSI protocol, while leaving out as much of the useless stuff as possible (MODE SELECT).

Fibre-channel is still Real Pricey, for the same reason that SCSI is -- "just because". Or, as the hardware vendors say "harrumph, well, it's all about volume".

Re:SATA propagates all the crap of PATA

[Anonymous Coward]

> 1394 was an attempt to keep the good parts of SCSI protocol, while leaving out as much of the useless stuff as possible (MODE SELECT).

1394 is NOT SCSI. It is an IEEE packet protocol that defines a bus with address space & data space. SCSI is a simple packet based bus.

Re:SATA propagates all the crap of PATA

[Zathrus]

Throughout the history of ATA, when drive capacities climb towards the addressable limit of the spec, the protocol is kludged by a team of drunken baboons to extend it for another generation

Yes. We should run out of space in the latest incarnation in roughly 50 or 60 years.

Unless, of course, you're expecting to implement a single drive with more than 144,115,188,075,855,872 bytes (that's 128 petabytes or 131072 terabytes) anytime soon.

Yes, previous extentions have been poor. Maxtor got it right for ATAPI-6 which has been adopted by the industry. 48-bit addressing of 512 byte sectors.

Re:SATA propagates all the crap of PATA

[ez76]

Maxtor got it right for ATAPI-6 which has been adopted by the industry

Disingenuous.

Re:please mark this post as troll.

[Anonymous Coward]

yeer so funnay

Real benefits ?

[IanBevan]

This article is very pro the S-ATA standard. However later on in the article it states that S-ATA hard disks will be of the same speed and size as current ATA. The article says that the only way to get real performance increases in disks is to make them faster - so then we get to the same problems as SCSI, namely noise and heat.
As far as I can see, a couple of pages of this article are denoted to the new smaller cable size and connector footprint - who really cares ? I run an overclocked PC and as such use readily-available rounded IDE cables to afford better air flow. What other tangible advantages is S-ATA going to offer ?

Re:Give me Firewire!-here we go again!

[Anonymous Coward]

Hi. Please learn the difference between bits and bytes before spouting off like a fool. Oh, and learn to hyperlink, I can't be bothered to copy and paste a link from someone who STILL doesn't know the difference between B and b...

Forgive my ignorance

[xagon7]

But why can't they simply use USB 2? It certaintly has the bandwidth, and the BIOS could allow USB NATIVE internal drives to be treaded like IDE. I simply do not understand the need for this new standard when FireWire or USB would suit perfectly, especially when the Avg xFer is around 10 MB/s and the USB Bus allows for up to 200 MB/s.

Re:Forgive my ignorance

[Anonymous Coward]

Your ignorance is deeper than you think. There is no way current USB speeds are anywhere near 200 MB/s. More like 200 Mb/s. There is a difference. MB means megabyte, Mb means megabit. There's more than a 1:8 ratio between the two (given that megabit means 1 million bits and megabyte means 1,048,576 bytes... at least if you don't listen to drive manufacturers).

Re:Forgive my ignorance

[Anonymous Coward]

Firewire 400Mb/sec
USB 2.0 480Mb/sec
SATA (I) 1.5Gb/sec

Best use for hard drive:
SATA
Firewire
USB 2.0

Why firewire over usb2, Firewire is designed for low latency applications such as streaming video or for using hard drives. USB 2.0 is not, as soon as you add another device to USB2 your drive suffers horribly.

Re:Forgive my ignorance

[SpaceJunkie]

Equally USB is more readily extendable than SATA, and would be tons cheaper given the amount of USB controlled devices on the market. Go XAGON. Unfortunately- the USB standard only delivers a 5v supply rail and a fairly low current(is it 100mA?). Drives use mechanical motors, which either need higher voltages at around 12v or higher currents. So you would still need external power. Wouldnt it be nice if there were 5v, 9v and 12v DC supply rails on a couple of the USB pins with a common ground. It may not hurt to allow a power-repeater int he USB Chain - which may act as device reporting back power stabilities in the line... Nice... Maybe I am just dreaming aloud here.

Actually, no.

[Rui del-Negro]

First, this is IDE (just as ATA-66 or ATA-133 are IDE).

Second, the reason why Betamax died (well, didn't actually die, but didn't take off, either) was Sony kept it a proprietary format, while JVC let pretty much everyone make VHS products.

Serial ATA is one of the most unrevolutionary evolutions ever made. Basically it just changes the cables. The drives stay pretty much the same, the controllers stay pretty much the same, the drivers can stay exactly the same. Instead of wide, flat cables and two disks per channel you now get thin round cables and just one disk per channel (but since the connectors are so much smaller, you can have many on the same board). It's a good thing.

There are basically three reasons for having multiple standards. The first is a purely commercial one. Brand A invents the A-link and patents it, and brand B decides to create B-link so they don't have to pay a fee to Brand A. The second is evolution. Sometimes, a standard needs to be replaced or updated to cope with new demands (ex., ATA-33 becomes ATA-66). The third is that some standards are specifically suited to some situations (ex., SCSI lets you connect a lot of drives, and has support for other kinds of peripherals, but IDE is cheaper to make, and enough for most people).

RMN
~~~

Re:Actually, no.

[Firethorn]

There's still two devices per channel, but no longer two devices per cable. These connectors come in pairs. There's actually fairly simple connectors that can convert between P-ATA and S-ATA

Re:Actually, no.

[Anonymous Coward]

Serial ATA is one of the most unrevolutionary evolutions ever made. Basically it just changes the cables. The drives stay pretty much the same, the controllers stay pretty much the same, the drivers can stay exactly the same

Holy cow. This couldn't be further from the truth.Thats like saying that the Linux kernel is pretty much the same as the Solaris kernel because you can get a BASH shell on both. In theory, the drivers can stay exactly the same, but thats about it.

Re:Actually, no.

[Rui del-Negro]

The main difference from, say, (p)ATA-133 to SATA is in the transport (ie, the cables and the electrical signals). The (logical) protocol itself remains pretty much the same, and therefore so do the controllers and the drives.

The proof that this is an evolution, and not a revolution is that most SATA solutions in the market right now (including some high-end RAID cards, etc.) use exactly the same chips as the (p)ATA models, and simply add a converter and a couple of SATA connectors.

Even in terms of transfer speed, the change is minimal (from 133 to 150), and pretty mcuh irrelevant (no current IDE drive comes even close to 100 MB/s, let alone 133).

RMN
~~~

Re:Give me Firewire!-here we go again!

[Wdomburg]

# Data transfer rates of up to 400 Mb/sec with 1.2 Gb/sec speeds in development

400Mb/sec vs 150MB/sec

Pay attention to case, it does matter. As for what's in development, call me when its actually available.

Matt

Solid State

[GT_Alias]

This article seems to be largely extolling the virtues of a smaller hard-drive cable (yes, I know there's other stuff in there, but you can't deny that they make a really big deal out of those cables).

I don't think Serial ATA is the monstrous revolution they'd like for it to be. I think solid state storage will represent that...when we no longer have to rely on precision mechanical components that become royally fscked with the introduction of 1 speck of dust...THAT will be a revolution.

Re:More "standards"

[Anonymous Coward]

Well, my penis is keyed to fit into a hot vagina, but the gay village tells me that some people can defeat that keying...

S-ATA is the Ghetto FC

[Duncan3]

It's real simple, ribbon cables SUCK, they cost more to make then serial so PC makers hate them.

So, here's how it is...

Fibre Channel - 2Mb/s(10Mb coming very soon), 126 drives, 10+ mile range, better then SCSI.

S-ATA - 1.2Mb/s(2.4Mb in 2004), 18" range?, IDE protocols for all your write-only data needs.

S-ATA is the Ghetto FibreChannel, just like IDE is crappy SCSI, expect similar suckiness and low quality to go with the low price and cheaper cables (to make, to buy they will cost more I'm sure).

But again, this is all about the creaper cables, since lets face it 95%+ of the machines out there only have one drive anyway.

Re:S-ATA is the Ghetto FC

[Anonymous Coward]

+5 insightful, and he didnt get a single number right... Good job moderators!

Re:S-ATA is the Ghetto FC

[Duncan3]

yea yea, s/M/G/g, it's late.

Re:S-ATA is the Ghetto FC

[Anonymous Coward]

Not only did you screw up the speed, but the cabling length of fibre channel is 10 kilometers not 10 miles. It's in the hardware spec...

Re:S-ATA is the Ghetto FC

[Vortran]

And a ghetto pc SHOULD have only one drive. That's another reason why it's a GHETTO pc.

At 320 MB/sec with LVD SCSI, I _still_ see my biggest system bottleneck in hard disk data throughput. It really irks me that I can spend $1,000 for a decent system (mobo, cpu, memory) and not even be able to come close to alleviating my hard disk bottleneck for another $1,000.

These days putting a hard drive in a new machine feels like putting a lawn mower engine in a Lamborghini.

I've looked at solid state drives. If I took a mortgage on my entire net worth and liquefied all my assets, I still could not afford solid state drives at $80,000 a piece. Especially on a network that runs over 250 GB of storage. :(

Vortran out

Re:S-ATA is the Ghetto FC

[bored]

Besides the fact that most FC drives are FC-SCSI hu? lol.. :>

Very poor article

[waltc]

Aside from the fact that this article was very poorly written, it's difficult to understand what the author is so excited about. Between phrases like "dawn of a new era" and so on, the author makes a terrible, rotten case for why anybody should be excited about this at all. Basically, all I got out of it that was of seemingly immediate importance was the fact that the author seems to think thinner, longer drive cabling is revolutionary and heralds a new day in personal computing.

The article was extremely misleading in that it said next to nothing about the kind of drive technology to be used in SATA drives. Is this because the author doesn't know anything about these drives, or is it because the author knows there's nothing new whatever in the current SATA technology as far as the actual drives go except for the interface and cabling?

From what little I've read the first SATA drives are standard parallel IDE drives with serial interfaces. Is this approach supposed to make them run faster, or something? *chuckle* (facetious question)

Without some interesting new drive technology to make the interface change worthwhile, what's the point, here? *IS* there some point aside from thinner/longer cables???

A couple of days ago I saw a 200GB WD SE with 8 megs of cache. I'm already enjoying the benefits of RAID 0 + 1--the current IDE subsystems are *already* much faster than the drives they host. What's the problem? Cables? These days you can buy well-made rounded IDE cables (that are not simple ribbon cables folded, spindled, and mutilated.)

Maybe I'll become impressed when I can read more about the drive technology planned here and how it differs (if it does) from current IDE drive technology, but right now I'm not impressed at all. It's articles like these that definitely give SATA a "bad name"--if it in fact deserves something better.

Re:Very poor article

[Anonymous Coward]

Mentioned earlier was the fact that today's IDE hard drives can't take advantage of the bandwidth available to them

. Basically until cooler, quieter, smoother drives can be manufactured in high volume, desktop hard drives will continue to make baby steps in speed. This doesn't' mean that the next generation drives released with Serial ATA support will not more advanced than current models. Look for 8MB cache buffers and seek times less than 8.9ms to be the target

Guess you missed those parts....

The big plusses from this...

[Anonymous Coward]

...longer cables. No, I'm not being facetious. My biggest frustration is building a super-sized tower system and not being able to put the drives in a spot that's better suited for cancelling or suppressing noise -- or dissipating heat -- because the damned cables don't reach that far! If SATA can do away with that, then I'm all over it like a dog on someone's leg.

More standards is a good thing, not a bad thing. More standards means more choices, and from those choices we can pick stuff that serves everyone better. Maybe the speed isn't the big thing -- yet. Maybe it doesn't have to be.

*cringes*

[Akardam]

Please, for the love of everything that's geek... DON'T use "drop" and "hard drive" in the same sentance.

(OT) Re:SCSI?

[FauxPasIII]

Last but not least the 10K III's....I've got (4) four of them operating in a RAID 0 array and combined they're considerably quieter than my 7200RPM IDE drive. Virtually silent in fact.

What about heat ? I may need to buy some of these =)

You got it wrong

[Anonymous Coward]

The prefered spelling on Slashdot is "rediculous".

IDE Technology -- What really needs to be fixed.

[Proudrooster]

You can stick a parallel to serial adapter on an IDE drive, reduce the cable size, but it's still a crappy IDE drive.

If IDE hardware developers read slashdot, here is a list of IDE problems I'd like to see fixed.

1. You can't HOTSWAP an IDE drive without risking blowing your drive, crontroller, or upsetting the powersupply.
2. You can't WARMSWAP an IDE drive, without risking blowing your drive, controller, or upsetting your powersupply.
3. IDE still only supports 2, yes 2 drivers per controller, which makes it impossible to do hardware RAID-5. That leaves us with software RAID-5 as our only option.
4. IDE cables can only stretch so far, so even if you could somehow manage to get 8 IDE controllers into a box, for a total of 16 drives, there would still be cable length issues. I think 1 m is max. We need differential IDE :)
5. IDE drives are just now able to verify data integrity, but thats good since we can start using IDE drives in servers that don't need 100% uptime.
6. ATA/100 Round IDE cables are already available. In fact I just ordered some that have a UV reflective coating for my next case mod which features a black light. Airflow isn't a big issue, in fact Compaq has been slicing up IDE cables for a long time now to increase airflow.
7. The SUSTAINED TRANSFER WRITE RATE of IDE drives is still not fast enough to store uncompressed NTSC video at 60 frames per second, or store high bandwidth Satellite streams.
8a. Size increase (GB's) are not keeping pace with read/write access speeds and simply adding cache RAM and tweaking seek algorithms isn't going to remedy this problem.
8b. As, internal volatile write caches grow larger, the risk of uncommitted writes being lost in a power outage or crash increases.

If serial ATA would let me connect 4 drives per controller, I might start getting excited. If I could start "hot swapping" IDE drives, I would get really excited.

However, going from "flat to round" and "parallel to serial" is about as exciting as Windows XP compared to Windows 2000. It does the same thing, only slightly different. Actually in the case of Windows XP, thats not true, since Windows XP is missing device drivers for older Digital Cameras, Scanners, Modems, Video Cards etc ... but assuming you could still use all your exiting hardware it would be about that exciting.

S-ATA exists for one reason...

[Francis Avila]

...and one reason only:

To get rid of those damn ribbon cables.

Don't believe the marketing hype. SATA isn't about faster speeds, or more advanced features, or any of that crap. S-ATA is about cables.

IDE is crippleware. At some point in the past there was probably a need for a simpler, less expensive counterpart to scsi for desktop systems, but frankly that need is gone. The price distinction between IDE and SCSI has long been totally artificial. Drive manufacturers make a drive, and then slap on whatever control board they need, IDE or SCSI. Makes no difference to them, except that they get to mark up the SCSI version. Pure marketing: they need to stratisfy their technology so the enterprise guys don't feel like they're sullying their hands with the same tech as those Walmart PC-consumer lusers.

Frankly I wish SCSI had those neat little connectors (and they soon will, with Serial attached SCSI), and I hate ribbon cables as much as the next guy, but I'm not going to be fooled into thinking this is any real improvement over IDE.

But even as little as this is, it's long overdue. Those ribbon cables are the enemy of all that is good and just and true in the world.

Remember folks, SATA is only one letter away from SATAN. Q.E.D. Evil.

Re:S-ATA exists for one reason...

[MikeBabcock]

On which note, serial scsi would be a great invention :)

Oh wait, that's firewire ... well, maybe we should put some push on the development of 800, 1600 and 3200Mbps speeds on firewire busses then; no SCSI IDs and no IDE channels either.

Re:Give me Firewire!-here we go again!

[Anonymous Coward]

"Pay attention to case, it does matter. As for what's in development, call me when its actually available."
1394b:100MB/sec-400MB/sec
[silicons already made]
http://www.ti.com/sc/docs/news/2001/01160.h tm
[Raid board available]
http://www.indigita.com/products/prod_ fireidt800pc i.ht

I'll call you when mines available, if you call me when your's is available.

Cable costs and prices?

[Anonymous Coward]

What are the cable prices going to be - any ideas (and costs to the manufaturers)? The retail price of the USB 2 cables are in the $20-25 range. If the SATA connectors are going to cost as much, or a significant portion thereof, esp. with the hard drive prices dropping to low levels, the cable price will be a significant part of the total system. The fact that you need one cable per drive only makes this worse.

My concern is...

[Anonymous Coward]

... what am I going to do with my 4 IDE drives? I've got nearly 120gb of space on these things, am I expected to just chuck them out the next time I upgrade my motherboard? Or will motherboards retain IDE support ad infintum via a plug converter?

Serial vs Parallel

[bertok]

I've noticed that the argument for serial over parallel is usually something along the lines of: At higher frequencies, it becomes increasingly difficult to synchronize the signal travelling down multiple parallel conductors, but this is not a problem with serial protocols, so despite having less wires, serial interfaces can be faster thanks to higher signal frequencies.

This is all fine and good, but why not just treat the wires in a parallel cable as individual serial wires? Sure, if you increase the signal frequency, it becomes next to impossible to guarantee that all the signals arrive at exactly the same time, but I don't see the need for bit-level synchronization. If each wire has its own protocol, its own synchronization, and its own buffers, then as long as there is synchronization at the packet level, there should be no need to worry about synchronizing at the bit level. This would allow both high frequencies, and lots of wires.

Re:Serial vs Parallel

[amorsen]

This is all fine and good, but why not just treat the wires in a parallel cable as individual serial wires? Sure, if you increase the signal frequency, it becomes next to impossible to guarantee that all the signals arrive at exactly the same time, but I don't see the need for bit-level synchronization. If each wire has its own protocol, its own synchronization, and its own buffers, then as long as there is synchronization at the packet level, there should be no need to worry about synchronizing at the bit level. This would allow both high frequencies, and lots of wires.

Congratulations, you have just invented the RDRAM bus. The disadvantage is price. 150MB/s from one set of wires is more than enough for current drives, and serial speeds increase all the time, so it should not be necessary for many years for hard drives.

buyer beware

[frovingslosh]

from the article: and although it wont officially be supported until Microsoft's Longhorn OS

This seems to say something that I've never seen admitted about serial ATA: that it has DRM built in! If you want to buy hard drives that get to decide what you can and can't store on them, go ahead, but I'm not going to buy into any DRM technology. Extra speed and a smaller cable will not tempt me into doing it; I'll stock up on the last of the regular ATA drives as the serial ATA's replace them.

Re:buyer beware

[entrigant]

What does that quote from the article have to do with DRM and Serial ATA? Serial ATA is designed to be as compatible as possible... hell iirc regular ide drivers work with serial ata. IDE -> Serial ATA adapters exist and are very simple... I seriously doubt Serial ATA has built in DRM. Besides why on earth would you build the DRM into the drive controller (or even the drive for that matter)?

Re:buyer beware

[frovingslosh]

Longhorn doesn't work unless all parts of the system employ DRM. That Longhorn is already stated as the oficial point of support for serial ATA, while the drives already work under current Windows, tells me that there is a Longhorn related feature waiting for us.

Why put it into a drive? Part of the cradle to grave DRM philosphy. To keep you from storing something "they" don't want you to. To control how you can use something that you do store (it's only accessable by some DRM approved applications). To limit how long you can retain some files. To limit the number of times you can view a file and to keep you from making a copy. Basically to decide what you do with your computer.

You need to do a little research, DRM built into a drive has been talked about for a while, but it looks like it's in the serial ATA drives, just not a marketing feature they want to advertise to the people who actually end up with them!

Re:buyer beware

[Anonymous Coward]

Because the specification says so.

As mentioned on /. earlier, DRM is part of the SATA spec.

And the problem isn't about what you can store on the drive. The problem is, when the drive sees something going onto the platter that it thinks is DRMed, it may put the entire drive into DRM mode. With a non-DRM OS, such as your self-compiled Linux, you can kiss your data goodbye.

Actually, no.

[Rui del-Negro]

Not quite. SATA controllers have one device per channel, with no master or slave.

You are probably thinking of the situation where the motherboard has a (p)ATA controller and a converter is used to connect it to SATA cables. In this situation, one SATA channel is assigned to the (p)ATA master and another to the (p)ATA slave. But from a SATA point of view, the two channels are completely independent, and only support one device each.

RMN
~~~

On the other hand

[Anonymous Coward]

On the other hand, parallel means one of your lightbulbs can break and you don't have buy all new Christmas lights.

Comment removed

[account_deleted]

Comment removed based on user account deletion

Comment removed

[account_deleted]

Comment removed based on user account deletion

More info

[Daniel Rutter]

I wrote a piece on this subject a while ago.

It, um, reads less like a press release than does the Explosive Labs piece :-).

Argh.

[Wakko Warner]

No they aren't.

They're expensive because they're better.

Are they somewhat overpriced? Why, yes, they are. But that does not diminish the fact that SCSI kicks IDE's ass all over the place.

Plz do not attempt to refute this. Thx.

- A.P.

Re:Argh.

[Nogami_Saeko]

Why should I care about SCSI? I don't run a server, and I don't care if my applications and data take a couple extra seconds to load?

For the price of the equivilent SCSI system, I can get at the very least 5x the storage on an IDE system. That's plenty of storage AND redundancy.

Don't get me wrong, I used to run all SCSI in my Amiga, and for a while I had SCSI in my PC, but SCSI just can't compete with monster cheap IDE drives.

$799 - Seagate Cheetah 73.4GB SCSI 10,000rpm
$575 - Seagate Cheetah 36.7GB SCSI 15,000rpm

$279 - Western Digital 120.0GB IDE

(cdn OEM prices)

Point.

Re:Argh.

[G-funk]

I never said they're not better.... But they're maybe worth twice the price. They're sold at 5X the price for a 10k drive, and abou 8X for a 15k drive. It's an artificial pricing. They've been making SCSI drives for at least 15 years, I think they're as common as they're going to get, and it's not like they're rare. Most servers around the world run on scsi (not as much now as it used to be, but still most).

Re:Argh.

[runderwo]

but SCSI just can't compete with monster cheap IDE drives.

Wrong. The manufacturers have chosen to segregate the market and to place SCSI drives at the high end. This is not a limitation of "SCSI", it is a marketing choice.

Re:Argh.

[Znork]

True, not as much now as it used to be, we're switching to FibreChannel attached storage for servers instead... ...which is even more expensive...

Re:Argh.

[Sabalon]

And what does that fiber channel plug into? A box with a fiber channel interface to the external world and a RAID array of SCSI disks inside the box.

Re:Argh.

[GooberToo]

They're expensive because they're better.

Back on planet earth, no one said otherwise. This is why they are a top shelf product. Having said that, you can make a better product and have it cost only a single digit percent in difference. If I had to spend 9% more to make a SCSI drive and can sale it for 5-20 times the price of an IDE drive, I'm fairly sure I would. Then again, that's fairly obvious...isn't it. ;)

In the example about diamonds that I gave, diamonds really are better than the typical pebble out my front door...but they are not 1000x better (price wise). A $1000.00 diamond should be able to be purchased for a couple of bucks (if that). They can't be because it's a premium product. The reasons it's 1000x more expensive rather than mearly 5-20x is because of the cartels.

Plz do not attempt to refute this. Thx.

Please do not attempt to refute how the real world works. Thanks. ;)

Re:Argh.

[RadioTV]

That depends on the controller in the drive enclosure you have.

1. There are FC controllers that use IDE drives.
2. Not all FC controllers support RAID
3. Most controlers use FC-AL connectors - not SCSI.

IDE drives are a new tech

[terminal.dk]

The first PCs did not have harddrives.

Then there wer esome with Winchester drives.

The first PC I put together for my father had a smallish like 20MB SCSI drive.

My cheap friends where using MFM or RLL drive. IDE drives were not yet invented. And the Macintosh was SCSI only for a long time.

IDE is just another passing tech in the low-end desktop PC market.

was this written by the CEO or what?

[terrox]

7 wires, 7 wires, Serial ATA will be great, Serial ATA!, Serial ATA with 7 wires, no more ribbons, ribbons gone, no more ribbons... blah blah - okay this story looked really really bad. If someone said "we are going to make a silent SCSI hardrive" then it would definately win.

Re:S-ATA Max Length

[Necroman]

The Serial ATA architecture replaces the wide Parallel ATA ribbon cable with a thin, flexible cable that can be up to 1 meter in length. The serial cable is smaller and easier to route inside the chassis (see Figure 2). The small-diameter cable can help improve air flow inside the PC system chassis and will facilitate future designs of smaller PC systems.

As from here

A compromise between SCSI and IDE

[iankerickson]

ACARD makes a series of SCSI-IDE bridge cards which connect to the SCSI chain on one side and an ATA hard disk on the other. They have several models, mostly depending on what type of SCSI cabling you have, costing from $50 to $80. They support large ATA disks, the cost of which plus the $70 for the bridge is still cheaper than most SCSI drives. If you don't need the warranty and physical traits of SCSI hard disks, but you want to be able to hook up 6 drives to your PC with only 1 IRQ and IO address or add 60-80 gigs of space for under $200, this might do the trick. They also come in handy for old workstation-era machines, like PowerMacs, SparcStations, or VAXes. The bridge doesn't require any drivers or software to work, since it just tunnels ATAPI and makes the IDE drive look like just another SCSI disk in the chain.

http://www.acard.com/eng/product/scside.html

Microland sells them in the US:
http://www.microlandusa.com/microland/

Some downsides:
- The hard disk has to be formatted while cabled to the SCSI-IDE brige. You can't move a drive from a regular IDE controller to the SCSI-IDE bridge without getting geometry errors.
- The interface is ATAPI only, so not all commands for the device may work. FE, firmware updaters and vendor utilities designed for the hard disk probably won't work the bridge.
- The utility to update the bridge's firmware is only for DOS/Windows.

There will probably be LVD-SATA bridges too in the future, if SATA truly catches on.

Great :)

[ascii]

Looks like we'll see faster floppy-drives sooner than we may think. Any day now ...

Various peripheral evolutions...

[phorm]

Parallel port: Does anyone still use this
I work at a school... they still have a DOT-Matrix or two in use (both as network or local printers. The cool thing is that these buggers still work almost as good as I remember them being 10 years ago (which is to say noisy as all heck, but still functional). We also had one of these for printing out (blah) COBOL code in college.
Parallel printing has evolved though. At some point we got EPP in conjunction to ECP.

I'd also like to recommend the usage of the PS2-style keyboard connector as a friendly successor to the old AT-style standard.

And in an addition for the parent
How long has the VGA pin-out been defined

Really old printers can actually have physically different pinsets. The old ones also didn't seem to have as many pins (though the places for them were there). Guess they thought ahead when designing the pin layout for monitors?

Re:Various peripheral evolutions...

[Clover_Kicker]

>I work at a school... they still have a DOT-Matrix
>or two in use

Dot matrix printers are great for schools. They're so slow/loud/annoying that people only print what they need, instead of using the school as their personal print shop.

A lot of places got "sticker shock" when they first introduced laser printers to student labs... Labs that had never bothered with printer quotas suddenly needed them.

Bzzzt!

[Anonymous Coward]

Think about what you just did - interesting, but completely wrong. Now, go back and measure CPU usage - not execution time (yes, there's a difference).

Re:Bzzzt!

[drsmithy]

Think about what you just did - interesting, but completely wrong.

I did precisely what the poster asked. I'm not entirely sure what they were trying to prove, though.

Now, go back and measure CPU usage - not execution time (yes, there's a difference).

I'm well aware. And the difference in CPU usage between IDE and SCSI on any remotely modern system is SFA.

Re:More "standards"

[Anonymous Coward]

I wouldn't call your palm a hot vagina.

For the love of God, mod NAZI parent post down!

[dirtyhippie]

for the love of god, mod nazi parent post down. thank you.

Re:For the love of God, mod NAZI parent post down!

[Anonymous Coward]

Intercourse, PA Within a short distance (~20 miles?) from Intercourse, PA, there are also towns named "Fertility", "Paradise", "Blue Ball", and "Bird-In-Hand".

Don't forget... Scotrun, PA. Try reading that 3 times fast when you're half asleep on your way to NYC

Hahahahaha. dude - that is so true. I've driven past SCROTUM PA a few times on the way to Penn State. Route 80 moe! WOHOOOO! ;p

Re:rounded cables not a good idea.

[Anonymous Coward]

I suggest you run some tests on your IDE bus, it's likely that your rounded IDE cable is causing interference on your bus, limiting its speed and increasing latency. Ribbon cables are designed to be a ribbon for a reason.

Re:IDE Technology -- What really needs to be fixed

[amorsen]

If you had read the article...

1. You can't HOTSWAP an IDE drive without risking blowing your drive, crontroller, or upsetting the powersupply.

With SATA you can.

2. You can't WARMSWAP an IDE drive, without risking blowing your drive, controller, or upsetting your powersupply.

With SATA you can.

3. IDE still only supports 2, yes 2 drivers per controller, which makes it impossible to do hardware RAID-5. That leaves us with software RAID-5 as our only option.

Who cares when you can get hardware RAID-controllers with 12 ports on one card? What is the great advantage of having the cable be the single point of failure for your whole RAID, like SCSI does?

4. IDE cables can only stretch so far, so even if you could somehow manage to get 8 IDE controllers into a box, for a total of 16 drives, there would still be cable length issues. I think 1 m is max. We need differential IDE :)

Ok, 1m can be a problem for some people. However most people do not have cases larger than 1m.

5. IDE drives are just now able to verify data integrity, but thats good since we can start using IDE drives in servers that don't need 100% uptime.

Err, why is it a problem when it is already fixed as you say?

6. ATA/100 Round IDE cables are already available. In fact I just ordered some that have a UV reflective coating for my next case mod which features a black light. Airflow isn't a big issue, in fact Compaq has been slicing up IDE cables for a long time now to increase airflow.

Round IDE-cables are expensive to produce and still large and inflexible. SATA solves it.

7. The SUSTAINED TRANSFER WRITE RATE of IDE drives is still not fast enough to store uncompressed NTSC video at 60 frames per second, or store high bandwidth Satellite streams.

So get the hardware RAID-controller and start streaming away. Oh wait, hardware RAID for SATA doesn't exist. 3ware is a figment of my imagination.

8a. Size increase (GB's) are not keeping pace with read/write access speeds and simply adding cache RAM and tweaking seek algorithms isn't going to remedy this problem.

You can't blame the interface for that. 150MB/s per drive for 12 drives on one card is way more than any SCSI solution supports -- and way more than current drives need.

8b. As, internal volatile write caches grow larger, the risk of uncommitted writes being lost in a power outage or crash increases.

So turn off the write cache. ATA supports Transaction Command Queueing although not all drives support it yet. By the time SATA drives become available, TCQ should be common.

floppy drive?

[Anonymous Coward]

I'm waiting for my serial floppy. a floppy drive at 150MB/s - yeah baby!!

Ofttopic - Overrated sig

[StrawberryFrog]

Don't be a pussy and choose Overrated (-1).

Sometimes it's the best option. We don't have "Pointless (-1)", "Stupid (-1)", "Badly written (-1)" or "Just Plain Wrong (-1)"

it's not all the same

[g4dget]

It's not all the same. You have a limited budget: are you going to put it into additional wires or additional electronics? Since the cost of high speed electronics has dropped through the floor while wires aren't getting cheaper, serial is becoming increasingly attractive. And that's even not taking into account all its other advantages.

Re:IDE ZEALOTS MUST DIE IN THE OVENS!

[Anonymous Coward]

CLITORIS CHOPPERS. Hi there you fucking Islamic career clerics, doctors of death, Waffen Schutzstaffel doctor Josef Mengele is a patron saint compared to you fucking ragheads. You suck. You aide and abet terror and death. You are partially responsible for the deaths of other fellow men. For this fratricide you shall pay dearly. Your soul is black with the stains of inaction, ineptitude and sympathies to those who walk the dark side. Your foul life is full of sins, not religious, just heinous, your karma is low, you don't confess, and you aren't in prison where you belong. You are your own dark, kept secret. I see through you, the worthless academic, the pseudo intellectual, the unproven unpublished un patented WASTE OF FUCKING FLESH. You are a drain on society, you are a member of the 1st world but pretend to not be. I hate you, you are a stained man.

Hi clitoris chopper, IDE ZEALOTS supports clitoris carving. You are Islamic, and of course are a fucking animal. I hate you you pull-start camel jockey lover. Towelheads, Camel Jockies, Sand Niggers, Ackmids, Abeebs, Carpet Flyers, Dune Coons, Rag Heads, Sand Scratchers, Habeebs, Abba-Dabbas, Camel-Humpers, Demi-niggers, Fig-Gobblers, Hucka-luckas (hucka hlacka ghalcka ghugh), Lefties (If you steal, you lose the right hand so, since they are thieves...) Ocnods, Pull-Start-ables (imagine pull starting Ossama's dirty rag like a Briggs and Stratton), Roach-Ranchers (habibs cant kill roaches by a tenant of Is-slum), Sand Moolies.

Shut up all you dirty fucking Islamic pigfucking swinehundts and the pigs, the communist fuckin Islamic terrorist supporter.

Take your fucking Koran and cram it up your ass. The sooner the earth sees Islam leave it, the better off it will be. Your Koran is Goat Piss.

I hope if there is a God and a Hell, you have to drink the liquidy shit from a Pig's ass, and Jewish Rabbis defecate on you.

I hate the stupid ISLAM fucks who read into the trash they come up with. Saddam Hussein [who needs to take a dirt nap] is higher on my sanity list than fucking Muslim "clerics." In fact, I like Saddam more than most of the other Arab leaders because he is secular. We should fucking nuke the Saudis and Mecca and Medina and turn it into rubble, then tell Saddam to remove the heads of all the buttfucking "royalty" in the area.

I want to wipe my ass with Mohammad's shroud. I want to grind his body up into bone meal and fertilize my garden with it.

Our tortured dead scream out in HORROR, asking for vengeance:

1. Kill all Camel Jockeys.
2. Kill all Mohammedans.
3. Kill all Dune Coons.
4. Kill all Rag Heads.
5. Kill all Towelheads.
6. Kill all Arabs.
7. Kill all Camel Rooters.
8. Kill all Osama Bin Laden supporters.

Nuke their countries to hell.

Nuke them again.

Death to Islam.

I piss on Mecca. I wipe my ass with the Koran. I shit upon Mohammed. I wipe the cum for a freshly fucked pussy with Mohammed's shroud then throw it in the pig sty so it can mire in pig shit as it decomposes.

I only hate with words, you fucking wet towel fucking scum killer, you maim, your terror bomber.

You will be judged and cast away by the powers that be, your death will get none of my pity and you will have precipitated it upon yourself, YOU xenophobic pieces of shit, your elitist religious country club will be your own undoing..

In the great continuum that it time your are those who serve to disrupt it by ending the brilliance and lives of those who your zealous foul religion call heathens and infidels. Your death will be celebrated, you will not be missed.

My rhetoric is a reflection of my anger at your, your Islamic death leaders, and your religions unwillingness to admit to what it really is, a death mongering cult.

Your religion is one which produces nothing that is meritorious, your artisans are not accomplished or made pariahs, social and economic structures in Islamic states are defunct, your religion is rife with inconsistency and moral shortcomings, your anti progress and western religion which is rooted in pagan beliefs is a pathetic made up religion that is the backwash of a crazed terrorist and mass killer, Mohammed. You cry Jihad, and call for holy war, and call for the death of the west and the infidels. We will defend ourselves. And since we know deep down what is right, and value our existence and the lives of our children and the meaning of freedoms, aspirations and some semblance of equality, we will crush you defending it. Prepare for your doom, each terrorist event only increases our resolve and fortitude, we must be forgiving and kind because your precious centers of idolatry, Mecca and Medina, are not sheets of glass yet.

One day, we will open a gold course and the 19TH hole bar will be in that fucking stone shack you foul idiots covet. Idolaters, pagan based, misguided pathetic violent destructive foul piece of trash religion.

Your corrupt leadership doesn't even attempt to save face. And we notice. Your religions inability to do anything but destroy is noted, and punishment will be exacted for your infractions, probably 10 fold, and you pigs will have precipitated on your own women and children the lancing fires of justice from the sky. Your bodies vaporized to ash where you can be one with the earth again from whence you came maybe one day your atoms will be incarnated again as a useful life form.

And the pussy bitch that defends Islam needs to die. And the Nation of Nigger Is-SLUM, where those sub creatures live, in the SLUMS of their own creation, is a piece of racist shit. So I give it back. You hate me, I hate you back 10 fold. Death to All Non-Secular Islam and Nigger Nation of Islam. Death.

DEATH. JIHAD against the JIHAD. I want to harvest organs from Islamic peoples who take their stupid shit religion seriously so they can be useful. Then I want Jewish Rabbis to piss and shit in the hole I left cutting your organs out, then I want to feed your Islamic bodies to pigs, let them shit you out in your final resting place, the pig sty.

SCSI is hard to configure

[g4dget]

SCSI configuration is not exactly user friendly: you need to work out the SCSI IDs and worry about termination. There are also a bunch of different SCSI versions you need to worry about. If you get things wrong, nothing may tell you about it, the drives may just fail in subtle ways.

IDE is much simpler: with cable select, you can just plug in anything anywhere and it works. Serial ATA will preserve that simplicity and improve on it.

My Little Rant..

[NoMercy]

For the past few years Ive had my PC with it's legacy ports: VGA, PATA, RS232, Parrellel, PS/2.

So out with the old and in with the new eh, so it's
DVI, SATA, USB1, USB2, Firewire.

It's just starting to annoy me that in our fight against legacy hardware all weve gone and done is replaced the ports with ones with funkier plugs, I guess I was nieve when I first heard the 'Universal' part of USB in thinking that it might actually be Universal.

Yes, you are :)

[Anonymous Coward]

SATA connectors are small, and motherboard realestate isnt really in short supply. Easy routing of the thin cables is much more important. Rounded ATA cables are non standard, and not nearly as flexible.

One device per controller is an advantage because it is cheap. Multidrop connections are hell, and in a PC with only a couple of devices completely unnecessary. Better keep the interface simple and run a few more cables. For RAID arrays they will have nice rails with a SATA connector for every drive bay no doubt.

Computational power needed to calculate XOR? You are having acid flashbacks, you could calculate gigabytes per second worth of XORs in a minimal amount of silicon nowadays ...

SCSI is adapting the single drop SATA interface for their own serial interface, speeding it up a little to keep up appearances of course ... but still, they are following suit.

Answer? More like response ...

[Anonymous Coward]

Silicon is so cheap that the price of the physical drives will become even more important in the future. If you buy a 3ware controller today you can put an ATA drive on it and it would perform exactly the same as a SCSI drive with the same throughput/latency. This is only going to get worse (for SCSI) in the future.

If you have dedicated hardware talking to a drive the protocol is really an insignificant factor in the performance, so for hardware RAID SCSI the protocol could become obsolete if they cannot win the battle on other fronts. Having support for fan-out routing gives SAS a small edge over SATA (although the potential for concentrators and native SATA routers is mentioned in the SATA-II extensions, I think they will standardize something soon) but I think SCSI will in the future have to rely more and more on the artificial seperation of the market by the drive manufacturers. They all have to keep playing ball of course, in that respect Maxtor acquiring SCSI buessinuess is one of the more important factors in SCSI's continued success.

Its pretty silly to position SATA/SAS as competitors for FC, not because of low-end/high-end considerations ... but because it is comparing apples and oranges. NAS/iSCSI are FC's competitors, and personally I think NAS will be victorious.

I dont quite get the gist of your last paragraph, on the one hand I could read it as a comment on SATA ... but it seems as relevant to SAS :)

Re:Answer? More like response ...

[Anonymous Coward]

Which iSCSI/NAS vendor do you work for?

Re:Answer? More like response ...

[scot4875]

so for hardware RAID SCSI the protocol could become obsolete if they cannot win the battle on other fronts

Why is this some sort of battle? The same people who make SCSI controllers also make IDE controllers (for the most part). The same people make both SCSI and IDE drives.

If a new standard comes out that obsoletes one, who the hell cares? It's surely not the hardware vendors, since all SCSI or IDE is to them is an acronym applied to their product. And it's definitely not SCSI or IDE themselves, since they aren't really people.

So again I ask, why is this a battle? It's like saying that there was a "battle" between Coaxial and Cat-5 ethernet cable. Or that there was a "battle" between B&W and Color TVs.

--Jeremy

Prehistory? Yes indeed.

[Anonymous Coward]

I guess my using PUNCHED cards and PAPER tape shending hours over a TTY doesn't count. But hey, when using cards, be sure to draw a diagonal line across the tops of the cards in marker...just in case you drop the deck. He He , been there and done that, I even used HEX to manually enter bootstrap instructions to some of the machines. Am I old or what?

Cabling mess not solved entirely.

[xyote]

Having build and rebuilt umpty ump times about 3 or 4 pc's to optimise hardware and disk configurations, I can say that Serial ATA will really help. You put 4 or 5 ide devices in a pc case and even with rounded ide cables, cable routing is still a hassle.

But serial ATA would not solve all the cabling problems. You still have that absolute spagetti mess of power supply connectors because they put on enough connectors for everything including those extra optional P4 connectors which don't all get used even with P4 motherboards. I'm seriously thinking of modding power supplies, screw the warrently. Just cut off most of the wires, put on generic inline connectors and build custom wiring setups. None of that piggy backing of y connectors connected to serial ATA power connector adapters, etc...

How old was this person?

[byron150]

Probably somebody caught this.....but this article reads like a six year old wrote it. Basically he's telling you, everything you know is going to change, and that it won't be an incredible performance increase over what we see now. Furthermore, he obviously didn't have an editor or a spell checker, and he pings from one topic to another just to come round and rehash things he's already said. WTF has journalism come to today?

Then WHEN

[ackthpt]

I've been following these and there's a number of manufacturers planning to make them available, Maxtor, Seagate, Western Digital, Fujitsu, et al, but dates have been pushed back. Seagate was to be shipping ST380023AS and ST3120023AS drives in late October, now I'm seeing late November or even December. Maxtor has stated they will ship in December, others I haven't found out about. There will be a SATA group presence at COMDEX. Here's a source of information, but it tends to be general and dated, aside from having some technical docs online, too.

Where to find one...

[Ixe]

I'd read something about "serial ata" when I was drueling at RAID stuff on 3ware's site but I didn't realize what it was until now...
To me it looks/sounds really cool, and I'd love to get a small raid array of these in my next computer, but has anyone seen any SATA drives on the market?
Dirt Cheap Drives and yahoo shopping show nothing....and no, neither does pricewatch.... I take it these drives don't exist yet? Then why are there RAID cards for them?

Someone please unconfuse me...

Okay SATA

[SpaceJunkie]

I take on board and agree with serial vs parallel arguments. I only use IDE on my desktop(not my servers) and because it is cheap.
PATA runs short on a few things- bulky parallel cables, lack of standardised connector locations, low bandwidth, limited drives per connector - they cannot be Daisy chained.
SCSI run short with bulky parallel cable, expensive to buy interfaces, cables and drives, drives tend to be noisy(although much faster) and heat up faster.
So SATA. It hot-plugable(one of SCSI's better features), its got high bandwidth(in theory only). It still has no standardised connector locations like SCSI- which would make hot swapping a whole lot easier. It still CANNOT be daisy chained, which means rats nests, and worse still having to buy another adapter card when you need more ports. It is serial- no bulky cables- nice thin ones. Which means less heat. The drives manufactured to run with it would need to be an extensive range from the low end-to the high end so it can be widely accepted in the user base and yet still deliver power performance when needed.
How open are the SATA standards? More to the point if controller chipsets are made-how easy would it be to make sure there are drivers which support them?
Dont get me wrong, I am looking forward to the future in serial drive interfacing (can you say firewire?) but I just have a number of requirements before I make an investment in a new technology.

Lower limit on time to obsolesence

[NetWurkGuy]

No PC technology is obsolete until it has had sufficient time to migrate from add-on boards onto most of the commonly used motherboards.

Average Joe? Puhleeze.

[gosand]

Now, is SCSI better for your average Joe? Maybe not significantly. Neither is 7200 vs 5400, 2MB vs 8MB buffers, or 8.9 vs 9.1 ms access times. However, if they could use one cable to connect 15 devices in their tower, they'd be alot happier than having the 8 cables they'd need to do it with current IDE tech (let alone IDE's relative inability to be used externally).

The average Joe will simply ship the whole computer back to Dell. Ask average Joe if he has an IDE drive or a SCSI drive in his computer, and see what kind of reaction you get. You'll either get Mr. Self-taught computer Joe, who will tell you he has a 30 Gee Bee and a 256 Em Bee, or someone who doesn't know and doesn't care.

People can say SCSI is better (or equivalent) to SATA, but the bottom line is it doesn't matter. The market, or more accurately the people driving the market, will decide. In the end, we are going to have technology that keeps getting better and better. Maybe SCSI missed the boat because of price. I know I wouldn't buy a SCSI drive for home, they are just too damn expensive. Servers - sure. But SATA is a way of sparking interest. If SCSI drives were cheaper, people would buy them, and if there was more interest in them, they would be cheaper. So SATA comes along, will garner interest because it is new, and it will probably take off. I don't think SCSI will go away any time soon, because of legacy support, but if it does, then are we really missing out on anything if SATA can pick up the slack?

IBM SSA

[Znonymous Coward]

IBM has been using this for quite some time in their RISC systems. It's freaking bad ass! You can have hundreds of drives in 1 machine and they work like an ethernet network sharing controller bandwidth.

http://www.storage.ibm.com/hardsoft/products/713 3/ 7133.htm

Why not a single host/slave interface? qjkx

[Anonymous Coward]

Why do we need this, usb2, and firewire? In the end, the speeds don't quite match, but it sure would be nice just to have a single interface, in and out. But that may not be worth keeping those ugly cables around any longer to wait for the new thing.

Lamenting wide spread SCSI adoption on the PC

[tbuskey]

The best thing Apple did was put SCSI in the mac plus. Suddenly you could add hard drives, cd roms, scanners, tape drives, ethernet adapters, serial port adapters.

I used to put my Syquest and DAT tape drive on a mac, PC, and Sun. I still use the DAT drive I bought in 1993. How many 10 year old peripherals do you use?

If PCs had gone to SCSI instead of IDE (remember MFM?) we'd all have cheap SCSI drives we could use on any platform. There'd be more innovation in SCSI.

Instead, I get IDE in my Ultra 5, Macintosh, and PC. Only 2 devices unless you want speed issues. It can only really be internal devices.

And I still need SCSI for my tape drive or other external media.

hey...

[Grifter]

speaking of x86/i88 ... does no one remember MFM?? it came before IDE, that all you had on an 8088 or an 8086

Re:IDE TROLLS: READ THIS-Choices

[Anonymous Coward]

" This just isn't the case. Apple products used SCSI exclusively for at least a decade and sold a pretty high volume of them. There were even SCSI scanners and a whole slew of SCSI external drives before USB. I still have an Adaptec SCSI card that came free with a scanner. All this never made a dent in SCSI prices.

SCSI had its chance on the desktop and blew it."

Oh this is rich. Using a vendor who's know for overall higher hardware cost compared to the industry, and saying SCSI "blew it".

If SCSI had started out being used on the x86 platform like it was on the Apple, THEN being dumped for IDE. Then you could crow about SCSI blowing it.

BTW Epson's high end scanners have your choice of SCSI, Firewire, USB, or Ethernet.

Sticker Shock

[phorm]

Can you explain the origin of the term "sticker shock" and its meaning. I've never heard that one before (have to keep up on my tech vocab)

Re:Sticker Shock

[einstein]

it means being surprised by the price sticker/actual cost. nothing computer related about it.
--

Re:Sticker Shock

[Anonymous Coward]

wow!
is that actual geek code???

You mean someone really still does that?

small long cables

[Grimwiz]

Ummm, I've been using small long cables to connect fast disks up since 2 years ago.

Its called Fiber Channel.

The Fiber over copper had small serial-looking cables around 5m long. Over optical it can go for miles. In speed they were around 200Mb/s. And its not a one-to-one connection, you can chain multiple drives together. You can even make a loop so that if someone unplugs a cable it all keeps working.

You can already buy disks with dual onboard fiber channel connectors, but more often you find a hardware raid controller at the far end that manages the disks.

Not cheap... But its here, usable now and well tested.

Who needs SATA when we've got Firewire?

[Valdrax]

Firewire solves all the major shortcomings of both SCSI and SATA. It provides fast transfer rates, intelligent, cheap controllers that offload CPU utilization, and has no problems with multiple devices daisy-chained off of one port. It's cheap and fast, only costing about $7 to add a Firewire port to a motherboard.

This addresses all of the SCSI issues you listed.

However, your SATA data paints a rosier picture of things then reality allows. Your 1.8 GBps controller is somewhat useless seeing as it's a PCI card, which won't be able to come close to using all that bandwidth. I'll be more impressed when ports are finally built into the motherboard. Also the lack of integrated power connector means that routing cable around a case is still not as simple as if Intel had continued to suggest internal Firewire for future PCs before getting huffy at Apple and starting its USB 2.0 movement. Furthermore the one port per one device limitation is onerous. While future versions are expected to provide daisy-chaining of drives, current revisions do not. This means you need one port per device, and I guarantee you no current devices will be using half the bandwidth of their connection. It's a waste. Furthermore, SATA still eats CPU just like all other forms of IDE because it lacks intelligent controllers.

I say forget SATA, what we need is internal Firewire. That was the nirvana of case wiring that we passed up a few years ago. I know that the SFF system I'm building will be quite cramped due to ATA/100 cables and power cables. If we'd adopted Firewire internally a few years ago like Intel originally suggested, my air flow problems would be solved already.

Re:Who needs SATA when we've got Firewire?

[egarland]

Firewire is unusable for system drives because the ID is dynamically assigned. There is no way to decide which comes first.

More importantly for large systems, if a drive fails in a RAID array and you pull it out and plug a new one back in it will get a different ID than the old one and thus not be part of the array it should be part of.

RAID

[CharlieO]

RAID (Redundant Array of Inexpensive Disks)

The RAID acronym is now Redundant Array of Independant Disks

'Inexpensive' refers back to the time that build a decent sized drive that presented itself to the host as a single entity was easier with an array of small drives, because of the huge cost of larger drives.

'Independant' is more in keeping with the modern reason for build such arrays.

Its not SCSI vs IDE its PARRALLEL vs SERIAL

[CharlieO]

All of IDE's shortcomings are fixed by SCSI

Define 'SCSI' and 'IDE', there are after all many standards. I assume you mean UltraATA33/66/100/133 vs SCSI2UW/SCSI3 to compare like with like!

But both are parrallel systems, and irrespective of the largely irrelvant SCSI vs IDE pissing contest, the problem that needs to be solved is the limitations of parrallel communications.

Parrallel comms has a problem as clock speeds get higher, the immpeadance of the wires gets harder to predict, your error checking and correcting (People do know thats there right?) technology has to get smarter. The timing differences on each conductor start to get near the same order as the clock pulses and you can't figure out if that bit is in the current word or the last. Multi conductor cables are terribly sensitive to crosstalk and other interference. Basically when it comes to high clockspeeds/frequencies then parrallel technology hits limitations.

Serial technology uses less conductors, so the immpeadance of the cable is much more predictable, its also less error prone as there are no real timing issues, and the error correction is easier. You can transmit on inverted pairs and largely reject environmental noise, and with only a couple of data wires crosstalk is predictable and can be coped with. Okay it has to go 8 times as fast to get the same throughput as an 8bit parrallel, 16 times as fast for 16bit parrallel and so on, but we're getting good at fast silicon these days.

So why do we have parrallel, and why is it old tech?

Because when you are limited by the clock speed of the silicon, parrallel moves data faster. Thats why your PC/UNIX box is choc full of parrallel interfaces between devices/chips, because the limitation used to be clock speed.

Now we are reaching clock speeds where physics starts to hurt on multi conductor cables, but now we can build very fast silicon so we can exploit low conductor count cables. As a bonus they are much better at covering distances.

This is why both SCSI and IDE have solved the problem in similar ways. Serial ATA / fibreChannel SCSI (yes I know that can be optical, but its still serial transmission)

In the quest for high clock speeds, then expect to see serial interfaces becoming the norm. What protocal they are talking (SCSI/SATA/USB/IEE1394) is largely irrelevant.

I thank you, and I'll leave the fanboys in both camps to slugg it out amongst themselves...

ANS - Physics

[CharlieO]

Read up on all the physics nasties that happen with parrallel conductors

See my other post further up

You can't treat each pair on its own, you have to account for the electrical fields from the other conductors in the same wire, the nasty spikes from god knows what else is in the same case, and the fact that some idiot just rounded the cable and destroyed the few assmuptions you can make about immpeadance matching on the cable so you don't get nasty refelections.

But yes you can have parrallel/serial hybrids, but generally you have one or the other. Otherwise you have to cope with both techniques problems!!

Rounded Cable = Bad Idea

[CharlieO]

I could explain why, but its better done and funnier here Dans Data - Fancy IDE leads - The Terrible Truth

If you don't follow the physics then trust me, I do, he knows, ditch the cables if you run faster than UltraATA33 over them if you value your data.

Use SiSoft Sandra to benchmark the drives, if they go faster at Ultra33 than at Ultra66 then you have problems. Been there, done the test with my Western Digital 80Gb/8Mb cache pair, seen the effects of nasty cable.

One CRC error will just slow the bus down, two errors in the same transmission the ATA standard won't detect and you get a corrupt byte on the disk. Finding that in the zip of l33t t00lz you had stashed away will really make your day.

Re:IDE Technology -- What really needs to be fixed

[CharlieO]

1. Stock IDE can Hotswap with correct cradle (kinda like SCSI can, so long as its an SCA connector), but does need controller like HighPoint that has the smarts to know whats going on.

2. Ditto Warm Swap

3. Agree

4. 80 conductor cables are limited to 40cm, and BTW are not differential as some say, they just have interleaved grounds to help cut the crosstalk.

5. Err, thats something to do with the drive, not the bus it talks over

6. Round cables are a bad idea, you destroy the whole point of the individual grounds I mentioned in point 4, the agro on the bus will cut your data throughput, and your data could be corrupting. See my other post. People like Compaq can get away with it because they know exactly what will be in the case (like no l33t cold cathode tube producing tons of EMF, and a kewl port in the side to destroy the cases EMF shielding anyway; to pick two problems from thin air)

7. Live in a part of the world that uses 50 fps PAL, trust me its better. Also no one in thier right minds uses uncompressed video when there are perfectly good broadcast standard codecs like the DV ones around. Guess you like the hard life.

8a. Agreed - thats why RAID exists - you can get better performance and/or reliablity than an individual drive unit regardless of the interface type.

8b. You mean like that internal volatile cache in your CPU, or that one in the buffer in your SCSI/IDE/MEMORY bus? The way to solve uncommitted writes is a journalling filesystem or 60USD of UPS, its not a problem of the interface.

Re:Sticker Shock (OT)

[Clover_Kicker]

"sticker shock" isn't really a technical term, it refers to getting a nasty surprise about the cost of something, in this case huge quantities of toner and paper.

I wasn't able to find a precise definition, or the origin of the phrase. I've usually heard it in the context of buyng a car, i.e. once you've added in freight+tax+rust treatment etc. etc. etc.

IDE/ATA nomenclature

[Anonymous Coward]

I always thought IDE was a misnomer. "Integrated drive electronics"? Don't SCSI drives also have their drive electronics integrated? I believe the name arose from a comparison to ST-506 where the drive electronics were on a separate controller board, with control signals for stepping, and the read and write data (FM/MFM/RLL), transferred over a cable to the drive. Try that at today's head transfer rates.

ATA is just as much a misnomer, since it stands for AT Attachment, and AT stands for "Advanced" Technology (well, maybe it was advanced for the early 80's).

Now we have Serial ATA, which looks nothing at all like the AT bus that ATA was originally attached to.

Yeah right Bastardly

[Anonymous Coward]

Sure thing. and when you got for the land speed record on the salt flats you can only use a certain kind of rocket motor, and it has to be limited to 7200 RPM. Why would you use a faster RPM turbine to break it! NO ITS AGAINST THE RULES. Fuck you, the land speed record can be gotten any way the fuck they want as long as the wheels stay on the ground. Strap a nacelle from teh startship enterprise, who cares.

If performance and reliability are criteria, IDE loses every time. Even better than a rocket motor in the land speed record. Its even more reliable than the consumer crap!

Sorry your such a shyster shylock and that you are too fucking cheap to regard quality, reliability and maximum speed. You have your SATA hard drive with that fucking flimsy connector.

Inexpensive Disks?

[Ionizor]

I'm afraid you have your acro wrong.

RAID is Redundant Array of Independent Disks.

Interesting info. Someone mod him up.

[Valdrax]

Firewire is unusable for system drives because the ID is dynamically assigned. There is no way to decide which comes first.

More importantly for large systems, if a drive fails in a RAID array and you pull it out and plug a new one back in it will get a different ID than the old one and thus not be part of the array it should be part of.

That's a pretty good objection. I honestly hope this gets moderated up. I had no idea this was a problem for Firewire.

JPC - Jerkoff. Puke. Cumguzzler.

[Anonymous Coward]

Hmm, fuck you snarky asshole. SCSI will be faster for some time. iSCSI on 10GE is the SCSI vapor now, but 320 is here and real and in the flesh. SATA is still a wet dream.

1. Another cheap ass loser hack. Cheap assed niggard shyster idiots use out of spec because they play quake and don't do work. No go back to over-clocking a Celeron or Athlon, FAST! Before you lost another second!

2.TCQ isn't the only "goodie" SCSI has. Try sparing, and more things than you deserve to know. I'm not going to defile Al Shugart by explaining to a mediocritomaton idiot like yourself why its better. He is laughing at you now. So am I.

3. I can put 15 drives per bus now. Fucktard. SATA isn't even out yet. I can put 15 devices on a 320MB./sec bus and I can get a RADI card with 3 busses on them. Let's see you do that with 3Ware you fucking retard, or EVER with SATA.

4. Fuck you.

5. Cheap shit connector. Have fun with broken Molex connectors and bent 40 pins while you wait for the vapor to clear. Suck the shit out of a mad cow's ass.

ASSHOLE.

Fuck you, Mark. And fuck your highfalutin cheers

[Anonymous Coward]

You are a cheap-assed stupid zealot asshole. You like power PC too? You are such a dump cheap assed fucking bitch if you think SCSI loses.

Yeah, Sun, HP and IBM are switching in droves to HIGH END IDE setups. Yeah right. And monkeys are flying out of my fucking ass.

Go back to playing Quake and shut your fucking cakehole, stupid fucking bitch.

I find it amusing that all the IDE ankle biters have to try and concoct bullshit ways for IDE to beat SCSI. That's their goal in life is to try and subjugate the best for less. They always fail. You are a failure too, fuckhead.

MOD PARENT DOWN

[Anonymous Coward]

-1, You're fucking old and boring us with your past

Re:This just looks expensive. shutup, sugarbitch.

[Anonymous Coward]

That has to be the stupidest, most unsupported, unfounded ridiculous pile of detritus I have ever seen defecated here. I won't even bother responding to each point - it is crap, rife with unsubstantiated conjecture, largely incoherent and ridiculous. Your own words serve as a testament to your foolishness. It is better to be thought of as a fool than to speak and remove all doubt. You have removed all doubt, "Our Survey Says: DING! Justin Cormack is an idiot, can't spell, can use a shift key, and doesn't know how to use ordered lists or use the "a" tag to link to this mystery fairy material that substantiates his ridiculous claims.

Mr. PhD? Really? I hope you don't make a habit of eructating the low level shit you just sprayed across the Internet into the cheesy MySQL backend of Slashdot to be forever entombed here. Your high and holy career academic self spelled officially, irreverent and devices and used that's without proper punctuation.

Here is a sample A and OL/LI tag usage which also aides in my colorful delivery of an attack on the vile purveyor of mediocrity and ass philanderer, Justin Cormack:

<a href="http://www.worldofbullshit.com/articles/magi cal_place_where_cormack_found_evidence_to_prove_hi s_mumbo_jumbo.html">Hi, I'm Justin - here is my link to a bullshit site that substantiated stupid things I say.</a><p>

Here is a litany of gripes I have with Cormack (thus demonstrating the ordered list):
<ol>
<li>Justin is stupid </li>
<li>Justin speaks of truths which he cannot corroborate</li>
<li>One must suspect that a person who displays said qualities likes to fuck dogs</li>
<li>Justin is the real Goat Fucker, not RMS.</li>
<li>Justin's pseudo intellectual underpinnings lead to a life of career academia. In this career, which is a vow of poverty since he is too stupid to patent anything useful, he is prone to liking cheap assed lame shit like IDE and SATA, because he cannot afford the real deal he deprecates the good shit.</li>
</ol>

And no, to see it all in action, parsed! With a special HIDDEN LINK!

Hi, I'm Justin - here is my link to a bullshit site that substantiated stupid things I say.

Here is a litany of gripes I have with Cormack (thus demonstrating the ordered list):

1. Justin is stupid
2. Justin speaks of truths which he cannot corroborate
3. One must suspect that a person who displays said qualities likes to fuck dogs
4. Justin is the real Goat Fucker, not RMS.
5. Justin's pseudo intellectual underpinnings lead to a life of career academia. In this career, which is a vow of poverty since he is too stupid to patent anything useful, he is prone to liking cheap assed lame shit like IDE and SATA, because he cannot afford the real deal he deprecates the good shit.

Nice spelling "doc". PhD me baby.

[Anonymous Coward]

What a retard.

Yes! You're missing a lot of things.

[egarland]

Why are there so many bad anti-SATA arguments being moderated up?

To counter your points:

Cable length:

Cable lenght of IDE *is* an issue in full towers and in large systems. Using more than 32 IDE drives in a IDE based storage system is very hard since you can't place that many within range of the controlers. 1 meter should increase the maximum number of drives within range to around 128 which makes for a very large storage server.

Connector size:

You can fit 8 SATA connectors in the space of 1 PATA connector that can service 2 drives. If you are doing hot-swap RAID each PATA port can only service one drive because you can't hotswap in master/slave configurations so this effectively gives 8 times the port density for RAID controlers. I doubt anyone will build a 64 drive SATA RAID controler anytime soon but the point is they could do it in the same space as an 8 drive controler.

Also, A motherboard manufacturer can fit 32 SATA ports in the space they used to take up with those 4 IDE ports. They won't, of course, because no desktop machine needs that many SATA ports.

One device per controller:

One device per controler helps in reliability, compatibility and bandwidth/drive. As I've said in other posts, SCSI and Fiber channel look fast until you fill the bus up and divide the available bandwidth by the number of drives.

RAID5 transfer rates:

Hardware accellerated RAID 5 can read exceptionally fast and is preferred for read heavy applications where redundancy is needed (My desktop). The bandwidth is exceptionally helpful in doing RAID5 rebuilds while still using the drive array. Take for example a 12 drive RAID5 array doing a rebuild and a large file read. If the rebuild is reading from 11 drives and writing to one, each at 20MB/s the rebuild is using 240MB/s. Then the OS can be reading from the 11 good drives at 20MB/s using another 220 MB/s. You are then using a total of 460 MB/s which would swamp any SCSI bus. In an SATA system with dedicated bandwith for each drive that isn't the case.

Speed:

Firewire and USB2 are both in the 40-48 MB/s range (400-480 Mb/s) SATA is 3 times that speed at 150MB/s (1.5Gb/s)

SCSI, FCAL and Firewire all have issues that make them unusable in the desktop harddrive space:

SCSI/FCAL:

• 
  When is the last time you had to compile the driver for your IDE controler into your kernel to get it to boot?
  
  IDE is unique among all the storage types because the software interface is a standard. I'm not talking about he cabling or singlaling, I'm talking about the way the OS talks to the hardware. All other methods of attaching storage need some sort of hardware specific driver to talk to the OS. PATA has always had this and SATA maintains backwards compatibility. This is a huge feature that no other method of attaching storage has.
  
  Chips to talk using modern SCSI signaling protocols are extremely expensive to produce as compared to SATA. I'd conservatively guess an order of magnitude different ($4 vs $40) but the difference is probably more. When you are selling your drive for $50 a $40 chip to attach it to the bus is not an option. FCAL is worse.
  

Firewire:

• 
  Firewire is unusable for system drives because the ID is dynamically assigned. There is no way to decide which drive comes first.
  
  More importantly for large systems, if a drive fails in a RAID array and you pull it out and plug a new one back in it will get a different ID than the old one and thus not be part of the array it should be part of.
  

Someone please moderate me up! All these "SATA is stupid, a tin can and string is better!" arguments are making my head ache

Karma: Bad. (Mostly the sum of smacking supid people upside the head)

Firewire is unusable for system drives

[egarland]

Firewire is unusable for system drives because the ID is dynamically assigned. There is no way to decide which drive comes first.

More importantly for large systems, if a drive fails in a RAID array and you pull it out and plug a new one back in it will get a different ID than the old one and thus not be part of the array it should be part of.

IDE is unique among all the storage types because the software interface is a standard. I'm not talking about he cabling or singlaling, I'm talking about the way the OS talks to the hardware. All other methods of attaching storage need some sort of hardware specific driver to talk to the OS. PATA has always had this and SATA maintains backwards compatibility. This is a huge feature that no other method of attaching storage has.

SCSI is not expensive "just because". It's expensive for the same reason that fast 3D cards are expensive, not because the volume is low but because the tecnology is complicated. Chips to talk using modern SCSI signaling protocols are extremely expensive to produce as compared to SATA. I'd conservatively guess an order of magnitude different ($4 vs $40) but the difference is probably more. When you are selling your drive for $50 a $40 chip to attach it to the bus is not an option. FCAL is worse.

(Arguments recycled from my previous posts)

Dispelling SATA myths

[egarland]

Why are there so many bad anti-SATA arguments being moderated up?

I'll counter some of the points made in posts here.

SCSI is faster:

No, it isn't. It's true that SCSI drives are currently faster and that high end SCSI is 320MB/s but speed of the bus isn't what's important, what matters is how fast you can get data to and from the drives.

Since no single drive can read or write at faster than 100 MB/s. The speed of the bus only comes into play with multiple drives and here is where SATA shines because each drive has it's own dedicated bandwith. Got 4 drives, that's 150x4=600MB/s. Got 8, 1.2GB/s. Got 32, 4.8GB/s (note that's GigaBYTES/Sec).

Then the argument comes that SCSI drives themselves are faster, have better seek times, faster transfer rates, longer warrenties, look better, blah blah, blah. This is a property of the drive mechanics, not of the interface. There wasn't enough demand for server class IDE drives to warrent manufacturers creating whole new lines for them. That won't be the case with SATA drives. There have alrady been server class SATA drives announced and only time will tell weather the ultra high end 15K RPM drives show up with SATA interfaces but I'd be surprised if they didn't.

Cable length:

Cable lenght of IDE *is* an issue in full towers and in large storage systems. Using more than 32 IDE drives in a IDE based storage system is very hard since you can't place that many within range of the controlers. 1 meter should increase the maximum number of drives within range to around 128 which makes for a very large storage server.

Connector size:

You can fit 8 SATA connectors in the space of 1 PATA connector. That's 4 times the port density of PATA. If you are doing hot-swap RAID each PATA port can only service one drive so this effectively gives 8 times the port density for IDE RAID controlers. I doubt anyone will build a 64 drive SATA RAID controler anytime soon but they could do it in the same space as an 8 drive controler.

Also, A motherboard manufacturer can fit 32 SATA ports in the space they used to take up with 4 IDE ports. They won't, of course, because no desktop machine needs that many SATA ports but I expect to see 8 (4 raid, 4 standard) or 6 standard.

One device per controller:

One device per controler helps in reliability, compatibility and bandwidth/drive. As I've said in other posts, SCSI and FCAL look fast until you fill the bus up and divide the available bandwidth by the number of drives.

This is also important for drive arrays since the device doesn't need to be configured as to which device it is. No master/slave. No SCSI id 12.

RAID5 transfer rates:

Hardware accellerated RAID 5 can read exceptionally fast and is preferred for read heavy applications where redundancy is needed (My desktop). The bandwidth of SATA is exceptionally helpful in doing RAID5 rebuilds while still using the drive array. Take for example a 12 drive RAID5 array doing a rebuild and a large file read. If the rebuild is reading from 11 drives and writing to one, each at 20MB/s the rebuild is using 240MB/s. Then the OS can be reading from the 11 good drives at 20MB/s using another 220 MB/s. You are then using a total of 460 MB/s which would swamp any SCSI bus. In an SATA system with dedicated bandwith for each drive that isn't the case.

SCSI, FCAL, Firewire and USB 2.0 all have issues that make them unusable in the desktop hard drive space:

SCSI/FCAL:

• Both SCSI and FCAL are just too expensive. This is not, as many people claime, because of small volume. SCSI controler chips are built in high enough volume to take advantage of economies of scale. They are expensive for the same reason that fast 3D cards are expensive. They are just big and complicated and hard to make. I'd conservatively guess a SCSI chip is an order of magnitude more than SATA ($30 vs $3) but the difference is probably more. When you are selling your drive for $50 a $30 chip to attach it to the bus is not an option. FCAL's cost is even worse.
• 
  
  Also, When is the last time you had to compile the driver for your IDE controler into your kernel to get it to boot?
  
  IDE is unique among all the storage types because the software interface is a standard. I'm not talking about he cabling or singlaling, I'm talking about the way the OS talks to the hardware. All other methods of attaching storage need some sort of hardware specific driver to talk to the OS. PATA has always had this and SATA maintains backwards compatibility. This is a huge feature that no other method of attaching storage has.
  
  

Firewire/USB:

• Firewire and USB are unusable for system drives because the ID is dynamically assigned. There is no way to decide which drive comes first.
• 
  
  More importantly for large systems, if a drive fails in a RAID array and you pull it out and plug a new one back in it will get a different ID than the old one and thus not be part of the array it should be part of.
  
  Firewire and USB2 are both in the 40-48 MB/s range (400-480 Mb/s) which is too slow for modern drives (especially when attaching multiple drives). SATA is 3 times that speed at 150MB/s (1.5Gb/s) with dedicated bandwidth for each drive.

Someone please moderate me up! All these "SATA is stupid! We should all switch to a tin can and string. It's so much better!" arguments are making my head ache

Karma: Evil (Mostly the sum of smacking supid people upside the head)

Re: Fuck you, Mark. And fuck your highfalutin chee

[Anonymous Coward]

I mean motorola powetr pc, you fucking dumb shit parent of parent. I like IBM power PC a lot. FUCK YOU WHORE.

SCSI fanboy...

[Wolfrider]

--I like SCSI as well - IDE limits you to four devices (sometimes only 2 if you have an OLD moboard), even old ISA Adaptec SCSI AHA1542 cards support 7 (8 counting the card.)

--Now I've got 2 old(er) AHA2940 Ultra Wides that will support 15 devices out of the box - 68 *plus* 50 pin. I've spent quite a bit of money putting together my SCSI chains, even tho I bought most of the HD's on the cheap. Under Linux they're easy to LVM together so you can have (2) 2-gig drives show up as one 4-gig filesystem. I even have an old Plextor 4-plex CDRom above my 8x4x32 Sony IDE burner for disc>disc copying and audio.

--The thing about SCSI though, is that the adapter card is important! Stay away from ISA. (Even a non-BIOSed PCI Advansys gives better performance than my old ISA AHA1542.)

Oh, and don't forget to terminate the chain! :)
.

Re:Give me Firewire!-here we go again!

[Salamander]

Yeah, but paying attention to case only works if the people providing numbers do so as well, and so many people screw up MB vs. Mb that you can't count on it. It's one of those things where it's better just to leave no room whatsoever for error by spelling it out.