Slashdot Mirror
Serial ATA and USB 2
An anonymous reader pointed us to an anandtech article that discusses the future of
device attachment. Specifically USB 2:Electric Boogaloo and Serial ATA.
Definitely 2 standards will likely matter a lot in the future.
That Serial ATA stuff looks interesting...
As far as Serial ATA goes, why reinvent the wheel? Why not just adopt the SSA protocol for drive attachment? If it was widely adopted the price would come down significantly. As far as speed and flexibility, it is already further along that Serial ATA is attempting to be. I guess that since it comes from IBM, the odds of it being adopted elsewhere (despite the published spec) are slim, though.
-- Two men say they're Jesus. One of them must be wrong. - Dire Straits
fellow karma whores:
in the interest of space conservation and sorting, and so that the rest of the discussion can be devoted solely to discussion of USB 2.0 and Serial ATA themselves, i would like to request that all Firewire-related flaming be posted as a reply to this message.
suggested topics:
-USB 2.0 is a pathetic excuse to destroy Firewire, designed solely to prevent a standard not controlled directly by Intel from gaining importance.
-Firewire/Serial ATA/USB 2.0 is not open enough in the sense that the open source movement would like it to be.
-Firewire is outrageously liscenced and expensive.
-USB 2.0 and Serial ATA will be far more widely used and supported than Firewire.
-Firewire will be far more widely used and supported than USB 2.0 and Serial ATA.
-WH04 D00D 1 \V4N7 4 830\VULF CLU573R 0F 1B00KZ
-[Firewire, Serial ATA, USB 2.0] is far technically superior to [Firewire, Serial ATA, USB 2.0]
-[Firewire, Serial ATA, USB 2.0] is vaporware.
-by the time [if ever] USB 2.0 comes to market, Firewire will already be in its second generation and far superior to the USB 2.0's first generation in every way USB 2.0 defeats Firewire now.
-Firewire is already widely supported.
OK, have fun!
Irritable, left-wing and possibly humorous bumper stickers and t-shirts
Their treatment of USB 2.0 was severely lacking. I wish Apple would drop its firewire tax (if not completely, then at least a few notches) so we could use a technology that was designed for things like this. This is the second time I've linked to this article today, but it's worth a read.
- http://www.mackido.com/Hardware/USB2.html
- http://www.mackido.com/Hardware/USB20.ht ml
It's easier to just link to these articles than just rehash the same old arguments every time USB 2.0 is mentioned. Suffice it to say it'll be more than a day late and a dollar short, but, sadly, it will probably catch on due to Intel's stranglehold on the chip market. Once again, if Apple would ease up on the 1394 tax, we would all be better off (and Apple would have at least one victory against Wintel under its belt). Alas, they will not do that, so tomorrow's iMacs will probably ship with USB 2, 3, and 4, and FireWire 2, 3, and 4 will be quietly brushed under the rug._________________
rooooar
Every last bit of it. It never gets implemented or used though. USB sat on Intel motherboards from the 430HX chipsets and beyond. Never used until MS got off it's ass and put out Win98. And even now, we still see computers shipping with IRQ wasting PS/2 and serial/parallel ports.
If there's one thing I admire Apple for, it's their periphreal design. Even on the OLD Macs there was ADB. Then Apple decided to use USB. And look at the iMac. Or a new G4 for that matter. Pure simplicity for ports on the back.
With things like this Serial ATA and Firewire, you can even eliminate the clutter *inside* the computer. I just hope it finally HAPPENS! Why do I have to pay for all those serial/parallel ports on my machine? If we'd all just *forget* about them the price on USB stuff would go way down.
Where's the ideal PC? No mucking with IRQ hogs, no mucking with old IDE, serial or parallel technology. And when we see it, heres to hoping Linux runs on it.
Suggestion -- if you number the items on the list, it's easier for the "me too!" people. Like, I could say "3, 4, 7, 9, 10!!!" to indicate my support for those items in your list.
Maybe this is the next generation of Slashdot posting... when the answers are so predictable, just number them, then we can all just post/vote for our favorites.
_________________
rooooar
That standard is IEEE-1394, also known as FireWire or i-Link.
Like Serial ATA, 1394 runs at very high speed over inexpensive cabling consisting of only two pairs of signal lines and one pair for power. The cabling does not impede airflow like parallel ATA cables.
Like Serial ATA, 1394 can be used to transfer data to or from ATA (IDE) interfaces, completely transparently to the host.
Like Serial ATA, 1394 can be (and is) implemented in extremely cheap chips. In fact, there are sub-$5 "tailgate" chips which provide a single-chip 1394-to-ATA adapter. If 1394 was integrated into the drive instead of Parallel ATA, the drive could actually be cheaper than it is now.
UNLIKE Serial ATA, 1394 can also be used to connect SCSI devices, digital cameras, digital audio and video, TCP/IP networking, and many other categories of devices. 1394 already appears to be the interface of choice for most upcoming consumer electronic gear.
UNLIKE Serial ATA, 1394 is already a recognized standard, and work is already underway to extend it to speeds of up to 3.2 Gbps.
UNLIKE Serial ATA, 1394 supports complex topologies: devices with multiple 1394 ports for daisy chaining and hubs. This provides considerable flexibility in how devices are hooked up.
UNLIKE Serial ATA, 1394 supports multiple masters on the same bus.
UNLIKE Serial ATA, 1394 is available NOW, and is already built into some computers.
UNLIKE Serial ATA, 1394 is already supported by Microsoft Windows, and to some extent, Linux.
So why do we need a new standard?
Part of the problem is probably Intel. Initially they announced that they were a supporter of 1394, and that they would build support for it into all of their chipset. They did this with USB, and now it's hard to buy a PC without USB. But when push came to shove, for some reason they didn't do it. Apparently this is due to their work on "USB 2", which pushes the speed of USB into the same range as 1394, but unfortunately still has most or all of the limitations of USB.
Part of the problem is probably Apple. They made ridiculous royalty demands ($1/port), and scared many vendors away. They've since backed down to much more reasonable numbers, but some of the damage was done.
Part of the problem is probably the ATA committee itself. They may be experiencing "NIH" syndrome, preferring to invent a new standard rather than using an existing one, no matter how suited the existing one is.
Part of the problem is just the standard chicken-and-egg question. If computers don't have 1394 interfaces, why should disk manufacturers build 1394 into disk drives? If disk drives don't have 1394, why should computer manufacturers build 1394 into the computers? Of course, serial ATA may have the same problem, but it may be less pronounced. The very fact that serial ATA is less functional may make it an easier sell from a marketing point of view.
What should be done? IMNSHO, they should scrap the proprietary Serial-ATA interface, and adopt 1394 as the official Serial ATA standard.
As far as USB 2.0 goes, well, I don't have any USB devices yet, so I guess I really don't care at this point.
I'm sure I've said several idiotic things here, so anyone who's more of an expert in these matters, please smack me around a bit.
"Destroy science and religion. Science would re-emerge exactly the same; but not religion." - Penn Jillette, paraphrased
I have a keyboard, mouse, monitor, nic, and headphones coming from my computer. None of them use any new fancy expensive technology. Is the ordinary user going to have every gadget in the world on his/her computer? Does anyone need 256(?) devices? Who wants to pay more for a usb mouse when it is less supported and more expensive? I don't think I need it and I'm intrested in knowing what kind of people do. Maybe everything will be USB someday and make things simpler, but I think everything is fine how it is. So... can anyone tell me how this will revolutionize computing?
Apple was charging a $1/port as of Jan 991 5/firewire.html
e wfirewirelincensing.html
http://www.macobserver.com/news/99/january/9901
Then it went to a $0.25/system as of May 99
http://www.macobserver.com/news/99/may/990512/n
How much more do you want it dropped, btw?
Does this mean Intel is charging nothing for it's USB implementations? Or that it's hidden in the costs of their chipsets, CPUs, etc?
-AS
-AS
*Pikachu*
Apple et all has lowered the cost to $0.25 per system, as opposed to $1 per port
Firewire licensing
So unless you think $0.25 per system is unreasonable(up the wazoo?), perhaps Firewire *does* rock?
-AS
-AS
*Pikachu*
It's because until iMacs came about, there was no *reason* to use USB; serial/parallel/PS2 all coexisted.
So Intel didn't push USB very much until after Apple did. You'd think Intel would return the favor by supporting Firewire, just to be fair.
I like Firewire. Unfortunately, the PC support is so poor, my next PC may have to be a Mac!(I have a DV camcorder)
-AS
-AS
*Pikachu*
May just be an iMac running Linux, then...
I mean, about the only thing missing is the Firewire HDs...
-AS
-AS
*Pikachu*
AFAIK, Firewire is not intended for use with internal devices. (Its internal counterpart is Device Bay, which, unfortunately, looks pretty dead.)
For that matter, Serial ATA is not intended for external devices, so they're really apples and oranges. (No pun intended.)
I, for one, am excited to see somebody is finally addressing the issue of internal connections. Installing a "parallel" ATA drive seems like such a cumbersome process in the era of USB.
MSK
The point of using USB or Firewire is simplicity; only 2 or 3 ports on the back of the PC, maybe the monitor, maybe the keyboard.
Which means, fundamentally, users won't have to figure out cables, converters, passthroughs.
Which means the ordinary user will plug his monitor(maybe) into his USB or Firewire port in the back, and then the keyboard into the monitor, or into the back, if desired, and then the mouse into the keyboard, or the monitor, or whatever. And then plug in the speakers. And the mic. And the modem. And the headphones. And the printer.
All with 2 or 3 ports.
Vs the 8 ports today(2 PS2, 2 USB, 2 parallel, 2 serial)
So just by dropping PS2, parallel, and serial, price goes down.
As does support costs for motherboard design, BIOs, drivers, OSes, and drivers having to deal with all of the above.
Whoever said USB would revolutionize it, anyway? It's an incremental improvement!
-AS
-AS
*Pikachu*
How about politics? Apple pushes Firewire, Intel pushes USB?
What does that have to do with the cost?
A firewire board costs $80 because of the costs of the PCI board, the drivers, the support, etc.
Imagine, if Intel just put firewire support into their chipset? What would it cost?
How about the cost of just the connectors?
I mean, of course the implementation is what makes firewire cost $80. How much does a add on USB board cost, then?
-AS
-AS
*Pikachu*
_________________
rooooar
If you can't connect a reasonable number of devices to a serial ATA chain (like, oh, 15, for instance?) it sounds to me like more hype than substance.
- A.P.
--
"One World, one Web, one Program" - Microsoft promotional ad
"Remember when the U.S. had a drug problem, and then we declared a War On Drugs, and now you can't buy drugs anymore?"
Not unless iMacs and Apple dies.
Not unless Sony stops making iLink camcorders, CDRWs, VCRs, digital TVs, and notebooks
Not unless Canon, Phillips, et al also stop making Firewire devices
Not unless Intel can push something better and cheaper than Firewire to all the above companies
-AS
-AS
*Pikachu*
I hope this "standard" goes down in flames. We have the opportunity to ditch the decrepit kludge known as ATA/IDE and what does Intel do? They scrape off some of the rust and add chrome mud flaps. They should be ashamed of themselves. Serial ATA is register compatible with the WD1003 disk controller. If you don't know what that is, ask your parents. It was introduced for the IBM PC/AT when 40 MB disk drives were hot stuff. All this "standard" does is to replace a parallel cable with a serial cable. It intentionally leaves all the accumulated crud of the ATA interface in place. There is no reason to drag this baggage into the future. ATA should be deprecated and replaced with a modern I/O interface such as IEEE-1394 or SCSI over a high speed, hot pluggable, serial interface.
Mea navis aericumbens anguillis abundat
1. Serial ATA is an internal standard, Firewire is an external standard (although it can be used internally). Explain to me why Apple includes ATA drives inside the G4 when it has an internal Firewire port?
2a. You do not need topology internal to the computer. So hubs and daisychaining is meaningless.
2b. Since four ports of Serial ATA could technically operate in parallel (the bandwidth is not shared), four devices have a combined available bandwidth of 600 MB/s, as opposed to firewire's 400 Mbps (~40 MB/s)
2c. The max bandwidth of firewire, 3.2 Gbps, is ~320 MB/s, making it about the same speed as two Serial ATA ports running at the initial speed (which is not the maximum bandwidth)
3. Serial ATA is a point to point protocol. There is no master.
4. Serial ATA is already supported under both windows and linux, past the extent of IEEE1394. This is because Serial ATA uses the same protocol as regular ATA, and thus works exactly the same on an OS level. Unless you look at the chipset, the OS probably will not know it isn't using parallel ATA.
5. ATA is a cheaper solution than Firewire. Currently all firewire drives are actually ATA drives with a ATA<->Firewire chip inside, so Serial ATA reduces their cost, as well as requires a smaller engineering cost to change the chips on the drive to be native Serial ATA.
6. <i>What should be done? IMNSHO, they should scrap the proprietary Serial-ATA interface, and adopt 1394 as the official Serial ATA standard.</i>
What makes you think that Serial ATA is a proprietary interface?? Why would it be any less of an open standard than Parallel ATA? At least you don't need to pay licensing fees for ATA.
This is my opinion, moderate down accordingly
You have to look at the interface between the motherboard or I/O card and the drive as an RF transmission line. You want constant impedance, correct termination and shielding. With parallel interfaces you have to also worry about timing skew, skew is when the signals do not arrive at the receiver at the same time, some are a little early or late. Ribbon cables introduce problems of crosstalk between adjacent wires in the cable. The ribbon cable's impedance may vary depending on how the cable is routed in the chassis. One way to deal with this is to double the number of wires in the ribbon cable and alternate between signal and ground. Each signal/ground pair can be twisted, like in twisted pair LAN cable. An external shield can also be wrapped around the ribbon cable. There are also problems with high power consumption in the driver chips that are connected to the cable. Higher signalling speeds increase power consumption, EMI and crosstalk. Termination becomes more critical as speed and length are increased. What worked at 10 MHz may be totally inadequate at 40 MHz. High speed parallel cables can get very expensive.
Mea navis aericumbens anguillis abundat
Serial ATA will only make sense if you can connect more than two damned devices to the chain.
If you had read the article, you would know that Serial-ATA is nothing like conventional IDE, and is a serial design, with a low-pin-count connector and a point-to-point design. You can have precisely one device connected to an SATA port. The idea is, of course, to have a bunch of SATA ports on the mainboard (you should be able to stuff six or eight in the space needed for existing 40-pin ATA ports).
Personally, I prefer firewire, which does support daisy-chaining.
dragonhawk@iname.microsoft.com
I do not like Microsoft. Remove them from my email address.
Firewire is scores different from USB. All Firewire devices work independant of the processor meaning my camcorder can transfer video directly to my hard drive while my processor is busy handling other tasks. USB on the otherhand needs the processor in order to communicate between two devices which ends up slowing the system down with large file transfers. Bandwidth isn't everything. Because Firewire drives have hteir own mini-processors you can have two devices (lets say a camcorder and FW hard drive) that can communicate without even needing a computer. The camcorder could just transfer the video to the hard drive by plugging the two together. USB devices will not work in such ways. Besides the licensing fee Apple charges to use the name "FireWire" is 25 per device (or port) which is negligible and that is because Apple owns the term "FireWire", Sony doesn't have to pay anything by calling their IEEE 1394 port the i.Link.
I'm a loner Dottie, a Rebel.
Does anyone know if Serial ATA will support more than 4 devices?
First, the article states quite clearly that Serial ATA is a point-to-point protocol. This means one and only one device connected per port. As SATA also has a low pin count, the plan is to have more SATA ports on the mainboard. You could probably fit six or eight SATA ports in the space needed for two 40-pin ATA ports.
Second, ATA has a limitation of two devices per bus (port). You get four devices by having two ATA ports. Want six devices? Use three ATA ports. Most likely, you'll need to buy an add-in ATA controller, as I've never seen or heard of a mainboard with more then two on-board ATA ports. Of course, ATA is incredibly brain-damaged, and generally requires an IRQ per bus on PCs (or breaks compatibility with many things). The answer to that, of course, is not to use ATA... :)
And no, I can't afford the inflated price of SCSI.
You can afford all that nifty hardware, but you cannot afford an extra $30 per device in order to get a bus that actually works and performs well? Well, your loss. :-) Me, I've been running an all-SCSI system for some time, and I love it. No looking back for me!
dragonhawk@iname.microsoft.com
I do not like Microsoft. Remove them from my email address.
The same is true for Serial ATA drives. You can bet that the first Serial ATA drives will NOT be cheaper than equivalent Parallel ATA drives. That will only happen as they ramp the volume.
If there was customer demand, they could start ramping production of 1394 drives now. Why should we wait until mid 2001 for them to start ramping Serial ATA? (I addressed this question in my earlier post.)
You need a non-trivial topology any time you want to hook up more devices than you have dedicated ports. If manufactured in equivalent quantities, hardware support for four 1394 ports (at 3.2 Gbps by 2001) should not cost more than four Serial ATA ports. Sure, but why compare two Serial ATA ports to only one 1394 port? With either interface the per-port cost will be about the same, but 1394 will offer 3.2 Gbps at about the same time that Serial ATA 1X will offer 1.5 Gbps. Probably sooner, in fact. Of course there's a master. The computer is the master; the disk drive is the slave. 1394 supports any mix of masters and slaves. If all you want to do is add one disk drive to a PC, you don't need that capability. But why restritct yourself if you don't have to? If you want to realize the claimed 1.5 Gbps performance of Serial ATA 1X, you'll probably need a different hardware-level register interface, with different device driver software (at the lowest level; some higher-level driver code may stay the same).It is true that 1394 hardware interfaces are not register-compatible with ATA ports, but 1394 drivers are already written.
Parallel ATA is cheaper today because it is manufactured in high volumes. Neither Serial ATA nor 1394 drives will be cheaper than Parallel ATA until and unless drives incorporating those interface start get manufactured in high volumes. Once the volumes are that high, Serial ATA or 1394 drives should be cheaper to manufacture than Parallel ATA, because they can use chips with lower pin counts, smaller board footprint, and fewer connector pins or edge fingers.Since both Serial ATA or 1394 offer the potential for higher performance than Parallel ATA at lower cost, but both would cost about the same amount, why not prefer the one with greater flexibility and performance.
Bad choice of words on my part. What I really meant was "a new and incompatible interface". Why use one of those, instead of a superior existing interface?I've sorta been hoping for the demise of ATA/IDE and then THIS news comes along. Of course other people have said it but I will too. IDE is a naturally inferior device interface in these times of lots of internal drives and massive amounts of storage. IDE has been one of the key determining factors in the shape and design of current PCs. Mid-towers are by far the most popular case design out now and even the desktop design before that only had four internal bays, as do most towers you can find now. There are only four bays because that is the limit on IDE drives unless you have an IDE expension card. ATA-100 is just stupid in my opinion, with a limit of devices per channel there's no way in hell to max out a channel's bandwidth unless you have a solid state drive. Even IF you maxed out two drives their internal transfer doesn't even come close to the max amount of bandwidth you have available. Not only is there a bunch of bandwidth wasted each drive needs an IRQ and DMA address, SCSI/FireWire only need a single DMA and IRQ since addressing is done between the devices and the controller. I've been chanting for IEEE 1394 to take over internal and external higher bandwidth devices and relagating USB to interfaces and small bandwidth outputs. Having one 400Mb/s (approx 50MB/s) bus would be really efficient for internal drives. Your 10x DVD and 7200rpm hard drive MIGHT fill up the wire but they'd need to be running full transfer at the same time. Even then you could just put other devices on another wire (like the S-ATA shematic). I support FireWire systems in the future for several reasons: less internal addresses used, super duper simple installation, fault tolerance, identical internal and external interface. Less internal addresses is good for the person who buys a full tower and fills it up with toys, easy installation helps everyone, fault tolerance means a loose cable won't totalfuck your RAID, and identical interfaces means removable drives or easily transportable devices that natively support hot swapping. As for USB 2.0 whoopdefrick.
I'm a loner Dottie, a Rebel.
Doesn't the Firewire tax only apply to the use of the trademark "Firewire"? From what I gathered, if you call it by the official (and much less sexy) name IEEE1394, you pay nothing.
But the computer industry is all about momentum. How long will you wait for something which is "real soon now" for such a long time?
The real problem is not getting the bits from A to B. The software abstraction layers, descriptors and class definitions were the parts that took the most time in the USB standards commitees. Microsoft's insistence on making USB one more jewel on Windows 98's crown also contributed a significant delay.
But this is nothing compared to how long 1394 is taking. An environment with no single master is much more complex. But you should also take into account the commitee effect - they have vast plans with cute acronyms to make it take control of everything in your house. Yeah, sure.
USB 2.0 will be identical to 1.1 from the operating system's point of view. It will use the same class drivers and in some cases the same vendor-supplied drivers. This will enable it to reach the market in a relatively short time.
It's not that I'm "pro USB" and "anti 1394" - both have interesting features the the other lacks. It's just reality.
----
Stop worrying about the risks of nuclear power and start worrying about the risks of not using nuclear power.
i've been thinking about this a great deal over the last minute and a half, and i realized something very important: an ibook beowulf cluster would, indeed, be a pretty cool idea. one word: Airport.
Airport would serve wonderfully as the high-speed private network Beowulf requires. and it would very much help with logistics-- no cabling required, which makes things a LOT easier. hell, you could just take the ibooks and stack them in the corner of the room. no messy cables or overloaded hubs.
While ibooks themselves would maybe be a tad expensive to buy them for just this purpose-- after all, you're paying for an LCD screen you won't use-- i'm wondering about what happens when iBooks start getting passed out to grade school students. Think about it; you've got about 20, 30 children per room. ach one is holding an ibook, and most of these are going unused for most of the time. So install the beowulf software on each ibook and have the school network propigate tasks to be used with the spare processor cycles. Suddenly this isn't a grade school anymore; it's a _supercomputer_, with upward of a couple hundred parrallel ibook nodes. This would go beyond cracking RC5 or ripping mp3s for the school administrator; you could actually rent out task time on the ibook beowulf the way they rent out supercomputers at universities. It would be a lot less reliable in terms of exact time because the students would be using some of the computing power to themselves, but still it could work pretty good, and maybe give some extra money to the schools. our schools are underfunded anyway, and hell- if they did something like this to bring in a little extra money, maybe they could _afford_ things like a decent computer network or computer teachers or laptops for the students.
And i'm sure the beowulf software would run wonderfully on the BSD core of mac os x. How well would Beowulf run in a loosely structured dynamic environment such as a school where the nodes of the network are being periodically individually shuffled around into different physical areas of the network, of out of it?
just a thought.
Irritable, left-wing and possibly humorous bumper stickers and t-shirts
Several posters have made comments that Apple has dropped their Firewire tax to a reasonable price of $0.25, so it shouldn't be a problem.
There's a little casualty issue here. Apple only dropped their prices *after* other companies began casting about for alternatives. Here's a MacKiDo quote concerning a 3 port solution: "Apple is now seeking US$3 in royalties on a 1394 chipset that sells for less than US$5." They go on to say that it was possible that "some of Apple's competitors--perhaps like Intel--are being charged higher licensing fees than those cooperating with the Macintosh platform." We don't know if that's true, but if Apple attempted to use 1394 as a weapon, then the reasons for USB 2.0 and Serial ATA are obvious.
Intel could have changed course after Apple dropped their prices, but sometimes projects acquire a life of their own once started. Intel did not charge any royalities for the original USB and announced that they planned to do the same for USB 2.0, so it's got a lot of external support as well. Plus, I haven't seen any guarantees from Apple that they won't raise the tax again if Firewire becomes the standard.
To quote from the article, "Most important is the fact that Serial ATA is software/register compatible with Parallel ATA, which means there is no need to rewrite anything at the driver or OS level."
Which means that Linux and Windows already support it, and not merely "to some extent".
Firewire is by far the technologically superior standard. I like technologically superior tools; that's why I have two Beta VCRs rotting in my attic. But I think SATA is going to be very popular for internally-connected devices like disk and tape drives, if only so manufacturers can avoid the higher cost of adopting an entirely new standard instead of just building off the existing one. As a manufacturer, which would you rather do: hand the team a full specification and tell them to implement it, or give them your existing code base and say, "hack this so it does I/O one bit at a time instead of eight"?
--
This is not my sandwich.
So? He falsely claimed that all PC users are idiots and fools for picking such hardware. That's what I slagged him for. I don't know why I responded at all either. Maybe he's just as wrong on that point, huh? At least I threw in a disclaimer saying I was making an assumption. I didn't see any hesitancy from his trollish claims.
From anyone else's point of view, that's still anecdotal. AFAIK, the only authoritative way to get pricing on the chips is to get quotes from the vendors.
Certainly they are. You can get the silicon for a low speed (1.5 Mbps) USB device from Cypress for under $1 in volume; the high-speed (12 Mbps) chips aren't much more.>SCSI is busmaster-based: only one drive can use the bus at a time.
Lest anyone misunderstand, this only means that one device (including initiators) can be _on the bus_ at once. It does not preclude there being more than one request outstanding to the same or multiple devices at one time, waiting for disks to spin etc.
Slashdot - News for Herds. Stuff that Splatters.