USB 3 in 2008, 10 Times as Fast

psychicsword writes "Intel and others plan to release a new version of the ubiquitous Universal Serial Bus technology in the first half of 2008, a revamp the chipmaker said will make data transfer rates more than 10 times as fast by adding fiber-optic links alongside the traditional copper wires." "The current USB 2.0 version has a top data-transfer rate of 480 megabits per second, so a tenfold increase would be 4.8 gigabits per second." This should make USB hard drives easier and faster to use."

Great.

[TaoPhoenix (980487)]

Incredible and grand news if it's on target, and doesn't dissolve into vapor.

Cue the Media Copying Discussions.

(Someone fast on their math: How long would that take to copy a new 0.90 Terabyte drive?)

Re:

[jimstapleton (999106)]

1.5 seconds if you all of your components were fast enough. The drive won't be.

Re:Great.

[morgan_greywolf (835522)]

1.5 seconds if you all of your components were fast enough. The drive won't be.

Exactly. There's still the slowdown associated with the mechanical aspects of the hard drive -- spin rate (RPM), average seek time (ms), etc. On top of that, most hard drive controllers are limited by the technology they use. For instance, a SATA hard drive, even plugged into a USB 2 or 3 port, is limited to 150 MB/s -- but, that's burst speed, not sustained transfer rate.

Re:Great.

[Anonymous Brave Guy (457657)]

On top of that, most hard drive controllers are limited by the technology they use. For instance, a SATA hard drive, even plugged into a USB 2 or 3 port, is limited to 150 MB/s -- but, that's burst speed, not sustained transfer rate.

Indeed. And realistically, it's going to be a pretty short burst: most hard drives today only have something like 8–16MB of cache that might be filled by a smart lookahead algorithm, so your best case with current hard drive technology is that you'll get perhaps 1/10 of a second of high-speed data transfer before hitting the physical barriers.

I'm not sure this is directly applicable to this discussion, though, because AFAIK all current USB drives use different storage technology anyway. It's going to be the limits of that technology that tell us whether USB3's theoretical speeds will actually be useful with storage hardware available in the same time frame.

0.9 TB / 4.8 Gb/s = 1500 seconds

[by Anonymous Coward]

WTF, a chain of "Exactly" and "Indeed", and no one realizing that 1.5 seconds is wrong by a factor of 1000?

Re:Great.

[antime (739998)]

The quoted speed of USB 3 is probably the bus speed, i.e. it's shared by all devices connected to the same host. So one disk won't saturate the bus, but if you plug in a bunch of them the bandwidth won't seem so incredibly massive anymore. Then you have to consider the bandwidth reserved by isochronous devices etc.

Re:Great.

[BosstonesOwn (794949)]

http://en.wikipedia.org/wiki/Flash_memory [wikipedia.org]

No Flash is slow to write , very fast to read. Hence Windows use of it for "ReadyBoost" caching. There is extremely low latency just not enough bandwidth to sustain high levels of I/O.

On the other hand , by introducing fiber into the link doesn't that take away the greatest part of usb ? being able to just fold up the cable and stuff it in your pocket along with a small hard drive ? I know I use it for restoring machines after catastrophic failures (yeah windows) and some times I don't go right back to my desk with the cable and drive and have to toss it in my pocket. I can't do that with fiber, it would fracture.

Re:

[pipatron (966506)]

Uh, what? 0.9TB/(4.8Gb/s) = 25.6 minutes, not 1.5 seconds, even IF the platters would cope with the new speed.

Re:Great.

[Technician (215283)]

Cue the Media Copying Discussions.

The RIAA and MPAA just joined Steve Balmer in needing new office furniture.

How exciting

[FileNotFound01 (1158889)]

This will come in handy when that 100,000 rpm USB drive I'm waiting for ships. It'll be faster and [even] easier to use, especially with the optional depleted uranium housing.

obligatory simpsons quote

[wwmedia (950346)]

Nerd: I've developed a program that downloads porn from the interet a million times faster than normal Marge: Who would need that much porn Homer: [drools]...oohhh..1 million times faster..

I'm more concerned with latency.

[jimstapleton (999106)]

It seems current hard drives test to 40-80M/s (dunno if it's bit or byte, we'll assume byte since it is worst case for my example)., averaging between 50 and 60M/s

480Mbit per second = 60MByte per second. That can handle the average case for a modern hard drive.

4.8GBit/second - 600MByte/s? To utilize that with a drive, you'd need a RAID external enclosure!

Re:I'm more concerned with latency.

[Laebshade (643478)]

I can't find the exact article, but you should read this one about the effective USB 2.0 speed [everythingusb.com]. It states that the effective maximum speed is only about 40MB/sec, and that 60MB/sec can't be achieved due to overhead/software limitations; not sure if this is true now.

Re:I'm more concerned with latency.

[Televiper2000 (1145415)]

My experience with USB is that it has lousy thru-put do to the way the drivers manage data on the host side. We did some heuristic timing tests on USB to serial devices and found that most of them actually degraded the thru-put (time send and receive a packet) of an RS232 connection. We found that devices with Silicon labs ICs could get the desired thru-put, but it seemed they would take up an entire USB channel to do so.

Re:I'm more concerned with latency.

[schwinn8 (982110)]

Exactly... Firewire400 works well for video streaming from a DV cam because it has very little overhead. Even though USB2 supposedly does 480Mbps, it can't do DV because there's too much overhead. Bottom line is, unless USB3 gets rid of the CPU dependency and overhead issues, I won't like it. Sure, with a "ten times" the performance, this won't hinder DV, but that doesn't make it good. I hope they make it systemically-efficient, instead of just ramping clock rates to reach these speeds.

Re:I'm more concerned with latency.

[Barny (103770)]

Mod parent up, hammer meets nail in their post :)

Bonus points if you hook a 108mb/s wireless lan adapter via USB and throw some large data files over it, watch your data speeds closely, and monitor system performance even closer.

Firewire (1394, ilink, DV port, whatever) really was the shit, not only fast, low overheads AND its a peer-2-peer setup, in a pinch you could daisy chain PCs with it for an impromptu 400mb/s lan.

Why didn't they just hang USB out to dry and get power into the eSATA spec and use that? At least then no extra chips would be needed on a mobo, external HDD would hookup with no loss in performance and we might finally see thumb drives that work natively with ANY os as... drives.

Size?

[toppavak (943659)]

I wonder how adding fiber optic links will affect size and power requirements of USB3 devices. Granted, small LED's use minuscule amounts of energy, but wouldn't having to squeeze in power supplies and photodiodes at each end of the cable make it more difficult to squeeze it all into the micro-USB-sized interfaces used on most phones and mp3 players?

Bottleneck?

[mrjb (547783)]

Currently I'm getting transfer rates of about 16 megabyte per second on hard drives connected via USB. That's roughly 160 megabit per second, whereas USB 2.0 can transfer up to 480 megabit per second. While I'm all for faster and better, the bottleneck seems to be elsewhere in this case.

Re:Bottleneck?

[hcdejong (561314)]

In the controller, likely. I'm getting 30% higher transfer rates with FW400 than with USB 2.0 on the same external disk.

Which doesn't give me high hopes for USB3. High-speed links are all good and well, but if they keep including cheap-ass controllers, what's the point?

Re:Bottleneck?

[Jah-Wren Ryel (80510)]

In the controller, likely. I'm getting 30% higher transfer rates with FW400 than with USB 2.0 on the same external disk.

It's as least as likely the problem is in the protocol. USB is synchronous - data every packet received must be acknowledged in a return packet before the next data packet can be transmitted. That back and forth for each data packet means a lot of wasted time where the channel is essentially idle. Sometimes using a shorter cable can make a noticeable improvement.

Firewire has both synchronous and asynchronous modes. In async mode, a bunch of packets can be transmitted before any acknowledgment back is required. That's bad if the cables is flakey, since it will result in a lot of retransmits, but bad firewire cables are the exception, not the rule. So async is almost always way more efficient than synch. I'm pretty certain that you are using the async mode for talking to your disk.

Yeah, but..

[theorem4 (1101729)]

Will this make the new cables more expensive?

Re:Yeah, but..

[LiNKz (257629)]

Also, if you integrate an element of fiber optics into a cable that routinely wrapped up, stepped on, or just basically abused, wouldn't it fail far easier than a standard cable?

In such an event...

[Junta (36770)]

I'll wager a broken fiber in a cable would manifest itself as 'USB2 only' connection.

Re:Yeah, but..

[ggeens (53767)]

When I was working on my Master's thesis, I had to splice optical fiber a few times. Believe me, it's not easy.

Glass fiber is very flexible. You can bend it in any way you want, it won't break. You can cut it, but that takes considerable force. If you break the fiber, you'll break the copper wires as well.

Personally, I think the weakest point in such a cable will be the connectors. Getting the light from one fiber to another requires careful alignment. Any deviation might causes loss of signal. Getting dirt into the connector is probably fatal.

oh goodie

[maniac/dev/null (170211)]

Oh good. Now I get to plunk down $20+ per cable for the latest USB standard. I really like that copper USB2 cables are just about down to free from some online retailers. Looks like that will not be the case with USB3.

The irony...

[packetmon (977047)]

In an interview after the speech, Gelsinger said there's typically a one- to two-year lag between the release of the specification and the availability of the technology,

In today's news, vendors worldwide urged one another to move quickly and get IPv6 deployed by the year 2025. When asked about the one or two year lag between the release of specs and the availability of the technology, vendors quickly pointed out the timeframe it took to implement Packet Over Bongo [eagle.auc.ca] and IPv6 for Refrigerators [glocom.org]. "It's been a long time in the making (IPv6) but we've finally succeeded in getting console connectivity to the fridge. We can now via a command prompt: finger lettuce" stated the happy refrigerator engineer. We never even knew of the existence of IPv4 for refrigerators. Engineers estimate another 20-80 year wait for IPv6.

Plug Shape

[Crock23A (1124275)]

Could be slightly off topic but I had to sound off on this one...

While I appreciate USB's capability for backwards computability, I would much rather have a plug shaped in such a way that I didn't have to flip it over every time I try to plug it in. I don't know about you guys but this is one of the most annoying aspects of using my computer, and I run Windows!

This would also be a great time to make a universal "other side" of the cable, rather than having a different plug for every single USB device. I have a mini plug for my camera, a big square one for my printer, a 2.5 mm jack to charge my MP3 player, etc. All these cables make a mess. If all my devices could share one cable, I'd be much happier.

Re:Plug Shape (SCSI was worse)

[rubberbando (784342)]

It could be worse, we could all be forced to use SCSI devices instead. That had a ton of port styles and shapes as well as internal and external versions of each. Also, you had to daisy chain your devices, secure them with a screwdriver/your fingers, configure each with its own ID number and make sure the end of the chain was terminated properly. Then to top it off, cables, adapters, and terminators were insanely expensive. I'd swear that every time I bought a new SCSI device that it was like playing a puz

Re:

[Maximum Prophet (716608)]

Also, did you know that the USB connector is exactly as wide as an RJ45 network connector. No, neither did I, until my mother plugged her mouse into the ethernet port. (:-)

Seriously, the connector should have double the number of pins as it needs, and they should be symmetrical. That would also increase reliability, because if the cable didn't work one way because of a bad pin, just flip it over until you can buy a new cable.

Re:

[Rob T Firefly (844560)]

All the others with 2.5mm and other proprietary ends that work on nothing else are solely the fault of the OEMs. Nobody asked them to do it, it never made sense to do it, and it's just a huge pain in the ass for everyone.

It makes a whole lot of sense to an OEM who wants to be the only one who can sell their customers a cable despite an open standard. It's the same reason for every standard out there which suppliers have taken it upon themselves to add their own "enhancements" to.

Re:Plug Shape

[Eccles (932)]

Having it be flippable would mean duplicating wires and/or contacts and would make the cables more susceptible to damage and more expensive.

I don't think the idea is to have the cable flippable, but instead to have some indication in the shape of which way around it goes. Firewire connects have a rounded end and a squared off one, for example.

Re:Plug Shape

[Aladrin (926209)]

You're right. I forgot the way more complicated solution. Silly me!

More half assed implementations.

[deniable (76198)]

Fiber and copper. Let's see how vendors screw this one up. USB 1, 1.1, 1.?, ?.?, 2, 2.75, 3...

Faster, possibly

[Tim C (15259)]

Although it'll depend on where the bottleneck actually is, of course.

But easier? How would it make using external HDDs easier?

Screw bandwidth...

[Balinares (316703)]

Give us a standard that actually delivers enough power that you don't need an additional power cord for just about every other device already... :/

Re:

[jimicus (737525)]

The problem with that is that a PSU for a powered 7-port USB hub already has to supply 3.5 amps. Much larger than that and with current technology you're getting into "big expensive PSU" territory.

So we should be able to boot from a USB flash

[Rooked_One (591287)]

drive? It would only make sense that since its solid state it would be faster than our primitive hard drives with their moving parts... (yes, I know about SS Hard drives and don't have 2500 dollars to spare)

Honest Question

[martyb (196687)]

I've got a question that has been nagging at me for quite a while and was hoping someone here could phrase an answer in terms a mere mortal could understand.

Why are there so many serial specifications?

We've got, off the top of my head, SCSI, USB, Ethernet, FireWire, and SATA to name a few. I do understand there are different protocols (all the way up from the physical to the application layers). Different applications of these technologies permit some optimizations that might not be applicable in other situations. But, at some point, the underlying technology is fast enough

Still, I can't help but think there should be some common denominator that ALL these communications standards can agree on, and through economies of scale, become universal standard(s). It just seems like people keep re-inventing the wheel with an eye toward THEIR favorite.

I thought we were getting close when they released gigabit Ethernet over UTP (unshielded twisted pair).

• can handle distances up to 100 meters
• fast data rate (1000 Mbps)
• supports lower data rates (100/10 Mbps)
• development is underway for 10Gbps, too.

So, for the sake of argument, why not have all of our serial devices just support gigabit Ethernet? Sure, you'd need a hub or switch in your PC to talk to all of the devices, but you already need something similar for the other protocols (USB hub, SCSI controller, etc.). It's a well-known technology with many implementations and is widely available. I'd willingly pay a few more bucks for each device if I could ditch all of these incompatible formats and just standardize on one SET of ports and cables for hooking things to (and within) my PC. And in those cases where a different connector is desired (e.g. for small form-factor devices like a digital camera), let me just get an adapter cable/plug that I can plug into my Ethernet port.

Is there any good, technical reason that is keeping us from having truly UNIVERSAL serial communications?

Re:Honest Question

[mlBrianR (51773)]

I think the main problem is repeated insertion/removal vs. semi-permanent installation.

USB connectors are designed to be inserted and removed over and over. They're held in by pressure against the connector, so they can be removed without having to push a tab or twist the connector to remove it.

UTP cables are designed to be plugged in, and then generally left alone. The UTP cable in my computer bag is in terrible shape.. the RJ45 connector is coming loose, the plastic retaining tab is broken off (so the cable often pops out of the jack on its own), etc.

I have USB devices which I've removed and inserted hundreds of times, and the connectors still work reliably.

Re:Honest Question

[smellsofbikes (890263)]

A bunch of other people have chimed in with parts of the answer already, and I thought I'd add some more.
Obviously each manufacturer wants you to use their standard and buy their hardware.
Different implementations came through at different times, and have different amounts of software/hardware overheads, and try to do different things.
RS232 has almost no necessary software overhead -- you do any and all the work with code you write. USB has *quite* a bit of software overhead to deal with device identification, and Ethernet has *enormous* amounts of overhead. In most small systems you have to buy an Ethernet software stack separately from the OS you're using.
USB tries to provide power. People are trying to glue power into Ethernet although it hasn't yet taken off.
People keep going off in odd wireless directions.
The fundamental problem, I think, is that there are several different connectivity needs and manufacturers are trying to get you to buy their solution to what they think are the most important needs. What you're asking for is something good for the industry in the long term, and that's not really in the direct interest of any particular company, so nobody's building anything for it.
The military embedded market seems to be moving towards gigabit or 10-gig fiber ethernet for all their interboard communications, but fiber has its own problems, and I'm not sure it's the right thing for a USB key you're carrying in your pocket all the time.
I believe that the SCSI module in linux handles firewire and USB, so from that standpoint it looks like it's a start towards universal communications, except for Ethernet. (Even though old SCSI is nothing like serial: it's the the ultimate expression of parallel communications, with some similarities to the old HP/GPIB parallel communication standard that's still used in for test communication but used to be a hard drive standard.) I have no idea what Windows does.

Re:Honest Question

[gillbates (106458)]

Is there any good, technical reason that is keeping us from having truly UNIVERSAL serial communications?

Yes.

Let me explain:

• USB, per standard (host side), must be able to source at least 500 mA. Even though there is a PoE (Power over Ethernet) standard, most choose not to implement it by default. Hence, ethernet can't power devices like flash drives and hard drives.
• USB uses four wires, ethernet twice as many. USB is a synchronous bus, meaning that there are (theoretically, at least) no collisions. A properly operating USB device will not stomp on someone else's data packet. Thus, for the given bitrate, a higher portion of the bandwidth is available to applications. Unlike ethernet, adding devices to the same physical connection will not degrade the overall bandwidth of the network. In practice, I've found 100 Mbit ethernet devices operating with a maximum throughput of about 35-40 Mbits/second because of collisions. And this was with *two* devices! To get a better throughput requires using routers (which minimize or eliminate collisions).
• RS232 is a pretty universal serial communication standard. However, it is also slow.
• There are tradeoffs between maximum cable length and the speed of the bus.
• There are tradeoffs between the number of signal lines and the cost of the device.
• There are tradeoffs between bitrate and the device cost.

So, the reason why we don't have a universal serial standard is because the different interfaces were designed with different goals in mind.

Re:Honest Question

[Yvanhoe (564877)]

Apple was thinking along these lines when they proposed firewire. I am not a Mac expert, but from what I have seen so far, firewire can be used for networking (does it use ethernet, I am not sure) video transfer, peripherals connection, external drive connections. From the start it was fast enough and designed for all these applications while we still struggle to get USB working everywhere at full speed...

Hope they do a better job on compatibility

[dpbsmith (263124)]

I do not look forward to the replacement of what was starting to be a reliable, ubiquitous standard that "satisficed" with a New! Improved! version that shows no signs of actually achieving significantly higher throughput with current devices. Why does USB have to compete with SATA? Why can't USB just be USB?

I've been seriously disappointed with the number of times I've interconnected USB 1.1 and USB 2.0 devices and had them almost work, only to encounter various strangeness and glitches. I don't know who's to blame... whether it's a fault in the standard or in vendors' faulty implementations... and life's too short to care, because know who's to blame wouldn't do much to help solve the problem.

On the whole, I blame the standard, because these days standards are so incredibly huge, bloated, and complex that it is extremely unlikely that anyone actually implements it fully correctly.

With today's sloppy practices of testing to the market ("Let's try it with the most popular devices, or the ones which are most important to our business") instead of testing to the standard, the result is all sorts of opportunities to build devices that comply with the standard but do things just a little differently than the most popular devices... and have them not work even though they "should."

A typical example was an IOmega external CD burner I bought once for a USB 1.1 Mac. (I chose it because it was $30 cheaper than a FireWire model, I wanted both PC and Mac present and future compatibility), and I didn't really care about speed. The drive actually burned perfect CDs, but it always claimed erroneously that an error had occurred. But how could a sane person rely on that? I returned it, bought a different USB 2.0 external CD burner from a different vendor... and encountered exactly the same problem.

I've also seen various glitches and strangenesses trying to use USB 1.1 thumb drives in USB 2.0 CPUs and vice versa.

Don't let the marketing guy name it this time.

[JoeD (12073)]

I can never remember which one is faster, "Hi Speed" or "Full Speed".

we're probably going to wind up with yet another ambiguous name like "Extreme Speed" or "Max Speed".

Just call it USB 3.0 and be done with it.

Re:Cable?

[YrWrstNtmr (564987)]

The last line in the article:
"It will be backward compatible, so current USB 2.0 devices will be able to plug into USB 3.0 ports."

Re:Cable?

[ddstreet (49825)]

> like if you plug a usb 1.X device onto a usb 2.0 bus, then everything slows to usb 1.X. IINM...

This is wrong, if you plug a USB 1.1 device into a USB 2.0 "bus" then it does NOT slow everything down. Specifically there are 2 cases:

1. You plug a USB 1.1 device directly into your computer (i.e. directly into the "host controller"). In this case, the USB 2.0 host controller (technically a EHCI chip) does NOT talk to your device. Instead, the EHCI chip has one or more USB 1.1 host controller chips (technically either a OHCI or UHCI chip, and called a "companion" chip when inside a EHCI chip) and your USB 1.1 device is connected electrically to that controller. You device is not on the USB 2.0 (EHCI) bus.

2. You plug a USB 1.1 device into a USB 2.0 hub. In this case, the USB 2.0 hub creates a complete USB 1.1 environment specifically for your device. On the host-facing side of the USB 2.0 hub, all communication continues to take place at USB 2.0 (i.e. 480Mbps) speeds. When the host wants to talk to your USB 1.1 device, it uses what is called "split transactions" to talk to it. Basically (I'm simplifying), this involves sending a "start" packet to the USB 2.0 hub. Then, the USB 2.0 (EHCI) controller goes on to do other things, while the USB 2.0 hub initiates the transfer to your device at USB 1.1 speeds. And data transferred from the USB 1.1 device is stored temporarily in the USB 2.0 hub. Eventually the USB 2.0 (EHCI) host sends a "finish" packet to the USB 2.0 hub. If the USB 1.1 transation finished, the USB 2.0 hub responds successfully (either with the incoming data or a "ack" that the outgoing data was sent) which completes the transation.

(There is also a combination case of those, where the EHCI chip does not contain a "companion" USB 1.1 chip, but instead contains an internal USB 2.0 partial hub - the "transaction translator" part - that handles talking to USB 1.1 devices. For bus usage purposes, this is effectively the same as using an external USB 2.0 hub, since the USB 1.1 devices do not appear on the USB 2.0 bus.)

Re:

[Stonent1 (594886)]

I think the fiber part will be inside the extra space in the connector in a way that doesn't interfere with the electrical part of it. Probably when you plug in a cable the electrical part asks the connection if it is USB3 capable and if the device responds yes, it turns on the fiber transceiver.

Re:Eat into firewire not likley

[TRRosen (720617)]

more speed is great but USB will never replace FireWire for video as its not a matter of speed but architecture. FireWire is a true bus USB is not...FireWire can guarantee bandwith USB can not.

Re:Eat into SATA?

[stewbacca (1033764)]

Last nail? They haven't even started fitting Firewire with a coffin yet. The only thing dying in this equation is USB2, and thankfully so. So it is faster than USB...joy, my mouse, printer and keyboard all now react the same speed, regardless of the interface speed boost. What's the point of USB2 again? If it doesn't boost the speed of my peripherals at least as well as my existing firewire400/800 ports, then why do I need it? It IS a pity that iPods stopped shipping with firewire and went to USB2, but that was a business choice to have maximum compatibility. Too bad my newer iPods can't transfer 2 songs per second anymore, like they used to when they were firewire400. But like many others have said, USB2 is "good enough" so it is really hard to get excited about USB3, which will be "gooder enough?"

Re:Anyone else here see a problem??

[aadvancedGIR (959466)]

Then I recommend you not to buy the USB-powered dildo.