Beta
×

Welcome to the Slashdot Beta site -- learn more here. Use the link in the footer or click here to return to the Classic version of Slashdot.

Thank you!

Before you choose to head back to the Classic look of the site, we'd appreciate it if you share your thoughts on the Beta; your feedback is what drives our ongoing development.

Beta is different and we value you taking the time to try it out. Please take a look at the changes we've made in Beta and  learn more about it. Thanks for reading, and for making the site better!

Intel Developers Demo USB 3.0 Throughput On Linux

timothy posted more than 5 years ago | from the future-sweetness dept.

Data Storage 231

Sarah Sharp writes "Intel's Open Source Technology Center is working on USB 3.0 support for Linux. USB 3.0 has wire speeds of 5Gbps and promises to be 10 times faster than USB 2.0. A recent video demo shows speeds that are 3.5 times faster than USB 2.0. The USB 3.0 drivers will be submitted to the mainline kernel when the eXtensible host controller interface (xHCI) specification reaches a 1.0 release."

cancel ×

231 comments

Sorry! There are no comments related to the filter you selected.

What's in a name... (5, Insightful)

alain94040 (785132) | more than 5 years ago | (#26105909)

USB 2.0 gave us high-speed and full-speed. Some marketing department had to work really hard on the USB 3.0 specs, to come up with... super-speed.

Now let's talk about the obvious problem: at 5 Gbit/s, it's faster than the Ethernet in my house (1 Gbit/s). Am I the only one who didn't really notice a 10X speed improvement when moving from 100 Mbit Ethernet to gigabit Ethernet? Conventional hard drives are just too slow.

Maybe SSD + USB 3.0 would be really cool. Imagine a Flash based HD camera talking to a Flash based hard drive. Is 2009 the year of the Flash?

Which brings me back to my original point: for the next generation USB, I propose the name flash-speed :-)

PS: thanks to Intel for helping Linux stay on the leading edge. It looks like Linux may even support this before Windows, thanks to the Windows 7 schedule... I just wish Intel's pre-conditions on contributing to the xHCI specs didn't start with stuff like:

Step 1. Print and execute the xHCI Contributor agreement. Note: The agreement must be executed by a corporate officer.

--
http://fairsoftware.net/ [fairsoftware.net]

Re:What's in a name... (2, Interesting)

Swizec (978239) | more than 5 years ago | (#26106015)

What I'm wondering with the SSD computer + USB3 + Flash camera combo is ... does the computer even have enough processing power to complete the transaction while letting the user multitask somewhat normally?

Or would the whole thing somehow circumvent the need to tell the OS what's going on with the file system?

Re:What's in a name... (4, Insightful)

Microlith (54737) | more than 5 years ago | (#26106045)

This is why Intel is pushing USB: it is entirely CPU dependent.

You won't notice it when you're running with X * 2 logical cores. It'll be shuffled off to some low utilization core.

Wha? (4, Informative)

Weaselmancer (533834) | more than 5 years ago | (#26106119)

Could you please explain that a bit?

It's my understanding that high throughput drivers usually use DMA. [mjmwired.net]

In my experience polled mode drivers are pretty rare. Especially in high throughput.

Re:Wha? (3, Insightful)

Lost Engineer (459920) | more than 5 years ago | (#26106233)

USB 2.0 requires the host to control all communication on the bus, and in practice uses more CPU time than something like 1394. I don't know if they changed this in USB3 or not.

Re:Wha? (2, Informative)

Anonymous Coward | more than 5 years ago | (#26106329)

The fact that USB is a polling protocol is a very low level decision. The CPU does not need to regularly ask each device for data. The USB controller does that.

Re:Wha? (5, Informative)

Hal_Porter (817932) | more than 5 years ago | (#26106405)

Yup the host sets up a structure in memory which lists all the USB endpoints. When a driver wants to do some IO it asks the host controller driver which adds a request into the structure with a pointer to a buffer. The host controller hardware reads the structure with busmaster DMA and generates the USB packets. When the device answers the host controller DMAs the data into the the driver's buffer interrupts the CPU. Then the host controller can pass the buffer back to the driver. Polling is done by leaving the request in the structure, it doesn't require any CPU activity. Intel like USB because they invented it, not as some sort of conspiracy to load your CPU.

Re:Wha? (4, Interesting)

lysergic.acid (845423) | more than 5 years ago | (#26106759)

so why do FireWire 400 readers still consistently beat out USB 2 [scribd.com] :

While USB 2.0's theoretical 480Mbp/s (60MBp/s) throughput should be sufficient for UDMA 4 CompactFlash, realthroughput is significantly less. Top hard drive manufacturers typically cite USB 2.0's best speed at 33MB/s, or abouthalf the speed of UDMA 4 CompactFlash, or 25% of UDMA 6 CompactFlash. There are myriad reasons for USB 2.0's'real world' speeds including: CPU overhead from its master/slave arrangement, NRZI encoding, and inexpensivechipset implementations. The USB 2.0 UDMA reader used in the benchmarks above uses one of the latest USBchipsets from Genesys Logic. While a new generation of that chipset should soon be available, we don't foresee itproviding throughput close to half of that of FireWire.

heck, those benchmarks show that even using FireWire 400 to read a PIO CompactFlash card still beats USB 2.0 UDMA reading a UDMA-enabled CompactFlash card.

Re:Wha? (0)

Anonymous Coward | more than 5 years ago | (#26106863)

Why do you only get 3.5MB/s out of a 54Mb/s wireless LAN connection? Same reason: The protocol uses the "wire" speed for other things beside raw data transfer. While the decision not to give devices the capability to initiate data transfers has no impact on the CPU usage, it does cause latencies and overhead on the wire.

Re:Wha? (5, Informative)

raynet (51803) | more than 5 years ago | (#26106927)

Taken from wikipedia: "Although high-speed USB 2.0 nominally runs at a higher signaling rate (480 Mbit/s) than FireWire 400, typical USB PC-hosts rarely exceed sustained transfers of 280 Mbit/s, with 240 Mbit/s being more typical. This is likely due to USB's reliance on the host-processor to manage low-level USB protocol, whereas FireWire delegates the same tasks to the interface hardware. For example, the FireWire host interface supports memory-mapped devices, which allows high-level protocols to run without loading the host CPU with interrupts and buffer-copy operations."

Re:Wha? (1)

Weaselmancer (533834) | more than 5 years ago | (#26107087)

Answers my question perfectly - thank you.

Re:Wha? (1, Interesting)

Anonymous Coward | more than 5 years ago | (#26106987)

Intel likes USB because it requires a host (aka PC).

Nope. (1)

Weaselmancer (533834) | more than 5 years ago | (#26107051)

Wrong. [wikipedia.org]

There's throughput and then there's latency (3, Interesting)

Gazzonyx (982402) | more than 5 years ago | (#26106639)

Well, I get high throughput with my NIC drivers that poll (I can't remember the kernel compile option for this ATM), but this is at the cost of a higher latency. The trade off is that I've got 5 NICs on this box and it turns out that without polling I get close to having an interrupt storm and spend all my time switching context to execute the drivers bottom half of the interrupt. With polling, the interrupt gets masked and I don't have to worry about servicing every interrupt coming down the line. My latency is higher, but I get more throughput for every time I service the bus as it has more packets to process. This also means I'm trading off space for time (I need larger ring buffers to queue packets) such that I have less memory for the system, but processes get more time on the processor between interrupts.

While not having to do with USB, the driver architect and concepts are likely very much the same.

Re:What's in a name... (2, Funny)

Anonymous Coward | more than 5 years ago | (#26106023)

Look, we both know that there will be a "USB ludicrous speed". Marketing has no say in it.

Re:What's in a name... (2, Funny)

Anonymous Coward | more than 5 years ago | (#26106571)

We've gone plaid.

Re:What's in a name... (3, Informative)

Microlith (54737) | more than 5 years ago | (#26106029)

Imagine a Flash based HD camera talking to a Flash based hard drive.

Maybe if said HD camera has a USB host controller, like that USB-2-GO stuff.

Otherwise, I suspect USB 3.0 is as braindead as USB 1.0 and will still require a computer to do all the actual work.

Re:What's in a name... (1)

eddy (18759) | more than 5 years ago | (#26106035)

>Maybe SSD + USB 3.0 would be really cool

Decidedly less cool than SSD and eSATA, which we already have. Though maybe not in cameras, but on the other hand, we don't have USB3 in cameras either so that's a tie.

Re:What's in a name... (2, Interesting)

Mad Merlin (837387) | more than 5 years ago | (#26106039)

The thing is that USB is bursty, in practice you'll probably still get much better speed out of Gigabit ethernet than you will with USB 3.0.

As for Gigabit ethernet, it's a massive upgrade from 100 megabit ethernet, at least in my usage. It only takes 2 modern drives in RAID 0 to saturate Gigabit ethernet, or just 1 fast SSD.

Re:What's in a name... (1)

More_Cowbell (957742) | more than 5 years ago | (#26106093)

'bursty' ... is that sort of like 'minty'? ;)

in practice you'll probably still get much better speed out of Gigabit ethernet than you will with USB 3.0.

Seriously though, [citation needed].

Re:What's in a name... (-1, Flamebait)

Anonymous Coward | more than 5 years ago | (#26106133)

citation? Are you a fucking retard? Spend 30 seconds verifying how USB works.

Re:What's in a name... (4, Informative)

Mad Merlin (837387) | more than 5 years ago | (#26106237)

'bursty' ... is that sort of like 'minty'? ;)

No, it's that max speeds for USB 2.0 refer to the max burst speeds, not the maximum sustainable speed. A single 7200 RPM drive attached via USB 2.0 will be substantially slower than if you attached it via SATA or IDE, even though 60 MB/s (= 480 Mbit/s) should be enough for most drives.

Re:What's in a name... (3, Interesting)

More_Cowbell (957742) | more than 5 years ago | (#26106871)

I appreciate the answer, but you replied to the bit where I was trying (poorly) for humor. I know what burst speed vs sustainable speed is all about. What I wanted you to explain is what makes you think a medium that has a burst speed of 4.8 Gbit/s will not be able to sustain > 1 Gbit/s (like your ethernet). I have read a bit, and not seen any info either way...

Re:What's in a name... (5, Interesting)

John Allsup (987) | more than 5 years ago | (#26106111)

I guess for hard drives, the question is how close to eSATA it gets.
Also, does USB3 still have the CPU overhead and latency of earlier USB compared to FW?

Re:What's in a name... (1)

Darkness404 (1287218) | more than 5 years ago | (#26106165)

PS: thanks to Intel for helping Linux stay on the leading edge. It looks like Linux may even support this before Windows, thanks to the Windows 7 schedule... I just wish Intel's pre-conditions on contributing to the xHCI specs didn't start with stuff like:

Honestly, Intel didn't have much choice, the NT kernel can't exactly be obtained, modified and distributed for free, OS X is too hardware-oriented, and there isn't really anything else (minus BSD and other *Nix variants)

Re:What's in a name... (2, Interesting)

Hal_Porter (817932) | more than 5 years ago | (#26106445)

Honestly, Intel didn't have much choice, the NT kernel can't exactly be obtained, modified and distributed for free

At the moment Windows supports three host controller drivers. OHCI and UHCI for USB 1.0 and EHCI for USB 2.0. There's nothing special about host controller drivers, anyone can write one. If they wanted they could write a host controller driver for xHCI and then Windows would support USB 3.0.

Re:What's in a name... (1)

hairyfeet (841228) | more than 5 years ago | (#26106637)

Not to mention someone with the money and industry clout of Intel would have no problem calling up MSFT and saying "We have this great new gadget we are about to release but we will require your source to complete it." and faster than you can say NDA I have no doubt that Intel would be looking at the Win7 source code, along with the source to anything else they wanted.

I personally am just glad this is from Intel and not MSFT, otherwise it could have ended up a Win7 only feature just like DX10 for Vista. Hopefully at launch Intel will make sure there are Windows 2K/XP/Vista drivers ready to go out of the gate so I can get to buying cards because the 27MBs max I get on USB 2 is just too slow with these larger HDDs.

Re:What's in a name... (0)

Anonymous Coward | more than 5 years ago | (#26106811)

and faster than you can say NDA I have no doubt that Intel would be looking at the Win7 source code, along with the source to anything else they wanted.

damn, they should have demoed USB 3.0 on Duke Nuke Forever then...

Re:What's in a name... (1, Informative)

code4fun (739014) | more than 5 years ago | (#26106195)

USB 2.0 gave us high-speed and full-speed. Some marketing department had to work really hard on the USB 3.0 specs, to come up with... super-speed.

I'm holding out for WARP speed...

Re:What's in a name... (2, Funny)

mog007 (677810) | more than 5 years ago | (#26106599)

What about ludicrous speed?

Re:What's in a name... (4, Funny)

Gazzonyx (982402) | more than 5 years ago | (#26106661)

USB 2.0 gave us high-speed and full-speed. Some marketing department had to work really hard on the USB 3.0 specs, to come up with... super-speed.

I'm holding out for WARP speed...

I'm holding out for plaid speed...

Re:What's in a name... (1)

TheRaven64 (641858) | more than 5 years ago | (#26107105)

That's only supported on OS/2.

Re:What's in a name... (2, Funny)

commodoresloat (172735) | more than 5 years ago | (#26106275)

Is 2009 the year of the Flash?

Indeed. On the desktop!!

Re:What's in a name... (4, Interesting)

metalhed77 (250273) | more than 5 years ago | (#26106287)

That USED to be true. It's not the hard drive, all the layers that get put in between when you access a disk over the network. Modern hard drives can easily do 60MB/s sustained.

For instance, I have a couple raid6 arrays which clock in at about 250 MB/s and 150MB/s natively. If I hook that machine up directly to another machine's ethernet port I only get about 30MB/s sharing the device w/ iSCSI. SMB and NFS yield similar results. This is true even though I can get over 900Mbps using iperf.

Sharing disks over gig-e sucks when you actually need throughput. It's great for when you just need to expand a SAN and speed is secondary. I've heard that bonding two Gig-e cards doesn't realize much of an improvement FWIW, so I assume latency is part of the reason it's slower.

Re:What's in a name... (1)

DogAlmity (664209) | more than 5 years ago | (#26106309)

Is 2009 the year of the Flash?

Replace Flash with Flasher and it sounds like my freshman year of college! Bam!

Re:What's in a name... (2, Informative)

gad_zuki! (70830) | more than 5 years ago | (#26106439)

>Am I the only one who didn't really notice a 10X speed improvement when moving from 100 Mbit Ethernet to gigabit Ethernet?

Well, youre probably not getting 10x. Depending on a slew of factors (your switch, cable length, etc) youre getting anywhere between 100 to 800 mbps. Have you tried any speed tests? With gigabit I can copy to my nas at 25 megabytes per second. At 100 I was getting under 12. So that's twice the speed for me, which is most likely limited by the CPU on my nas and not ethernet.

>Conventional hard drives are just too slow.

Not really. Current drives go way past the limitations of USB2. We need a faster USB. Firewire is dying so USB needs to take up the slack on fast local connections. Shame esata isnt taking off with the home market.

>It looks like Linux may even support this before Windows, thanks to the Windows 7 schedule

USB 3.0 will work like any device: with a driver. I expect both XP and Vista to have it as manufacturers will simply write their own drivers without waiting for MS to package it into a service pack.

Re:What's in a name... (1)

gbjbaanb (229885) | more than 5 years ago | (#26106739)

With gigabit I can copy to my nas at 25 megabytes per second. At 100 I was getting under 12. So that's twice the speed for me, which is most likely limited by the CPU on my nas and not ethernet.

When the networks stops being the bottleneck, you usually find it shifts somewhere else - I think now your bottleneck is the HDDs write performance. My NAS copies at 25MBps but before I reformatted it from its default RAID5 on its useless raid card, I was getting 6MBps (its now JBOD with software RAID), the CPU isn't the bottleneck.

With USB, I reckon we will get it for Vista and XP as the manufacturers will write their own drivers - just like with Win98/ME where they always shipped a little driver CD with every USB device you bought.

Re:What's in a name... (1)

xianthax (963773) | more than 5 years ago | (#26106449)

Keep in mind that USB is a shared bandwidth architecture so you are getting 5gbps divided up among all the devices on that particular USB host controller which actually can make a quite large difference, i know it will for me with the 10 USB devices, not counting usb drives, that are normally attached my system. Also, USB is a very overhead intensive architecture, USB 2.0 @ 480mbps signal rate really would only hit data rates of ~320mbps most of the time.. cheers, x

Re:What's in a name... (1)

jonbryce (703250) | more than 5 years ago | (#26106595)

I don't get anything like 320mbs with my USB Hard Drives. I have one drive which I can plug into 480mbs USB or 400mbs Firewire, and it is massively faster on Firewire.

Re:What's in a name... (1)

slimjim8094 (941042) | more than 5 years ago | (#26106491)

Linux actually has much better USB2 support than Windows... as in much better throughput. Each device gets to use more bandwidth.

Re:What's in a name... (1, Interesting)

Anonymous Coward | more than 5 years ago | (#26106787)

Do you have some benchmarks to back that up? The best I have seen with Linux is around 25MB/s (that was a couple of years back though), with XP x64 (which is more or less Windows 2003) I get 32MB/s with a good enclosure.

Re:What's in a name... (2, Informative)

LoRdTAW (99712) | more than 5 years ago | (#26106509)

Gigabit Ethernet is a vast improvement over 100Mbit. Two windows boxes with fast SATA drives I see no less than 20 megabytes/second transfer speeds on a Vista64 XP64. Top speeds exceed 30 MB/sec (~300+Mbps)! My home server runs Linux but for some reason SAMBA is dog slow no matter how much I tweak the damn conf file. 10-12MB/sec tops for Linux Windows (without tweaks it was 3-4MB/sec!).

I have a four disk 1.5TB raid 5 array using SATA disks on a pciX controller and mdadm. Copying from the array to an **old crusty 20 gig ATA** root drive I see 40+ MB/second! So saying today's drives are too slow is not the case. I would love to see the speed with an SSD, bet it would easily soar over 100MB/sec! Wish SAMBA could keep up.

I have yet to actually test my Linux notebook with NFS to the server as I just use wireless so its always going to be slow. But saying you see no increase means you aren't really taxing the network.

PS if anyone knows how to speed up SAMBA under Ubuntu 8.04 please let me know. I used all the tcp_nodelay and the other tcp settings but nothing really works.

Re:What's in a name... (0)

Anonymous Coward | more than 5 years ago | (#26106999)

10-12MB/sec tops for Linux Windows (without tweaks it was 3-4MB/sec!).

Linux Windows? What is this "Linux Windows" of which you speak?

Re:What's in a name... (1)

LoRdTAW (99712) | more than 5 years ago | (#26107061)

Aw god dammit. There were supposed to be a double arrow in between the two. I had a mental lapse and used the > brackets that are used for HTML code and Slashdot thought they were HTML tags and did not display them.

It was supposed to read as "Linux to Windows" or "Windows to Linux". Same goes for "Vista64 XP64".

       

Re:What's in a name... (1)

sjames (1099) | more than 5 years ago | (#26106513)

For a single device, you probably won't really notice 5Gbps. However, let's say you have 3 USB drives that can sustain 1Gbps each. If you hang them off of a decent USB hub, you'll be glad the bus can do 5Gbps.

Re:What's in a name... (0)

Anonymous Coward | more than 5 years ago | (#26106541)

Print and execute the xHCI Contributor agreement.

I wonder if they'd accept burning at the stake as a means of execution. It does seem rather fitting for printed matter, anyway.

Re:What's in a name... (2, Funny)

averagegeek (1431079) | more than 5 years ago | (#26106853)

PS: thanks to Intel for helping Linux stay on the leading edge. It looks like Linux may even support this before Windows, thanks to the Windows 7 schedule

The real question is...will Tux get fat with all the new code?

Re:What's in a name... (1)

operagost (62405) | more than 5 years ago | (#26106997)

Getting 1 Gbps out of Gigabit Ethernet requires that the host bus support it (standard PCI is barely fast enough) and that jumbo frames are used. Most SOHO and even some enterprise implementations fall short in practice.

What do you do with it? (1)

Bruce Perens (3872) | more than 5 years ago | (#26105951)

Replace HDMI?
HD-resolution cameras, etc?
The next, even more expensive, version of the USRP?

Re:What do you do with it? (0)

Anonymous Coward | more than 5 years ago | (#26105981)

How about we use it to attach hard disks without the connection being the bottleneck?

Re:What do you do with it? (1)

Bruce Perens (3872) | more than 5 years ago | (#26106261)

[using it for disks]

SATA 2 is 300 Mega BYTES - not bits - per second or about 1/2 the projected maximum rate for USB 3. Besides the speed, USB 3 would need an interrupt capability, and data integrity verification, neither of which USB 2 has. I've not read the 3.0 spec to see if they are there. USB OTG is more than a bit of a kludge, and not well supported, hopefully that's not what 3.0 uses to have multiple masters.

Sure, the USB connector is more sturdy, but I've seen a lot of external SATA connectors for computers.

3.5x faster (0)

Anonymous Coward | more than 5 years ago | (#26105955)

So, at this point USB 3 gives us speeds that 3-1/2 times faster than USB 2 in real world usage. Great! That's where plain old FireWire was in 1996.

Re:3.5x faster (2, Informative)

imamac (1083405) | more than 5 years ago | (#26106031)

Uh. No. In 1996 FireWire was at 393 Mbit/sec (S400 standard). USB 3 seems like it will be plenty faster. There is more than jus speed advantage, though. FireWire likes to change plugs at every new generation. USB does not.

Re:3.5x faster (2, Insightful)

Anonymous Coward | more than 5 years ago | (#26106061)

If we're talking actual real world speeds (not the theoretical best case scenario ideal lab conditions crap), then yeah, that's about where FireWire sat in it's first iteration.

Re:3.5x faster (1)

imamac (1083405) | more than 5 years ago | (#26106075)

If we're talking actual real world speeds (not the theoretical best case scenario ideal lab conditions crap), then yeah, that's about where FireWire sat in it's first iteration.

Real world usage is about 250 for USB 2. Multiply that number by 3 and then compare it to 400. Then tell me which one is bigger.

Re:3.5x faster (1)

LKM (227954) | more than 5 years ago | (#26106347)

Firewire 800 is bigger.

Re:3.5x faster (0)

Anonymous Coward | more than 5 years ago | (#26106843)

No. Good disk enclosures achieve about 32MB/s (on Windows anyway, I haven't seen more than 25MB/s on Linux). The best firewire speed I have seen is close to 40MB/s (on 400mbit firewire).

Re:3.5x faster (0)

Anonymous Coward | more than 5 years ago | (#26106081)

FireWire likes to change plugs at every new generation. USB does not.

This time it does. Besides, considering that there is a whole zoo of mini-usb connectors because there was no standard for a smaller device connector, USB has changed plugs more often than Firewire, even though there are only two generations of USB so far.

Re:3.5x faster (1, Informative)

LKM (227954) | more than 5 years ago | (#26106341)

It seems USB3 it will be about as fast as Firewire 800. And until then, we'll be stuck with sucky USB2 speeds because Firewire is essentially dead. This is simply incredibly annoying.

Re:3.5x faster (1)

raynet (51803) | more than 5 years ago | (#26106965)

Has Netcraft already confirmed the death of Firewire? Until that happens I'll keep using my Firewire enclosures, thank you very much.

Re:3.5x faster (0)

Anonymous Coward | more than 5 years ago | (#26106915)

As I stated previously, FW 3200 uses FW800 standard plugs and cables. So your statement is false.

It also doesn't seem like you comprehended what I wrote very well, so I'll try again:

FW400 = about 380Mbps (real world)
USB2 = about 250Mbps (real world, claimed 480Mbps)
FW800 = about 750Mbps (real world)
USB3 = we think it will be about 1.5Gbps real world, despite claims of "up to" 5Gbps
FW3200 = we think it will be about 3Gbps real world

Bottom line: USB has fundamental design issues that keep it from reaching its potential. FW doesn't. USB makers lie (a LOT) about performance. FW makers don't. USB3 will be faster than USB2, but not as fast as FW3200.

Geeks are not like they used to be (0)

Anonymous Coward | more than 5 years ago | (#26106051)

... in the past, hormoned-up kids would have been foaming on about the non-technical aspects of the video.

Re:Geeks are not like they used to be (0)

Anonymous Coward | more than 5 years ago | (#26107001)

oh, don't worry. i'm sure even now there are legions of slashdotters stalking that Intel rep over the internet and filling her inbox with perverse inquiries--that'll teach her to display her e-mail address in a slashdotted video.

CPU usage (1, Redundant)

PhrostyMcByte (589271) | more than 5 years ago | (#26106139)

Like any good slashdotter, I'm not reading the article until after I post. Is 3.0 still going to be heavy on the CPU? Really, the best thing they could do is take the good stuff from firewire and slap a USB logo on it. All the cheap stuff can continue to use 2.0, while the bandwidth intensive stuff in 3.0 can have their own controllers.

But it doesn't fix it (1, Interesting)

_merlin (160982) | more than 5 years ago | (#26106159)

USB3 will make wire speeds faster, and devices more expensive, but it won't deliver the performance we need, because they haven't fixed the root issues. USB is a silly polling system where the host has to ask each device in the tree if it has anything to say, and then (if it's a "bulk" endpoint), allocate time and finally do the transfer (interrupt and iso endpoints have time allocated all the time). Unless they make fundamental changes (which they won't), USB will load up the host excessively and give disappointing performance. But at least with USB3, the price to add it to a device shouldn't be that much lower than FireWire, so we might see more people making the right choice for what to support.

Re:But it doesn't fix it (1)

sjames (1099) | more than 5 years ago | (#26106559)

Firewire isn't going to win. A USB3 device may be more expensive than a USB2 device (in turn more expensive than a low or full speed device), but if I have a USB3 port, I plug it in to a USB3 hub and plug all of the above into that.

No polling (4, Interesting)

asifyoucare (302582) | more than 5 years ago | (#26107125)

According to http://www.usb.org/developers/presentations [usb.org] , USB 3 eliminates polling entirely.

USB 3 has several transfer modes, including interrupt, bulk, and streaming, and a design goal was to lower the host overhead. I don't know how successful they've been but it looks hopeful.

I guess we need to wait for benchmarks.

cool, at least it is progress (1)

FudRucker (866063) | more than 5 years ago | (#26106169)

yeah yeah, i read the comments about gigabit ethernet being faster, thats not the point, usb 3 is still better than usb 2, enjoy the weekend...

Re:cool, at least it is progress (5, Funny)

thermian (1267986) | more than 5 years ago | (#26106435)

yeah yeah, i read the comments about gigabit ethernet being faster, thats not the point, usb 3 is still better than usb 2, enjoy the weekend...

We're geeks, reading stuff like this *is* enjoying the weekend.....

Re:cool, at least it is progress (3, Insightful)

TheRaven64 (641858) | more than 5 years ago | (#26107141)

So is FireWire400, once you subtract the protocol overhead from both. Will USB 3 be faster than FireWire800 (which I have been using for the last few years) in real world use? And will FireWire3200 be shipping by the time USB3 is found in real products?

Motherboards (2, Interesting)

Enderandrew (866215) | more than 5 years ago | (#26106189)

When can I buy my first motherboard that is USB 3.0 compliant? I want to build a rig in the spring. I'd consider holding off until the summer to get USB 3 so it is more future proof, but I won't wait another year.

Re:Motherboards (1)

Xero (19560) | more than 5 years ago | (#26106303)

I'm sure that you will be able purchase an addon card when the time comes that you will need it.

Re:Motherboards (1)

eebra82 (907996) | more than 5 years ago | (#26106339)

The question is, what do you really need it for? You would need peripherals with USB3 to benefit from it and most USB items don't even need such raw speed. Keyboards, mice, printers and many other things do just fine.

Don't wait for USB3. When you really need USB3, just get a PCI card with two or three ports and voila. These things hardly cost more than 20 to 30 bucks.

Re:Motherboards (1)

Enderandrew (866215) | more than 5 years ago | (#26106407)

Video capture is the first thing that springs to mind, as well as external HDDs, flash storage, etc. Right now, copying gigs of data to external storage is slow with USB 2. Also, video capture is problematic. If the data isn't moving fast enough, I drop frames of video.

Re:Motherboards (1)

macemoneta (154740) | more than 5 years ago | (#26106605)

Video capture is the first thing that springs to mind, as well as external HDDs, flash storage, etc. Right now, copying gigs of data to external storage is slow with USB 2. Also, video capture is problematic. If the data isn't moving fast enough, I drop frames of video.

Firewire for the video capture and eSATA for the external hard drives will solve both problems. Even eSATA flash drives are showing up on the market now.

Re:Motherboards (3, Insightful)

kklein (900361) | more than 5 years ago | (#26106779)

Please don't say "rig."

Re:Motherboards (0)

Anonymous Coward | more than 5 years ago | (#26106919)

Yes, the correct term is "box"

Re:Motherboards (1)

averagegeek (1431079) | more than 5 years ago | (#26106817)

I wouldn't worry about that. Expiation boards should work just as well.

+5, Funny (-1, Offtopic)

this great guy (922511) | more than 5 years ago | (#26106255)

Geek girl. Plugging things into other things. Laptop running Hardy Hardon^H^H^H^HHeron.
Just wait for the torrent of +5, Funny jokes about to get posted...

Re:+5, Funny (0)

Anonymous Coward | more than 5 years ago | (#26106515)

there's a girl in the video?

brb

latency badness (4, Interesting)

r00t (33219) | more than 5 years ago | (#26106477)

USB suffers from 1 ms time quantization and thus latency. I see nothing about fixing this.

Example badness:

When running MIDI over USB, timing is forced onto 1 ms slots. Normally when playing a chord, the keys don't all hit at exactly the same moment. You can't really tell, except that this makes the music sound natural. With the 1 ms problem, the keys happen at exactly the same moment (bad) or spread out into two separate events (worse).

Re:latency badness (1)

freedumb2000 (966222) | more than 5 years ago | (#26106681)

Is firewire a good alternative without that problem?

Compared to USB 1... (5, Interesting)

MonoSynth (323007) | more than 5 years ago | (#26106479)

This shows where Linux is nowadays. It took literally years before USB1 was even supported and now Intel uses Linux to prove USB3's performance!

Re:Compared to USB 1... (0)

BitZtream (692029) | more than 5 years ago | (#26107059)

Too bad they used Windows to show it performing about twice as fast as the Linux test ...

I can't really talk about my Linux demo without talking about the Windows Demo that was in the SuperSpeed Developers Conference keynote. The demo was created by the Intel team that works closely with the USB-IF. It was the same demo they used for IDF Taipei in August 2008. The demo used the same Fresco Logic USB 3.0 prototypes and nearly the same PC system that I used.

Their goal was to show the maximum speed possible from the host controller and USB 3.0 device. To do that, they ran a simple compliance test suite that allocated a giant DMA buffer and sent data as fast as possible to the USB 3.0 device. The device was programmed to use the USB 3.0 protocol, but it was basically a loop back device. Their demo showed speeds of 318 MBps.

And

The Windows demo saw around 318 MBps, while the Linux demo typically showed 125 MBps. I saw as high as 233 MBps while formatting the disk. dd is not the best application to use for performance testing; I only used to whip up a simple demo.

But hey, whats the fun in being a fanboy if you don't ignore everything that isn't benificial to your cause?

Future Problems..... (2, Funny)

IHC Navistar (967161) | more than 5 years ago | (#26106511)

USB 1.1: Low-Speed and Full-Speed

USB 2.0: High-Speed

USB 3.0: Super-Speed

USB 4.0: Mega-Speed

USB 5.0: Ultra-Speed

USB 6.0: ???-Speed

Re:Future Problems..... (5, Funny)

Jeoh (1393645) | more than 5 years ago | (#26106549)

USB 7.0 Monster-Speed USB 8.0 Ludicrous-Speed USB 9.0 HOLY SHIT

Re:Future Problems..... (1)

Arthur Grumbine (1086397) | more than 5 years ago | (#26107067)

USB 10.0: Low-Speed (it went so fast it went back in time and got USB 1.0's designator)
No worries about this, though, as far as we can tell only The Borg will be able to achieve this level of technology. We'll be stuck at USB 9.99999...

Re:Future Problems..... (0, Redundant)

Daimanta (1140543) | more than 5 years ago | (#26106567)

USB 6.0: Ludicrous-Speed
USB 7.0: Holy shit!

Bleh, been playing too much UT

Re:Future Problems..... (0)

Anonymous Coward | more than 5 years ago | (#26106647)

USB 6.0: Super-Shiny-Happy-Speed

Re:Future Problems..... (0)

Anonymous Coward | more than 5 years ago | (#26106663)

USB 6.0: Ludicrous-Speed

Re:Future Problems..... (1)

MonoSynth (323007) | more than 5 years ago | (#26106723)

USB 6.0: God-speed

Because the Second Coming will be Real Soon Now (tm), while USB 6.0 will take more than three Real Soon Now (tm)'s...

Re:Future Problems..... (3, Funny)

Briareos (21163) | more than 5 years ago | (#26106743)

USB 7.0: Profit-Speed!

Re:Future Problems..... (1)

Nathrael (1251426) | more than 5 years ago | (#26106971)

Don't forget about USB 6.5: ???

Re:Future Problems..... (0)

Anonymous Coward | more than 5 years ago | (#26106849)

That's easy: USB 6.0:ÂUber-Speed.

Re:Future Problems..... (1)

asifyoucare (302582) | more than 5 years ago | (#26107131)

Profit Speed?

Firewire Not Dead, Doing Pretty Good Actually (3, Interesting)

Anonymous Coward | more than 5 years ago | (#26106517)

Whenever a story about USB3 is written, the following caveats should be mandated by law if necessary:

1. Speed claims are theoretical, and do not reflect real-world results by a long shot. Lots of overhead, CPU dependence, etc.

USB2 promised 480Mbps and never delivered it. You get 250Mbps on a good day. Now we have marketing claims that USB3 will be "10x faster," yet a video demo shows it's 3.5x faster. That's 1.5Gbps, not 5Gbps.

2. Firewire 3200 is approved and on the way. It will be faster than USB3, backward-compatible with FW800 (same cables and ports) and should begin appearing on Macs in January. Firewire isn't dead; Firewire 400 is being eased out in favour of faster versions.

If FW 3200 performs like its predecessors, it should be (in real-world usage) routinely about 2x faster than USB3.

Moral of the story: don't settle for mediocre.

Re:Firewire Not Dead, Doing Pretty Good Actually (1, Informative)

Hal_Porter (817932) | more than 5 years ago | (#26106673)

USB2 promised 480Mbps and never delivered it. You get 250Mbps on a good day. Now we have marketing claims that USB3 will be "10x faster," yet a video demo shows it's 3.5x faster. That's 1.5Gbps, not 5Gbps.

From the article

The Windows demo saw around 318 MBps, while the Linux demo typically showed 125 MBps. I saw as high as 233 MBps while formatting the disk. dd is not the best application to use for performance testing; I only used to whip up a simple demo.

Application layer measurements showed poor performance (around 2 MBps). I think two things added fixed latencies between the application layer and the host controller hardware. First, there was a massive amount of debugging output in the host controller driver and mass storage driver. Second, I had placed some msleep() calls in the USB MSD driver so that I could see the debugging output and trigger a PCI analyzer at the same time. I didn't have time to take those out before I ran my demo. I need to run more tests to disable debugging and profile the upper layer stack for other bottlenecks.

i.e. the 3.5x figure is from something which is not optimized. Actually it doesn't sound like the host controller or mass storage hardware is optimized either, she said it could use longer burst sizes. Plus it's an FPGA, not an ASIC. It's too early to judge performance yet.

Still the Windows demo figure of 318MB/s is quite close to the 350MB/sec projected max speed for USB 3.0 from the video.

sex with a tr0ll (-1, Offtopic)

Anonymous Coward | more than 5 years ago | (#26106705)

Re:sex with a tr0ll (1)

Nathrael (1251426) | more than 5 years ago | (#26106985)

Now where did I place that device that allows me to hit people on their foreheads over the Internet...

Security (2, Informative)

MSG (12810) | more than 5 years ago | (#26106855)

An awful lot of people are looking down their noses at USB 3 because it's not Firewire. Has everyone forgotten that Firewire grants devices DMA access to physical memory? Any physically connected device can be used to bypass the system's security. I'm grateful that USB isn't more like Firewire.

Load More Comments
Slashdot Login

Need an Account?

Forgot your password?

Submission Text Formatting Tips

We support a small subset of HTML, namely these tags:

  • b
  • i
  • p
  • br
  • a
  • ol
  • ul
  • li
  • dl
  • dt
  • dd
  • em
  • strong
  • tt
  • blockquote
  • div
  • quote
  • ecode

"ecode" can be used for code snippets, for example:

<ecode>    while(1) { do_something(); } </ecode>