Asus Delivers Speed Boost With USB Attached SCSI Protocol 93
MojoKid writes "When USB debuted in 1999, it offered maximum throughput of 12Mb/s. Today, USB 3.0 offers 4.8Gb/s. Interestingly, modern USB 3 controllers use the same Bulk-Only Transport (BOT) protocol that first debuted in 1999. Before the advent of USB 3, relying on BOT made sense. Since hard drives were significantly faster than the USB 2 bus itself, the HDD was always going to be waiting on the host controller. USB 3 changed that. With 4.8Gbits/s of throughput (600MB/s), only the highest-end hardware is capable of saturating the bus. That's exposed some of BOT's weaknesses. UASP, or the USB Attached SCSI Protocol, is designed to fix these limitations, and bring USB 3 fully into the 21st century. It does this by implementing queue functions, reducing command latency, and allowing the device to transfer commands and data independently from each other. Asus is the first manufacturer to have implemented UASP in current generation motherboards and the benchmarks show transfer speeds can be improved significantly."
This will never catch on if... (Score:2)
Asus doesn't inexpensively license the technology to other board oems. Not sure how much of this is software and how much is hardware, but if there is a special USB-SCSI command set that is separate from plain SCSI then they will need to be open and supporting on that front for all OS's as well.
Re: (Score:2)
Or Asus sells their own external storage devices to their customers that are Asus branded for use with Asus machines. They have a pretty popular gaming line, which could drive enough volume. And that would give an advantage to their server line and their workstation line over the competition.
Re: (Score:1)
Or Asus sells their own external storage devices to their customers that are Asus branded for use with Asus machines. They have a pretty popular gaming line, which could drive enough volume. And that would give an advantage to their server line and their workstation line over the competition.
If so they might just as well use ESATA or SAS or something. The entire point of USB is that it's open enough to be used by many different manufacturers and still keep everything working together.
Re: (Score:3)
In the protocol arena, I find it funny to discuss adding SCSI moves a technology into "the twenty-first century".. :-)
Speaking of that, something else strikes me...
USB debuted in 1999?
I had USB in Windows 98.
So 1.0 must have been so slow, that it ran backwards in time!
Re:This will never catch on if... (Score:5, Informative)
USB debuted in 1999?
I had USB in Windows 98.
TFS is just plain wrong. From https://en.wikipedia.org/wiki/USB [wikipedia.org]...
"The original USB 1.0 specification, which was introduced in January 1996, defined data transfer rates of 1.5 Mbit/s "Low Speed" and 12 Mbit/s "Full Speed". The first widely used version of USB was 1.1, which was released in September 1998. The 12 Mbit/s data rate was intended for higher-speed devices such as disk drives, and the lower 1.5 Mbit/s rate for low data rate devices such as joysticks."
Re: (Score:3, Informative)
No, USB 1.0 headers were present on some motherboards in 1996 or so. Practically no device support, barely anyone knew what it was. USB 1.1 debuted in 1998. iMac was the first machine to get rid of the old peripherial ports in favor of USB 1.1, in 1998. It drove great demand for USB devices. USB 2.0 was early 00's stuff.
Re: (Score:2)
I think everyone at the time (asus, tyan, supermicro) had headers on the board for this new serial stuff but no devices and no standard pinout, either. not even sure the bios had much but they DID have headers and so could list 'usb' on the mobo box.
firewire was also just starting out and it was not clear which one would be used or what device or if either protocol would 'win'. firewire didn't appear until later but usb 'headers' were a bad industry joke when this was just coming out. I think it was abou
Re: (Score:1)
Re: (Score:3)
Yeah the problem on the Windows side was drivers and devices. Kinda chicken and egg problem. Manufacturers didn't want to develop drivers and make devices until they knew consumers would buy it. Consumers wouldn't buy devices until they knew there were drivers. USB would be adopted eventually; it was just a matter of time.
The iMac didn't start USB adoption but it helped speed it along as there was only USB or FireWire. FireWire would be too expensive and overkill for most peripherals. Manufacturers kne
Re: (Score:3)
Good point. But it appears that USB hardware is cheaper than esata, I don't know if that reflects costs of manufacturer but I'd assume so.
Also you could have it fall back to the standard.
Re:This will never catch on if... (Score:5, Informative)
It isn't proprietary - it is part of the USB3 spec, but hardware that actually supports it appears to have been missing, until now. There has been a Linux driver for a while now, and TFA says Windows 8 will implement it too.
Re: (Score:2)
And while we first question it, will it fix the shortcomings USB keyboards has to PS/2 keyboards?
Re: (Score:2)
And while we first question it, will it fix the shortcomings USB keyboards has to PS/2 keyboards?
Which shortcomings are those?
Re:This will never catch on if... (Score:4, Informative)
You can only use six non-modifier keys at the same time. This is a problem for playing older multiplayer games. See appendix B.1 of the USB HID 1.1 specification.
Re: (Score:2)
Re: (Score:3)
Asus doesn't inexpensively license the technology to other board oems. Not sure how much of this is software and how much is hardware, but if there is a special USB-SCSI command set that is separate from plain SCSI then they will need to be open and supporting on that front for all OS's as well.
I came to say the same thing. Linux users can no longer buy Asus motherboards (at least not the budget boards) as the new integrated LAN card does not support the legacy Realtek drivers. Even Windows cannot get online with them until one installs the near 1 GiB "driver disk" with all its other unrelated junk. And before you tell me to just install a PCI LAN card, some models (including the one I bought [asus.com]) don't even have PCI slots!
I didn't mean to rant. But Asus can no longer be trusted as a supplier, so any
Re: (Score:2)
That wouldn't stop you buying a PCI Express network adapter.
None of my local retailers stock them, and ordering one rivals the price of another motherboard.
Re: (Score:2)
Wait, really? Where do you live again (I should remember from Debian-User, but I don't)?
Anyway, is looks like r8169.ko should be fine since 3.2?
Re: (Score:2)
Thanks, I live in Beersheba, Israel. I don't see your name / handle in the Debian archives!
Although Debian and Suse both detected the LAN card as r8169, this motherboard actually uses an 8111E. The drivers for this card are not included in the kernels of any released Linux OS, I don't know about the recent 3.5, though. My complaint is that the LAN card does not support the legacy drivers in reduced-thoroughput mode. Even Windows 7 would not get online with a stock Windows install, one needs to install the d
Re: (Score:1)
1. they use the same parts as everyone else. their software is as bloated and buggy as everyone else
2. appealing to effete homosexuals does not imply good design.
3. you mean pathetic, ignorant, arrogant, narcissistic, histrionic assholes who think they're a cut above when they're just defending a bandwagon the same way they claim their 'lower castes' do, except that they're easier to rip off because they know jack and shit about technology. they just think expensive+shiny plastic = better. ignorance is blis
I like my drives (Score:5, Funny)
like I like my women, FAST, WIDE and SCSI
Re: (Score:2)
Every american sysadmin I've talked to also calls it "scuzzy". I wasn't even aware some people pronounced it "sexy".
Re: (Score:2)
Hey that sounds a lot like my booze. I always like swill liquor.
Re: (Score:1)
like I like my women, FAST, WIDE and SCSI
Some are so wide that are even bus parallelism is possible.
Re: (Score:1)
Oh yeah? Well I like my women the way I like my filesystems. FAT and 32!
Re: (Score:2)
I like my women on my drive.
Re: (Score:2)
like I like my women, FAST, WIDE and SCSI
You remind me of the time that I discovered that USB and LAN ports have the same width. It turns out that when plugging in a keyboard without looking, it might wind up in the unused onboard LAN port. That was the same day that I was repremanded for trying to plug something else into the wrong port. Both experiences ended with me frustrated.
throughput vs bandwidth (Score:5, Insightful)
When USB debuted in 1999, it offered maximum throughput of 12Mb/s.
Well, no, it didn't. It was based on 12Mb/s signaling rate, but delivered substantially lower actual throughput. There's a paper on the usb.org website that runs through it all, showing how the relatively large overhead of the protocol affects throughput.
Re: (Score:1)
Plus USB didn't debute in 1999, 1.0 was released in 1996.
Re: (Score:2)
..and 1.1 debuted in 1998.
Re: (Score:2)
I wonder if the summary should have said USB 2.0?
I first had access to a machine with USB at least a couple of years before 1999; it was a brand-new, state-of-the-art desktop machine that I'd been issued at work. It was issued to me when I started that job, and that would have been probably 1997, if I recall right.
Re: (Score:3)
You could get 8Mbps on the isochronous channel if you were the only isochronous device on the bus, plus, IIRC, 256Kbps on the bulk channel in both directions and a teensy little bit more on the interrupt channel if you were being creative/dangerous. If there were no isochronous devices on the bus, I think you could get something like 8.5Mbps on the bulk channel.
Of course, it's been over a decade since I've worked on a USB device, so I could be wrong. Except about the isochronous channel - coming up with a
Re: (Score:2)
You could get 8Mbps on the isochronous channel if you were the only isochronous device on the bus, plus, IIRC, 256Kbps on the bulk channel in both directions and a teensy little bit more on the interrupt channel if you were being creative/dangerous. If there were no isochronous devices on the bus, I think you could get something like 8.5Mbps on the bulk channel.
That's what I remember, that at the extreme limit you could get about 70% of the bandwidth actually carrying data. I didn't post specific numbers because my memory about it is much less detailed than yours.
In other words... (Score:1)
FireWire-over-USB?
Re: (Score:3)
No, Firewire (Apple's implementation of IEEE1394) would allow two external drives to talk directly to each other without going through the host.
This isn't even like SCSI, as there's no true DMA. It's more akin to NCQ. The benefits are there, if you use it for copying from RAM or SSD to USB. Otherwise, you won't notice much difference.
I'd much prefer ESATA myself, not the least because it can allow AHCI and TRIM, but also because it won't slow down if you use multiple drives simultaneously.
Re:In other words... (Score:4, Informative)
esata is just sata with some very very minor phys layer changes. its still sata.
and sata is identical to sas at the phy layer (controllers often can be used for both with diff firmware). ide, as we once knew it, morphed into sata and sata and scsi are now 'friends' in a way.
ahci is the 'real' form of sata. old compatible stuff was just that, running ide over over the sata phy layer.
trim exists whether you run esata or local sata. trim does need ahci (ie, true modern sata) but does not care or know if its internal or external.
just to clear that up a little..
Re: (Score:2)
Yup, and they don't matter because any modern PHY is designed to support both interfaces.
Re: (Score:1)
This isn't even like SCSI, as there's no true DMA.
I'm afraid this is wrong coming and going. Unfortunately it requires a rather longwinded explanation.
1. SCSI does not imply DMA. SCSI is, loosely speaking, two layers. One is a protocol layer consisting of a set of packet-like commands and responses. The other is a physical layer to transport the commands and responses. The protocol layer has no concept of host memory addresses -- it's just commands like "read logical block number 19235". DMA has no meaning there. As for the physical layer, the SCSI
Re: (Score:2)
Not quite yet. They still have to up the deliverable wattage even more, bring OTG into the high end device range, and switch to a more sensible UTP cabling and line coding to extend the range.
They'll get there... it's the way of the world. Two people invent two things. One thing is thorough, well engineered, but expensive and requires some level of experience to understand -- the other is cheap but braindead-simple and barely functional. The latter wins in the market, and when its shortcomings start garn
Re: (Score:1)
Does SATA fit into the mix anymore? (Score:4, Interesting)
With UASP sufficient to provide a good disk interface, will new motherboards keep it simple and eliminate the SATA controller and ports? Will new internal hard drives simply have USB connectors?
According to Electronic Design [electronicdesign.com],
So, a kernel could have a single SAS driver that supports all SAS, SATA, and USB block devices. This could be a marvelous convergence.
Re: (Score:3)
Good disk performances at the expense of high CPU use. USB is the winmodem of storage it will never be the preferred method if your want performance. I expect there will be plenty of SATA to USB3 bridge chips available.
Re: (Score:1)
Except that at least USB is a defined protocol. Winmodems were not.
Re: (Score:3, Interesting)
So, a kernel could have a single SAS driver that supports all SAS, SATA, and USB block devices. This could be a marvelous convergence.
I know FreeBSD does that, using the CAM (Common Access Method) subsystem. Presumably other OSes do something similar.
Re: (Score:1)
1999? (Score:1)
This is oldish news (Score:1)
USB as RAM? (Score:2)
Re: (Score:1)
Latency and price, dude.
Re: (Score:2)
As soon as they get (at least) SSD-class wear levelling? Having noticed that my longest lived thumb drives tend to be the ones I don't use that often, I'm assuming that such drives aren't as durable as SSDs when it comes to rewrite operations. An SSD in a USB 3 thumb drive form factor, now that would be something for an ultimate Linux Live Distro.
Re:USB as RAM? (Score:5, Interesting)
search for 'vertical usb flash' and you can find internal tiny usb 'thumbdrives' that mount right on the 10pin (iirc) usb mobo header. inside the case. has been that way since about the start of vista days (1gb was somewhat common as a 'cache' you could use).
They call 'em: "Flash Modules" (Score:2)
Quite interesting, all sorts of inside ports can be used to plug flash memory:
http://www.supertalent.com/products/ssd_category_detail.php?type=FDM [supertalent.com]
The little ones to plug into usb3 ports are 32g already... I'm often finding myself with unused usb connectors on the motherboard these days. There is also sata and pata.
Re: (Score:1)
The most primitive DDR memory (PC-1600, 1.6 GB/s) is more than twice as fast as USB 3.0 (625 GB/s). USB 3.0 is closest to PC-66 (533 GB/s).
Re: (Score:2)
I think you meant MB/s for the last two. :)
Re: (Score:1)
With speeds now comparable to DDR memory, what's to stop blank USB sticks being used as a temporary RAM boost?
Lots. Starting with, what happens when you pull the stick out while it has random parts of your system memory on it?
Re: (Score:2)
Re: (Score:1)
USB sticks generally have horrible controllers which once in a while take a meditative break for a second or 5. If you are the type who enjoys occasional time-outs from your work, you will love it. However, you get about the same effect from not upgrading your RAM in the first place.
There are quality USB sticks with decent controllers, of course, and with proper OS support they apparently work quite well, but they're generally expensive.
Great for audio (Score:4, Interesting)
This finally resolves the biggest problem for USB interfaces and hard drives for audio. The primary factor for performance in audio has always been access speed (seek time), and not throughput. Audio software has to access dozens of separate audio files in a very timely manner frequently, and the overhead of the USB protocol has always been a wrench in the gears. From what I'm reading, UASP offers the same advantages NCQ (Native Command Queuing) offers in SATA, which allowed for much higher track counts on the same drive rather than spreading files across several drives, which was a pain in the butt. It was only with NCQ in ~2005 that SATA finally caught up with SCSI-2 (ca 1994) in audio performance, provided the drive was 7200rpm or faster. Firewire has some form of queuing system built into the host, so it's always been better than USB for audio, but it is vanishing from laptops and desktop motherboards, even Apple products.
Now watch how long it takes before audio hardware manufacturers adopt it, and feel our pain. The first Firewire audio interfaces came out about 4 years after Firewire was standard on Mac desktops...
Re: (Score:2)
Re: (Score:2)
USB has host controllers. Always has.
Just wanted to point out that the statement wasn't that USB don't (or didn't) have host controllers, so this is irrelevant as a response.
Re: (Score:2)
Re: (Score:1)
USB3 did not solve this problem. It just increased the bandwidth.
The standard USB3 controller interface supports DMA. It is actually a relatively decent interface, unlike the horrors of its predecessors.
SCSI over USB?! (Score:5, Funny)
Just when I'm really, really tired of the acronyms, there's SCSI over USB. What's next, orange juice out of apples? Kia to Tesla conversion kits? Vegan outback steakhouses? Elegant Perl code?!
Re: (Score:2)
Layer cakes are next.
Re: (Score:3)
The seven-layer cake is a lie.
Re: (Score:2)
Dogs and cats living together?!
Nah.. (Score:2)
Thunderbolt will chew them all.
Re: (Score:2)
USB slow compared to Thunderbolt (Score:2)
Gigabyte was first (Score:1)
http://www.bit-tech.net/news/industry/2010/08/17/gigabyte-first-to-support-uasp-usb-attache/1
Why not Superspeed for SSD, hi-speed for HDD? (Score:2)
USB3 includes superspeed in addition to everything that USB1 and USB2 had - low speed (for keyboards and mice), full speed (for printers, scanners and so on), high speed (for HDDs and camcorders) and now superspeed. The way USB3 is being thought of is like it can only support superspeed, which is not the case at all. 3 just implies the current revision of the standard, nothing more, nothing less. An USB keyboard which one buys will be USB3 - just a low speed one.
Why not use the 4.8Gb/s for just SSDs, w
It doesn't make a big difference for HDDs (Score:1)