<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN">
<html>
<head>
<meta content="text/html; charset=UTF-8" http-equiv="Content-Type">
</head>
<body text="#000000" bgcolor="#ffffff">
It is recognized as USB3, but as I said, I have no USB3 devices to test
it with (my assumption of the "noSuperSpeed" comment). Notice it is
"xhci_hcd" rather then "ohci_hcd".<br>
<br>
[ 22.397278] xhci_hcd 0000:07:00.0: PCI INT A -> Link[LNND] ->
GSI 19 (level, low) -> IRQ 19<br>
[ 22.397305] xhci_hcd 0000:07:00.0: setting latency timer to 64<br>
[ 22.397309] xhci_hcd 0000:07:00.0: xHCI Host Controller<br>
[ 22.397397] xhci_hcd 0000:07:00.0: new USB bus registered, assigned
bus number 3<br>
[ 22.397537] xhci_hcd 0000:07:00.0: irq 19, io mem 0xfe7fe000<br>
[ 22.397576] usb usb3: config 1 interface 0 altsetting 0 endpoint
0x81 has no SuperSpeed companion descriptor<br>
[ 22.397646] usb usb3: configuration #1 chosen from 1 choice<br>
[ 22.397651] xHCI xhci_add_endpoint called for root hub<br>
[ 22.397653] xHCI xhci_check_bandwidth called for root hub<br>
<br>
USB3 is indeed supported in the kernel. You will have to check for
support for an individual chipset depending on your controller though,
as there is more then one, but as long as the manufacturer has
co-operated with the kernel people, I imagine any chipset will be
supported. <br>
<br>
One of the advantages USB3 will have over SATA is that it is a serial
port. You will be able to daisy chain multiple devices to the one
port, which you cannot do with SATA. Also hotplugging will work better
with USB3 then it does with SATA. There may be other advantages as
well, I am not sure.<br>
<br>
In terms of pure speed SATA may likely be better though -- I believe
there are some speed tests of USB3 out there that you could search
online for.<br>
<br>
I don't think the goal of USB3 was to compete with SATA, it was just to
make faster USB. It will be use full for many things other then just
plugging in disks (video?).<br>
<br>
<br>
<br>
<pre class="moz-signature" cols="72">- Steven</pre>
<br>
On 06/19/2010 11:00 AM, Chris Irwin wrote:
<blockquote cite="mid:1276959638.20043.22.camel@Thinkpad" type="cite">
<pre wrap="">On Fri, 2010-06-18 at 21:07 -0400, unsolicited wrote:
</pre>
<blockquote type="cite">
<pre wrap="">But, vis a vis eSata, why go down the USB road? OK, I know, no eSata
port. But also, likely, no USB3 port.
Internally, be it internal flash drive or bay, you know it's going to
be SATA based, not USB based.
</pre>
<blockquote type="cite">
<pre wrap="">SATA-III will also benefit "Small" virtualization users with
on-host storage. "Big" virt users will have centralized network
storage (and thus still benefit according to your rule above), but
us smaller guys running multiple VMs locally will potentially see a
benefit.
</pre>
</blockquote>
<pre wrap="">
Right, I get the whole SATA III thing, if drives are a bottleneck,
it's the USB3 thing that nobody's said 'Why?' over eSata, yet.
</pre>
</blockquote>
<pre wrap="">
I don't have an answer. I think eSATA will be faster, but whether or not
you actually need that speed.... One of the big benefits of USB is that
it is used for more than just storage. But what else needs to transfer
that much data? Video & Still cameras are glorified mass storage
devices...
I wonder if we'll see USB3 "RAM" extenders. Plug it in and it holds your
swap...
</pre>
<blockquote type="cite">
<blockquote type="cite">
<blockquote type="cite">
<pre wrap="">- even on a home connected web server, the limitation will be ISP
speed, not disk speed? IIRC, typically systems are disk bound,
but there's a whole lot of 'stuff' between the CPU and disk,
preventing an increase in disk speed from providing an equivalent
increase in system speed? (And this is even presuming sufficient
requests are coming in sufficiently often to "make 'it'
worthwhile"?
</pre>
</blockquote>
<pre wrap="">
I use unison to sync $HOME between my laptop and server. It runs on
both local and remote hosts, examines my data on each, then
presents a merge-list (which it executes using an rsync-like
method). The part where my two $HOME directories are being examined
takes more time (by far) than the actual data sync over the network
(even using wifi). Faster disks on my server, even given the 'slow'
network link, would still be a benefit.
</pre>
</blockquote>
<pre wrap="">
Hold on, is the issue there disk speed, or CPU speed calculating the
deltas?
</pre>
</blockquote>
<pre wrap="">
I'd say disk speed. I have an SSD in my laptop, and unison indicates it
is waiting for the remote
</pre>
<blockquote type="cite">
<blockquote type="cite">
<blockquote type="cite">
<pre wrap="">- if drives are SATA, and the bus is USB3, why USB3 instead of
just staying with (e)SATA?
</pre>
</blockquote>
<pre wrap="">
Getting a USB3 enclosure for your drive would allow backwards
compatibility with USB2 hosts -- granted, most eSATA enclosures
also have USB2.0 ports anyway. Some SATA chipsets don't like hot
unplugging.
eSATA drives need a separate source for power, versus one
power+data cord for USB.
</pre>
</blockquote>
<pre wrap="">
Right, but your .jpg above shows that ain't necessarily so.
</pre>
</blockquote>
<pre wrap="">
The only problem is: when can you assume people have that? I still see
laptops that come exclusively with VGA output, nevermind DVI, HDMI, or
DisplayPort.
</pre>
<blockquote type="cite">
<pre wrap="">So, the USB / firewire 'next level' race is back on, but joined by
eSata now.
</pre>
</blockquote>
<pre wrap="">
The fight is on for storage devices. USB already won everything else. I
don't see firewire going after they keyborad/mouse/webcam connector
market.
</pre>
<pre wrap="">
<fieldset class="mimeAttachmentHeader"></fieldset>
_______________________________________________
kwlug-disc_kwlug.org mailing list
<a class="moz-txt-link-abbreviated" href="mailto:kwlug-disc_kwlug.org@kwlug.org">kwlug-disc_kwlug.org@kwlug.org</a>
<a class="moz-txt-link-freetext" href="http://astoria.ccjclearline.com/mailman/listinfo/kwlug-disc_kwlug.org">http://astoria.ccjclearline.com/mailman/listinfo/kwlug-disc_kwlug.org</a>
</pre>
</blockquote>
</body>
</html>