Funnily enough, we just had this discussion at work.
The HS-USB data rate is it's theoretical maximum transport layer rate.
But with protocol overhead, there's is NO WAY HD's will get 60MB/s
Compare this with Ethernet (100Mbs) or GigE (1Gbps) and TCP. There is
NO WAY you will get 1Gbs TCP transfer. You'd be happy with 80% of
that, and estatic with 90% (in some recent performance tests at work,
were able to squeeze 850Mbs with TCP over GigE). There is a comparison
similarity between the TCP overhead (using buffers, waiting for ACK's
etc) as there is with the HD transfer protocols
You don't want to use TCP for this because almost all of TCP overhead is
set up for *unreliable, shared* transport as opposed to a cable which is
*reliable, dedicated* transport.
I'm not sure about that.
TCP helps enourmously over dedicated, reliable transport becoz the app
on the other end cannot read the data as fast as it is pumped in (so the
buffers fill up), so TCP backs off transmission
With an unreliable protocol (UDP), the buffers overflow and packets get
dropped, regardless of the transport reliability
--
Michael O'Keefe | [EMAIL PROTECTED]
Live on and Ride a 03 BMW F650GSDakar| [EMAIL PROTECTED] / |
I like less more or less less than |Work:+1 858 845 3514 / |
more. UNIX-live it,love it,fork() it |Fax :+1 858 845 2652 /_p_|
My views are MINE ALONE, blah, blah, |Home:+1 760 788 1296 \`O'|
blah, yackety yack - don't come back |Fax :+1 858 _/_\|_,
--
[email protected]
http://www.kernel-panic.org/cgi-bin/mailman/listinfo/kplug-list
