[e2e] Re: Are you interested in TOEs and related issues

[Nicolas Christin]

[Trimming off laundry list of cc's to avoid multiple cross-postings.]

On Thu, 5 Mar 2004, stanislav shalunov wrote:

> Right now, one can do almost 8Gb/s with a single TCP stream over 10GE
> (let's say 5 or 6Gb/s with more common hardware).  The limiting factor
> is currently host bus speed.  There's nothing (except for compression
> on the bus side, but it should be clear we're not going there) that an
> offload engine can do about host bus speed.  By the time host busses
> faster than 10Gb/s are commonly available, pretty routine x86 box
> should handle 10GE saturation.

Stanislav,

Are these numbers actually discussed in more details somewhere? I quoted
some benchmarking numbers from the FreeBSD community a couple of weeks
ago on this very mailing-list, and they appeared to be significantly
more modest (~1-4 Gbps, and that was UDP as far as I can gather, on
Xeon machines).

I do not dispute the numbers that you mention, I am just curious about
the hardware/OS/software used and the type of experiment.

> Note that since even at 10Gb/s one CPU is enough to saturate the link
> with 9kB packets, [...]

Same question as above.

-- 
Nicolas