Re: Does SMP significantly increase LVS performance ?

[Joseph Mack <mack@xxxxxxxxxxx>]

On Mon, 13 Mar 2000, Kyle Sparger wrote:

> point, a big part of what happened with the Mindcraft benchmarks was
> blamed on the fact that the kernel's TCP/IP stack is (was?) not
> multithreaded.

I think what Julian was alluding to is that only one cpu can be in the
kernel at any one time in 2.2 kernels, and LVS is all kernel code. 

Joe

--
Joseph Mack mack@xxxxxxxxxxx