Re: [2.4.17/18pre] VM and swap - it's really unusable

[Robert Love]

On Mon, 2002-01-21 at 15:52, Marcelo Tosatti wrote:

> > I guess the point is, everyone argues preemption is detrimental to
> > throughput.  I'm not going to argue that we aren't adding complexity,
> > because clearly we are.  But now we have tests showing throughput is
> > improved and people still argue.  I've seen the same behavior under
> > bonnie, timing kernel compiles, etc ...
> 
> Sure, you've seen it. But _why_ it happens ?
> 
> That is the point.

Daniel just reiterated it, but I suspect we better multitask a mix of
tasks.  I/O-bound tasks that are woken can be run quicker and thus
throughput increases.

I'm not trying to tout preempt-kernel as a throughput solution.  I think
it is a neat and promising side-note to the patch, and one that
benchmarks are correlating.  Ignore it as a statistical error and
consider throughput untouched if you want. 

	Robert Love