Re: please revert bogus patch to vmscan.c

[Linus Torvalds]

On Mon, 29 Oct 2001, Benjamin LaHaise wrote:
>
> Think of CPUs with tagged tlbs and lots of entries.  Or even a system that
> only runs 1 threaded app.  Easily triggerable.  If people want to optimise
> it, great.  But go for correctness first, please...

"easily triggerable"?

I doubt you'll find _any_ system where you can trigger it. Think about it:
in order to get the kind of VM pressure that causes page-outs, your TLB
pressure will be a lot higher than _any_ CPU I have ever heard about.

256 TLB entries is considered "a lot". Tagged or not, if the VM pressure
is so big that we need to swap, those 256 entries are a grain of sand in
sahara.

		Linus