Re: [PATCH] mm - implement swap prefetching

[Con Kolivas <kernel@kolivas.org>]

On Tue, 11 Oct 2005 00:35, Jesper Juhl wrote:
> On 10/10/05, Con Kolivas <kernel@kolivas.org> wrote:
> > Andrew could you please consider this for -mm
> >
> > Small changes to the style after suggestions from Pekka Enberg (thanks),
> > and changed the default size of prefetch to gently increase with size of
> > ram. Functionally this is the same code as vm-swap_prefetch-15 and I
> > believe ready for a wider audience.
>
> +	  What this will do on workstations is slowly bring back applications
> +	  that have swapped out after memory intensive workloads back into
> +	  physical ram if you have free ram at a later stage and the machine
> +	  is relatively idle. This means that when you come back to your
> +	  computer after leaving it idle for a while, applications will come
> +	  to life faster. Note that your swap usage will appear to increase
> +	  but these are cached pages, can be dropped freely by the vm, and it
> +	  should stabilise around 50% swap usage.
> +
> +	  Desktop users will most likely want to say Y.
>
> How about a little note about the impact for server users as well?
> You recommend that desktop users enable this, but you don't give any
> recommendation for servers.

Your guess is as good as mine. I can easily demonstrate a benefit when using 
it with desktop workloads but a server? It's not expensive to run but I don't 
really know if it's advantageous either. If I had to take a guess, a server 
that had multiple user logins running applications would benefit, but 
database, web servers etc I doubt would benefit.

Cheers,
Con