Re: readahead benchmark

[Andrew Morton]

On Mon, 5 Jun 2006 08:28:07 +0800
Fengguang Wu <fengguang.wu@xxxxxxxxx> wrote:

> On Sun, Jun 04, 2006 at 01:50:11PM -0700, Andrew Morton wrote:
> > readahead-kconfig-options.patch
> [...] 
> >  It's early days yet - needs heaps more performance testing.  The results
> >  from "Linux Portal" <linportal@xxxxxxxxx> were discouraging.
> 
> I found this mail from the lkml archive, did you happen to have more
> results?
> 

Sorry, I had the wrong tester.  Voluspa <lista1@xxxxxxxxx>: "Conclusion: On
_this_ machine, with _these_ operations, Adaptive Readahead in its current
incarnation and default settings is a _loss_."

> 
> There is an interesting (although simple) benchmark of Wu's adaptive
> readahead patchset (v12) together with graphs here:
> 
>   http://linux.inet.hr/adaptive_readahead_benchmark.html
> 
> In that simple test it definitely looks promising (3x speedup).

That's postgreql again.

We know there's a problem at present with postgresql.  Has anyone tried to
fix it, without going and rewriting everything?
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/