Re: [PATCH] reducing overheads in fget/fput

Andrew Morton (akpm@digeo.com)
Fri, 2 May 2003 21:00:03 -0700


Dipankar Sarma <dipankar@in.ibm.com> wrote:
>
> On Fri, May 02, 2003 at 01:54:04PM -0700, Andrew Morton wrote:
> > Dipankar Sarma <dipankar@in.ibm.com> wrote:
> > > Here is a patch that fixes that.
> >
> > This patch is fairly foul.
>
> Not sure what your grouse is, but I don't like the fget_ligth()/fput_light
> semantics myself. They don't seem natural, but I can't think of
> better way to do this.

Precisely.

> >
> > > kernel sys time std-dev
> > > ------------ -------- -------
> > > UP - vanilla 2.104 0.028
> > > SMP - vanilla 2.976 0.023
> > > UP - file 1.867 0.019
> > > SMP - file 2.719 0.026
> >
> > But it is localised, and makes a substantial difference.
>
> If I haven't broken too many things, then I will try to get some
> performance results from large machines.

P4's will like it more.

> >
> > I inlined fput_light:
>
> Looks good.

I also renamed `flag' to `fput_needed' everywhere.

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/