Re: [PATCH 1/1] indirect function calls elimination in IO eliminate

["Randy.Dunlap" <rdunlap@xenotime.net>]

On Thu, 13 Oct 2005, Ananiev, Leonid I wrote:

> >From Leonid Ananiev
>
>       Fully modular io schedulers and enables online switching between
> them was introduced in Linux 2.6.10 but as a result percentage of CPU
> using by kernel was increased and performance degradation is marked on
> Itanium. A cause of degradation is in more steps for indirect IO
> scheduler type specific function calls.
>       The patch eliminates 45 indirect function calls in 16 elevator
> functions. Sysbench fileio benchmark throughput was increased at 2% for
> noop elevator after patching.
>
> Signed-off-by: Leonid Ananiev leonid.i.ananiev@intel.com

Hi-

Put <...> around the email address.

> ---

patching file drivers/block/as-iosched.c
patch: **** malformed patch at line 39:


Ugh.  Does exchange (server) add all of those extra lines?

> diff -rup linux-2.6.14-rc2/drivers/block/as-iosched.c
> linux-2.6.14-rc2elv1/drivers/block/as-iosched.c
>
> --- linux-2.6.14-rc2/drivers/block/as-iosched.c      2005-09-24
> 09:13:54.000000000 +0400
>
> +++ linux-2.6.14-rc2elv1/drivers/block/as-iosched.c  2005-10-13
> 04:18:12.000000000 +0400
>
> @@ -614,7 +614,7 @@ static void as_antic_stop(struct as_data
>
>  static void as_antic_timeout(unsigned long data)
>
>  {
>
>       struct request_queue *q = (struct request_queue *)data;
>
> -     struct as_data *ad = q->elevator->elevator_data;
>
> +     struct as_data *ad = q->elevator.elevator_data;
>
>       unsigned long flags;
>
>
>
>       spin_lock_irqsave(q->queue_lock, flags);

-- 
~Randy
-
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/