Re: cache_reap(): Further reduction in interrupt holdoff

["Pekka Enberg" <penberg@cs.helsinki.fi>]

Hi,

(Christoph, please use penberg@cs.helsinki.fi instead.)

On 3/4/06, Christoph Lameter <clameter@engr.sgi.com> wrote:
> cache_reap takes the l3->list_lock (disabling interrupts) unconditionally and
> then does a few checks and maybe does some cleanup. This patch makes
> cache_reap() only take the lock if there is work to do and then the lock
> is taken and released for each cleaning action.
>
> The checking of when to do the next reaping is done without any locking
> and becomes racy. Should not matter since reaping can also be skipped
> if the slab mutex cannot be acquired.

The cache chain mutex is mostly used by /proc/slabinfo and not taken
that often, I think. But yeah, I don't think next reaping is an issue
either.

On 3/4/06, Christoph Lameter <clameter@engr.sgi.com> wrote:
> The same is true for the touched processing. If we get this wrong once
> in awhile then we will mistakenly clean or not clean the shared cache.
> This will impact performance slightly.

Touched processing worries me little because it's used when there's
high allocation pressure. Do you have any numbers where this patch
helps?

                                         Pekka
-
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/