[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20181106140801.GO27423@dhcp22.suse.cz>
Date: Tue, 6 Nov 2018 15:08:01 +0100
From: Michal Hocko <mhocko@...nel.org>
To: Arun KS <arunks@...eaurora.org>
Cc: arunks.linux@...il.com, akpm@...ux-foundation.org, vbabka@...e.cz,
osalvador@...e.de, linux-kernel@...r.kernel.org,
linux-mm@...ck.org, getarunks@...il.com
Subject: Re: [PATCH v6 2/2] mm/page_alloc: remove software prefetching in
__free_pages_core
On Tue 06-11-18 11:33:14, Arun KS wrote:
> They not only increase the code footprint, they actually make things
> slower rather than faster. Remove them as contemporary hardware doesn't
> need any hint.
I guess I have already asked for that. When you argue about performance
then always add some numbers.
I do agree we want to get rid of the prefetching because it is just too
of an micro-optimization without any reasonable story behind.
> Suggested-by: Dan Williams <dan.j.williams@...el.com>
> Signed-off-by: Arun KS <arunks@...eaurora.org>
> ---
> mm/page_alloc.c | 6 +-----
> 1 file changed, 1 insertion(+), 5 deletions(-)
>
> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index 7cf503f..a1b9a6a 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -1270,14 +1270,10 @@ void __free_pages_core(struct page *page, unsigned int order)
> struct page *p = page;
> unsigned int loop;
>
> - prefetchw(p);
> - for (loop = 0; loop < (nr_pages - 1); loop++, p++) {
> - prefetchw(p + 1);
> + for (loop = 0; loop < nr_pages ; loop++, p++) {
> __ClearPageReserved(p);
> set_page_count(p, 0);
> }
> - __ClearPageReserved(p);
> - set_page_count(p, 0);
>
> page_zone(page)->managed_pages += nr_pages;
> set_page_refcounted(page);
> --
> 1.9.1
--
Michal Hocko
SUSE Labs
Powered by blists - more mailing lists