From: Dennis Zhou <dennis@kernel.org>
To: Wonhuyk Yang <vvghjk1234@gmail.com>
Cc: Tejun Heo <tj@kernel.org>, Christoph Lameter <cl@linux.com>,
linux-mm@kvack.org
Subject: Re: [PATCH] percpu: Reduce the number of cpu distance comparisions
Date: Fri, 30 Oct 2020 20:19:46 +0000 [thread overview]
Message-ID: <20201030201946.GA1061822@google.com> (raw)
In-Reply-To: <20201030013820.29758-1-vvghjk1234@gmail.com>
Hello,
On Fri, Oct 30, 2020 at 10:38:20AM +0900, Wonhuyk Yang wrote:
> From: Wonhyuk Yang <vvghjk1234@gmail.com>
>
> To build group_map[] and group_cnt[], we find out which group
> CPUs belong to by comparing the distance of the cpu. However,
> this includes cases where comparisons are not required.
>
> This patch uses a bitmap to record CPUs that is not classified in
> the group. CPUs that we know which group they belong to should be
> cleared from the bitmap. In result, we can reduce the number of
> unnecessary comparisons.
>
> Signed-off-by: Wonhyuk Yang <vvghjk1234@gmail.com>
> ---
> mm/percpu.c | 32 ++++++++++++++++++--------------
> 1 file changed, 18 insertions(+), 14 deletions(-)
>
> diff --git a/mm/percpu.c b/mm/percpu.c
> index 66a93f096394..d19ca484eee4 100644
> --- a/mm/percpu.c
> +++ b/mm/percpu.c
> @@ -2669,6 +2669,7 @@ static struct pcpu_alloc_info * __init pcpu_build_alloc_info(
> {
> static int group_map[NR_CPUS] __initdata;
> static int group_cnt[NR_CPUS] __initdata;
> + static struct cpumask mask __initdata;
> const size_t static_size = __per_cpu_end - __per_cpu_start;
> int nr_groups = 1, nr_units = 0;
> size_t size_sum, min_unit_size, alloc_size;
> @@ -2702,24 +2703,27 @@ static struct pcpu_alloc_info * __init pcpu_build_alloc_info(
> upa--;
> max_upa = upa;
>
> + cpumask_copy(&mask, cpu_possible_mask);
> +
> /* group cpus according to their proximity */
> - for_each_possible_cpu(cpu) {
> - group = 0;
> - next_group:
> - for_each_possible_cpu(tcpu) {
> - if (cpu == tcpu)
> - break;
> - if (group_map[tcpu] == group && cpu_distance_fn &&
> - (cpu_distance_fn(cpu, tcpu) > LOCAL_DISTANCE ||
> - cpu_distance_fn(tcpu, cpu) > LOCAL_DISTANCE)) {
> - group++;
> - nr_groups = max(nr_groups, group + 1);
> - goto next_group;
> - }
> - }
> + for (group = 0; !cpumask_empty(&mask); group++) {
> + /* pop the group's first cpu */
> + cpu = cpumask_first(&mask);
> group_map[cpu] = group;
> group_cnt[group]++;
> + cpumask_clear_cpu(cpu, &mask);
> +
> + for_each_cpu(tcpu, &mask) {
> + if (!cpu_distance_fn ||
> + (cpu_distance_fn(cpu, tcpu) == LOCAL_DISTANCE &&
> + cpu_distance_fn(tcpu, cpu) == LOCAL_DISTANCE)) {
> + group_map[tcpu] = group;
> + group_cnt[group]++;
> + cpumask_clear_cpu(tcpu, &mask);
> + }
> + }
> }
> + nr_groups = group;
>
> /*
> * Wasted space is caused by a ratio imbalance of upa to group_cnt.
> --
> 2.17.1
>
Sorry for the delay. It's been a little bit of a busy week for me and it
always takes me a moment to wrap my head around this code.
I've applied this to percpu#for-5.11.
Thanks,
Dennis
prev parent reply other threads:[~2020-10-30 20:20 UTC|newest]
Thread overview: 2+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-10-30 1:38 [PATCH] percpu: Reduce the number of cpu distance comparisions Wonhuyk Yang
2020-10-30 20:19 ` Dennis Zhou [this message]
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20201030201946.GA1061822@google.com \
--to=dennis@kernel.org \
--cc=cl@linux.com \
--cc=linux-mm@kvack.org \
--cc=tj@kernel.org \
--cc=vvghjk1234@gmail.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.