From: SeongJae Park <sj@kernel.org>
To: Xin Hao <xhao@linux.alibaba.com>
Cc: sj@kernel.org, akpm@linux-foundation.org, damon@lists.linux.dev,
linux-mm@kvack.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH] mm/damon: simplify scheme create in lru_sort.c
Date: Tue, 13 Sep 2022 15:43:21 +0000 [thread overview]
Message-ID: <20220913154321.45954-1-sj@kernel.org> (raw)
In-Reply-To: <20220913152245.25224-1-xhao@linux.alibaba.com>
Hi Xin,
On Tue, 13 Sep 2022 23:22:45 +0800 Xin Hao <xhao@linux.alibaba.com> wrote:
> In damon_lru_sort_new_hot_scheme() and damon_lru_sort_new_cold_scheme(),
> they have so much in common, so we can combine them into a single
> function, and we just need to distinguish their differences.
>
> Signed-off-by: Xin Hao <xhao@linux.alibaba.com>
> ---
> mm/damon/lru_sort.c | 82 +++++++++++++++++----------------------------
> 1 file changed, 30 insertions(+), 52 deletions(-)
>
> diff --git a/mm/damon/lru_sort.c b/mm/damon/lru_sort.c
> index 8415e18fcf0e..62063ed43224 100644
> --- a/mm/damon/lru_sort.c
> +++ b/mm/damon/lru_sort.c
> @@ -257,15 +257,15 @@ module_param(nr_cold_quota_exceeds, ulong, 0400);
> static struct damon_ctx *ctx;
> static struct damon_target *target;
>
> -/* Create a DAMON-based operation scheme for hot memory regions */
> -static struct damos *damon_lru_sort_new_hot_scheme(unsigned int hot_thres)
> +static inline struct damos *damon_lru_sort_new_scheme(unsigned int thres,
> + enum damos_action action)
> {
> struct damos_access_pattern pattern = {
> /* Find regions having PAGE_SIZE or larger size */
> .min_sz_region = PAGE_SIZE,
> .max_sz_region = ULONG_MAX,
> /* and accessed for more than the threshold */
> - .min_nr_accesses = hot_thres,
> + .min_nr_accesses = 0,
> .max_nr_accesses = UINT_MAX,
> /* no matter its age */
> .min_age_region = 0,
> @@ -292,60 +292,38 @@ static struct damos *damon_lru_sort_new_hot_scheme(unsigned int hot_thres)
> .weight_age = 0,
> };
>
> - return damon_new_scheme(
> - &pattern,
> - /* prioritize those on LRU lists, as soon as found */
> - DAMOS_LRU_PRIO,
> - /* under the quota. */
> - "a,
> - /* (De)activate this according to the watermarks. */
> - &wmarks);
> + switch (action) {
> + case DAMOS_LRU_PRIO:
> + pattern.min_nr_accesses = thres;
> + break;
> + case DAMOS_LRU_DEPRIO:
> + pattern.min_age_region = thres;
> + quota.weight_nr_accesses = 0;
> + quota.weight_age = 1;
> + break;
I would like to do this from damon_lru_sort_new_{hot,cold}_scheme() instead.
> + default:
> + return NULL;
> + }
> +
> + return damon_new_scheme(&pattern,
> + /* mark those as not accessed, as soon as found */
> + action,
> + /* under the quota. */
> + "a,
> + /* (De)activate this according to the watermarks. */
> + &wmarks);
> +}
> +
> +/* Create a DAMON-based operation scheme for hot memory regions */
> +static struct damos *damon_lru_sort_new_hot_scheme(unsigned int hot_thres)
> +{
> + return damon_lru_sort_new_scheme(hot_thres, DAMOS_LRU_PRIO);
> }
>
> /* Create a DAMON-based operation scheme for cold memory regions */
> static struct damos *damon_lru_sort_new_cold_scheme(unsigned int cold_thres)
> {
> - struct damos_access_pattern pattern = {
> - /* Find regions having PAGE_SIZE or larger size */
> - .min_sz_region = PAGE_SIZE,
> - .max_sz_region = ULONG_MAX,
> - /* and not accessed at all */
> - .min_nr_accesses = 0,
> - .max_nr_accesses = 0,
> - /* for min_age or more micro-seconds */
> - .min_age_region = cold_thres,
> - .max_age_region = UINT_MAX,
> - };
> - struct damos_watermarks wmarks = {
> - .metric = DAMOS_WMARK_FREE_MEM_RATE,
> - .interval = wmarks_interval,
> - .high = wmarks_high,
> - .mid = wmarks_mid,
> - .low = wmarks_low,
> - };
> - struct damos_quota quota = {
> - /*
> - * Do not try LRU-lists sorting of cold pages for more than
> - * half of quota_ms milliseconds within
> - * quota_reset_interval_ms.
> - */
> - .ms = quota_ms / 2,
> - .sz = 0,
> - .reset_interval = quota_reset_interval_ms,
> - /* Within the quota, mark colder regions not accessed first. */
> - .weight_sz = 0,
> - .weight_nr_accesses = 0,
> - .weight_age = 1,
> - };
> -
> - return damon_new_scheme(
> - &pattern,
> - /* mark those as not accessed, as soon as found */
> - DAMOS_LRU_DEPRIO,
> - /* under the quota. */
> - "a,
> - /* (De)activate this according to the watermarks. */
> - &wmarks);
> + return damon_lru_sort_new_scheme(cold_thres, DAMOS_LRU_DEPRIO);
> }
>
> static int damon_lru_sort_apply_parameters(void)
> --
> 2.31.0
And, yes, LRU_SORT is a mess. I'm also trying to make some cleanups like this:
https://git.kernel.org/pub/scm/linux/kernel/git/sj/linux.git/commit/?h=damon/next&id=366451cd82e71ff0227caa0c6b7b6f9ae2659c29
I'd like to apply your patch and then rebase my cleanups on it, but it might be
not a one second work. Could I ask you to wait until my cleanups are done? I
will post the patches within this week.
Thanks,
SJ
next prev parent reply other threads:[~2022-09-13 15:43 UTC|newest]
Thread overview: 4+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-09-13 15:22 Xin Hao
2022-09-13 15:43 ` SeongJae Park [this message]
2022-09-14 0:35 ` haoxin
2022-09-14 8:06 ` SeongJae Park
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=20220913154321.45954-1-sj@kernel.org \
--to=sj@kernel.org \
--cc=akpm@linux-foundation.org \
--cc=damon@lists.linux.dev \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=xhao@linux.alibaba.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox