| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <CAGsJ_4zr_toOjd976AA5uBctVokVn+xZdvGo1TTZAg2XH0zmKQ@mail.gmail.com>
Date: Fri, 18 Mar 2022 14:15:48 +1300
From: Barry Song <21cnbao@...il.com>
To: Yu Zhao <yuzhao@...gle.com>
Cc: Andrew Morton <akpm@...ux-foundation.org>,
Linus Torvalds <torvalds@...ux-foundation.org>,
Andi Kleen <ak@...ux.intel.com>,
Aneesh Kumar <aneesh.kumar@...ux.ibm.com>,
Catalin Marinas <catalin.marinas@....com>,
Dave Hansen <dave.hansen@...ux.intel.com>,
Hillf Danton <hdanton@...a.com>, Jens Axboe <axboe@...nel.dk>,
Jesse Barnes <jsbarnes@...gle.com>,
Johannes Weiner <hannes@...xchg.org>,
Jonathan Corbet <corbet@....net>,
Matthew Wilcox <willy@...radead.org>,
Mel Gorman <mgorman@...e.de>,
Michael Larabel <Michael@...haellarabel.com>,
Michal Hocko <mhocko@...nel.org>,
Mike Rapoport <rppt@...nel.org>,
Rik van Riel <riel@...riel.com>,
Vlastimil Babka <vbabka@...e.cz>,
Will Deacon <will@...nel.org>,
Ying Huang <ying.huang@...el.com>,
LAK <linux-arm-kernel@...ts.infradead.org>,
Linux Doc Mailing List <linux-doc@...r.kernel.org>,
LKML <linux-kernel@...r.kernel.org>,
Linux-MM <linux-mm@...ck.org>,
Kernel Page Reclaim v2 <page-reclaim@...gle.com>,
x86 <x86@...nel.org>, Brian Geffon <bgeffon@...gle.com>,
Jan Alexander Steffens <heftig@...hlinux.org>,
Oleksandr Natalenko <oleksandr@...alenko.name>,
Steven Barrett <steven@...uorix.net>,
Suleiman Souhlal <suleiman@...gle.com>,
Daniel Byrne <djbyrne@....edu>,
Donald Carr <d@...os-reins.com>,
Holger Hoffstätte <holger@...lied-asynchrony.com>,
Konstantin Kharlamov <Hi-Angel@...dex.ru>,
Shuang Zhai <szhai2@...rochester.edu>,
Sofia Trinh <sofia.trinh@....works>,
Vaibhav Jain <vaibhav@...ux.ibm.com>
Subject: Re: [PATCH v9 03/14] mm/vmscan.c: refactor shrink_node()
On Wed, Mar 9, 2022 at 3:47 PM Yu Zhao <yuzhao@...gle.com> wrote:
>
> This patch refactors shrink_node() to improve readability for the
> upcoming changes to mm/vmscan.c.
>
> Signed-off-by: Yu Zhao <yuzhao@...gle.com>
> Acked-by: Brian Geffon <bgeffon@...gle.com>
> Acked-by: Jan Alexander Steffens (heftig) <heftig@...hlinux.org>
> Acked-by: Oleksandr Natalenko <oleksandr@...alenko.name>
> Acked-by: Steven Barrett <steven@...uorix.net>
> Acked-by: Suleiman Souhlal <suleiman@...gle.com>
> Tested-by: Daniel Byrne <djbyrne@....edu>
> Tested-by: Donald Carr <d@...os-reins.com>
> Tested-by: Holger Hoffstätte <holger@...lied-asynchrony.com>
> Tested-by: Konstantin Kharlamov <Hi-Angel@...dex.ru>
> Tested-by: Shuang Zhai <szhai2@...rochester.edu>
> Tested-by: Sofia Trinh <sofia.trinh@....works>
> Tested-by: Vaibhav Jain <vaibhav@...ux.ibm.com>
Reviewed-by: Barry Song <baohua@...nel.org>
seems nice refactoring since we are going to skip the whole
function for lru_gen later:
static void prepare_scan_count(pg_data_t *pgdat, struct scan_control *sc)
{
unsigned long file;
struct lruvec *target_lruvec;
if (lru_gen_enabled())
return;
...
}
> ---
> mm/vmscan.c | 198 +++++++++++++++++++++++++++-------------------------
> 1 file changed, 104 insertions(+), 94 deletions(-)
>
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index 59b14e0d696c..8e744cdf802f 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -2718,6 +2718,109 @@ enum scan_balance {
> SCAN_FILE,
> };
>
> +static void prepare_scan_count(pg_data_t *pgdat, struct scan_control *sc)
> +{
> + unsigned long file;
> + struct lruvec *target_lruvec;
> +
> + target_lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup, pgdat);
> +
> + /*
> + * Flush the memory cgroup stats, so that we read accurate per-memcg
> + * lruvec stats for heuristics.
> + */
> + mem_cgroup_flush_stats();
> +
> + /*
> + * Determine the scan balance between anon and file LRUs.
> + */
> + spin_lock_irq(&target_lruvec->lru_lock);
> + sc->anon_cost = target_lruvec->anon_cost;
> + sc->file_cost = target_lruvec->file_cost;
> + spin_unlock_irq(&target_lruvec->lru_lock);
> +
> + /*
> + * Target desirable inactive:active list ratios for the anon
> + * and file LRU lists.
> + */
> + if (!sc->force_deactivate) {
> + unsigned long refaults;
> +
> + refaults = lruvec_page_state(target_lruvec,
> + WORKINGSET_ACTIVATE_ANON);
> + if (refaults != target_lruvec->refaults[0] ||
> + inactive_is_low(target_lruvec, LRU_INACTIVE_ANON))
> + sc->may_deactivate |= DEACTIVATE_ANON;
> + else
> + sc->may_deactivate &= ~DEACTIVATE_ANON;
> +
> + /*
> + * When refaults are being observed, it means a new
> + * workingset is being established. Deactivate to get
> + * rid of any stale active pages quickly.
> + */
> + refaults = lruvec_page_state(target_lruvec,
> + WORKINGSET_ACTIVATE_FILE);
> + if (refaults != target_lruvec->refaults[1] ||
> + inactive_is_low(target_lruvec, LRU_INACTIVE_FILE))
> + sc->may_deactivate |= DEACTIVATE_FILE;
> + else
> + sc->may_deactivate &= ~DEACTIVATE_FILE;
> + } else
> + sc->may_deactivate = DEACTIVATE_ANON | DEACTIVATE_FILE;
> +
> + /*
> + * If we have plenty of inactive file pages that aren't
> + * thrashing, try to reclaim those first before touching
> + * anonymous pages.
> + */
> + file = lruvec_page_state(target_lruvec, NR_INACTIVE_FILE);
> + if (file >> sc->priority && !(sc->may_deactivate & DEACTIVATE_FILE))
> + sc->cache_trim_mode = 1;
> + else
> + sc->cache_trim_mode = 0;
> +
> + /*
> + * Prevent the reclaimer from falling into the cache trap: as
> + * cache pages start out inactive, every cache fault will tip
> + * the scan balance towards the file LRU. And as the file LRU
> + * shrinks, so does the window for rotation from references.
> + * This means we have a runaway feedback loop where a tiny
> + * thrashing file LRU becomes infinitely more attractive than
> + * anon pages. Try to detect this based on file LRU size.
> + */
> + if (!cgroup_reclaim(sc)) {
> + unsigned long total_high_wmark = 0;
> + unsigned long free, anon;
> + int z;
> +
> + free = sum_zone_node_page_state(pgdat->node_id, NR_FREE_PAGES);
> + file = node_page_state(pgdat, NR_ACTIVE_FILE) +
> + node_page_state(pgdat, NR_INACTIVE_FILE);
> +
> + for (z = 0; z < MAX_NR_ZONES; z++) {
> + struct zone *zone = &pgdat->node_zones[z];
> +
> + if (!managed_zone(zone))
> + continue;
> +
> + total_high_wmark += high_wmark_pages(zone);
> + }
> +
> + /*
> + * Consider anon: if that's low too, this isn't a
> + * runaway file reclaim problem, but rather just
> + * extreme pressure. Reclaim as per usual then.
> + */
> + anon = node_page_state(pgdat, NR_INACTIVE_ANON);
> +
> + sc->file_is_tiny =
> + file + free <= total_high_wmark &&
> + !(sc->may_deactivate & DEACTIVATE_ANON) &&
> + anon >> sc->priority;
> + }
> +}
> +
> /*
> * Determine how aggressively the anon and file LRU lists should be
> * scanned. The relative value of each set of LRU lists is determined
> @@ -3188,109 +3291,16 @@ static void shrink_node(pg_data_t *pgdat, struct scan_control *sc)
> unsigned long nr_reclaimed, nr_scanned;
> struct lruvec *target_lruvec;
> bool reclaimable = false;
> - unsigned long file;
>
> target_lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup, pgdat);
>
> again:
> - /*
> - * Flush the memory cgroup stats, so that we read accurate per-memcg
> - * lruvec stats for heuristics.
> - */
> - mem_cgroup_flush_stats();
> -
> memset(&sc->nr, 0, sizeof(sc->nr));
>
> nr_reclaimed = sc->nr_reclaimed;
> nr_scanned = sc->nr_scanned;
>
> - /*
> - * Determine the scan balance between anon and file LRUs.
> - */
> - spin_lock_irq(&target_lruvec->lru_lock);
> - sc->anon_cost = target_lruvec->anon_cost;
> - sc->file_cost = target_lruvec->file_cost;
> - spin_unlock_irq(&target_lruvec->lru_lock);
> -
> - /*
> - * Target desirable inactive:active list ratios for the anon
> - * and file LRU lists.
> - */
> - if (!sc->force_deactivate) {
> - unsigned long refaults;
> -
> - refaults = lruvec_page_state(target_lruvec,
> - WORKINGSET_ACTIVATE_ANON);
> - if (refaults != target_lruvec->refaults[0] ||
> - inactive_is_low(target_lruvec, LRU_INACTIVE_ANON))
> - sc->may_deactivate |= DEACTIVATE_ANON;
> - else
> - sc->may_deactivate &= ~DEACTIVATE_ANON;
> -
> - /*
> - * When refaults are being observed, it means a new
> - * workingset is being established. Deactivate to get
> - * rid of any stale active pages quickly.
> - */
> - refaults = lruvec_page_state(target_lruvec,
> - WORKINGSET_ACTIVATE_FILE);
> - if (refaults != target_lruvec->refaults[1] ||
> - inactive_is_low(target_lruvec, LRU_INACTIVE_FILE))
> - sc->may_deactivate |= DEACTIVATE_FILE;
> - else
> - sc->may_deactivate &= ~DEACTIVATE_FILE;
> - } else
> - sc->may_deactivate = DEACTIVATE_ANON | DEACTIVATE_FILE;
> -
> - /*
> - * If we have plenty of inactive file pages that aren't
> - * thrashing, try to reclaim those first before touching
> - * anonymous pages.
> - */
> - file = lruvec_page_state(target_lruvec, NR_INACTIVE_FILE);
> - if (file >> sc->priority && !(sc->may_deactivate & DEACTIVATE_FILE))
> - sc->cache_trim_mode = 1;
> - else
> - sc->cache_trim_mode = 0;
> -
> - /*
> - * Prevent the reclaimer from falling into the cache trap: as
> - * cache pages start out inactive, every cache fault will tip
> - * the scan balance towards the file LRU. And as the file LRU
> - * shrinks, so does the window for rotation from references.
> - * This means we have a runaway feedback loop where a tiny
> - * thrashing file LRU becomes infinitely more attractive than
> - * anon pages. Try to detect this based on file LRU size.
> - */
> - if (!cgroup_reclaim(sc)) {
> - unsigned long total_high_wmark = 0;
> - unsigned long free, anon;
> - int z;
> -
> - free = sum_zone_node_page_state(pgdat->node_id, NR_FREE_PAGES);
> - file = node_page_state(pgdat, NR_ACTIVE_FILE) +
> - node_page_state(pgdat, NR_INACTIVE_FILE);
> -
> - for (z = 0; z < MAX_NR_ZONES; z++) {
> - struct zone *zone = &pgdat->node_zones[z];
> - if (!managed_zone(zone))
> - continue;
> -
> - total_high_wmark += high_wmark_pages(zone);
> - }
> -
> - /*
> - * Consider anon: if that's low too, this isn't a
> - * runaway file reclaim problem, but rather just
> - * extreme pressure. Reclaim as per usual then.
> - */
> - anon = node_page_state(pgdat, NR_INACTIVE_ANON);
> -
> - sc->file_is_tiny =
> - file + free <= total_high_wmark &&
> - !(sc->may_deactivate & DEACTIVATE_ANON) &&
> - anon >> sc->priority;
> - }
> + prepare_scan_count(pgdat, sc);
>
> shrink_node_memcgs(pgdat, sc);
>
> --
> 2.35.1.616.g0bdcbb4464-goog
>
Thanks
Barry
Powered by blists - more mailing lists