linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Yu Zhao <yuzhao@google.com>
To: Andrew Morton <akpm@linux-foundation.org>,
	 Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andi Kleen <ak@linux.intel.com>,
	Catalin Marinas <catalin.marinas@arm.com>,
	 Dave Hansen <dave.hansen@linux.intel.com>,
	Hillf Danton <hdanton@sina.com>,  Jens Axboe <axboe@kernel.dk>,
	Jesse Barnes <jsbarnes@google.com>,
	 Johannes Weiner <hannes@cmpxchg.org>,
	Jonathan Corbet <corbet@lwn.net>,
	 Matthew Wilcox <willy@infradead.org>,
	Mel Gorman <mgorman@suse.de>,
	 Michael Larabel <Michael@michaellarabel.com>,
	Michal Hocko <mhocko@kernel.org>,
	 Rik van Riel <riel@surriel.com>,
	Vlastimil Babka <vbabka@suse.cz>, Will Deacon <will@kernel.org>,
	 Ying Huang <ying.huang@intel.com>,
	linux-arm-kernel@lists.infradead.org,  linux-doc@vger.kernel.org,
	linux-kernel@vger.kernel.org, linux-mm@kvack.org,
	 page-reclaim@google.com, x86@kernel.org,
	Yu Zhao <yuzhao@google.com>,
	 Konstantin Kharlamov <Hi-Angel@yandex.ru>
Subject: [PATCH v6 3/9] mm/vmscan.c: refactor shrink_node()
Date: Tue,  4 Jan 2022 13:22:22 -0700	[thread overview]
Message-ID: <20220104202227.2903605-4-yuzhao@google.com> (raw)
In-Reply-To: <20220104202227.2903605-1-yuzhao@google.com>

This patch refactors shrink_node() to improve readability for the
upcoming changes to mm/vmscan.c.

Signed-off-by: Yu Zhao <yuzhao@google.com>
Tested-by: Konstantin Kharlamov <Hi-Angel@yandex.ru>
---
 mm/vmscan.c | 198 +++++++++++++++++++++++++++-------------------------
 1 file changed, 104 insertions(+), 94 deletions(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 700434db5735..b6c5fd885216 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2716,6 +2716,109 @@ 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
@@ -3186,109 +3289,16 @@ 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);
 
-- 
2.34.1.448.ga2b2bfdf31-goog



  parent reply	other threads:[~2022-01-04 20:23 UTC|newest]

Thread overview: 111+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-01-04 20:22 [PATCH v6 0/9] Multigenerational LRU Framework Yu Zhao
2022-01-04 20:22 ` [PATCH v6 1/9] mm: x86, arm64: add arch_has_hw_pte_young() Yu Zhao
2022-01-05 10:45   ` Will Deacon
2022-01-05 20:47     ` Yu Zhao
2022-01-06 10:30       ` Will Deacon
2022-01-07  7:25         ` Yu Zhao
2022-01-11 14:19           ` Will Deacon
2022-01-11 22:27             ` Yu Zhao
2022-01-04 20:22 ` [PATCH v6 2/9] mm: x86: add CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG Yu Zhao
2022-01-04 21:24   ` Linus Torvalds
2022-01-04 20:22 ` Yu Zhao [this message]
2022-01-04 20:22 ` [PATCH v6 4/9] mm: multigenerational lru: groundwork Yu Zhao
2022-01-04 21:34   ` Linus Torvalds
2022-01-11  8:16   ` Aneesh Kumar K.V
2022-01-12  2:16     ` Yu Zhao
2022-01-04 20:22 ` [PATCH v6 5/9] mm: multigenerational lru: mm_struct list Yu Zhao
2022-01-07  9:06   ` Michal Hocko
2022-01-08  0:19     ` Yu Zhao
2022-01-10 15:21       ` Michal Hocko
2022-01-12  8:08         ` Yu Zhao
2022-01-04 20:22 ` [PATCH v6 6/9] mm: multigenerational lru: aging Yu Zhao
2022-01-06 16:06   ` Michal Hocko
2022-01-06 21:27     ` Yu Zhao
2022-01-07  8:43       ` Michal Hocko
2022-01-07 21:12         ` Yu Zhao
2022-01-06 16:12   ` Michal Hocko
2022-01-06 21:41     ` Yu Zhao
2022-01-07  8:55       ` Michal Hocko
2022-01-07  9:00         ` Michal Hocko
2022-01-10  3:58           ` Yu Zhao
2022-01-10 14:37             ` Michal Hocko
2022-01-13  9:43               ` Yu Zhao
2022-01-13 12:02                 ` Michal Hocko
2022-01-19  6:31                   ` Yu Zhao
2022-01-19  9:44                     ` Michal Hocko
2022-01-10 15:01     ` Michal Hocko
2022-01-10 16:01       ` Vlastimil Babka
2022-01-10 16:25         ` Michal Hocko
2022-01-11 23:16       ` Yu Zhao
2022-01-12 10:28         ` Michal Hocko
2022-01-13  9:25           ` Yu Zhao
2022-01-07 13:11   ` Michal Hocko
2022-01-07 23:36     ` Yu Zhao
2022-01-10 15:35       ` Michal Hocko
2022-01-11  1:18         ` Yu Zhao
2022-01-11  9:00           ` Michal Hocko
     [not found]         ` <1641900108.61dd684cb0e59@mail.inbox.lv>
2022-01-11 12:15           ` Michal Hocko
2022-01-11 14:22         ` Alexey Avramov
2022-01-07 14:44   ` Michal Hocko
2022-01-10  4:47     ` Yu Zhao
2022-01-10 10:54       ` Michal Hocko
2022-01-19  7:04         ` Yu Zhao
2022-01-19  9:42           ` Michal Hocko
2022-01-23 21:28             ` Yu Zhao
2022-01-24 14:01               ` Michal Hocko
2022-01-10 16:57   ` Michal Hocko
2022-01-12  1:01     ` Yu Zhao
2022-01-12 10:17       ` Michal Hocko
2022-01-12 23:43         ` Yu Zhao
2022-01-13 11:57           ` Michal Hocko
2022-01-23 21:40             ` Yu Zhao
2022-01-04 20:22 ` [PATCH v6 7/9] mm: multigenerational lru: eviction Yu Zhao
2022-01-11 10:37   ` Aneesh Kumar K.V
2022-01-12  8:05     ` Yu Zhao
2022-01-04 20:22 ` [PATCH v6 8/9] mm: multigenerational lru: user interface Yu Zhao
2022-01-10 10:27   ` Mike Rapoport
2022-01-12  8:35     ` Yu Zhao
2022-01-12 10:31       ` Michal Hocko
2022-01-12 15:45       ` Mike Rapoport
2022-01-13  9:47         ` Yu Zhao
2022-01-13 10:31   ` Aneesh Kumar K.V
2022-01-13 23:02     ` Yu Zhao
2022-01-14  5:20       ` Aneesh Kumar K.V
2022-01-14  6:50         ` Yu Zhao
2022-01-04 20:22 ` [PATCH v6 9/9] mm: multigenerational lru: Kconfig Yu Zhao
2022-01-04 21:39   ` Linus Torvalds
2022-01-04 20:22 ` [PATCH v6 0/9] Multigenerational LRU Framework Yu Zhao
2022-01-04 20:30 ` Yu Zhao
2022-01-04 21:43   ` Linus Torvalds
2022-01-05 21:12     ` Yu Zhao
2022-01-07  9:38   ` Michal Hocko
2022-01-07 18:45     ` Yu Zhao
2022-01-10 15:39       ` Michal Hocko
2022-01-10 22:04         ` Yu Zhao
2022-01-10 22:46           ` Jesse Barnes
2022-01-11  1:41             ` Linus Torvalds
2022-01-11 10:40             ` Michal Hocko
2022-01-11  8:41   ` Yu Zhao
2022-01-11  8:53     ` Holger Hoffstätte
2022-01-11  9:26     ` Jan Alexander Steffens (heftig)
2022-01-11 16:04     ` Shuang Zhai
2022-01-12  1:46     ` Suleiman Souhlal
2022-01-12  6:07     ` Sofia Trinh
2022-01-12 16:17       ` Daniel Byrne
2022-01-18  9:21     ` Yu Zhao
2022-01-18  9:36     ` Donald Carr
2022-01-19 20:19     ` Steven Barrett
2022-01-19 22:25     ` Brian Geffon
2022-01-05  2:44 ` Shuang Zhai
2022-01-05  8:55 ` SeongJae Park
2022-01-05 10:53   ` Yu Zhao
2022-01-05 11:25     ` SeongJae Park
2022-01-05 21:06       ` Yu Zhao
2022-01-10 14:49 ` Alexey Avramov
2022-01-11 10:24 ` Alexey Avramov
2022-01-12 20:56 ` Oleksandr Natalenko
2022-01-13  8:59   ` Yu Zhao
2022-01-23  5:43 ` Barry Song
2022-01-25  6:48   ` Yu Zhao
2022-01-28  8:54     ` Barry Song
2022-02-08  9:16       ` Yu Zhao

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=20220104202227.2903605-4-yuzhao@google.com \
    --to=yuzhao@google.com \
    --cc=Hi-Angel@yandex.ru \
    --cc=Michael@michaellarabel.com \
    --cc=ak@linux.intel.com \
    --cc=akpm@linux-foundation.org \
    --cc=axboe@kernel.dk \
    --cc=catalin.marinas@arm.com \
    --cc=corbet@lwn.net \
    --cc=dave.hansen@linux.intel.com \
    --cc=hannes@cmpxchg.org \
    --cc=hdanton@sina.com \
    --cc=jsbarnes@google.com \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mgorman@suse.de \
    --cc=mhocko@kernel.org \
    --cc=page-reclaim@google.com \
    --cc=riel@surriel.com \
    --cc=torvalds@linux-foundation.org \
    --cc=vbabka@suse.cz \
    --cc=will@kernel.org \
    --cc=willy@infradead.org \
    --cc=x86@kernel.org \
    --cc=ying.huang@intel.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