linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Yu Zhao <yuzhao@google.com>
To: linux-mm@kvack.org
Cc: Alex Shi <alexs@kernel.org>, Andi Kleen <ak@linux.intel.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	Benjamin Manes <ben.manes@gmail.com>,
	Dave Chinner <david@fromorbit.com>,
	Dave Hansen <dave.hansen@linux.intel.com>,
	Hillf Danton <hdanton@sina.com>, Jens Axboe <axboe@kernel.dk>,
	Johannes Weiner <hannes@cmpxchg.org>,
	Jonathan Corbet <corbet@lwn.net>,
	Joonsoo Kim <iamjoonsoo.kim@lge.com>,
	Matthew Wilcox <willy@infradead.org>,
	Mel Gorman <mgorman@suse.de>, Miaohe Lin <linmiaohe@huawei.com>,
	Michael Larabel <michael@michaellarabel.com>,
	Michal Hocko <mhocko@suse.com>,
	Michel Lespinasse <michel@lespinasse.org>,
	Rik van Riel <riel@surriel.com>, Roman Gushchin <guro@fb.com>,
	Rong Chen <rong.a.chen@intel.com>,
	SeongJae Park <sjpark@amazon.de>,
	Tim Chen <tim.c.chen@linux.intel.com>,
	Vlastimil Babka <vbabka@suse.cz>, Yang Shi <shy828301@gmail.com>,
	Ying Huang <ying.huang@intel.com>, Zi Yan <ziy@nvidia.com>,
	linux-kernel@vger.kernel.org, lkp@lists.01.org,
	page-reclaim@google.com, Yu Zhao <yuzhao@google.com>
Subject: [PATCH v2 07/16] mm/vmscan.c: refactor shrink_node()
Date: Tue, 13 Apr 2021 00:56:24 -0600	[thread overview]
Message-ID: <20210413065633.2782273-8-yuzhao@google.com> (raw)
In-Reply-To: <20210413065633.2782273-1-yuzhao@google.com>

Heuristics that determine scan balance between anon and file LRUs are
rather independent. Move them into a separate function to improve
readability.

Signed-off-by: Yu Zhao <yuzhao@google.com>
---
 mm/vmscan.c | 186 +++++++++++++++++++++++++++-------------------------
 1 file changed, 98 insertions(+), 88 deletions(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 562e87cbd7a1..1a24d2e0a4cb 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2224,6 +2224,103 @@ 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);
+
+	/*
+	 * 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
@@ -2669,7 +2766,6 @@ 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);
 
@@ -2679,93 +2775,7 @@ static void shrink_node(pg_data_t *pgdat, struct scan_control *sc)
 	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);
 
-- 
2.31.1.295.g9ea45b61b8-goog


  parent reply	other threads:[~2021-04-13  6:57 UTC|newest]

Thread overview: 57+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-04-13  6:56 [PATCH v2 00/16] Multigenerational LRU Framework Yu Zhao
2021-04-13  6:56 ` [PATCH v2 01/16] include/linux/memcontrol.h: do not warn in page_memcg_rcu() if !CONFIG_MEMCG Yu Zhao
2021-04-13  6:56 ` [PATCH v2 02/16] include/linux/nodemask.h: define next_memory_node() if !CONFIG_NUMA Yu Zhao
2021-04-13  6:56 ` [PATCH v2 03/16] include/linux/huge_mm.h: define is_huge_zero_pmd() if !CONFIG_TRANSPARENT_HUGEPAGE Yu Zhao
2021-04-13  6:56 ` [PATCH v2 04/16] include/linux/cgroup.h: export cgroup_mutex Yu Zhao
2021-04-13  6:56 ` [PATCH v2 05/16] mm/swap.c: export activate_page() Yu Zhao
2021-04-13  6:56 ` [PATCH v2 06/16] mm, x86: support the access bit on non-leaf PMD entries Yu Zhao
2021-04-13  6:56 ` Yu Zhao [this message]
2021-04-13  6:56 ` [PATCH v2 08/16] mm: multigenerational lru: groundwork Yu Zhao
2021-04-13  6:56 ` [PATCH v2 09/16] mm: multigenerational lru: activation Yu Zhao
2021-04-13  6:56 ` [PATCH v2 10/16] mm: multigenerational lru: mm_struct list Yu Zhao
2021-04-14 14:36   ` Matthew Wilcox
2021-04-13  6:56 ` [PATCH v2 11/16] mm: multigenerational lru: aging Yu Zhao
2021-04-13  6:56 ` [PATCH v2 12/16] mm: multigenerational lru: eviction Yu Zhao
2021-04-13  6:56 ` [PATCH v2 13/16] mm: multigenerational lru: page reclaim Yu Zhao
2021-04-13  6:56 ` [PATCH v2 14/16] mm: multigenerational lru: user interface Yu Zhao
2021-04-13  6:56 ` [PATCH v2 15/16] mm: multigenerational lru: Kconfig Yu Zhao
2021-04-13  6:56 ` [PATCH v2 16/16] mm: multigenerational lru: documentation Yu Zhao
2021-04-13  7:51 ` [PATCH v2 00/16] Multigenerational LRU Framework SeongJae Park
2021-04-13 16:13   ` Jens Axboe
2021-04-13 16:42     ` SeongJae Park
2021-04-13 23:14     ` Dave Chinner
2021-04-14  2:29       ` Rik van Riel
     [not found]         ` <CAOUHufafMcaG8sOS=1YMy2P_6p0R1FzP16bCwpUau7g1-PybBQ@mail.gmail.com>
2021-04-14  6:15           ` Huang, Ying
2021-04-14  7:58             ` Yu Zhao
2021-04-14  8:27               ` Huang, Ying
2021-04-14 13:51                 ` Rik van Riel
2021-04-14 15:56                   ` Andi Kleen
2021-04-14 15:58                   ` [page-reclaim] " Shakeel Butt
2021-04-14 18:45                   ` Yu Zhao
2021-04-14 15:51           ` Andi Kleen
2021-04-14 15:58             ` Rik van Riel
2021-04-14 19:14               ` Yu Zhao
2021-04-14 19:41                 ` Rik van Riel
2021-04-14 20:08                   ` Yu Zhao
2021-04-14 19:04             ` Yu Zhao
2021-04-15  3:00               ` Andi Kleen
2021-04-15  7:13                 ` Yu Zhao
2021-04-15  8:19                   ` Huang, Ying
2021-04-15  9:57                   ` Michel Lespinasse
2021-04-24  2:33                     ` Yu Zhao
2021-04-24  3:30                       ` Andi Kleen
2021-04-24  4:16                         ` Yu Zhao
2021-04-14  3:40       ` Yu Zhao
2021-04-14  4:50         ` Dave Chinner
2021-04-14  7:16           ` Yu Zhao
2021-04-14 10:00             ` Yu Zhao
2021-04-15  1:36             ` Dave Chinner
2021-04-24 21:21               ` Yu Zhao
2021-04-14 14:43       ` Jens Axboe
2021-04-14 19:42         ` Yu Zhao
2021-04-15  1:21         ` Dave Chinner
2021-04-14 17:43 ` Johannes Weiner
2021-04-27 10:35   ` Yu Zhao
2021-04-29 23:46 ` Konstantin Kharlamov
2021-04-30  6:37   ` Konstantin Kharlamov
2021-04-30 19:31     ` 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=20210413065633.2782273-8-yuzhao@google.com \
    --to=yuzhao@google.com \
    --cc=ak@linux.intel.com \
    --cc=akpm@linux-foundation.org \
    --cc=alexs@kernel.org \
    --cc=axboe@kernel.dk \
    --cc=ben.manes@gmail.com \
    --cc=corbet@lwn.net \
    --cc=dave.hansen@linux.intel.com \
    --cc=david@fromorbit.com \
    --cc=guro@fb.com \
    --cc=hannes@cmpxchg.org \
    --cc=hdanton@sina.com \
    --cc=iamjoonsoo.kim@lge.com \
    --cc=linmiaohe@huawei.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=lkp@lists.01.org \
    --cc=mgorman@suse.de \
    --cc=mhocko@suse.com \
    --cc=michael@michaellarabel.com \
    --cc=michel@lespinasse.org \
    --cc=page-reclaim@google.com \
    --cc=riel@surriel.com \
    --cc=rong.a.chen@intel.com \
    --cc=shy828301@gmail.com \
    --cc=sjpark@amazon.de \
    --cc=tim.c.chen@linux.intel.com \
    --cc=vbabka@suse.cz \
    --cc=willy@infradead.org \
    --cc=ying.huang@intel.com \
    --cc=ziy@nvidia.com \
    --subject='Re: [PATCH v2 07/16] mm/vmscan.c: refactor shrink_node()' \
    /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

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).