From: Yu Zhao <yuzhao@google.com>
To: Stephen Rothwell <sfr@rothwell.id.au>, linux-mm@kvack.org
Cc: "Andi Kleen" <ak@linux.intel.com>,
	"Andrew Morton" <akpm@linux-foundation.org>,
	"Aneesh Kumar" <aneesh.kumar@linux.ibm.com>,
	"Barry Song" <21cnbao@gmail.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>,
	"Linus Torvalds" <torvalds@linux-foundation.org>,
	"Matthew Wilcox" <willy@infradead.org>,
	"Mel Gorman" <mgorman@suse.de>,
	"Michael Larabel" <Michael@michaellarabel.com>,
	"Michal Hocko" <mhocko@kernel.org>,
	"Mike Rapoport" <rppt@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, page-reclaim@google.com,
	x86@kernel.org, "Yu Zhao" <yuzhao@google.com>,
	"Barry Song" <baohua@kernel.org>,
	"Brian Geffon" <bgeffon@google.com>,
	"Jan Alexander Steffens" <heftig@archlinux.org>,
	"Oleksandr Natalenko" <oleksandr@natalenko.name>,
	"Steven Barrett" <steven@liquorix.net>,
	"Suleiman Souhlal" <suleiman@google.com>,
	"Daniel Byrne" <djbyrne@mtu.edu>,
	"Donald Carr" <d@chaos-reins.com>,
	"Holger Hoffstätte" <holger@applied-asynchrony.com>,
	"Konstantin Kharlamov" <Hi-Angel@yandex.ru>,
	"Shuang Zhai" <szhai2@cs.rochester.edu>,
	"Sofia Trinh" <sofia.trinh@edi.works>,
	"Vaibhav Jain" <vaibhav@linux.ibm.com>
Subject: [PATCH v10 03/14] mm/vmscan.c: refactor shrink_node()
Date: Wed,  6 Apr 2022 21:15:15 -0600	[thread overview]
Message-ID: <20220407031525.2368067-4-yuzhao@google.com> (raw)
In-Reply-To: <20220407031525.2368067-1-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>
Reviewed-by: Barry Song <baohua@kernel.org>
Acked-by: Brian Geffon <bgeffon@google.com>
Acked-by: Jan Alexander Steffens (heftig) <heftig@archlinux.org>
Acked-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Acked-by: Steven Barrett <steven@liquorix.net>
Acked-by: Suleiman Souhlal <suleiman@google.com>
Tested-by: Daniel Byrne <djbyrne@mtu.edu>
Tested-by: Donald Carr <d@chaos-reins.com>
Tested-by: Holger Hoffstätte <holger@applied-asynchrony.com>
Tested-by: Konstantin Kharlamov <Hi-Angel@yandex.ru>
Tested-by: Shuang Zhai <szhai2@cs.rochester.edu>
Tested-by: Sofia Trinh <sofia.trinh@edi.works>
Tested-by: Vaibhav Jain <vaibhav@linux.ibm.com>
---
 mm/vmscan.c | 198 +++++++++++++++++++++++++++-------------------------
 1 file changed, 104 insertions(+), 94 deletions(-)
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 1678802e03e7..2232cb55af41 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2644,6 +2644,109 @@ 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
@@ -3114,109 +3217,16 @@ 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);
 
-- 
2.35.1.1094.g7c7d902a7c-goog
next prev parent reply	other threads:[~2022-04-07  3:16 UTC|newest]
Thread overview: 98+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-04-07  3:15 [PATCH v10 00/14] Multi-Gen LRU Framework Yu Zhao
2022-04-07  3:15 ` [PATCH v10 01/14] mm: x86, arm64: add arch_has_hw_pte_young() Yu Zhao
2022-04-07  3:15 ` [PATCH v10 02/14] mm: x86: add CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG Yu Zhao
2022-04-07  3:15 ` Yu Zhao [this message]
2022-04-16  6:48   ` [PATCH v10 03/14] mm/vmscan.c: refactor shrink_node() Miaohe Lin
2022-04-07  3:15 ` [PATCH v10 04/14] Revert "include/linux/mm_inline.h: fold __update_lru_size() into its sole caller" Yu Zhao
2022-04-16  6:50   ` Miaohe Lin
2022-04-07  3:15 ` [PATCH v10 05/14] mm: multi-gen LRU: groundwork Yu Zhao
2022-04-12  2:16   ` Andrew Morton
2022-04-12  7:06     ` Peter Zijlstra
2022-04-20  0:39       ` Yu Zhao
2022-04-20 20:07         ` Linus Torvalds
2022-04-26 22:39     ` Yu Zhao
2022-04-26 23:42       ` Andrew Morton
2022-04-27  1:18         ` Yu Zhao
2022-04-27  1:34           ` Andrew Morton
2022-04-07  3:15 ` [PATCH v10 06/14] mm: multi-gen LRU: minimal implementation Yu Zhao
2022-04-14  6:03   ` Barry Song
2022-04-14 20:36     ` Yu Zhao
2022-04-14 21:39       ` Andrew Morton
2022-04-14 22:14         ` Yu Zhao
2022-04-15 10:15         ` Barry Song
2022-04-15 20:17           ` Yu Zhao
2022-04-15 10:26       ` Barry Song
2022-04-15 20:18         ` Yu Zhao
     [not found]   ` <71af92d2-0777-c318-67fb-8f7d52c800bb@huawei.com>
2022-04-14 20:53     ` Yu Zhao
2022-04-15  2:23       ` Chen Wandun
2022-04-15  5:25         ` Yu Zhao
2022-04-15  6:31           ` Chen Wandun
2022-04-15  6:44             ` Yu Zhao
2022-04-15  9:27               ` Chen Wandun
2022-04-18  9:58   ` Barry Song
2022-04-19  0:53     ` Yu Zhao
2022-04-19  4:25       ` Barry Song
2022-04-19  4:36         ` Barry Song
2022-04-19 22:25           ` Yu Zhao
2022-04-19 22:20         ` Yu Zhao
2022-04-07  3:15 ` [PATCH v10 07/14] mm: multi-gen LRU: exploit locality in rmap Yu Zhao
2022-04-27  4:32   ` Aneesh Kumar K.V
2022-04-27  4:38     ` Yu Zhao
2022-04-27  5:31       ` Aneesh Kumar K V
2022-04-27  6:00         ` Yu Zhao
2022-04-07  3:15 ` [PATCH v10 08/14] mm: multi-gen LRU: support page table walks Yu Zhao
2022-04-12  2:16   ` Andrew Morton
2022-04-12  7:10     ` Peter Zijlstra
2022-04-15  5:30       ` Yu Zhao
2022-04-15  1:14     ` Yu Zhao
2022-04-15  1:56       ` Andrew Morton
2022-04-15  6:25         ` Yu Zhao
2022-04-15 19:15           ` Andrew Morton
2022-04-15 20:11             ` Yu Zhao
2022-04-15 21:32               ` Andrew Morton
2022-04-15 21:36                 ` Linus Torvalds
2022-04-15 22:57                   ` Yu Zhao
2022-04-15 23:03                     ` Linus Torvalds
2022-04-15 23:24                       ` [page-reclaim] " Jesse Barnes
2022-04-15 23:31                         ` Matthew Wilcox
2022-04-15 23:37                           ` Jesse Barnes
2022-04-15 23:49                       ` Yu Zhao
2022-04-16 16:32                 ` Justin Forbes
2022-04-19 22:32                   ` Yu Zhao
2022-04-29 14:10   ` zhong jiang
2022-04-30  8:34     ` Yu Zhao
2022-04-07  3:15 ` [PATCH v10 09/14] mm: multi-gen LRU: optimize multiple memcgs Yu Zhao
2022-04-07  3:15 ` [PATCH v10 10/14] mm: multi-gen LRU: kill switch Yu Zhao
2022-04-12  2:16   ` Andrew Morton
2022-04-26 20:57     ` Yu Zhao
2022-04-26 22:22       ` Andrew Morton
2022-04-27  1:11         ` Yu Zhao
2022-04-07  3:15 ` [PATCH v10 11/14] mm: multi-gen LRU: thrashing prevention Yu Zhao
2022-04-07  3:15 ` [PATCH v10 12/14] mm: multi-gen LRU: debugfs interface Yu Zhao
2022-04-12  2:16   ` Andrew Morton
2022-04-16  0:03     ` Yu Zhao
2022-04-16  4:20       ` Andrew Morton
2022-04-26  6:59         ` Yu Zhao
2022-04-26 21:30           ` Andrew Morton
2022-04-26 22:15             ` Yu Zhao
2022-04-07  3:15 ` [PATCH v10 13/14] mm: multi-gen LRU: admin guide Yu Zhao
2022-04-07 12:41   ` Bagas Sanjaya
2022-04-07 12:51     ` Jonathan Corbet
2022-04-12  2:16   ` Andrew Morton
2022-04-16  2:22     ` Yu Zhao
2022-04-07  3:15 ` [PATCH v10 14/14] mm: multi-gen LRU: design doc Yu Zhao
2022-04-07 11:39   ` Huang Shijie
2022-04-07 12:41   ` Bagas Sanjaya
2022-04-07 12:52     ` Jonathan Corbet
2022-04-08  4:48       ` Bagas Sanjaya
2022-04-12  2:16   ` Andrew Morton
2022-04-26  7:42     ` Yu Zhao
2022-04-07  3:24 ` [PATCH v10 00/14] Multi-Gen LRU Framework Yu Zhao
2022-04-07  8:31   ` Stephen Rothwell
2022-04-07  9:08     ` Yu Zhao
2022-04-07  9:41     ` Yu Zhao
2022-04-07 12:13       ` Stephen Rothwell
2022-04-08  2:08         ` Yu Zhao
2022-04-12  2:15 ` Andrew Morton
2022-04-14  5:06 ` Andrew Morton
2022-04-20  0:50   ` 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=20220407031525.2368067-4-yuzhao@google.com \
    --to=yuzhao@google.com \
    --cc=21cnbao@gmail.com \
    --cc=Hi-Angel@yandex.ru \
    --cc=Michael@michaellarabel.com \
    --cc=ak@linux.intel.com \
    --cc=akpm@linux-foundation.org \
    --cc=aneesh.kumar@linux.ibm.com \
    --cc=axboe@kernel.dk \
    --cc=baohua@kernel.org \
    --cc=bgeffon@google.com \
    --cc=catalin.marinas@arm.com \
    --cc=corbet@lwn.net \
    --cc=d@chaos-reins.com \
    --cc=dave.hansen@linux.intel.com \
    --cc=djbyrne@mtu.edu \
    --cc=hannes@cmpxchg.org \
    --cc=hdanton@sina.com \
    --cc=heftig@archlinux.org \
    --cc=holger@applied-asynchrony.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=oleksandr@natalenko.name \
    --cc=page-reclaim@google.com \
    --cc=riel@surriel.com \
    --cc=rppt@kernel.org \
    --cc=sfr@rothwell.id.au \
    --cc=sofia.trinh@edi.works \
    --cc=steven@liquorix.net \
    --cc=suleiman@google.com \
    --cc=szhai2@cs.rochester.edu \
    --cc=torvalds@linux-foundation.org \
    --cc=vaibhav@linux.ibm.com \
    --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;
as well as URLs for NNTP newsgroup(s).