linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Yu Zhao <yuzhao@google.com>
To: Andrew Morton <akpm@linux-foundation.org>, linux-mm@kvack.org
Cc: "Andi Kleen" <ak@linux.intel.com>,
	"Aneesh Kumar" <aneesh.kumar@linux.ibm.com>,
	"Catalin Marinas" <catalin.marinas@arm.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>,
	"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>,
	"Peter Zijlstra" <peterz@infradead.org>,
	"Tejun Heo" <tj@kernel.org>, "Vlastimil Babka" <vbabka@suse.cz>,
	"Will Deacon" <will@kernel.org>,
	linux-arm-kernel@lists.infradead.org, linux-doc@vger.kernel.org,
	linux-kernel@vger.kernel.org, x86@kernel.org,
	page-reclaim@google.com, "Yu Zhao" <yuzhao@google.com>,
	"Barry Song" <baohua@kernel.org>,
	"Miaohe Lin" <linmiaohe@huawei.com>,
	"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 v11 03/14] mm/vmscan.c: refactor shrink_node()
Date: Tue, 17 May 2022 19:46:22 -0600	[thread overview]
Message-ID: <20220518014632.922072-4-yuzhao@google.com> (raw)
In-Reply-To: <20220518014632.922072-1-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>
Reviewed-by: Miaohe Lin <linmiaohe@huawei.com>
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);
 
-- 
2.36.0.550.gb090851708-goog


  parent reply	other threads:[~2022-05-18  1:47 UTC|newest]

Thread overview: 41+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-05-18  1:46 [PATCH v11 00/14] Multi-Gen LRU Framework Yu Zhao
2022-05-18  1:46 ` [PATCH v11 01/14] mm: x86, arm64: add arch_has_hw_pte_young() Yu Zhao
2022-05-18  1:46 ` [PATCH v11 02/14] mm: x86: add CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG Yu Zhao
2022-05-18  1:46 ` Yu Zhao [this message]
2022-05-18  1:46 ` [PATCH v11 04/14] Revert "include/linux/mm_inline.h: fold __update_lru_size() into its sole caller" Yu Zhao
2022-05-18  1:46 ` [PATCH v11 05/14] mm: multi-gen LRU: groundwork Yu Zhao
2022-06-09  5:33   ` zhong jiang
2022-05-18  1:46 ` [PATCH v11 06/14] mm: multi-gen LRU: minimal implementation Yu Zhao
2022-06-09 12:34   ` zhong jiang
2022-06-09 14:46     ` zhong jiang
2022-05-18  1:46 ` [PATCH v11 07/14] mm: multi-gen LRU: exploit locality in rmap Yu Zhao
2022-06-06  9:25   ` Barry Song
2022-06-07  7:37     ` Barry Song
2022-06-07 10:21       ` Will Deacon
2022-06-06 22:37         ` Barry Song
2022-06-07 10:43           ` Will Deacon
2022-06-07 21:06             ` Yu Zhao
2022-06-08  0:43               ` Barry Song
2022-06-08 15:51                 ` Linus Torvalds
2022-06-08 22:45                   ` Barry Song
2022-06-16 21:55                     ` Yu Zhao
2022-06-16 22:33                       ` Barry Song
2022-06-16 23:29                         ` Yu Zhao
2022-06-17  1:42                           ` Yu Zhao
2022-06-17  2:01                             ` Barry Song
2022-06-17  3:03                               ` Yu Zhao
2022-06-17  3:17                                 ` Yu Zhao
2022-06-19 20:36                                   ` Yu Zhao
2022-06-19 21:56                                     ` Barry Song
2022-06-07 19:07       ` Yu Zhao
2022-06-08  7:48         ` Barry Song
2022-06-07 18:58     ` Yu Zhao
2022-05-18  1:46 ` [PATCH v11 08/14] mm: multi-gen LRU: support page table walks Yu Zhao
2022-05-18  1:46 ` [PATCH v11 09/14] mm: multi-gen LRU: optimize multiple memcgs Yu Zhao
2022-05-18  1:46 ` [PATCH v11 10/14] mm: multi-gen LRU: kill switch Yu Zhao
2022-05-18  1:46 ` [PATCH v11 11/14] mm: multi-gen LRU: thrashing prevention Yu Zhao
2022-05-18  1:46 ` [PATCH v11 12/14] mm: multi-gen LRU: debugfs interface Yu Zhao
2022-05-18  1:46 ` [PATCH v11 13/14] mm: multi-gen LRU: admin guide Yu Zhao
2022-05-18  1:46 ` [PATCH v11 14/14] mm: multi-gen LRU: design doc Yu Zhao
2022-05-18  2:05 ` [PATCH v11 00/14] Multi-Gen LRU Framework Jens Axboe
2022-06-07 22:47   ` 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=20220518014632.922072-4-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=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=linmiaohe@huawei.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=peterz@infradead.org \
    --cc=rppt@kernel.org \
    --cc=sofia.trinh@edi.works \
    --cc=steven@liquorix.net \
    --cc=suleiman@google.com \
    --cc=szhai2@cs.rochester.edu \
    --cc=tj@kernel.org \
    --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 \
    /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).