All of lore.kernel.org
 help / color / mirror / Atom feed
From: Yu Zhao <yuzhao@google.com>
To: linux-mm@kvack.org
Cc: Alex Shi <alex.shi@linux.alibaba.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	Dave Hansen <dave.hansen@linux.intel.com>,
	Hillf Danton <hdanton@sina.com>,
	Johannes Weiner <hannes@cmpxchg.org>,
	Joonsoo Kim <iamjoonsoo.kim@lge.com>,
	Matthew Wilcox <willy@infradead.org>,
	Mel Gorman <mgorman@suse.de>, Michal Hocko <mhocko@suse.com>,
	Roman Gushchin <guro@fb.com>, Vlastimil Babka <vbabka@suse.cz>,
	Wei Yang <richard.weiyang@linux.alibaba.com>,
	Yang Shi <shy828301@gmail.com>, Ying Huang <ying.huang@intel.com>,
	linux-kernel@vger.kernel.org, page-reclaim@google.com,
	Yu Zhao <yuzhao@google.com>
Subject: [PATCH v1 08/14] mm/vmscan.c: refactor shrink_node()
Date: Sat, 13 Mar 2021 00:57:41 -0700	[thread overview]
Message-ID: <20210313075747.3781593-9-yuzhao@google.com> (raw)
In-Reply-To: <20210313075747.3781593-1-yuzhao@google.com>

Heuristics in shrink_node() are rather independent and can be
refactored 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);
 
-- 
2.31.0.rc2.261.g7f71774620-goog


  parent reply	other threads:[~2021-03-13  7:59 UTC|newest]

Thread overview: 89+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-03-13  7:57 [PATCH v1 00/14] Multigenerational LRU Yu Zhao
2021-03-13  7:57 ` Yu Zhao
2021-03-13  7:57 ` [PATCH v1 01/14] include/linux/memcontrol.h: do not warn in page_memcg_rcu() if !CONFIG_MEMCG Yu Zhao
2021-03-13  7:57   ` Yu Zhao
2021-03-13 15:09   ` Matthew Wilcox
2021-03-14  7:45     ` Yu Zhao
2021-03-13  7:57 ` [PATCH v1 02/14] include/linux/nodemask.h: define next_memory_node() if !CONFIG_NUMA Yu Zhao
2021-03-13  7:57   ` Yu Zhao
2021-03-13  7:57 ` [PATCH v1 03/14] include/linux/huge_mm.h: define is_huge_zero_pmd() if !CONFIG_TRANSPARENT_HUGEPAGE Yu Zhao
2021-03-13  7:57   ` Yu Zhao
2021-03-13  7:57 ` [PATCH v1 04/14] include/linux/cgroup.h: export cgroup_mutex Yu Zhao
2021-03-13  7:57   ` Yu Zhao
2021-03-13  7:57 ` [PATCH v1 05/14] mm/swap.c: export activate_page() Yu Zhao
2021-03-13  7:57   ` Yu Zhao
2021-03-13  7:57 ` [PATCH v1 06/14] mm, x86: support the access bit on non-leaf PMD entries Yu Zhao
2021-03-13  7:57   ` Yu Zhao
2021-03-14 22:12   ` Zi Yan
2021-03-14 22:51     ` Matthew Wilcox
2021-03-15  0:03       ` Yu Zhao
2021-03-15  0:27         ` Zi Yan
2021-03-15  1:04           ` Yu Zhao
2021-03-14 23:22   ` Dave Hansen
2021-03-15  3:16     ` Yu Zhao
2021-03-13  7:57 ` [PATCH v1 07/14] mm/pagewalk.c: add pud_entry_post() for post-order traversals Yu Zhao
2021-03-13  7:57   ` Yu Zhao
2021-03-13  7:57 ` Yu Zhao [this message]
2021-03-13  7:57   ` [PATCH v1 08/14] mm/vmscan.c: refactor shrink_node() Yu Zhao
2021-03-13  7:57 ` [PATCH v1 09/14] mm: multigenerational lru: mm_struct list Yu Zhao
2021-03-13  7:57   ` Yu Zhao
2021-03-15 19:40   ` Rik van Riel
2021-03-15 19:40     ` Rik van Riel
2021-03-16  2:07     ` Huang, Ying
2021-03-16  2:07       ` Huang, Ying
2021-03-16  3:57       ` Yu Zhao
2021-03-16  6:44         ` Huang, Ying
2021-03-16  6:44           ` Huang, Ying
2021-03-16  7:56           ` Yu Zhao
2021-03-17  3:37             ` Huang, Ying
2021-03-17  3:37               ` Huang, Ying
2021-03-17 10:46               ` Yu Zhao
2021-03-22  3:13                 ` Huang, Ying
2021-03-22  3:13                   ` Huang, Ying
2021-03-22  8:08                   ` Yu Zhao
2021-03-24  6:58                     ` Huang, Ying
2021-03-24  6:58                       ` Huang, Ying
2021-04-10 18:48                       ` Yu Zhao
2021-04-10 18:48                         ` Yu Zhao
2021-04-13  3:06                         ` Huang, Ying
2021-04-13  3:06                           ` Huang, Ying
2021-03-13  7:57 ` [PATCH v1 10/14] mm: multigenerational lru: core Yu Zhao
2021-03-13  7:57   ` Yu Zhao
2021-03-15  2:02   ` Andi Kleen
2021-03-15  2:02     ` Andi Kleen
2021-03-15  3:37     ` Yu Zhao
2021-03-13  7:57 ` [PATCH v1 11/14] mm: multigenerational lru: page activation Yu Zhao
2021-03-13  7:57   ` Yu Zhao
2021-03-16 16:34   ` Matthew Wilcox
2021-03-16 21:29     ` Yu Zhao
2021-03-13  7:57 ` [PATCH v1 12/14] mm: multigenerational lru: user space interface Yu Zhao
2021-03-13  7:57   ` Yu Zhao
2021-03-13 12:23   ` kernel test robot
2021-03-13 12:23     ` kernel test robot
2021-03-13  7:57 ` [PATCH v1 13/14] mm: multigenerational lru: Kconfig Yu Zhao
2021-03-13  7:57   ` Yu Zhao
2021-03-13 12:53   ` kernel test robot
2021-03-13 12:53     ` kernel test robot
2021-03-13 13:36   ` kernel test robot
2021-03-13 13:36     ` kernel test robot
2021-03-13  7:57 ` [PATCH v1 14/14] mm: multigenerational lru: documentation Yu Zhao
2021-03-13  7:57   ` Yu Zhao
2021-03-19  9:31   ` Alex Shi
2021-03-22  6:09     ` Yu Zhao
2021-03-14 22:48 ` [PATCH v1 00/14] Multigenerational LRU Zi Yan
2021-03-15  0:52   ` Yu Zhao
2021-03-15  1:13 ` Hillf Danton
2021-03-15  6:49   ` Yu Zhao
2021-03-15 18:00 ` Dave Hansen
2021-03-16  2:24   ` Yu Zhao
2021-03-16 14:50     ` Dave Hansen
2021-03-16 20:30       ` Yu Zhao
2021-03-16 21:14         ` Dave Hansen
2021-04-10  9:21           ` Yu Zhao
2021-04-13  3:02             ` Huang, Ying
2021-04-13  3:02               ` Huang, Ying
2021-04-13 23:00               ` Yu Zhao
2021-04-13 23:00                 ` Yu Zhao
2021-03-15 18:38 ` Yang Shi
2021-03-15 18:38   ` Yang Shi
2021-03-16  3:38   ` 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=20210313075747.3781593-9-yuzhao@google.com \
    --to=yuzhao@google.com \
    --cc=akpm@linux-foundation.org \
    --cc=alex.shi@linux.alibaba.com \
    --cc=dave.hansen@linux.intel.com \
    --cc=guro@fb.com \
    --cc=hannes@cmpxchg.org \
    --cc=hdanton@sina.com \
    --cc=iamjoonsoo.kim@lge.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mgorman@suse.de \
    --cc=mhocko@suse.com \
    --cc=page-reclaim@google.com \
    --cc=richard.weiyang@linux.alibaba.com \
    --cc=shy828301@gmail.com \
    --cc=vbabka@suse.cz \
    --cc=willy@infradead.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.