linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: "解 咏梅" <yongmeixie@hotmail.com>
To: "akpm@linux-foundation.org" <akpm@linux-foundation.org>,
	"linux-mm@kvack.org" <linux-mm@kvack.org>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>
Subject: 回复: [PATCH] mm:vmscan: fix extra adjustment for lruvec's nonresident_age in case of reactivation
Date: Mon, 20 Sep 2021 03:11:02 +0000	[thread overview]
Message-ID: <TYYP286MB11150F9D24DF4DEFF5D89F8DC5A09@TYYP286MB1115.JPNP286.PROD.OUTLOOK.COM> (raw)
In-Reply-To: <TYCP286MB1108D012DA436CA72029ACA7C5DF9@TYCP286MB1108.JPNP286.PROD.OUTLOOK.COM>


[-- Attachment #1.1: Type: text/plain, Size: 3434 bytes --]

Sorry, list_move can cause some problem when deleting a entry not on list any more (AKA DEBUG_LIST in enabled)
I corrected the patch as the attached.

Best Regards,
Yongmei.
________________________________
发件人: Yongmei Xie <yongmeixie@hotmail.com>
发送时间: 2021年9月19日 23:25
收件人: akpm@linux-foundation.org <akpm@linux-foundation.org>; linux-mm@kvack.org <linux-mm@kvack.org>; linux-kernel@vger.kernel.org <linux-kernel@vger.kernel.org>
抄送: yongmeixie@hotmail.com <yongmeixie@hotmail.com>
主题: [PATCH] mm:vmscan: fix extra adjustment for lruvec's nonresident_age in case of reactivation

Before commit #31d8fcac, VM didn't increase nonresident_age (AKA inactive age for
file pages) in shrink_page_list. When putback_inactive_pages was converged with
move_pages_to_lru, both shrink_active_list and shrink_page_list use the same
function to handle move pages to the appropriate lru under lru lock's protection.

At those day, VM didn't increase nonresident_age for second chance promotion.
Commit #31d8fcac fix the problem. Definitely, we should account the activation
for second chance. But move_pages_to_lru is used in reactivation in active lru
as well for protecting code section. So I suggest to add another variable to
tell whether reactivation or not.

Signed-off-by: Yongmei Xie <yongmeixie@hotmail.com>
---
 mm/vmscan.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 74296c2d1fed..85ccafcd4912 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2152,7 +2152,8 @@ static int too_many_isolated(struct pglist_data *pgdat, int file,
  * Returns the number of pages moved to the given lruvec.
  */
 static unsigned int move_pages_to_lru(struct lruvec *lruvec,
-                                     struct list_head *list)
+                                     struct list_head *list,
+                                     bool reactivation)
 {
         int nr_pages, nr_moved = 0;
         LIST_HEAD(pages_to_free);
@@ -2203,7 +2204,7 @@ static unsigned int move_pages_to_lru(struct lruvec *lruvec,
                 add_page_to_lru_list(page, lruvec);
                 nr_pages = thp_nr_pages(page);
                 nr_moved += nr_pages;
-               if (PageActive(page))
+               if (PageActive(page) && !reactivation)
                         workingset_age_nonresident(lruvec, nr_pages);
         }

@@ -2281,7 +2282,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
         nr_reclaimed = shrink_page_list(&page_list, pgdat, sc, &stat, false);

         spin_lock_irq(&lruvec->lru_lock);
-       move_pages_to_lru(lruvec, &page_list);
+       move_pages_to_lru(lruvec, &page_list, false);

         __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken);
         item = current_is_kswapd() ? PGSTEAL_KSWAPD : PGSTEAL_DIRECT;
@@ -2418,8 +2419,8 @@ static void shrink_active_list(unsigned long nr_to_scan,
          */
         spin_lock_irq(&lruvec->lru_lock);

-       nr_activate = move_pages_to_lru(lruvec, &l_active);
-       nr_deactivate = move_pages_to_lru(lruvec, &l_inactive);
+       nr_activate = move_pages_to_lru(lruvec, &l_active, true);
+       nr_deactivate = move_pages_to_lru(lruvec, &l_inactive, false);
         /* Keep all free pages in l_active list */
         list_splice(&l_inactive, &l_active);

--
2.18.2


[-- Attachment #1.2: Type: text/html, Size: 6608 bytes --]

[-- Attachment #2: v2-0001-mm-vmscan-remove-unnecessary-lru-lock-unlock-lock.patch --]
[-- Type: application/octet-stream, Size: 2536 bytes --]

From d25dea3adb696454cc926b644566e055008d752a Mon Sep 17 00:00:00 2001
From: Yongmei Xie <yongmeixie@hotmail.com>
Date: Sun, 19 Sep 2021 22:57:50 +0800
Subject: [PATCH v2] mm:vmscan remove unnecessary lru lock unlock/lock pair

There's code redundant in move_pages_to_lru. When there're multiple of mlocked pages
or compound pages, the original implementation tries to unlock and then lock to handle
some exceptional case.

Signed-off-by: Yongmei Xie <yongmeixie@hotmail.com>
---
 mm/vmscan.c | 32 ++++++++++++++++++++++++--------
 1 file changed, 24 insertions(+), 8 deletions(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 74296c2d1fed..045ca34272c1 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2156,6 +2156,8 @@ static unsigned int move_pages_to_lru(struct lruvec *lruvec,
 {
 	int nr_pages, nr_moved = 0;
 	LIST_HEAD(pages_to_free);
+	LIST_HEAD(pages_to_putback);
+	LIST_HEAD(compound_pages_to_free);
 	struct page *page;
 
 	while (!list_empty(list)) {
@@ -2163,9 +2165,7 @@ static unsigned int move_pages_to_lru(struct lruvec *lruvec,
 		VM_BUG_ON_PAGE(PageLRU(page), page);
 		list_del(&page->lru);
 		if (unlikely(!page_evictable(page))) {
-			spin_unlock_irq(&lruvec->lru_lock);
-			putback_lru_page(page);
-			spin_lock_irq(&lruvec->lru_lock);
+			list_add(&page->lru, &pages_to_putback);
 			continue;
 		}
 
@@ -2185,11 +2185,9 @@ static unsigned int move_pages_to_lru(struct lruvec *lruvec,
 		if (unlikely(put_page_testzero(page))) {
 			__clear_page_lru_flags(page);
 
-			if (unlikely(PageCompound(page))) {
-				spin_unlock_irq(&lruvec->lru_lock);
-				destroy_compound_page(page);
-				spin_lock_irq(&lruvec->lru_lock);
-			} else
+			if (unlikely(PageCompound(page)))
+				list_add(&page->lru, &compound_pages_to_free);
+			else
 				list_add(&page->lru, &pages_to_free);
 
 			continue;
@@ -2207,6 +2205,24 @@ static unsigned int move_pages_to_lru(struct lruvec *lruvec,
 			workingset_age_nonresident(lruvec, nr_pages);
 	}
 
+	spin_unlock_irq(&lruvec->lru_lock);
+	/*
+	 * Putback as a batch to reduce unlock/lock pair for unevictable pages
+	 */
+	while (!list_empty(&pages_to_putback)) {
+		page = lru_to_page(&pages_to_putback);
+		putback_lru_page(page);
+	}
+
+	/*
+	 * Free compound page as a batch to reduce unnecessary unlock/lock
+	 */
+	while (!list_empty(&compound_pages_to_free)) {
+		page = lru_to_page(&compound_pages_to_free);
+		destroy_compound_page(page);
+	}
+	spin_lock_irq(&lruvec->lru_lock);
+
 	/*
 	 * To save our caller's stack, now use input list for pages to free.
 	 */
-- 
2.18.2


  reply	other threads:[~2021-09-20  3:11 UTC|newest]

Thread overview: 5+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-09-19 15:25 [PATCH] mm:vmscan: fix extra adjustment for lruvec's nonresident_age in case of reactivation Yongmei Xie
2021-09-20  3:11 ` 解 咏梅 [this message]
2021-09-21 14:48 ` Johannes Weiner
     [not found]   ` <TYYP286MB11150330E283CC23CB16E40CC5A29@TYYP286MB1115.JPNP286.PROD.OUTLOOK.COM>
2021-10-01 16:43     ` 回复: " Johannes Weiner
     [not found]       ` <TYYP286MB1115E3D67A88FFF1BFB68996C5B19@TYYP286MB1115.JPNP286.PROD.OUTLOOK.COM>
2021-10-07 16:34         ` 回复: " Johannes Weiner

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=TYYP286MB11150F9D24DF4DEFF5D89F8DC5A09@TYYP286MB1115.JPNP286.PROD.OUTLOOK.COM \
    --to=yongmeixie@hotmail.com \
    --cc=akpm@linux-foundation.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.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).