From: Jan Kara <jack@suse.cz> To: <linux-mm@kvack.org> Cc: Mel Gorman <mgorman@suse.de>, "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>, <linux-fsdevel@vger.kernel.org>, Jan Kara <jack@suse.cz> Subject: [PATCH 1/7] mm: Speedup cancel_dirty_page() for clean pages Date: Tue, 10 Oct 2017 17:19:31 +0200 [thread overview] Message-ID: <20171010151937.26984-2-jack@suse.cz> (raw) In-Reply-To: <20171010151937.26984-1-jack@suse.cz> cancel_dirty_page() does quite some work even for clean pages (fetching of mapping, locking of memcg, atomic bit op on page flags) so it accounts for ~2.5% of cost of truncation of a clean page. That is not much but still dumb for something we don't need at all. Check whether a page is actually dirty and avoid any work if not. Acked-by: Mel Gorman <mgorman@suse.de> Signed-off-by: Jan Kara <jack@suse.cz> --- include/linux/mm.h | 8 +++++++- mm/page-writeback.c | 4 ++-- 2 files changed, 9 insertions(+), 3 deletions(-) diff --git a/include/linux/mm.h b/include/linux/mm.h index 065d99deb847..d14a9bb2a3d7 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1430,7 +1430,13 @@ void account_page_cleaned(struct page *page, struct address_space *mapping, struct bdi_writeback *wb); int set_page_dirty(struct page *page); int set_page_dirty_lock(struct page *page); -void cancel_dirty_page(struct page *page); +void __cancel_dirty_page(struct page *page); +static inline void cancel_dirty_page(struct page *page) +{ + /* Avoid atomic ops, locking, etc. when not actually needed. */ + if (PageDirty(page)) + __cancel_dirty_page(page); +} int clear_page_dirty_for_io(struct page *page); int get_cmdline(struct task_struct *task, char *buffer, int buflen); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 0b9c5cbe8eba..c3bed3f5cd24 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2623,7 +2623,7 @@ EXPORT_SYMBOL(set_page_dirty_lock); * page without actually doing it through the VM. Can you say "ext3 is * horribly ugly"? Thought you could. */ -void cancel_dirty_page(struct page *page) +void __cancel_dirty_page(struct page *page) { struct address_space *mapping = page_mapping(page); @@ -2644,7 +2644,7 @@ void cancel_dirty_page(struct page *page) ClearPageDirty(page); } } -EXPORT_SYMBOL(cancel_dirty_page); +EXPORT_SYMBOL(__cancel_dirty_page); /* * Clear a page's dirty flag, while caring for dirty memory accounting. -- 2.12.3 -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@kvack.org. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
WARNING: multiple messages have this Message-ID (diff)
From: Jan Kara <jack@suse.cz> To: linux-mm@kvack.org Cc: Mel Gorman <mgorman@suse.de>, "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>, linux-fsdevel@vger.kernel.org, Jan Kara <jack@suse.cz> Subject: [PATCH 1/7] mm: Speedup cancel_dirty_page() for clean pages Date: Tue, 10 Oct 2017 17:19:31 +0200 [thread overview] Message-ID: <20171010151937.26984-2-jack@suse.cz> (raw) In-Reply-To: <20171010151937.26984-1-jack@suse.cz> cancel_dirty_page() does quite some work even for clean pages (fetching of mapping, locking of memcg, atomic bit op on page flags) so it accounts for ~2.5% of cost of truncation of a clean page. That is not much but still dumb for something we don't need at all. Check whether a page is actually dirty and avoid any work if not. Acked-by: Mel Gorman <mgorman@suse.de> Signed-off-by: Jan Kara <jack@suse.cz> --- include/linux/mm.h | 8 +++++++- mm/page-writeback.c | 4 ++-- 2 files changed, 9 insertions(+), 3 deletions(-) diff --git a/include/linux/mm.h b/include/linux/mm.h index 065d99deb847..d14a9bb2a3d7 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1430,7 +1430,13 @@ void account_page_cleaned(struct page *page, struct address_space *mapping, struct bdi_writeback *wb); int set_page_dirty(struct page *page); int set_page_dirty_lock(struct page *page); -void cancel_dirty_page(struct page *page); +void __cancel_dirty_page(struct page *page); +static inline void cancel_dirty_page(struct page *page) +{ + /* Avoid atomic ops, locking, etc. when not actually needed. */ + if (PageDirty(page)) + __cancel_dirty_page(page); +} int clear_page_dirty_for_io(struct page *page); int get_cmdline(struct task_struct *task, char *buffer, int buflen); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 0b9c5cbe8eba..c3bed3f5cd24 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2623,7 +2623,7 @@ EXPORT_SYMBOL(set_page_dirty_lock); * page without actually doing it through the VM. Can you say "ext3 is * horribly ugly"? Thought you could. */ -void cancel_dirty_page(struct page *page) +void __cancel_dirty_page(struct page *page) { struct address_space *mapping = page_mapping(page); @@ -2644,7 +2644,7 @@ void cancel_dirty_page(struct page *page) ClearPageDirty(page); } } -EXPORT_SYMBOL(cancel_dirty_page); +EXPORT_SYMBOL(__cancel_dirty_page); /* * Clear a page's dirty flag, while caring for dirty memory accounting. -- 2.12.3 -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@kvack.org. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2017-10-10 15:19 UTC|newest] Thread overview: 33+ messages / expand[flat|nested] mbox.gz Atom feed top 2017-10-10 15:19 [PATCH 0/7 v1] Speed up page cache truncation Jan Kara 2017-10-10 15:19 ` Jan Kara 2017-10-10 15:19 ` Jan Kara [this message] 2017-10-10 15:19 ` [PATCH 1/7] mm: Speedup cancel_dirty_page() for clean pages Jan Kara 2017-10-10 15:19 ` [PATCH 2/7] mm: Refactor truncate_complete_page() Jan Kara 2017-10-10 15:19 ` Jan Kara 2017-10-10 15:19 ` [PATCH 3/7] mm: Factor out page cache page freeing into a separate function Jan Kara 2017-10-10 15:19 ` Jan Kara 2017-10-10 15:19 ` [PATCH 4/7] mm: Move accounting updates before page_cache_tree_delete() Jan Kara 2017-10-10 15:19 ` Jan Kara 2017-10-10 15:19 ` [PATCH 5/7] mm: Move clearing of page->mapping to page_cache_tree_delete() Jan Kara 2017-10-10 15:19 ` Jan Kara 2017-10-10 15:19 ` [PATCH 6/7] mm: Factor out checks and accounting from __delete_from_page_cache() Jan Kara 2017-10-10 15:19 ` Jan Kara 2017-10-10 15:19 ` [PATCH 7/7] mm: Batch radix tree operations when truncating pages Jan Kara 2017-10-10 15:19 ` Jan Kara 2017-10-11 7:39 ` Mel Gorman 2017-10-17 23:05 ` Andrew Morton 2017-10-17 23:05 ` Andrew Morton 2017-10-18 10:44 ` Jan Kara 2017-10-10 17:25 ` [PATCH 0/7 v1] Speed up page cache truncation Andi Kleen 2017-10-10 17:25 ` Andi Kleen 2017-10-11 8:06 ` Jan Kara 2017-10-11 16:51 ` Andi Kleen 2017-10-11 17:34 ` Dave Hansen 2017-10-11 17:59 ` Mel Gorman 2017-10-11 18:37 ` Andi Kleen 2017-10-11 21:06 ` Jan Kara 2017-10-11 21:24 ` Dave Chinner 2017-10-12 9:09 ` Mel Gorman 2017-10-12 14:07 ` Jan Kara 2017-10-17 16:21 [PATCH 0/7 v2] " Jan Kara 2017-10-17 16:21 ` [PATCH 1/7] mm: Speedup cancel_dirty_page() for clean pages Jan Kara 2017-10-17 16:21 ` Jan Kara
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=20171010151937.26984-2-jack@suse.cz \ --to=jack@suse.cz \ --cc=kirill.shutemov@linux.intel.com \ --cc=linux-fsdevel@vger.kernel.org \ --cc=linux-mm@kvack.org \ --cc=mgorman@suse.de \ /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: linkBe 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.