linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
To: linux-kernel@vger.kernel.org
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
	stable@vger.kernel.org, Joonsoo Kim <iamjoonsoo.kim@lge.com>,
	Vlastimil Babka <vbabka@suse.cz>, Mel Gorman <mgorman@suse.de>,
	Rik van Riel <riel@redhat.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	Linus Torvalds <torvalds@linux-foundation.org>
Subject: [PATCH 3.14 23/37] mm/compaction: do not call suitable_migration_target() on every page
Date: Tue,  7 Oct 2014 16:19:40 -0700	[thread overview]
Message-ID: <20141007231827.772180887@linuxfoundation.org> (raw)
In-Reply-To: <20141007231827.043235686@linuxfoundation.org>

3.14-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Joonsoo Kim <iamjoonsoo.kim@lge.com>

commit 01ead5340bcf5f3a1cd2452c75516d0ef4d908d7 upstream.

suitable_migration_target() checks that pageblock is suitable for
migration target.  In isolate_freepages_block(), it is called on every
page and this is inefficient.  So make it called once per pageblock.

suitable_migration_target() also checks if page is highorder or not, but
it's criteria for highorder is pageblock order.  So calling it once
within pageblock range has no problem.

Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

---
 mm/compaction.c |   13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -244,6 +244,7 @@ static unsigned long isolate_freepages_b
 	struct page *cursor, *valid_page = NULL;
 	unsigned long flags;
 	bool locked = false;
+	bool checked_pageblock = false;
 
 	cursor = pfn_to_page(blockpfn);
 
@@ -275,8 +276,16 @@ static unsigned long isolate_freepages_b
 			break;
 
 		/* Recheck this is a suitable migration target under lock */
-		if (!strict && !suitable_migration_target(page))
-			break;
+		if (!strict && !checked_pageblock) {
+			/*
+			 * We need to check suitability of pageblock only once
+			 * and this isolate_freepages_block() is called with
+			 * pageblock range, so just check once is sufficient.
+			 */
+			checked_pageblock = true;
+			if (!suitable_migration_target(page))
+				break;
+		}
 
 		/* Recheck this is a buddy page under lock */
 		if (!PageBuddy(page))



  parent reply	other threads:[~2014-10-07 23:20 UTC|newest]

Thread overview: 40+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-10-07 23:19 [PATCH 3.14 00/37] 3.14.21-stable review Greg Kroah-Hartman
2014-10-07 23:19 ` [PATCH 3.14 01/37] udf: Avoid infinite loop when processing indirect ICBs Greg Kroah-Hartman
2014-10-07 23:19 ` [PATCH 3.14 02/37] perf: fix perf bug in fork() Greg Kroah-Hartman
2014-10-07 23:19 ` [PATCH 3.14 03/37] mm: migrate: Close race between migration completion and mprotect Greg Kroah-Hartman
2014-10-07 23:19 ` [PATCH 3.14 04/37] cpufreq: integrator: fix integrator_cpufreq_remove return type Greg Kroah-Hartman
2014-10-07 23:19 ` [PATCH 3.14 05/37] md/raid5: disable DISCARD by default due to safety concerns Greg Kroah-Hartman
2014-10-07 23:19 ` [PATCH 3.14 06/37] drm/i915: Flush the PTEs after updating them before suspend Greg Kroah-Hartman
2014-10-07 23:19 ` [PATCH 3.14 07/37] Fix problem recognizing symlinks Greg Kroah-Hartman
2014-10-07 23:19 ` [PATCH 3.14 08/37] init/Kconfig: Fix HAVE_FUTEX_CMPXCHG to not break up the EXPERT menu Greg Kroah-Hartman
2014-10-07 23:19 ` [PATCH 3.14 09/37] ring-buffer: Fix infinite spin in reading buffer Greg Kroah-Hartman
2014-10-07 23:19 ` [PATCH 3.14 10/37] CIFS: Fix SMB2 readdir error handling Greg Kroah-Hartman
2014-10-07 23:19 ` [PATCH 3.14 11/37] hugetlb: ensure hugepage access is denied if hugepages are not supported Greg Kroah-Hartman
2014-10-07 23:19 ` [PATCH 3.14 12/37] mm, thp: move invariant bug check out of loop in __split_huge_page_map Greg Kroah-Hartman
2014-10-07 23:19 ` [PATCH 3.14 13/37] mm: numa: Do not mark PTEs pte_numa when splitting huge pages Greg Kroah-Hartman
2014-10-07 23:19 ` [PATCH 3.14 14/37] media: vb2: fix VBI/poll regression Greg Kroah-Hartman
2014-10-07 23:19 ` [PATCH 3.14 15/37] jiffies: Fix timeval conversion to jiffies Greg Kroah-Hartman
2014-10-07 23:19 ` [PATCH 3.14 16/37] mm: exclude memoryless nodes from zone_reclaim Greg Kroah-Hartman
2014-10-07 23:19 ` [PATCH 3.14 17/37] swap: change swap_info singly-linked list to list_head Greg Kroah-Hartman
2014-10-07 23:19 ` [PATCH 3.14 18/37] lib/plist: add helper functions Greg Kroah-Hartman
2014-10-07 23:19 ` [PATCH 3.14 19/37] lib/plist: add plist_requeue Greg Kroah-Hartman
2014-10-07 23:19 ` [PATCH 3.14 20/37] swap: change swap_list_head to plist, add swap_avail_head Greg Kroah-Hartman
2014-10-07 23:19 ` [PATCH 3.14 21/37] mm, compaction: avoid isolating pinned pages Greg Kroah-Hartman
2014-10-07 23:19 ` [PATCH 3.14 22/37] mm/compaction: disallow high-order page for migration target Greg Kroah-Hartman
2014-10-07 23:19 ` Greg Kroah-Hartman [this message]
2014-10-07 23:19 ` [PATCH 3.14 24/37] drbd: fix regression out of mem, failed to invoke fence-peer helper Greg Kroah-Hartman
2014-10-07 23:19 ` [PATCH 3.14 25/37] mm/compaction: change the timing to check to drop the spinlock Greg Kroah-Hartman
2014-10-07 23:19 ` [PATCH 3.14 26/37] mm/compaction: check pageblock suitability once per pageblock Greg Kroah-Hartman
2014-10-07 23:19 ` [PATCH 3.14 27/37] mm/compaction: clean-up code on success of ballon isolation Greg Kroah-Hartman
2014-10-07 23:19 ` [PATCH 3.14 28/37] mm, compaction: determine isolation mode only once Greg Kroah-Hartman
2014-10-07 23:19 ` [PATCH 3.14 29/37] mm, compaction: ignore pageblock skip when manually invoking compaction Greg Kroah-Hartman
2014-10-07 23:19 ` [PATCH 3.14 30/37] mm/readahead.c: fix readahead failure for memoryless NUMA nodes and limit readahead pages Greg Kroah-Hartman
2014-10-07 23:19 ` [PATCH 3.14 31/37] mm: optimize put_mems_allowed() usage Greg Kroah-Hartman
2014-10-07 23:19 ` [PATCH 3.14 32/37] mm/filemap.c: avoid always dirtying mapping->flags on O_DIRECT Greg Kroah-Hartman
2014-10-07 23:19 ` [PATCH 3.14 33/37] mm: vmscan: respect NUMA policy mask when shrinking slab on direct reclaim Greg Kroah-Hartman
2014-10-07 23:19 ` [PATCH 3.14 34/37] mm: vmscan: shrink_slab: rename max_pass -> freeable Greg Kroah-Hartman
2014-10-07 23:19 ` [PATCH 3.14 35/37] vmscan: reclaim_clean_pages_from_list() must use mod_zone_page_state() Greg Kroah-Hartman
2014-10-07 23:19 ` [PATCH 3.14 36/37] mm: per-thread vma caching Greg Kroah-Hartman
2014-10-07 23:19 ` [PATCH 3.14 37/37] mm: dont pointlessly use BUG_ON() for sanity check Greg Kroah-Hartman
2014-10-08  2:48 ` [PATCH 3.14 00/37] 3.14.21-stable review Guenter Roeck
2014-10-08 20:05 ` Shuah Khan

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=20141007231827.772180887@linuxfoundation.org \
    --to=gregkh@linuxfoundation.org \
    --cc=akpm@linux-foundation.org \
    --cc=iamjoonsoo.kim@lge.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mgorman@suse.de \
    --cc=riel@redhat.com \
    --cc=stable@vger.kernel.org \
    --cc=torvalds@linux-foundation.org \
    --cc=vbabka@suse.cz \
    /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).