From: Mel Gorman <mgorman@techsingularity.net>
To: Linux-MM <linux-mm@kvack.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>,
Rik van Riel <riel@redhat.com>, Vlastimil Babka <vbabka@suse.cz>,
David Rientjes <rientjes@google.com>,
Joonsoo Kim <iamjoonsoo.kim@lge.com>,
Michal Hocko <mhocko@kernel.org>,
LKML <linux-kernel@vger.kernel.org>,
Mel Gorman <mgorman@techsingularity.net>
Subject: [PATCH 03/10] mm, page_alloc: Remove unnecessary recalculations for dirty zone balancing
Date: Wed, 12 Aug 2015 11:45:28 +0100 [thread overview]
Message-ID: <1439376335-17895-4-git-send-email-mgorman@techsingularity.net> (raw)
In-Reply-To: <1439376335-17895-1-git-send-email-mgorman@techsingularity.net>
File-backed pages that will be immediately are balanced between zones but
it's unnecessarily expensive. Move consider_zone_balanced into the alloc_context
instead of checking bitmaps multiple times. The patch also gives the parameter
a more meaningful name.
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Acked-by: David Rientjes <rientjes@google.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
---
mm/internal.h | 1 +
mm/page_alloc.c | 11 +++++++----
2 files changed, 8 insertions(+), 4 deletions(-)
diff --git a/mm/internal.h b/mm/internal.h
index 36b23f1e2ca6..9331f802a067 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -129,6 +129,7 @@ struct alloc_context {
int classzone_idx;
int migratetype;
enum zone_type high_zoneidx;
+ bool spread_dirty_pages;
};
/*
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 5e1f6f4370bc..94f2f6bdd6d5 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2297,8 +2297,6 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
struct zoneref *z;
struct page *page = NULL;
struct zone *zone;
- bool consider_zone_dirty = (alloc_flags & ALLOC_WMARK_LOW) &&
- (gfp_mask & __GFP_WRITE);
int nr_fair_skipped = 0;
bool zonelist_rescan;
@@ -2350,14 +2348,14 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
*
* XXX: For now, allow allocations to potentially
* exceed the per-zone dirty limit in the slowpath
- * (ALLOC_WMARK_LOW unset) before going into reclaim,
+ * (spread_dirty_pages unset) before going into reclaim,
* which is important when on a NUMA setup the allowed
* zones are together not big enough to reach the
* global limit. The proper fix for these situations
* will require awareness of zones in the
* dirty-throttling and the flusher threads.
*/
- if (consider_zone_dirty && !zone_dirty_ok(zone))
+ if (ac->spread_dirty_pages && !zone_dirty_ok(zone))
continue;
mark = zone->watermark[alloc_flags & ALLOC_WMARK_MASK];
@@ -2997,6 +2995,10 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
/* We set it here, as __alloc_pages_slowpath might have changed it */
ac.zonelist = zonelist;
+
+ /* Dirty zone balancing only done in the fast path */
+ ac.spread_dirty_pages = (gfp_mask & __GFP_WRITE);
+
/* The preferred zone is used for statistics later */
preferred_zoneref = first_zones_zonelist(ac.zonelist, ac.high_zoneidx,
ac.nodemask, &ac.preferred_zone);
@@ -3014,6 +3016,7 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
* complete.
*/
alloc_mask = memalloc_noio_flags(gfp_mask);
+ ac.spread_dirty_pages = false;
page = __alloc_pages_slowpath(alloc_mask, order, &ac);
}
--
2.4.6
next prev parent reply other threads:[~2015-08-12 10:45 UTC|newest]
Thread overview: 37+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-08-12 10:45 [PATCH 00/10] Remove zonelist cache and high-order watermark checking v2 Mel Gorman
2015-08-12 10:45 ` [PATCH 01/10] mm, page_alloc: Delete the zonelist_cache Mel Gorman
2015-08-20 13:18 ` Michal Hocko
2015-08-20 13:42 ` Mel Gorman
2015-08-21 9:29 ` Michal Hocko
2015-08-20 13:30 ` Vlastimil Babka
2015-08-20 14:17 ` Mel Gorman
2015-08-20 14:45 ` Vlastimil Babka
2015-08-12 10:45 ` [PATCH 02/10] mm, page_alloc: Remove unnecessary parameter from zone_watermark_ok_safe Mel Gorman
2015-08-20 12:30 ` Michal Hocko
2015-08-12 10:45 ` Mel Gorman [this message]
2015-08-20 12:45 ` [PATCH 03/10] mm, page_alloc: Remove unnecessary recalculations for dirty zone balancing Michal Hocko
2015-08-20 13:45 ` Mel Gorman
2015-08-20 14:25 ` Michal Hocko
2015-08-12 10:45 ` [PATCH 04/10] mm, page_alloc: Remove unnecessary taking of a seqlock when cpusets are disabled Mel Gorman
2015-08-13 0:16 ` David Rientjes
2015-08-17 11:58 ` Mel Gorman
2015-08-12 10:45 ` [PATCH 05/10] mm, page_alloc: Use masks and shifts when converting GFP flags to migrate types Mel Gorman
2015-08-12 14:45 ` Christoph Lameter
2015-08-12 10:45 ` [PATCH 06/10] mm: page_alloc: Distinguish between being unable to sleep, unwilling to unwilling and avoiding waking kswapd Mel Gorman
2015-08-12 13:22 ` Michal Hocko
2015-08-19 14:44 ` Vlastimil Babka
2015-08-20 9:14 ` Mel Gorman
2015-08-21 13:42 ` Vlastimil Babka
2015-08-21 20:39 ` Mel Gorman
2015-08-12 10:45 ` [PATCH 07/10] mm: page_alloc: Rename __GFP_WAIT to __GFP_RECLAIM Mel Gorman
2015-08-20 12:28 ` Michal Hocko
2015-08-20 12:46 ` Michal Hocko
2015-08-21 14:20 ` Vlastimil Babka
2015-08-21 20:56 ` Mel Gorman
2015-08-12 10:45 ` [PATCH 08/10] mm, page_alloc: Remove MIGRATE_RESERVE Mel Gorman
2015-08-12 10:45 ` [PATCH 09/10] mm, page_alloc: Reserve pageblocks for high-order atomic allocations on demand Mel Gorman
2015-08-12 10:45 ` [PATCH 10/10] mm, page_alloc: Only enforce watermarks for order-0 allocations Mel Gorman
-- strict thread matches above, loose matches on Subject: below --
2015-07-20 8:00 [RFC PATCH 00/10] Remove zonelist cache and high-order watermark checking Mel Gorman
2015-07-20 8:00 ` [PATCH 03/10] mm, page_alloc: Remove unnecessary recalculations for dirty zone balancing Mel Gorman
2015-07-22 0:08 ` David Rientjes
2015-07-23 12:28 ` Mel Gorman
2015-07-28 12:25 ` Vlastimil Babka
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=1439376335-17895-4-git-send-email-mgorman@techsingularity.net \
--to=mgorman@techsingularity.net \
--cc=hannes@cmpxchg.org \
--cc=iamjoonsoo.kim@lge.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mhocko@kernel.org \
--cc=riel@redhat.com \
--cc=rientjes@google.com \
--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).