All of lore.kernel.org
 help / color / mirror / Atom feed
From: Fengguang Wu <fengguang.wu@intel.com>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: Greg Thelen <gthelen@google.com>, Jan Kara <jack@suse.cz>,
	Ying Han <yinghan@google.com>,
	"hannes@cmpxchg.org" <hannes@cmpxchg.org>,
	KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>,
	Rik van Riel <riel@redhat.com>,
	Johannes Weiner <jweiner@redhat.com>,
	Fengguang Wu <fengguang.wu@intel.com>
Cc: Linux Memory Management List <linux-mm@kvack.org>
Cc: LKML <linux-kernel@vger.kernel.org>
Subject: [PATCH 8/9] mm: dont set __GFP_WRITE on ramfs/sysfs writes
Date: Tue, 28 Feb 2012 22:00:30 +0800	[thread overview]
Message-ID: <20120228144747.440418051@intel.com> (raw)
In-Reply-To: 20120228140022.614718843@intel.com

[-- Attachment #1: mm-__GFP_WRITE-cap_account_dirty.patch --]
[-- Type: text/plain, Size: 886 bytes --]

Try to avoid page reclaim waits when writing to ramfs/sysfs etc.

Maybe not a big deal...

CC: Johannes Weiner <jweiner@redhat.com>
Signed-off-by: Fengguang Wu <fengguang.wu@intel.com>
---
 mm/filemap.c |    8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

--- linux.orig/mm/filemap.c	2012-02-28 10:24:12.000000000 +0800
+++ linux/mm/filemap.c	2012-02-28 10:25:55.568321275 +0800
@@ -2340,9 +2340,13 @@ struct page *grab_cache_page_write_begin
 	int status;
 	gfp_t gfp_mask;
 	struct page *page;
-	gfp_t lru_gfp_mask = GFP_KERNEL | __GFP_WRITE;
+	gfp_t lru_gfp_mask = GFP_KERNEL;
 
-	gfp_mask = mapping_gfp_mask(mapping) | __GFP_WRITE;
+	gfp_mask = mapping_gfp_mask(mapping);
+	if (mapping_cap_account_dirty(mapping)) {
+		gfp_mask |= __GFP_WRITE;
+		lru_gfp_mask |= __GFP_WRITE;
+	}
 	if (flags & AOP_FLAG_NOFS) {
 		gfp_mask &= ~__GFP_FS;
 		lru_gfp_mask &= ~__GFP_FS;



WARNING: multiple messages have this Message-ID (diff)
From: Fengguang Wu <fengguang.wu@intel.com>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: Greg Thelen <gthelen@google.com>, Jan Kara <jack@suse.cz>,
	Ying Han <yinghan@google.com>,
	"hannes@cmpxchg.org" <hannes@cmpxchg.org>,
	KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>,
	Rik van Riel <riel@redhat.com>,
	Johannes Weiner <jweiner@redhat.com>,
	Fengguang Wu <fengguang.wu@intel.com>,
	Linux Memory Management List <linux-mm@kvack.org>,
	LKML <linux-kernel@vger.kernel.org>
Subject: [PATCH 8/9] mm: dont set __GFP_WRITE on ramfs/sysfs writes
Date: Tue, 28 Feb 2012 22:00:30 +0800	[thread overview]
Message-ID: <20120228144747.440418051@intel.com> (raw)
In-Reply-To: 20120228140022.614718843@intel.com

[-- Attachment #1: mm-__GFP_WRITE-cap_account_dirty.patch --]
[-- Type: text/plain, Size: 1189 bytes --]

Try to avoid page reclaim waits when writing to ramfs/sysfs etc.

Maybe not a big deal...

CC: Johannes Weiner <jweiner@redhat.com>
Signed-off-by: Fengguang Wu <fengguang.wu@intel.com>
---
 mm/filemap.c |    8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

--- linux.orig/mm/filemap.c	2012-02-28 10:24:12.000000000 +0800
+++ linux/mm/filemap.c	2012-02-28 10:25:55.568321275 +0800
@@ -2340,9 +2340,13 @@ struct page *grab_cache_page_write_begin
 	int status;
 	gfp_t gfp_mask;
 	struct page *page;
-	gfp_t lru_gfp_mask = GFP_KERNEL | __GFP_WRITE;
+	gfp_t lru_gfp_mask = GFP_KERNEL;
 
-	gfp_mask = mapping_gfp_mask(mapping) | __GFP_WRITE;
+	gfp_mask = mapping_gfp_mask(mapping);
+	if (mapping_cap_account_dirty(mapping)) {
+		gfp_mask |= __GFP_WRITE;
+		lru_gfp_mask |= __GFP_WRITE;
+	}
 	if (flags & AOP_FLAG_NOFS) {
 		gfp_mask &= ~__GFP_FS;
 		lru_gfp_mask &= ~__GFP_FS;


--
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/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

  parent reply	other threads:[~2012-02-28 14:58 UTC|newest]

Thread overview: 116+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-02-28 14:00 [PATCH 0/9] [RFC] pageout work and dirty reclaim throttling Fengguang Wu
2012-02-28 14:00 ` Fengguang Wu
2012-02-28 14:00 ` [PATCH 1/9] memcg: add page_cgroup flags for dirty page tracking Fengguang Wu
2012-02-28 14:00   ` Fengguang Wu
2012-02-29  0:50   ` KAMEZAWA Hiroyuki
2012-02-29  0:50     ` KAMEZAWA Hiroyuki
2012-03-04  1:29     ` Fengguang Wu
2012-03-04  1:29       ` Fengguang Wu
2012-02-28 14:00 ` [PATCH 2/9] memcg: add dirty page accounting infrastructure Fengguang Wu
2012-02-28 14:00   ` Fengguang Wu
2012-02-28 22:37   ` Andrew Morton
2012-02-28 22:37     ` Andrew Morton
2012-02-29  0:27     ` Fengguang Wu
2012-02-29  0:27       ` Fengguang Wu
2012-02-28 14:00 ` [PATCH 3/9] memcg: add kernel calls for memcg dirty page stats Fengguang Wu
2012-02-28 14:00   ` Fengguang Wu
2012-02-29  1:10   ` KAMEZAWA Hiroyuki
2012-02-29  1:10     ` KAMEZAWA Hiroyuki
2012-02-28 14:00 ` [PATCH 4/9] memcg: dirty page accounting support routines Fengguang Wu
2012-02-28 14:00   ` Fengguang Wu
2012-02-28 15:15   ` Fengguang Wu
2012-02-28 15:15     ` Fengguang Wu
2012-02-28 22:45   ` Andrew Morton
2012-02-28 22:45     ` Andrew Morton
2012-02-29  1:15     ` KAMEZAWA Hiroyuki
2012-02-29  1:15       ` KAMEZAWA Hiroyuki
2012-02-28 14:00 ` [PATCH 5/9] writeback: introduce the pageout work Fengguang Wu
2012-02-28 14:00   ` Fengguang Wu
2012-02-29  0:04   ` Andrew Morton
2012-02-29  0:04     ` Andrew Morton
2012-02-29  2:31     ` Fengguang Wu
2012-02-29  2:31       ` Fengguang Wu
2012-02-29 13:28     ` Fengguang Wu
2012-02-29 13:28       ` Fengguang Wu
2012-03-01 11:04     ` Jan Kara
2012-03-01 11:04       ` Jan Kara
2012-03-01 11:41       ` Fengguang Wu
2012-03-01 11:41         ` Fengguang Wu
2012-03-01 16:50         ` Jan Kara
2012-03-01 16:50           ` Jan Kara
2012-03-01 19:46         ` Andrew Morton
2012-03-01 19:46           ` Andrew Morton
2012-03-03 13:25           ` Fengguang Wu
2012-03-03 13:25             ` Fengguang Wu
2012-03-07  0:37             ` Andrew Morton
2012-03-07  0:37               ` Andrew Morton
2012-03-07  5:40               ` Fengguang Wu
2012-03-07  5:40                 ` Fengguang Wu
2012-03-01 19:42       ` Andrew Morton
2012-03-01 19:42         ` Andrew Morton
2012-03-01 21:15         ` Jan Kara
2012-03-01 21:15           ` Jan Kara
2012-03-01 21:22           ` Andrew Morton
2012-03-01 21:22             ` Andrew Morton
2012-03-01 12:36     ` Fengguang Wu
2012-03-01 12:36       ` Fengguang Wu
2012-03-01 16:38       ` Jan Kara
2012-03-01 16:38         ` Jan Kara
2012-03-02  4:48         ` Fengguang Wu
2012-03-02  4:48           ` Fengguang Wu
2012-03-02  9:59           ` Jan Kara
2012-03-02  9:59             ` Jan Kara
2012-03-02 10:39             ` Fengguang Wu
2012-03-02 10:39               ` Fengguang Wu
2012-03-02 19:57               ` Andrew Morton
2012-03-02 19:57                 ` Andrew Morton
2012-03-03 13:55                 ` Fengguang Wu
2012-03-03 13:55                   ` Fengguang Wu
2012-03-03 14:27                   ` Fengguang Wu
2012-03-03 14:27                     ` Fengguang Wu
2012-03-04 11:13                     ` Fengguang Wu
2012-03-04 11:13                       ` Fengguang Wu
2012-03-07 15:48                   ` Artem Bityutskiy
2012-03-07 15:48                     ` Artem Bityutskiy
2012-03-09  7:31                     ` Fengguang Wu
2012-03-09  7:31                       ` Fengguang Wu
2012-03-09  9:51                       ` Jan Kara
2012-03-09  9:51                         ` Jan Kara
2012-03-09 10:24                         ` Artem Bityutskiy
2012-03-09 10:24                           ` Artem Bityutskiy
2012-03-09 16:10                         ` Artem Bityutskiy
2012-03-09 16:10                           ` Artem Bityutskiy
2012-03-09 21:11                           ` Jan Kara
2012-03-09 21:11                             ` Jan Kara
2012-03-12 12:36                             ` Artem Bityutskiy
2012-03-12 12:36                               ` Artem Bityutskiy
2012-03-12 14:02                               ` Jan Kara
2012-03-12 14:02                                 ` Jan Kara
2012-03-12 14:21                                 ` Artem Bityutskiy
2012-03-12 14:21                                   ` Artem Bityutskiy
2012-03-09 10:15                   ` Jan Kara
2012-03-09 10:15                     ` Jan Kara
2012-03-09 15:10                     ` Fengguang Wu
2012-03-09 15:10                       ` Fengguang Wu
2012-02-29 13:51   ` [PATCH v2 " Fengguang Wu
2012-02-29 13:51     ` Fengguang Wu
2012-03-01 13:35     ` Fengguang Wu
2012-03-01 13:35       ` Fengguang Wu
2012-03-02  6:22       ` [PATCH v3 " Fengguang Wu
2012-03-02  6:22         ` Fengguang Wu
2012-02-28 14:00 ` [PATCH 6/9] vmscan: dirty reclaim throttling Fengguang Wu
2012-02-28 14:00   ` Fengguang Wu
2012-02-28 14:00 ` [PATCH 7/9] mm: pass __GFP_WRITE to memcg charge and reclaim routines Fengguang Wu
2012-02-28 14:00   ` Fengguang Wu
2012-02-28 14:00 ` Fengguang Wu [this message]
2012-02-28 14:00   ` [PATCH 8/9] mm: dont set __GFP_WRITE on ramfs/sysfs writes Fengguang Wu
2012-03-01 10:13   ` Johannes Weiner
2012-03-01 10:13     ` Johannes Weiner
2012-03-01 10:30     ` Fengguang Wu
2012-03-01 10:30       ` Fengguang Wu
2012-02-28 14:00 ` [PATCH 9/9] mm: debug vmscan waits Fengguang Wu
2012-02-28 14:00   ` Fengguang Wu
2012-03-02  6:59   ` [RFC PATCH] mm: don't treat anonymous pages as dirtyable pages Fengguang Wu
2012-03-02  6:59     ` Fengguang Wu
2012-03-02  7:18     ` Fengguang Wu
2012-03-02  7:18       ` Fengguang Wu

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=20120228144747.440418051@intel.com \
    --to=fengguang.wu@intel.com \
    --cc=akpm@linux-foundation.org \
    --cc=gthelen@google.com \
    --cc=hannes@cmpxchg.org \
    --cc=jack@suse.cz \
    --cc=jweiner@redhat.com \
    --cc=kamezawa.hiroyu@jp.fujitsu.com \
    --cc=riel@redhat.com \
    --cc=yinghan@google.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.