From: Greg Thelen <gthelen@google.com>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: linux-kernel@vger.kernel.org, linux-mm@kvack.org,
containers@lists.osdl.org, Andrea Righi <arighi@develer.com>,
Balbir Singh <balbir@linux.vnet.ibm.com>,
KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>,
Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>,
Minchan Kim <minchan.kim@gmail.com>,
Ciju Rajan K <ciju@linux.vnet.ibm.com>,
David Rientjes <rientjes@google.com>,
Wu Fengguang <fengguang.wu@intel.com>,
Greg Thelen <gthelen@google.com>
Subject: [PATCH v4 11/11] memcg: check memcg dirty limits in page writeback
Date: Fri, 29 Oct 2010 00:09:14 -0700 [thread overview]
Message-ID: <1288336154-23256-12-git-send-email-gthelen@google.com> (raw)
In-Reply-To: <1288336154-23256-1-git-send-email-gthelen@google.com>
If the current process is in a non-root memcg, then
balance_dirty_pages() will consider the memcg dirty limits
as well as the system-wide limits. This allows different
cgroups to have distinct dirty limits which trigger direct
and background writeback at different levels.
Signed-off-by: Andrea Righi <arighi@develer.com>
Signed-off-by: Greg Thelen <gthelen@google.com>
---
Changelog since v3:
- Leave determine_dirtyable_memory() static. v3 made is non-static.
- balance_dirty_pages() now considers both system and memcg dirty limits and
usage data. This data is retrieved with global_dirty_info() and
memcg_dirty_info().
mm/page-writeback.c | 109 ++++++++++++++++++++++++++++++++++++--------------
1 files changed, 78 insertions(+), 31 deletions(-)
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index b3bb2fb..57caee5 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -131,6 +131,18 @@ EXPORT_SYMBOL(laptop_mode);
static struct prop_descriptor vm_completions;
static struct prop_descriptor vm_dirties;
+static unsigned long dirty_writeback_pages(void)
+{
+ s64 ret;
+
+ ret = mem_cgroup_page_stat(MEMCG_NR_DIRTY_WRITEBACK_PAGES);
+ if (ret < 0)
+ ret = global_page_state(NR_UNSTABLE_NFS) +
+ global_page_state(NR_WRITEBACK);
+
+ return ret;
+}
+
/*
* couple the period to the dirty_ratio:
*
@@ -398,45 +410,67 @@ unsigned long determine_dirtyable_memory(void)
}
/*
+ * The dirty limits will be lifted by 1/4 for PF_LESS_THROTTLE (ie. nfsd) and
+ * runtime tasks.
+ */
+static inline void adjust_dirty_info(struct dirty_info *info)
+{
+ struct task_struct *tsk;
+
+ if (info->background_thresh >= info->dirty_thresh)
+ info->background_thresh = info->dirty_thresh / 2;
+ tsk = current;
+ if (tsk->flags & PF_LESS_THROTTLE || rt_task(tsk)) {
+ info->background_thresh += info->background_thresh / 4;
+ info->dirty_thresh += info->dirty_thresh / 4;
+ }
+}
+
+/*
* global_dirty_info - return background-writeback and dirty-throttling
* thresholds as well as dirty usage metrics.
*
* Calculate the dirty thresholds based on sysctl parameters
* - vm.dirty_background_ratio or vm.dirty_background_bytes
* - vm.dirty_ratio or vm.dirty_bytes
- * The dirty limits will be lifted by 1/4 for PF_LESS_THROTTLE (ie. nfsd) and
- * runtime tasks.
*/
void global_dirty_info(struct dirty_info *info)
{
- unsigned long background;
- unsigned long dirty;
unsigned long available_memory = determine_dirtyable_memory();
- struct task_struct *tsk;
if (vm_dirty_bytes)
- dirty = DIV_ROUND_UP(vm_dirty_bytes, PAGE_SIZE);
+ info->dirty_thresh = DIV_ROUND_UP(vm_dirty_bytes, PAGE_SIZE);
else
- dirty = (vm_dirty_ratio * available_memory) / 100;
+ info->dirty_thresh = (vm_dirty_ratio * available_memory) / 100;
if (dirty_background_bytes)
- background = DIV_ROUND_UP(dirty_background_bytes, PAGE_SIZE);
+ info->background_thresh =
+ DIV_ROUND_UP(dirty_background_bytes, PAGE_SIZE);
else
- background = (dirty_background_ratio * available_memory) / 100;
+ info->background_thresh =
+ (dirty_background_ratio * available_memory) / 100;
info->nr_reclaimable = global_page_state(NR_FILE_DIRTY) +
global_page_state(NR_UNSTABLE_NFS);
info->nr_writeback = global_page_state(NR_WRITEBACK);
- if (background >= dirty)
- background = dirty / 2;
- tsk = current;
- if (tsk->flags & PF_LESS_THROTTLE || rt_task(tsk)) {
- background += background / 4;
- dirty += dirty / 4;
- }
- info->background_thresh = background;
- info->dirty_thresh = dirty;
+ adjust_dirty_info(info);
+}
+
+/*
+ * Calculate the background-writeback and dirty-throttling thresholds and dirty
+ * usage metrics from the current task's memcg dirty limit parameters. Returns
+ * false if no memcg limits exist.
+ */
+static bool memcg_dirty_info(struct dirty_info *info)
+{
+ unsigned long available_memory = determine_dirtyable_memory();
+
+ if (!mem_cgroup_dirty_info(available_memory, info))
+ return false;
+
+ adjust_dirty_info(info);
+ return true;
}
/*
@@ -480,7 +514,8 @@ unsigned long bdi_dirty_limit(struct backing_dev_info *bdi, unsigned long dirty)
static void balance_dirty_pages(struct address_space *mapping,
unsigned long write_chunk)
{
- struct dirty_info dirty_info;
+ struct dirty_info sys_info;
+ struct dirty_info memcg_info;
long bdi_nr_reclaimable;
long bdi_nr_writeback;
unsigned long bdi_thresh;
@@ -497,19 +532,27 @@ static void balance_dirty_pages(struct address_space *mapping,
.range_cyclic = 1,
};
- global_dirty_info(&dirty_info);
+ global_dirty_info(&sys_info);
+
+ if (!memcg_dirty_info(&memcg_info))
+ memcg_info = sys_info;
/*
* Throttle it only when the background writeback cannot
* catch-up. This avoids (excessively) small writeouts
* when the bdi limits are ramping up.
*/
- if (dirty_info.nr_reclaimable + dirty_info.nr_writeback <=
- (dirty_info.background_thresh +
- dirty_info.dirty_thresh) / 2)
+ if ((sys_info.nr_reclaimable + sys_info.nr_writeback <=
+ (sys_info.background_thresh +
+ sys_info.dirty_thresh) / 2) &&
+ (memcg_info.nr_reclaimable + memcg_info.nr_writeback <=
+ (memcg_info.background_thresh +
+ memcg_info.dirty_thresh) / 2))
break;
- bdi_thresh = bdi_dirty_limit(bdi, dirty_info.dirty_thresh);
+ bdi_thresh = bdi_dirty_limit(bdi,
+ min(sys_info.dirty_thresh,
+ memcg_info.dirty_thresh));
bdi_thresh = task_dirty_limit(current, bdi_thresh);
/*
@@ -538,9 +581,12 @@ static void balance_dirty_pages(struct address_space *mapping,
*/
dirty_exceeded =
(bdi_nr_reclaimable + bdi_nr_writeback > bdi_thresh)
- || (dirty_info.nr_reclaimable +
- dirty_info.nr_writeback >
- dirty_info.dirty_thresh);
+ || (sys_info.nr_reclaimable +
+ sys_info.nr_writeback >
+ sys_info.dirty_thresh)
+ || (memcg_info.nr_reclaimable +
+ memcg_info.nr_writeback >
+ memcg_info.dirty_thresh);
if (!dirty_exceeded)
break;
@@ -593,8 +639,10 @@ static void balance_dirty_pages(struct address_space *mapping,
* background_thresh, to keep the amount of dirty memory low.
*/
if ((laptop_mode && pages_written) ||
- (!laptop_mode && (dirty_info.nr_reclaimable >
- dirty_info.background_thresh)))
+ (!laptop_mode && ((sys_info.nr_reclaimable >
+ sys_info.background_thresh) ||
+ (memcg_info.nr_reclaimable >
+ memcg_info.background_thresh))))
bdi_start_background_writeback(bdi);
}
@@ -666,8 +714,7 @@ void throttle_vm_writeout(gfp_t gfp_mask)
dirty_info.dirty_thresh +=
dirty_info.dirty_thresh / 10; /* wheeee... */
- if (global_page_state(NR_UNSTABLE_NFS) +
- global_page_state(NR_WRITEBACK) <= dirty_info.dirty_thresh)
+ if (dirty_writeback_pages() <= dirty_info.dirty_thresh)
break;
congestion_wait(BLK_RW_ASYNC, HZ/10);
--
1.7.3.1
--
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:[~2010-10-29 7:15 UTC|newest]
Thread overview: 37+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-10-29 7:09 [PATCH v4 00/11] memcg: per cgroup dirty page accounting Greg Thelen
2010-10-29 7:09 ` [PATCH v4 01/11] memcg: add page_cgroup flags for dirty page tracking Greg Thelen
2010-10-29 7:09 ` [PATCH v4 02/11] memcg: document cgroup dirty memory interfaces Greg Thelen
2010-10-29 11:03 ` Wu Fengguang
2010-10-29 21:35 ` Greg Thelen
2010-10-30 3:02 ` Wu Fengguang
2010-10-29 20:19 ` Andrew Morton
2010-10-29 21:37 ` Greg Thelen
2010-10-29 7:09 ` [PATCH v4 03/11] memcg: create extensible page stat update routines Greg Thelen
2010-10-31 14:48 ` Ciju Rajan K
2010-10-31 20:11 ` Greg Thelen
2010-11-01 20:16 ` Ciju Rajan K
2010-11-02 19:35 ` Ciju Rajan K
2010-10-29 7:09 ` [PATCH v4 04/11] memcg: add lock to synchronize page accounting and migration Greg Thelen
2010-10-29 7:09 ` [PATCH v4 05/11] writeback: create dirty_info structure Greg Thelen
2010-10-29 7:50 ` KAMEZAWA Hiroyuki
2010-11-18 0:49 ` Andrew Morton
2010-11-18 0:50 ` Andrew Morton
2010-11-18 2:02 ` Greg Thelen
2010-10-29 7:09 ` [PATCH v4 06/11] memcg: add dirty page accounting infrastructure Greg Thelen
2010-10-29 11:13 ` Wu Fengguang
2010-10-29 11:17 ` KAMEZAWA Hiroyuki
2010-10-29 7:09 ` [PATCH v4 07/11] memcg: add kernel calls for memcg dirty page stats Greg Thelen
2010-10-29 7:09 ` [PATCH v4 08/11] memcg: add dirty limits to mem_cgroup Greg Thelen
2010-10-29 7:41 ` KAMEZAWA Hiroyuki
2010-10-29 16:00 ` Greg Thelen
2010-10-29 7:09 ` [PATCH v4 09/11] memcg: CPU hotplug lockdep warning fix Greg Thelen
2010-10-29 20:19 ` Andrew Morton
2010-10-29 7:09 ` [PATCH v4 10/11] memcg: add cgroupfs interface to memcg dirty limits Greg Thelen
2010-10-29 7:43 ` KAMEZAWA Hiroyuki
2010-10-29 7:09 ` Greg Thelen [this message]
2010-10-29 7:48 ` [PATCH v4 11/11] memcg: check memcg dirty limits in page writeback KAMEZAWA Hiroyuki
2010-10-29 16:06 ` Greg Thelen
2010-10-31 20:03 ` Wu Fengguang
2010-10-29 20:19 ` [PATCH v4 00/11] memcg: per cgroup dirty page accounting Andrew Morton
2010-10-30 21:46 ` Greg Thelen
2010-11-02 19:33 ` Ciju Rajan K
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=1288336154-23256-12-git-send-email-gthelen@google.com \
--to=gthelen@google.com \
--cc=akpm@linux-foundation.org \
--cc=arighi@develer.com \
--cc=balbir@linux.vnet.ibm.com \
--cc=ciju@linux.vnet.ibm.com \
--cc=containers@lists.osdl.org \
--cc=fengguang.wu@intel.com \
--cc=kamezawa.hiroyu@jp.fujitsu.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=minchan.kim@gmail.com \
--cc=nishimura@mxp.nes.nec.co.jp \
--cc=rientjes@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 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).