Linux-Fsdevel Archive on lore.kernel.org
 help / color / Atom feed
From: Tejun Heo <tj@kernel.org>
To: axboe@kernel.dk
Cc: linux-kernel@vger.kernel.org, jack@suse.cz, hch@infradead.org,
	hannes@cmpxchg.org, linux-fsdevel@vger.kernel.org,
	vgoyal@redhat.com, lizefan@huawei.com, cgroups@vger.kernel.org,
	linux-mm@kvack.org, mhocko@suse.cz, clm@fb.com,
	fengguang.wu@intel.com, david@fromorbit.com, gthelen@google.com,
	Tejun Heo <tj@kernel.org>
Subject: [PATCH 09/19] writeback: add dirty_throttle_control->pos_ratio
Date: Mon,  6 Apr 2015 16:04:24 -0400
Message-ID: <1428350674-8303-10-git-send-email-tj@kernel.org> (raw)
In-Reply-To: <1428350674-8303-1-git-send-email-tj@kernel.org>

wb_position_ratio() is used to calculate pos_ratio, which is used for
two purposes.  wb_update_dirty_ratelimit() uses it to adjust
wb->[balanced_]dirty_ratelimit gradually and balance_dirty_pages() to
immediately adjust dirty_ratelimit right before applying it to
determine pause duration.

While wb_update_dirty_ratelimit() is separately rate limited from
balance_dirty_pages(), on the run where the ratelimit is updated, we
end up calculating pos_ratio twice with the same parameters.

This patch adds dirty_throttle_control->pos_ratio.
balance_dirty_pages() calculates it once per run and
wb_update_dirty_ratelimit() uses the value stored in
dirty_throttle_control.

This removes the duplicate calculation and also will help implementing
memcg wb_domain.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Jan Kara <jack@suse.cz>
Cc: Wu Fengguang <fengguang.wu@intel.com>
Cc: Greg Thelen <gthelen@google.com>
---
 mm/page-writeback.c | 36 +++++++++++++++++++++---------------
 1 file changed, 21 insertions(+), 15 deletions(-)

diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 33b1536..3450520 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -135,6 +135,8 @@ struct dirty_throttle_control {
 	unsigned long		wb_dirty;	/* per-wb counterparts */
 	unsigned long		wb_thresh;
 	unsigned long		wb_bg_thresh;
+
+	unsigned long		pos_ratio;
 };
 
 #define GDTC_INIT(__wb)		.wb = (__wb)
@@ -717,7 +719,7 @@ static long long pos_ratio_polynom(unsigned long setpoint,
  *   card's wb_dirty may rush to many times higher than wb_setpoint.
  * - the wb dirty thresh drops quickly due to change of JBOD workload
  */
-static unsigned long wb_position_ratio(struct dirty_throttle_control *dtc)
+static void wb_position_ratio(struct dirty_throttle_control *dtc)
 {
 	struct bdi_writeback *wb = dtc->wb;
 	unsigned long write_bw = wb->avg_write_bandwidth;
@@ -731,8 +733,10 @@ static unsigned long wb_position_ratio(struct dirty_throttle_control *dtc)
 	long long pos_ratio;		/* for scaling up/down the rate limit */
 	long x;
 
+	dtc->pos_ratio = 0;
+
 	if (unlikely(dtc->dirty >= limit))
-		return 0;
+		return;
 
 	/*
 	 * global setpoint
@@ -770,18 +774,20 @@ static unsigned long wb_position_ratio(struct dirty_throttle_control *dtc)
 	if (unlikely(wb->bdi->capabilities & BDI_CAP_STRICTLIMIT)) {
 		long long wb_pos_ratio;
 
-		if (dtc->wb_dirty < 8)
-			return min_t(long long, pos_ratio * 2,
-				     2 << RATELIMIT_CALC_SHIFT);
+		if (dtc->wb_dirty < 8) {
+			dtc->pos_ratio = min_t(long long, pos_ratio * 2,
+					   2 << RATELIMIT_CALC_SHIFT);
+			return;
+		}
 
 		if (dtc->wb_dirty >= wb_thresh)
-			return 0;
+			return;
 
 		wb_setpoint = dirty_freerun_ceiling(wb_thresh,
 						    dtc->wb_bg_thresh);
 
 		if (wb_setpoint == 0 || wb_setpoint == wb_thresh)
-			return 0;
+			return;
 
 		wb_pos_ratio = pos_ratio_polynom(wb_setpoint, dtc->wb_dirty,
 						 wb_thresh);
@@ -807,7 +813,8 @@ static unsigned long wb_position_ratio(struct dirty_throttle_control *dtc)
 		 * is 2. We might want to tweak this if we observe the control
 		 * system is too slow to adapt.
 		 */
-		return min(pos_ratio, wb_pos_ratio);
+		dtc->pos_ratio = min(pos_ratio, wb_pos_ratio);
+		return;
 	}
 
 	/*
@@ -888,7 +895,7 @@ static unsigned long wb_position_ratio(struct dirty_throttle_control *dtc)
 			pos_ratio *= 8;
 	}
 
-	return pos_ratio;
+	dtc->pos_ratio = pos_ratio;
 }
 
 static void wb_update_write_bandwidth(struct bdi_writeback *wb,
@@ -1009,7 +1016,6 @@ static void wb_update_dirty_ratelimit(struct dirty_throttle_control *dtc,
 	unsigned long dirty_rate;
 	unsigned long task_ratelimit;
 	unsigned long balanced_dirty_ratelimit;
-	unsigned long pos_ratio;
 	unsigned long step;
 	unsigned long x;
 
@@ -1019,12 +1025,11 @@ static void wb_update_dirty_ratelimit(struct dirty_throttle_control *dtc,
 	 */
 	dirty_rate = (dirtied - wb->dirtied_stamp) * HZ / elapsed;
 
-	pos_ratio = wb_position_ratio(dtc);
 	/*
 	 * task_ratelimit reflects each dd's dirty rate for the past 200ms.
 	 */
 	task_ratelimit = (u64)dirty_ratelimit *
-					pos_ratio >> RATELIMIT_CALC_SHIFT;
+					dtc->pos_ratio >> RATELIMIT_CALC_SHIFT;
 	task_ratelimit++; /* it helps rampup dirty_ratelimit from tiny values */
 
 	/*
@@ -1375,7 +1380,6 @@ static void balance_dirty_pages(struct address_space *mapping,
 	bool dirty_exceeded = false;
 	unsigned long task_ratelimit;
 	unsigned long dirty_ratelimit;
-	unsigned long pos_ratio;
 	struct backing_dev_info *bdi = wb->bdi;
 	bool strictlimit = bdi->capabilities & BDI_CAP_STRICTLIMIT;
 	unsigned long start_time = jiffies;
@@ -1433,6 +1437,9 @@ static void balance_dirty_pages(struct address_space *mapping,
 
 		dirty_exceeded = (gdtc->wb_dirty > gdtc->wb_thresh) &&
 			((gdtc->dirty > gdtc->thresh) || strictlimit);
+
+		wb_position_ratio(gdtc);
+
 		if (dirty_exceeded && !wb->dirty_exceeded)
 			wb->dirty_exceeded = 1;
 
@@ -1444,8 +1451,7 @@ static void balance_dirty_pages(struct address_space *mapping,
 		}
 
 		dirty_ratelimit = wb->dirty_ratelimit;
-		pos_ratio = wb_position_ratio(gdtc);
-		task_ratelimit = ((u64)dirty_ratelimit * pos_ratio) >>
+		task_ratelimit = ((u64)dirty_ratelimit * gdtc->pos_ratio) >>
 							RATELIMIT_CALC_SHIFT;
 		max_pause = wb_max_pause(wb, gdtc->wb_dirty);
 		min_pause = wb_min_pause(wb, max_pause,
-- 
2.1.0

  parent reply index

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-04-06 20:04 [PATCHSET 2/3 v2 block/for-4.1/core] writeback: cgroup writeback backpressure propagation Tejun Heo
2015-04-06 20:04 ` [PATCH 01/19] memcg: make mem_cgroup_read_{stat|event}() iterate possible cpus instead of online Tejun Heo
2015-04-06 20:04 ` [PATCH 02/19] writeback: clean up wb_dirty_limit() Tejun Heo
2015-04-06 20:04 ` [PATCH 03/19] writeback: reorganize [__]wb_update_bandwidth() Tejun Heo
2015-04-06 20:04 ` [PATCH 04/19] writeback: implement wb_domain Tejun Heo
2015-04-06 20:04 ` [PATCH 05/19] writeback: move global_dirty_limit into wb_domain Tejun Heo
2015-04-06 20:04 ` [PATCH 06/19] writeback: consolidate dirty throttle parameters into dirty_throttle_control Tejun Heo
2015-04-06 20:04 ` [PATCH 07/19] writeback: add dirty_throttle_control->wb_bg_thresh Tejun Heo
2015-04-06 20:04 ` [PATCH 08/19] writeback: make __wb_calc_thresh() take dirty_throttle_control Tejun Heo
2015-04-06 20:04 ` Tejun Heo [this message]
2015-04-06 20:04 ` [PATCH 10/19] writeback: add dirty_throttle_control->wb_completions Tejun Heo
2015-04-06 20:04 ` [PATCH 11/19] writeback: add dirty_throttle_control->dom Tejun Heo
2015-04-06 20:04 ` [PATCH 12/19] writeback: make __wb_writeout_inc() and hard_dirty_limit() take wb_domaas a parameter Tejun Heo
2015-04-06 20:04 ` [PATCH 13/19] writeback: separate out domain_dirty_limits() Tejun Heo
2015-04-06 20:04 ` [PATCH 14/19] writeback: move over_bground_thresh() to mm/page-writeback.c Tejun Heo
2015-04-06 20:04 ` [PATCH 15/19] writeback: update wb_over_bg_thresh() to use wb_domain aware operations Tejun Heo
2015-04-06 20:04 ` [PATCH 16/19] writeback: implement memcg wb_domain Tejun Heo
2015-04-06 20:04 ` [PATCH 17/19] writeback: reset wb_domain->dirty_limit[_tstmp] when memcg domain size changes Tejun Heo
2015-04-06 20:04 ` [PATCH 18/19] writeback: implement memcg writeback domain based throttling Tejun Heo
2015-04-06 20:04 ` [PATCH 19/19] mm: vmscan: disable memcg direct reclaim stalling if cgroup writeback support is in use Tejun Heo
2015-04-06 20:07 ` [PATCHSET 2/3 v2 block/for-4.1/core] writeback: cgroup writeback backpressure propagation Tejun Heo
2015-05-22 22:23 [PATCHSET 2/3 v3 block/for-4.2/core] " Tejun Heo
2015-05-22 22:23 ` [PATCH 09/19] writeback: add dirty_throttle_control->pos_ratio Tejun Heo

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=1428350674-8303-10-git-send-email-tj@kernel.org \
    --to=tj@kernel.org \
    --cc=axboe@kernel.dk \
    --cc=cgroups@vger.kernel.org \
    --cc=clm@fb.com \
    --cc=david@fromorbit.com \
    --cc=fengguang.wu@intel.com \
    --cc=gthelen@google.com \
    --cc=hannes@cmpxchg.org \
    --cc=hch@infradead.org \
    --cc=jack@suse.cz \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=lizefan@huawei.com \
    --cc=mhocko@suse.cz \
    --cc=vgoyal@redhat.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

Linux-Fsdevel Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-fsdevel/0 linux-fsdevel/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-fsdevel linux-fsdevel/ https://lore.kernel.org/linux-fsdevel \
		linux-fsdevel@vger.kernel.org
	public-inbox-index linux-fsdevel

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-fsdevel


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git