linux-kernel - [PATCH v2] mm/page-writeback: raise wb_thresh to prevent write blocking with strictlimit

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite for Android: free password hash cracker in your pocket

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20241119114444.3925495-1-jimzhao.ai@gmail.com>
Date: Tue, 19 Nov 2024 19:44:42 +0800
From: Jim Zhao <jimzhao.ai@...il.com>
To: jimzhao.ai@...il.com
Cc: jack@...e.cz,
	akpm@...ux-foundation.org,
	linux-fsdevel@...r.kernel.org,
	linux-kernel@...r.kernel.org,
	linux-mm@...ck.org,
	willy@...radead.org
Subject: [PATCH v2] mm/page-writeback: raise wb_thresh to prevent write blocking with strictlimit

With the strictlimit flag, wb_thresh acts as a hard limit in
balance_dirty_pages() and wb_position_ratio().  When device write
operations are inactive, wb_thresh can drop to 0, causing writes to be
blocked.  The issue occasionally occurs in fuse fs, particularly with
network backends, the write thread is blocked frequently during a period.
To address it, this patch raises the minimum wb_thresh to a controllable
level, similar to the non-strictlimit case.

Signed-off-by: Jim Zhao <jimzhao.ai@...il.com>
---
Changes in v2:
1. Consolidate all wb_thresh bumping logic in __wb_calc_thresh for consistency;
2. Replace the limit variable with thresh for calculating the bump value,
as __wb_calc_thresh is also used to calculate the background threshold;
3. Add domain_dirty_avail in wb_calc_thresh to get dtc->dirty.
---
 mm/page-writeback.c | 48 ++++++++++++++++++++++-----------------------
 1 file changed, 23 insertions(+), 25 deletions(-)

diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index e5a9eb795f99..8b13bcb42de3 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -917,7 +917,9 @@ static unsigned long __wb_calc_thresh(struct dirty_throttle_control *dtc,
 				      unsigned long thresh)
 {
 	struct wb_domain *dom = dtc_dom(dtc);
+	struct bdi_writeback *wb = dtc->wb;
 	u64 wb_thresh;
+	u64 wb_max_thresh;
 	unsigned long numerator, denominator;
 	unsigned long wb_min_ratio, wb_max_ratio;
 
@@ -931,11 +933,27 @@ static unsigned long __wb_calc_thresh(struct dirty_throttle_control *dtc,
 	wb_thresh *= numerator;
 	wb_thresh = div64_ul(wb_thresh, denominator);
 
-	wb_min_max_ratio(dtc->wb, &wb_min_ratio, &wb_max_ratio);
+	wb_min_max_ratio(wb, &wb_min_ratio, &wb_max_ratio);
 
 	wb_thresh += (thresh * wb_min_ratio) / (100 * BDI_RATIO_SCALE);
-	if (wb_thresh > (thresh * wb_max_ratio) / (100 * BDI_RATIO_SCALE))
-		wb_thresh = thresh * wb_max_ratio / (100 * BDI_RATIO_SCALE);
+
+	/*
+	 * It's very possible that wb_thresh is close to 0 not because the
+	 * device is slow, but that it has remained inactive for long time.
+	 * Honour such devices a reasonable good (hopefully IO efficient)
+	 * threshold, so that the occasional writes won't be blocked and active
+	 * writes can rampup the threshold quickly.
+	 */
+	if (thresh > dtc->dirty) {
+		if (unlikely(wb->bdi->capabilities & BDI_CAP_STRICTLIMIT))
+			wb_thresh = max(wb_thresh, (thresh - dtc->dirty) / 100);
+		else
+			wb_thresh = max(wb_thresh, (thresh - dtc->dirty) / 8);
+	}
+
+	wb_max_thresh = thresh * wb_max_ratio / (100 * BDI_RATIO_SCALE);
+	if (wb_thresh > wb_max_thresh)
+		wb_thresh = wb_max_thresh;
 
 	return wb_thresh;
 }
@@ -944,6 +962,7 @@ unsigned long wb_calc_thresh(struct bdi_writeback *wb, unsigned long thresh)
 {
 	struct dirty_throttle_control gdtc = { GDTC_INIT(wb) };
 
+	domain_dirty_avail(&gdtc, true);
 	return __wb_calc_thresh(&gdtc, thresh);
 }
 
@@ -1120,12 +1139,6 @@ static void 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) {
-			dtc->pos_ratio = min_t(long long, pos_ratio * 2,
-					   2 << RATELIMIT_CALC_SHIFT);
-			return;
-		}
-
 		if (dtc->wb_dirty >= wb_thresh)
 			return;
 
@@ -1196,14 +1209,6 @@ static void wb_position_ratio(struct dirty_throttle_control *dtc)
 	 */
 	if (unlikely(wb_thresh > dtc->thresh))
 		wb_thresh = dtc->thresh;
-	/*
-	 * It's very possible that wb_thresh is close to 0 not because the
-	 * device is slow, but that it has remained inactive for long time.
-	 * Honour such devices a reasonable good (hopefully IO efficient)
-	 * threshold, so that the occasional writes won't be blocked and active
-	 * writes can rampup the threshold quickly.
-	 */
-	wb_thresh = max(wb_thresh, (limit - dtc->dirty) / 8);
 	/*
 	 * scale global setpoint to wb's:
 	 *	wb_setpoint = setpoint * wb_thresh / thresh
@@ -1459,17 +1464,10 @@ static void wb_update_dirty_ratelimit(struct dirty_throttle_control *dtc,
 	 * balanced_dirty_ratelimit = task_ratelimit * write_bw / dirty_rate).
 	 * Hence, to calculate "step" properly, we have to use wb_dirty as
 	 * "dirty" and wb_setpoint as "setpoint".
-	 *
-	 * We rampup dirty_ratelimit forcibly if wb_dirty is low because
-	 * it's possible that wb_thresh is close to zero due to inactivity
-	 * of backing device.
 	 */
 	if (unlikely(wb->bdi->capabilities & BDI_CAP_STRICTLIMIT)) {
 		dirty = dtc->wb_dirty;
-		if (dtc->wb_dirty < 8)
-			setpoint = dtc->wb_dirty + 1;
-		else
-			setpoint = (dtc->wb_thresh + dtc->wb_bg_thresh) / 2;
+		setpoint = (dtc->wb_thresh + dtc->wb_bg_thresh) / 2;
 	}
 
 	if (dirty < setpoint) {
-- 
2.20.1