All of lore.kernel.org
 help / color / mirror / Atom feed
From: Mel Gorman <mgorman@techsingularity.net>
To: Linux-MM <linux-mm@kvack.org>
Cc: NeilBrown <neilb@suse.de>, Theodore Ts'o <tytso@mit.edu>,
	Andreas Dilger <adilger.kernel@dilger.ca>,
	"Darrick J . Wong" <djwong@kernel.org>,
	Matthew Wilcox <willy@infradead.org>,
	Michal Hocko <mhocko@suse.com>,
	Dave Chinner <david@fromorbit.com>,
	Rik van Riel <riel@surriel.com>, Vlastimil Babka <vbabka@suse.cz>,
	Johannes Weiner <hannes@cmpxchg.org>,
	Jonathan Corbet <corbet@lwn.net>,
	Linux-fsdevel <linux-fsdevel@vger.kernel.org>,
	LKML <linux-kernel@vger.kernel.org>,
	Mel Gorman <mgorman@techsingularity.net>
Subject: [PATCH 3/5] mm/vmscan: Throttle reclaim when no progress is being made
Date: Mon, 20 Sep 2021 09:54:34 +0100	[thread overview]
Message-ID: <20210920085436.20939-4-mgorman@techsingularity.net> (raw)
In-Reply-To: <20210920085436.20939-1-mgorman@techsingularity.net>

Memcg reclaim throttles on congestion if no reclaim progress is made.
This makes little sense, it might be due to writeback or a host of
other factors.

For !memcg reclaim, it's messy. Direct reclaim primarily is throttled
in the page allocator if it is failing to make progress. Kswapd
throttles if too many pages are under writeback and marked for
immediate reclaim.

This patch explicitly throttles if reclaim is failing to make progress.

Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
---
 include/linux/mmzone.h        |  1 +
 include/trace/events/vmscan.h |  4 +++-
 mm/memcontrol.c               | 10 +--------
 mm/vmscan.c                   | 38 +++++++++++++++++++++++++++++++++++
 4 files changed, 43 insertions(+), 10 deletions(-)

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index ca65d6a64bdd..7c08cc91d526 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -276,6 +276,7 @@ enum lru_list {
 enum vmscan_throttle_state {
 	VMSCAN_THROTTLE_WRITEBACK,
 	VMSCAN_THROTTLE_ISOLATED,
+	VMSCAN_THROTTLE_NOPROGRESS,
 	NR_VMSCAN_THROTTLE,
 };
 
diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h
index d4905bd9e9c4..f25a6149d3ba 100644
--- a/include/trace/events/vmscan.h
+++ b/include/trace/events/vmscan.h
@@ -29,11 +29,13 @@
 
 #define _VMSCAN_THROTTLE_WRITEBACK	(1 << VMSCAN_THROTTLE_WRITEBACK)
 #define _VMSCAN_THROTTLE_ISOLATED	(1 << VMSCAN_THROTTLE_ISOLATED)
+#define _VMSCAN_THROTTLE_NOPROGRESS	(1 << VMSCAN_THROTTLE_NOPROGRESS)
 
 #define show_throttle_flags(flags)						\
 	(flags) ? __print_flags(flags, "|",					\
 		{_VMSCAN_THROTTLE_WRITEBACK,	"VMSCAN_THROTTLE_WRITEBACK"},	\
-		{_VMSCAN_THROTTLE_ISOLATED,	"VMSCAN_THROTTLE_ISOLATED"}	\
+		{_VMSCAN_THROTTLE_ISOLATED,	"VMSCAN_THROTTLE_ISOLATED"},	\
+		{_VMSCAN_THROTTLE_NOPROGRESS,	"VMSCAN_THROTTLE_NOPROGRESS"}	\
 		) : "VMSCAN_THROTTLE_NONE"
 
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index b762215d73eb..8479919a633c 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3470,19 +3470,11 @@ static int mem_cgroup_force_empty(struct mem_cgroup *memcg)
 
 	/* try to free all pages in this cgroup */
 	while (nr_retries && page_counter_read(&memcg->memory)) {
-		int progress;
-
 		if (signal_pending(current))
 			return -EINTR;
 
-		progress = try_to_free_mem_cgroup_pages(memcg, 1,
-							GFP_KERNEL, true);
-		if (!progress) {
+		if (!try_to_free_mem_cgroup_pages(memcg, 1, GFP_KERNEL, true))
 			nr_retries--;
-			/* maybe some writeback is necessary */
-			congestion_wait(BLK_RW_ASYNC, HZ/10);
-		}
-
 	}
 
 	return 0;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index eb81dcac15b2..18b9826953a0 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -3307,6 +3307,33 @@ static inline bool compaction_ready(struct zone *zone, struct scan_control *sc)
 	return zone_watermark_ok_safe(zone, 0, watermark, sc->reclaim_idx);
 }
 
+static void consider_reclaim_throttle(pg_data_t *pgdat, struct scan_control *sc)
+{
+	/* If reclaim is making progress, wake any throttled tasks. */
+	if (sc->nr_reclaimed) {
+		wait_queue_head_t *wqh;
+
+		wqh = &pgdat->reclaim_wait[VMSCAN_THROTTLE_NOPROGRESS];
+		if (waitqueue_active(wqh))
+			wake_up_interruptible_all(wqh);
+
+		return;
+	}
+
+	/*
+	 * Do not throttle kswapd on NOPROGRESS as it will throttle on
+	 * VMSCAN_THROTTLE_WRITEBACK if there are too many pages under
+	 * writeback and marked for immediate reclaim at the tail of
+	 * the LRU.
+	 */
+	if (current_is_kswapd())
+		return;
+
+	/* Throttle if making no progress at high prioities. */
+	if (sc->priority < DEF_PRIORITY - 2)
+		reclaim_throttle(pgdat, VMSCAN_THROTTLE_NOPROGRESS, HZ/10);
+}
+
 /*
  * This is the direct reclaim path, for page-allocating processes.  We only
  * try to reclaim pages from zones which will satisfy the caller's allocation
@@ -3391,6 +3418,7 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
 			continue;
 		last_pgdat = zone->zone_pgdat;
 		shrink_node(zone->zone_pgdat, sc);
+		consider_reclaim_throttle(zone->zone_pgdat, sc);
 	}
 
 	/*
@@ -3765,6 +3793,16 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
 	trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed);
 	set_task_reclaim_state(current, NULL);
 
+	if (!nr_reclaimed) {
+		struct zoneref *z;
+		pg_data_t *pgdat;
+
+		z = first_zones_zonelist(zonelist, sc.reclaim_idx, sc.nodemask);
+		pgdat = zonelist_zone(z)->zone_pgdat;
+
+		reclaim_throttle(pgdat, VMSCAN_THROTTLE_NOPROGRESS, HZ/10);
+	}
+
 	return nr_reclaimed;
 }
 #endif
-- 
2.31.1


  parent reply	other threads:[~2021-09-20  8:55 UTC|newest]

Thread overview: 33+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-09-20  8:54 [RFC PATCH 0/5] Remove dependency on congestion_wait in mm/ Mel Gorman
2021-09-20  8:54 ` [PATCH 1/5] mm/vmscan: Throttle reclaim until some writeback completes if congested Mel Gorman
2021-09-20 23:19   ` NeilBrown
2021-09-21 11:12     ` Mel Gorman
2021-09-21 21:27       ` NeilBrown
2021-09-21  0:13   ` NeilBrown
2021-09-21 10:58     ` Mel Gorman
2021-09-21 21:40       ` NeilBrown
2021-09-22  6:04       ` Dave Chinner
2021-09-22  8:03         ` Mel Gorman
2021-09-22 12:16   ` Hillf Danton
2021-09-22 14:13     ` Mel Gorman
2021-09-20  8:54 ` [PATCH 2/5] mm/vmscan: Throttle reclaim and compaction when too may pages are isolated Mel Gorman
2021-09-20 23:27   ` NeilBrown
2021-09-21 11:03     ` Mel Gorman
2021-09-21 18:45   ` Yang Shi
2021-09-21 18:45     ` Yang Shi
2021-09-22  8:11     ` Mel Gorman
2021-09-20  8:54 ` Mel Gorman [this message]
2021-09-20 23:31   ` [PATCH 3/5] mm/vmscan: Throttle reclaim when no progress is being made NeilBrown
2021-09-21 11:16     ` Mel Gorman
2021-09-21 21:46       ` NeilBrown
2021-09-22  9:21         ` Mel Gorman
2021-09-20  8:54 ` [PATCH 4/5] mm/writeback: Throttle based on page writeback instead of congestion Mel Gorman
2021-09-20  8:54 ` [PATCH 5/5] mm/page_alloc: Remove the throttling logic from the page allocator Mel Gorman
2021-09-20 11:42 ` [RFC PATCH 0/5] Remove dependency on congestion_wait in mm/ Matthew Wilcox
2021-09-20 12:50   ` Mel Gorman
2021-09-20 14:11     ` David Sterba
2021-09-21 11:18       ` Mel Gorman
2021-09-20 19:51   ` Mel Gorman
2021-09-21 20:46 ` Dave Chinner
2021-09-22 17:52   ` Mel Gorman
2021-09-29 10:09 [PATCH 0/5] Remove dependency on congestion_wait in mm/ v2 Mel Gorman
2021-09-29 10:09 ` [PATCH 3/5] mm/vmscan: Throttle reclaim when no progress is being made Mel Gorman

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=20210920085436.20939-4-mgorman@techsingularity.net \
    --to=mgorman@techsingularity.net \
    --cc=adilger.kernel@dilger.ca \
    --cc=corbet@lwn.net \
    --cc=david@fromorbit.com \
    --cc=djwong@kernel.org \
    --cc=hannes@cmpxchg.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mhocko@suse.com \
    --cc=neilb@suse.de \
    --cc=riel@surriel.com \
    --cc=tytso@mit.edu \
    --cc=vbabka@suse.cz \
    --cc=willy@infradead.org \
    --subject='Re: [PATCH 3/5] mm/vmscan: Throttle reclaim when no progress is being made' \
    /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

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.