linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Johannes Weiner <hannes@cmpxchg.org>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>,
	Suren Baghdasaryan <surenb@google.com>,
	Michal Hocko <mhocko@suse.com>,
	linux-mm@kvack.org, cgroups@vger.kernel.org,
	linux-kernel@vger.kernel.org, kernel-team@fb.com
Subject: [PATCH 07/11] mm: vmscan: split shrink_node() into node part and memcgs part
Date: Mon,  3 Jun 2019 17:07:42 -0400	[thread overview]
Message-ID: <20190603210746.15800-8-hannes@cmpxchg.org> (raw)
In-Reply-To: <20190603210746.15800-1-hannes@cmpxchg.org>

This function is getting long and unwieldy. The new shrink_node()
handles the generic (node) reclaim aspects:
  - global vmpressure notifications
  - writeback and congestion throttling
  - reclaim/compaction management
  - kswapd giving up on unreclaimable nodes

It then calls shrink_node_memcgs() which handles cgroup specifics:
  - the cgroup tree traversal
  - memory.low considerations
  - per-cgroup slab shrinking callbacks
  - per-cgroup vmpressure notifications

Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
---
 mm/vmscan.c | 29 ++++++++++++++++++-----------
 1 file changed, 18 insertions(+), 11 deletions(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index b85111474ee2..ee79b39d0538 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2665,24 +2665,15 @@ static bool pgdat_memcg_congested(pg_data_t *pgdat, struct mem_cgroup *memcg)
 		(memcg && memcg_congested(pgdat, memcg));
 }
 
-static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc)
+static void shrink_node_memcgs(pg_data_t *pgdat, struct scan_control *sc)
 {
-	struct reclaim_state *reclaim_state = current->reclaim_state;
 	struct mem_cgroup *root = sc->target_mem_cgroup;
 	struct mem_cgroup_reclaim_cookie reclaim = {
 		.pgdat = pgdat,
 		.priority = sc->priority,
 	};
-	unsigned long nr_reclaimed, nr_scanned;
-	bool reclaimable = false;
 	struct mem_cgroup *memcg;
 
-again:
-	memset(&sc->nr, 0, sizeof(sc->nr));
-
-	nr_reclaimed = sc->nr_reclaimed;
-	nr_scanned = sc->nr_scanned;
-
 	memcg = mem_cgroup_iter(root, NULL, &reclaim);
 	do {
 		struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat);
@@ -2750,6 +2741,22 @@ static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc)
 			break;
 		}
 	} while ((memcg = mem_cgroup_iter(root, memcg, &reclaim)));
+}
+
+static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc)
+{
+	struct reclaim_state *reclaim_state = current->reclaim_state;
+	struct mem_cgroup *root = sc->target_mem_cgroup;
+	unsigned long nr_reclaimed, nr_scanned;
+	bool reclaimable = false;
+
+again:
+	memset(&sc->nr, 0, sizeof(sc->nr));
+
+	nr_reclaimed = sc->nr_reclaimed;
+	nr_scanned = sc->nr_scanned;
+
+	shrink_node_memcgs(pgdat, sc);
 
 	if (reclaim_state) {
 		sc->nr_reclaimed += reclaim_state->reclaimed_slab;
@@ -2757,7 +2764,7 @@ static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc)
 	}
 
 	/* Record the subtree's reclaim efficiency */
-	vmpressure(sc->gfp_mask, sc->target_mem_cgroup, true,
+	vmpressure(sc->gfp_mask, root, true,
 		   sc->nr_scanned - nr_scanned,
 		   sc->nr_reclaimed - nr_reclaimed);
 
-- 
2.21.0


  parent reply	other threads:[~2019-06-03 22:00 UTC|newest]

Thread overview: 24+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-06-03 21:07 [PATCH 00/11] mm: fix page aging across multiple cgroups Johannes Weiner
2019-06-03 21:07 ` [PATCH 01/11] mm: vmscan: move inactive_list_is_low() swap check to the caller Johannes Weiner
2019-11-07  2:50   ` Shakeel Butt
2019-11-08  3:43     ` Andrew Morton
2019-06-03 21:07 ` [PATCH 02/11] mm: clean up and clarify lruvec lookup procedure Johannes Weiner
2019-11-07  2:50   ` Shakeel Butt
2019-06-03 21:07 ` [PATCH 03/11] mm: vmscan: simplify lruvec_lru_size() Johannes Weiner
2019-11-07  2:51   ` Shakeel Butt
2019-06-03 21:07 ` [PATCH 04/11] mm: vmscan: naming fixes: cgroup_reclaim() and writeback_working() Johannes Weiner
2019-11-07  2:51   ` Shakeel Butt
2019-06-03 21:07 ` [PATCH 05/11] mm: vmscan: replace shrink_node() loop with a retry jump Johannes Weiner
2019-11-07  2:51   ` Shakeel Butt
2019-06-03 21:07 ` [PATCH 06/11] mm: vmscan: turn shrink_node_memcg() into shrink_lruvec() Johannes Weiner
2019-11-07  2:51   ` Shakeel Butt
2019-06-03 21:07 ` Johannes Weiner [this message]
2019-11-07  2:51   ` [PATCH 07/11] mm: vmscan: split shrink_node() into node part and memcgs part Shakeel Butt
2019-06-03 21:07 ` [PATCH 08/11] mm: vmscan: harmonize writeback congestion tracking for nodes & memcgs Johannes Weiner
2019-11-07  2:52   ` Shakeel Butt
2019-06-03 21:07 ` [PATCH 09/11] mm: vmscan: move file exhaustion detection to the node level Johannes Weiner
2019-11-07  2:52   ` Shakeel Butt
2019-06-03 21:07 ` [PATCH 10/11] mm: vmscan: detect file thrashing at the reclaim root Johannes Weiner
2019-06-03 21:07 ` [PATCH 11/11] mm: vmscan: enforce inactive:active ratio " Johannes Weiner
2019-11-07  2:50 ` [PATCH 00/11] mm: fix page aging across multiple cgroups Shakeel Butt
2019-11-07 17:45   ` Johannes Weiner

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=20190603210746.15800-8-hannes@cmpxchg.org \
    --to=hannes@cmpxchg.org \
    --cc=akpm@linux-foundation.org \
    --cc=aryabinin@virtuozzo.com \
    --cc=cgroups@vger.kernel.org \
    --cc=kernel-team@fb.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mhocko@suse.com \
    --cc=surenb@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).