1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
|
From 93147736b5b3a21bea24313bfc7a696829932009 Mon Sep 17 00:00:00 2001
From: Yu Zhao <yuzhao@google.com>
Date: Wed, 21 Dec 2022 21:19:05 -0700
Subject: [PATCH 27/29] mm: multi-gen LRU: clarify scan_control flags
Among the flags in scan_control:
1. sc->may_swap, which indicates swap constraint due to memsw.max, is
supported as usual.
2. sc->proactive, which indicates reclaim by memory.reclaim, may not
opportunistically skip the aging path, since it is considered less
latency sensitive.
3. !(sc->gfp_mask & __GFP_IO), which indicates IO constraint, lowers
swappiness to prioritize file LRU, since clean file pages are more
likely to exist.
4. sc->may_writepage and sc->may_unmap, which indicates opportunistic
reclaim, are rejected, since unmapped clean pages are already
prioritized. Scanning for more of them is likely futile and can
cause high reclaim latency when there is a large number of memcgs.
The rest are handled by the existing code.
Link: https://lkml.kernel.org/r/20221222041905.2431096-8-yuzhao@google.com
Signed-off-by: Yu Zhao <yuzhao@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Michael Larabel <Michael@MichaelLarabel.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Suren Baghdasaryan <surenb@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/vmscan.c | 55 +++++++++++++++++++++++++++--------------------------
1 file changed, 28 insertions(+), 27 deletions(-)
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2905,6 +2905,9 @@ static int get_swappiness(struct lruvec
struct mem_cgroup *memcg = lruvec_memcg(lruvec);
struct pglist_data *pgdat = lruvec_pgdat(lruvec);
+ if (!sc->may_swap)
+ return 0;
+
if (!can_demote(pgdat->node_id, sc) &&
mem_cgroup_get_nr_swap_pages(memcg) < MIN_LRU_BATCH)
return 0;
@@ -3952,7 +3955,7 @@ static void walk_mm(struct lruvec *lruve
} while (err == -EAGAIN);
}
-static struct lru_gen_mm_walk *set_mm_walk(struct pglist_data *pgdat)
+static struct lru_gen_mm_walk *set_mm_walk(struct pglist_data *pgdat, bool force_alloc)
{
struct lru_gen_mm_walk *walk = current->reclaim_state->mm_walk;
@@ -3960,7 +3963,7 @@ static struct lru_gen_mm_walk *set_mm_wa
VM_WARN_ON_ONCE(walk);
walk = &pgdat->mm_walk;
- } else if (!pgdat && !walk) {
+ } else if (!walk && force_alloc) {
VM_WARN_ON_ONCE(current_is_kswapd());
walk = kzalloc(sizeof(*walk), __GFP_HIGH | __GFP_NOMEMALLOC | __GFP_NOWARN);
@@ -4146,7 +4149,7 @@ static bool try_to_inc_max_seq(struct lr
goto done;
}
- walk = set_mm_walk(NULL);
+ walk = set_mm_walk(NULL, true);
if (!walk) {
success = iterate_mm_list_nowalk(lruvec, max_seq);
goto done;
@@ -4215,8 +4218,6 @@ static bool lruvec_is_reclaimable(struct
struct mem_cgroup *memcg = lruvec_memcg(lruvec);
DEFINE_MIN_SEQ(lruvec);
- VM_WARN_ON_ONCE(sc->memcg_low_reclaim);
-
/* see the comment on lru_gen_page */
gen = lru_gen_from_seq(min_seq[LRU_GEN_FILE]);
birth = READ_ONCE(lruvec->lrugen.timestamps[gen]);
@@ -4472,12 +4473,8 @@ static bool isolate_page(struct lruvec *
{
bool success;
- /* unmapping inhibited */
- if (!sc->may_unmap && page_mapped(page))
- return false;
-
/* swapping inhibited */
- if (!(sc->may_writepage && (sc->gfp_mask & __GFP_IO)) &&
+ if (!(sc->gfp_mask & __GFP_IO) &&
(PageDirty(page) ||
(PageAnon(page) && !PageSwapCache(page))))
return false;
@@ -4574,9 +4571,8 @@ static int scan_pages(struct lruvec *lru
__count_vm_events(PGSCAN_ANON + type, isolated);
/*
- * There might not be eligible pages due to reclaim_idx, may_unmap and
- * may_writepage. Check the remaining to prevent livelock if it's not
- * making progress.
+ * There might not be eligible pages due to reclaim_idx. Check the
+ * remaining to prevent livelock if it's not making progress.
*/
return isolated || !remaining ? scanned : 0;
}
@@ -4836,8 +4832,7 @@ static long get_nr_to_scan(struct lruvec
struct mem_cgroup *memcg = lruvec_memcg(lruvec);
DEFINE_MAX_SEQ(lruvec);
- if (mem_cgroup_below_min(memcg) ||
- (mem_cgroup_below_low(memcg) && !sc->memcg_low_reclaim))
+ if (mem_cgroup_below_min(memcg))
return 0;
if (!should_run_aging(lruvec, max_seq, sc, can_swap, &nr_to_scan))
@@ -4865,17 +4860,14 @@ static bool try_to_shrink_lruvec(struct
long nr_to_scan;
unsigned long scanned = 0;
unsigned long nr_to_reclaim = get_nr_to_reclaim(sc);
+ int swappiness = get_swappiness(lruvec, sc);
+
+ /* clean file pages are more likely to exist */
+ if (swappiness && !(sc->gfp_mask & __GFP_IO))
+ swappiness = 1;
while (true) {
int delta;
- int swappiness;
-
- if (sc->may_swap)
- swappiness = get_swappiness(lruvec, sc);
- else if (!cgroup_reclaim(sc) && get_swappiness(lruvec, sc))
- swappiness = 1;
- else
- swappiness = 0;
nr_to_scan = get_nr_to_scan(lruvec, sc, swappiness);
if (nr_to_scan <= 0)
@@ -5005,12 +4997,13 @@ static void lru_gen_shrink_lruvec(struct
struct blk_plug plug;
VM_WARN_ON_ONCE(global_reclaim(sc));
+ VM_WARN_ON_ONCE(!sc->may_writepage || !sc->may_unmap);
lru_add_drain();
blk_start_plug(&plug);
- set_mm_walk(lruvec_pgdat(lruvec));
+ set_mm_walk(NULL, false);
if (try_to_shrink_lruvec(lruvec, sc))
lru_gen_rotate_memcg(lruvec, MEMCG_LRU_YOUNG);
@@ -5066,11 +5059,19 @@ static void lru_gen_shrink_node(struct p
VM_WARN_ON_ONCE(!global_reclaim(sc));
+ /*
+ * Unmapped clean pages are already prioritized. Scanning for more of
+ * them is likely futile and can cause high reclaim latency when there
+ * is a large number of memcgs.
+ */
+ if (!sc->may_writepage || !sc->may_unmap)
+ goto done;
+
lru_add_drain();
blk_start_plug(&plug);
- set_mm_walk(pgdat);
+ set_mm_walk(pgdat, false);
set_initial_priority(pgdat, sc);
@@ -5088,7 +5089,7 @@ static void lru_gen_shrink_node(struct p
clear_mm_walk();
blk_finish_plug(&plug);
-
+done:
/* kswapd should never fail */
pgdat->kswapd_failures = 0;
}
@@ -5656,7 +5657,7 @@ static ssize_t lru_gen_seq_write(struct
set_task_reclaim_state(current, &sc.reclaim_state);
flags = memalloc_noreclaim_save();
blk_start_plug(&plug);
- if (!set_mm_walk(NULL)) {
+ if (!set_mm_walk(NULL, true)) {
err = -ENOMEM;
goto done;
}
|
