diff options
author | Yu Zhao <yuzhao@google.com> | 2022-12-22 07:19:04 +0300 |
---|---|---|
committer | Andrew Morton <akpm@linux-foundation.org> | 2023-01-19 04:12:49 +0300 |
commit | e4dde56cd208674ce899b47589f263499e5b8cdc (patch) | |
tree | 6671ed8dfd119d855fcae2a47243c579e9eaff29 /include/linux/mmzone.h | |
parent | 77d4459a4a1a472b7309e475f962dda87d950abd (diff) | |
download | linux-e4dde56cd208674ce899b47589f263499e5b8cdc.tar.xz |
mm: multi-gen LRU: per-node lru_gen_folio lists
For each node, memcgs are divided into two generations: the old and
the young. For each generation, memcgs are randomly sharded into
multiple bins to improve scalability. For each bin, an RCU hlist_nulls
is virtually divided into three segments: the head, the tail and the
default.
An onlining memcg is added to the tail of a random bin in the old
generation. The eviction starts at the head of a random bin in the old
generation. The per-node memcg generation counter, whose reminder (mod
2) indexes the old generation, is incremented when all its bins become
empty.
There are four operations:
1. MEMCG_LRU_HEAD, which moves an memcg to the head of a random bin in
its current generation (old or young) and updates its "seg" to
"head";
2. MEMCG_LRU_TAIL, which moves an memcg to the tail of a random bin in
its current generation (old or young) and updates its "seg" to
"tail";
3. MEMCG_LRU_OLD, which moves an memcg to the head of a random bin in
the old generation, updates its "gen" to "old" and resets its "seg"
to "default";
4. MEMCG_LRU_YOUNG, which moves an memcg to the tail of a random bin
in the young generation, updates its "gen" to "young" and resets
its "seg" to "default".
The events that trigger the above operations are:
1. Exceeding the soft limit, which triggers MEMCG_LRU_HEAD;
2. The first attempt to reclaim an memcg below low, which triggers
MEMCG_LRU_TAIL;
3. The first attempt to reclaim an memcg below reclaimable size
threshold, which triggers MEMCG_LRU_TAIL;
4. The second attempt to reclaim an memcg below reclaimable size
threshold, which triggers MEMCG_LRU_YOUNG;
5. Attempting to reclaim an memcg below min, which triggers
MEMCG_LRU_YOUNG;
6. Finishing the aging on the eviction path, which triggers
MEMCG_LRU_YOUNG;
7. Offlining an memcg, which triggers MEMCG_LRU_OLD.
Note that memcg LRU only applies to global reclaim, and the
round-robin incrementing of their max_seq counters ensures the
eventual fairness to all eligible memcgs. For memcg reclaim, it still
relies on mem_cgroup_iter().
Link: https://lkml.kernel.org/r/20221222041905.2431096-7-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>
Diffstat (limited to 'include/linux/mmzone.h')
-rw-r--r-- | include/linux/mmzone.h | 117 |
1 files changed, 115 insertions, 2 deletions
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 6c96ee823dbd..815c7c2edf45 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -7,6 +7,7 @@ #include <linux/spinlock.h> #include <linux/list.h> +#include <linux/list_nulls.h> #include <linux/wait.h> #include <linux/bitops.h> #include <linux/cache.h> @@ -367,6 +368,15 @@ struct page_vma_mapped_walk; #define LRU_GEN_MASK ((BIT(LRU_GEN_WIDTH) - 1) << LRU_GEN_PGOFF) #define LRU_REFS_MASK ((BIT(LRU_REFS_WIDTH) - 1) << LRU_REFS_PGOFF) +/* see the comment on MEMCG_NR_GENS */ +enum { + MEMCG_LRU_NOP, + MEMCG_LRU_HEAD, + MEMCG_LRU_TAIL, + MEMCG_LRU_OLD, + MEMCG_LRU_YOUNG, +}; + #ifdef CONFIG_LRU_GEN enum { @@ -426,6 +436,14 @@ struct lru_gen_folio { atomic_long_t refaulted[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS]; /* whether the multi-gen LRU is enabled */ bool enabled; +#ifdef CONFIG_MEMCG + /* the memcg generation this lru_gen_folio belongs to */ + u8 gen; + /* the list segment this lru_gen_folio belongs to */ + u8 seg; + /* per-node lru_gen_folio list for global reclaim */ + struct hlist_nulls_node list; +#endif }; enum { @@ -479,12 +497,87 @@ void lru_gen_init_lruvec(struct lruvec *lruvec); void lru_gen_look_around(struct page_vma_mapped_walk *pvmw); #ifdef CONFIG_MEMCG + +/* + * For each node, memcgs are divided into two generations: the old and the + * young. For each generation, memcgs are randomly sharded into multiple bins + * to improve scalability. For each bin, the hlist_nulls is virtually divided + * into three segments: the head, the tail and the default. + * + * An onlining memcg is added to the tail of a random bin in the old generation. + * The eviction starts at the head of a random bin in the old generation. The + * per-node memcg generation counter, whose reminder (mod MEMCG_NR_GENS) indexes + * the old generation, is incremented when all its bins become empty. + * + * There are four operations: + * 1. MEMCG_LRU_HEAD, which moves an memcg to the head of a random bin in its + * current generation (old or young) and updates its "seg" to "head"; + * 2. MEMCG_LRU_TAIL, which moves an memcg to the tail of a random bin in its + * current generation (old or young) and updates its "seg" to "tail"; + * 3. MEMCG_LRU_OLD, which moves an memcg to the head of a random bin in the old + * generation, updates its "gen" to "old" and resets its "seg" to "default"; + * 4. MEMCG_LRU_YOUNG, which moves an memcg to the tail of a random bin in the + * young generation, updates its "gen" to "young" and resets its "seg" to + * "default". + * + * The events that trigger the above operations are: + * 1. Exceeding the soft limit, which triggers MEMCG_LRU_HEAD; + * 2. The first attempt to reclaim an memcg below low, which triggers + * MEMCG_LRU_TAIL; + * 3. The first attempt to reclaim an memcg below reclaimable size threshold, + * which triggers MEMCG_LRU_TAIL; + * 4. The second attempt to reclaim an memcg below reclaimable size threshold, + * which triggers MEMCG_LRU_YOUNG; + * 5. Attempting to reclaim an memcg below min, which triggers MEMCG_LRU_YOUNG; + * 6. Finishing the aging on the eviction path, which triggers MEMCG_LRU_YOUNG; + * 7. Offlining an memcg, which triggers MEMCG_LRU_OLD. + * + * Note that memcg LRU only applies to global reclaim, and the round-robin + * incrementing of their max_seq counters ensures the eventual fairness to all + * eligible memcgs. For memcg reclaim, it still relies on mem_cgroup_iter(). + */ +#define MEMCG_NR_GENS 2 +#define MEMCG_NR_BINS 8 + +struct lru_gen_memcg { + /* the per-node memcg generation counter */ + unsigned long seq; + /* each memcg has one lru_gen_folio per node */ + unsigned long nr_memcgs[MEMCG_NR_GENS]; + /* per-node lru_gen_folio list for global reclaim */ + struct hlist_nulls_head fifo[MEMCG_NR_GENS][MEMCG_NR_BINS]; + /* protects the above */ + spinlock_t lock; +}; + +void lru_gen_init_pgdat(struct pglist_data *pgdat); + void lru_gen_init_memcg(struct mem_cgroup *memcg); void lru_gen_exit_memcg(struct mem_cgroup *memcg); -#endif +void lru_gen_online_memcg(struct mem_cgroup *memcg); +void lru_gen_offline_memcg(struct mem_cgroup *memcg); +void lru_gen_release_memcg(struct mem_cgroup *memcg); +void lru_gen_rotate_memcg(struct lruvec *lruvec, int op); + +#else /* !CONFIG_MEMCG */ + +#define MEMCG_NR_GENS 1 + +struct lru_gen_memcg { +}; + +static inline void lru_gen_init_pgdat(struct pglist_data *pgdat) +{ +} + +#endif /* CONFIG_MEMCG */ #else /* !CONFIG_LRU_GEN */ +static inline void lru_gen_init_pgdat(struct pglist_data *pgdat) +{ +} + static inline void lru_gen_init_lruvec(struct lruvec *lruvec) { } @@ -494,6 +587,7 @@ static inline void lru_gen_look_around(struct page_vma_mapped_walk *pvmw) } #ifdef CONFIG_MEMCG + static inline void lru_gen_init_memcg(struct mem_cgroup *memcg) { } @@ -501,7 +595,24 @@ static inline void lru_gen_init_memcg(struct mem_cgroup *memcg) static inline void lru_gen_exit_memcg(struct mem_cgroup *memcg) { } -#endif + +static inline void lru_gen_online_memcg(struct mem_cgroup *memcg) +{ +} + +static inline void lru_gen_offline_memcg(struct mem_cgroup *memcg) +{ +} + +static inline void lru_gen_release_memcg(struct mem_cgroup *memcg) +{ +} + +static inline void lru_gen_rotate_memcg(struct lruvec *lruvec, int op) +{ +} + +#endif /* CONFIG_MEMCG */ #endif /* CONFIG_LRU_GEN */ @@ -1243,6 +1354,8 @@ typedef struct pglist_data { #ifdef CONFIG_LRU_GEN /* kswap mm walk data */ struct lru_gen_mm_walk mm_walk; + /* lru_gen_folio list */ + struct lru_gen_memcg memcg_lru; #endif CACHELINE_PADDING(_pad2_); |