From 8c20e2eb5f2a0175b774134685e4d7bd93e85ff8 Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Wed, 21 Dec 2022 21:18:59 -0700 Subject: [PATCH 01/19] UPSTREAM: mm: multi-gen LRU: rename lru_gen_struct to lru_gen_folio Patch series "mm: multi-gen LRU: memcg LRU", v3. Overview ======== An memcg LRU is a per-node LRU of memcgs. It is also an LRU of LRUs, since each node and memcg combination has an LRU of folios (see mem_cgroup_lruvec()). Its goal is to improve the scalability of global reclaim, which is critical to system-wide memory overcommit in data centers. Note that memcg reclaim is currently out of scope. Its memory bloat is a pointer to each lruvec and negligible to each pglist_data. In terms of traversing memcgs during global reclaim, it improves the best-case complexity from O(n) to O(1) and does not affect the worst-case complexity O(n). Therefore, on average, it has a sublinear complexity in contrast to the current linear complexity. The basic structure of an memcg LRU can be understood by an analogy to the active/inactive LRU (of folios): 1. It has the young and the old (generations), i.e., the counterparts to the active and the inactive; 2. The increment of max_seq triggers promotion, i.e., the counterpart to activation; 3. Other events trigger similar operations, e.g., offlining an memcg triggers demotion, i.e., the counterpart to deactivation. In terms of global reclaim, it has two distinct features: 1. Sharding, which allows each thread to start at a random memcg (in the old generation) and improves parallelism; 2. Eventual fairness, which allows direct reclaim to bail out at will and reduces latency without affecting fairness over some time. The commit message in patch 6 details the workflow: https://lore.kernel.org/r/20221222041905.2431096-7-yuzhao@google.com/ The following is a simple test to quickly verify its effectiveness. Test design: 1. Create multiple memcgs. 2. Each memcg contains a job (fio). 3. All jobs access the same amount of memory randomly. 4. The system does not experience global memory pressure. 5. Periodically write to the root memory.reclaim. Desired outcome: 1. All memcgs have similar pgsteal counts, i.e., stddev(pgsteal) over mean(pgsteal) is close to 0%. 2. The total pgsteal is close to the total requested through memory.reclaim, i.e., sum(pgsteal) over sum(requested) is close to 100%. Actual outcome [1]: MGLRU off MGLRU on stddev(pgsteal) / mean(pgsteal) 75% 20% sum(pgsteal) / sum(requested) 425% 95% #################################################################### MEMCGS=128 for ((memcg = 0; memcg < $MEMCGS; memcg++)); do mkdir /sys/fs/cgroup/memcg$memcg done start() { echo $BASHPID > /sys/fs/cgroup/memcg$memcg/cgroup.procs fio -name=memcg$memcg --numjobs=1 --ioengine=mmap \ --filename=/dev/zero --size=1920M --rw=randrw \ --rate=64m,64m --random_distribution=random \ --fadvise_hint=0 --time_based --runtime=10h \ --group_reporting --minimal } for ((memcg = 0; memcg < $MEMCGS; memcg++)); do start & done sleep 600 for ((i = 0; i < 600; i++)); do echo 256m >/sys/fs/cgroup/memory.reclaim sleep 6 done for ((memcg = 0; memcg < $MEMCGS; memcg++)); do grep "pgsteal " /sys/fs/cgroup/memcg$memcg/memory.stat done #################################################################### [1]: This was obtained from running the above script (touches less than 256GB memory) on an EPYC 7B13 with 512GB DRAM for over an hour. This patch (of 8): The new name lru_gen_folio will be more distinct from the coming lru_gen_memcg. Link: https://lkml.kernel.org/r/20221222041905.2431096-1-yuzhao@google.com Link: https://lkml.kernel.org/r/20221222041905.2431096-2-yuzhao@google.com Signed-off-by: Yu Zhao Cc: Johannes Weiner Cc: Jonathan Corbet Cc: Michael Larabel Cc: Michal Hocko Cc: Mike Rapoport Cc: Roman Gushchin Cc: Suren Baghdasaryan Signed-off-by: Andrew Morton Bug: 274865848 (cherry picked from commit 391655fe08d1f942359a11148aa9aaf3f99d6d6f) Change-Id: I7df67e0e2435ba28f10eaa57d28d98b61a9210a6 Signed-off-by: T.J. Mercier --- include/linux/mm_inline.h | 4 ++-- include/linux/mmzone.h | 6 +++--- mm/vmscan.c | 34 +++++++++++++++++----------------- mm/workingset.c | 4 ++-- 4 files changed, 24 insertions(+), 24 deletions(-) --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -178,7 +178,7 @@ static inline void lru_gen_update_size(s int zone = folio_zonenum(folio); int delta = folio_nr_pages(folio); enum lru_list lru = type * LRU_INACTIVE_FILE; - struct lru_gen_struct *lrugen = &lruvec->lrugen; + struct lru_gen_folio *lrugen = &lruvec->lrugen; VM_WARN_ON_ONCE(old_gen != -1 && old_gen >= MAX_NR_GENS); VM_WARN_ON_ONCE(new_gen != -1 && new_gen >= MAX_NR_GENS); @@ -224,7 +224,7 @@ static inline bool lru_gen_add_folio(str int gen = folio_lru_gen(folio); int type = folio_is_file_lru(folio); int zone = folio_zonenum(folio); - struct lru_gen_struct *lrugen = &lruvec->lrugen; + struct lru_gen_folio *lrugen = &lruvec->lrugen; VM_WARN_ON_ONCE_FOLIO(gen != -1, folio); --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -404,7 +404,7 @@ enum { * The number of pages in each generation is eventually consistent and therefore * can be transiently negative when reset_batch_size() is pending. */ -struct lru_gen_struct { +struct lru_gen_folio { /* the aging increments the youngest generation number */ unsigned long max_seq; /* the eviction increments the oldest generation numbers */ @@ -461,7 +461,7 @@ struct lru_gen_mm_state { struct lru_gen_mm_walk { /* the lruvec under reclaim */ struct lruvec *lruvec; - /* unstable max_seq from lru_gen_struct */ + /* unstable max_seq from lru_gen_folio */ unsigned long max_seq; /* the next address within an mm to scan */ unsigned long next_addr; @@ -524,7 +524,7 @@ struct lruvec { unsigned long flags; #ifdef CONFIG_LRU_GEN /* evictable pages divided into generations */ - struct lru_gen_struct lrugen; + struct lru_gen_folio lrugen; /* to concurrently iterate lru_gen_mm_list */ struct lru_gen_mm_state mm_state; #endif --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -3190,7 +3190,7 @@ static int get_nr_gens(struct lruvec *lr static bool __maybe_unused seq_is_valid(struct lruvec *lruvec) { - /* see the comment on lru_gen_struct */ + /* see the comment on lru_gen_folio */ return get_nr_gens(lruvec, LRU_GEN_FILE) >= MIN_NR_GENS && get_nr_gens(lruvec, LRU_GEN_FILE) <= get_nr_gens(lruvec, LRU_GEN_ANON) && get_nr_gens(lruvec, LRU_GEN_ANON) <= MAX_NR_GENS; @@ -3596,7 +3596,7 @@ struct ctrl_pos { static void read_ctrl_pos(struct lruvec *lruvec, int type, int tier, int gain, struct ctrl_pos *pos) { - struct lru_gen_struct *lrugen = &lruvec->lrugen; + struct lru_gen_folio *lrugen = &lruvec->lrugen; int hist = lru_hist_from_seq(lrugen->min_seq[type]); pos->refaulted = lrugen->avg_refaulted[type][tier] + @@ -3611,7 +3611,7 @@ static void read_ctrl_pos(struct lruvec static void reset_ctrl_pos(struct lruvec *lruvec, int type, bool carryover) { int hist, tier; - struct lru_gen_struct *lrugen = &lruvec->lrugen; + struct lru_gen_folio *lrugen = &lruvec->lrugen; bool clear = carryover ? NR_HIST_GENS == 1 : NR_HIST_GENS > 1; unsigned long seq = carryover ? lrugen->min_seq[type] : lrugen->max_seq + 1; @@ -3688,7 +3688,7 @@ static int folio_update_gen(struct folio static int folio_inc_gen(struct lruvec *lruvec, struct folio *folio, bool reclaiming) { int type = folio_is_file_lru(folio); - struct lru_gen_struct *lrugen = &lruvec->lrugen; + struct lru_gen_folio *lrugen = &lruvec->lrugen; int new_gen, old_gen = lru_gen_from_seq(lrugen->min_seq[type]); unsigned long new_flags, old_flags = READ_ONCE(folio->flags); @@ -3733,7 +3733,7 @@ static void update_batch_size(struct lru static void reset_batch_size(struct lruvec *lruvec, struct lru_gen_mm_walk *walk) { int gen, type, zone; - struct lru_gen_struct *lrugen = &lruvec->lrugen; + struct lru_gen_folio *lrugen = &lruvec->lrugen; walk->batched = 0; @@ -4250,7 +4250,7 @@ static bool inc_min_seq(struct lruvec *l { int zone; int remaining = MAX_LRU_BATCH; - struct lru_gen_struct *lrugen = &lruvec->lrugen; + struct lru_gen_folio *lrugen = &lruvec->lrugen; int new_gen, old_gen = lru_gen_from_seq(lrugen->min_seq[type]); if (type == LRU_GEN_ANON && !can_swap) @@ -4286,7 +4286,7 @@ static bool try_to_inc_min_seq(struct lr { int gen, type, zone; bool success = false; - struct lru_gen_struct *lrugen = &lruvec->lrugen; + struct lru_gen_folio *lrugen = &lruvec->lrugen; DEFINE_MIN_SEQ(lruvec); VM_WARN_ON_ONCE(!seq_is_valid(lruvec)); @@ -4307,7 +4307,7 @@ next: ; } - /* see the comment on lru_gen_struct */ + /* see the comment on lru_gen_folio */ if (can_swap) { min_seq[LRU_GEN_ANON] = min(min_seq[LRU_GEN_ANON], min_seq[LRU_GEN_FILE]); min_seq[LRU_GEN_FILE] = max(min_seq[LRU_GEN_ANON], lrugen->min_seq[LRU_GEN_FILE]); @@ -4329,7 +4329,7 @@ static void inc_max_seq(struct lruvec *l { int prev, next; int type, zone; - struct lru_gen_struct *lrugen = &lruvec->lrugen; + struct lru_gen_folio *lrugen = &lruvec->lrugen; spin_lock_irq(&lruvec->lru_lock); @@ -4387,7 +4387,7 @@ static bool try_to_inc_max_seq(struct lr bool success; struct lru_gen_mm_walk *walk; struct mm_struct *mm = NULL; - struct lru_gen_struct *lrugen = &lruvec->lrugen; + struct lru_gen_folio *lrugen = &lruvec->lrugen; VM_WARN_ON_ONCE(max_seq > READ_ONCE(lrugen->max_seq)); @@ -4452,7 +4452,7 @@ static bool should_run_aging(struct lruv unsigned long old = 0; unsigned long young = 0; unsigned long total = 0; - struct lru_gen_struct *lrugen = &lruvec->lrugen; + struct lru_gen_folio *lrugen = &lruvec->lrugen; struct mem_cgroup *memcg = lruvec_memcg(lruvec); for (type = !can_swap; type < ANON_AND_FILE; type++) { @@ -4737,7 +4737,7 @@ static bool sort_folio(struct lruvec *lr int delta = folio_nr_pages(folio); int refs = folio_lru_refs(folio); int tier = lru_tier_from_refs(refs); - struct lru_gen_struct *lrugen = &lruvec->lrugen; + struct lru_gen_folio *lrugen = &lruvec->lrugen; VM_WARN_ON_ONCE_FOLIO(gen >= MAX_NR_GENS, folio); @@ -4837,7 +4837,7 @@ static int scan_folios(struct lruvec *lr int scanned = 0; int isolated = 0; int remaining = MAX_LRU_BATCH; - struct lru_gen_struct *lrugen = &lruvec->lrugen; + struct lru_gen_folio *lrugen = &lruvec->lrugen; struct mem_cgroup *memcg = lruvec_memcg(lruvec); VM_WARN_ON_ONCE(!list_empty(list)); @@ -5237,7 +5237,7 @@ done: static bool __maybe_unused state_is_valid(struct lruvec *lruvec) { - struct lru_gen_struct *lrugen = &lruvec->lrugen; + struct lru_gen_folio *lrugen = &lruvec->lrugen; if (lrugen->enabled) { enum lru_list lru; @@ -5519,7 +5519,7 @@ static void lru_gen_seq_show_full(struct int i; int type, tier; int hist = lru_hist_from_seq(seq); - struct lru_gen_struct *lrugen = &lruvec->lrugen; + struct lru_gen_folio *lrugen = &lruvec->lrugen; for (tier = 0; tier < MAX_NR_TIERS; tier++) { seq_printf(m, " %10d", tier); @@ -5569,7 +5569,7 @@ static int lru_gen_seq_show(struct seq_f unsigned long seq; bool full = !debugfs_real_fops(m->file)->write; struct lruvec *lruvec = v; - struct lru_gen_struct *lrugen = &lruvec->lrugen; + struct lru_gen_folio *lrugen = &lruvec->lrugen; int nid = lruvec_pgdat(lruvec)->node_id; struct mem_cgroup *memcg = lruvec_memcg(lruvec); DEFINE_MAX_SEQ(lruvec); @@ -5823,7 +5823,7 @@ void lru_gen_init_lruvec(struct lruvec * { int i; int gen, type, zone; - struct lru_gen_struct *lrugen = &lruvec->lrugen; + struct lru_gen_folio *lrugen = &lruvec->lrugen; lrugen->max_seq = MIN_NR_GENS + 1; lrugen->enabled = lru_gen_enabled(); --- a/mm/workingset.c +++ b/mm/workingset.c @@ -223,7 +223,7 @@ static void *lru_gen_eviction(struct fol unsigned long token; unsigned long min_seq; struct lruvec *lruvec; - struct lru_gen_struct *lrugen; + struct lru_gen_folio *lrugen; int type = folio_is_file_lru(folio); int delta = folio_nr_pages(folio); int refs = folio_lru_refs(folio); @@ -252,7 +252,7 @@ static void lru_gen_refault(struct folio unsigned long token; unsigned long min_seq; struct lruvec *lruvec; - struct lru_gen_struct *lrugen; + struct lru_gen_folio *lrugen; struct mem_cgroup *memcg; struct pglist_data *pgdat; int type = folio_is_file_lru(folio);