When multiple memcgs are available, it is possible to make better choices based on generations and tiers and therefore improve the overall performance under global memory pressure. This patch adds a rudimentary optimization to select memcgs that can drop single-use unmapped clean pages first. Doing so reduces the chance of going into the aging path or swapping. These two operations can be costly. A typical example that benefits from this optimization is a server running mixed types of workloads, e.g., heavy anon workload in one memcg and heavy buffered I/O workload in the other. Though this optimization can be applied to both kswapd and direct reclaim, it is only added to kswapd to keep the patchset manageable. Later improvements will cover the direct reclaim path. Server benchmark results: Mixed workloads: fio (buffered I/O): -[28, 30]% IOPS BW patch1-7: 3117k 11.9GiB/s patch1-8: 2217k 8661MiB/s memcached (anon): +[247, 251]% Ops/sec KB/sec patch1-7: 563772.35 21900.01 patch1-8: 1968343.76 76461.24 Mixed workloads: fio (buffered I/O): -[4, 6]% IOPS BW 5.17-rc2: 2338k 9133MiB/s patch1-8: 2217k 8661MiB/s memcached (anon): +[524, 530]% Ops/sec KB/sec 5.17-rc2: 313821.65 12190.55 patch1-8: 1968343.76 76461.24 Configurations: (changes since patch 5) cat mixed.sh modprobe brd rd_nr=2 rd_size=56623104 swapoff -a mkswap /dev/ram0 swapon /dev/ram0 mkfs.ext4 /dev/ram1 mount -t ext4 /dev/ram1 /mnt memtier_benchmark -S /var/run/memcached/memcached.sock \ -P memcache_binary -n allkeys --key-minimum=1 \ --key-maximum=50000000 --key-pattern=P:P -c 1 -t 36 \ --ratio 1:0 --pipeline 8 -d 2000 fio -name=mglru --numjobs=36 --directory=/mnt --size=1408m \ --buffered=1 --ioengine=io_uring --iodepth=128 \ --iodepth_batch_submit=32 --iodepth_batch_complete=32 \ --rw=randread --random_distribution=random --norandommap \ --time_based --ramp_time=10m --runtime=90m --group_reporting & pid=$! sleep 200 memtier_benchmark -S /var/run/memcached/memcached.sock \ -P memcache_binary -n allkeys --key-minimum=1 \ --key-maximum=50000000 --key-pattern=R:R -c 1 -t 36 \ --ratio 0:1 --pipeline 8 --randomize --distinct-client-seed kill -INT $pid wait Client benchmark results: no change (CONFIG_MEMCG=n) Signed-off-by: Yu Zhao <yuzhao@xxxxxxxxxx> Acked-by: Brian Geffon <bgeffon@xxxxxxxxxx> Acked-by: Jan Alexander Steffens (heftig) <heftig@xxxxxxxxxxxxx> Acked-by: Oleksandr Natalenko <oleksandr@xxxxxxxxxxxxxx> Acked-by: Steven Barrett <steven@xxxxxxxxxxxx> Acked-by: Suleiman Souhlal <suleiman@xxxxxxxxxx> Tested-by: Daniel Byrne <djbyrne@xxxxxxx> Tested-by: Donald Carr <d@xxxxxxxxxxxxxxx> Tested-by: Holger Hoffstätte <holger@xxxxxxxxxxxxxxxxxxxxxx> Tested-by: Konstantin Kharlamov <Hi-Angel@xxxxxxxxx> Tested-by: Shuang Zhai <szhai2@xxxxxxxxxxxxxxxx> Tested-by: Sofia Trinh <sofia.trinh@edi.works> Tested-by: Vaibhav Jain <vaibhav@xxxxxxxxxxxxx> --- mm/vmscan.c | 45 +++++++++++++++++++++++++++++++++++++++++---- 1 file changed, 41 insertions(+), 4 deletions(-) diff --git a/mm/vmscan.c b/mm/vmscan.c index 67dc4190e790..7375c9dae08f 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -127,6 +127,13 @@ struct scan_control { /* Always discard instead of demoting to lower tier memory */ unsigned int no_demotion:1; +#ifdef CONFIG_LRU_GEN + /* help make better choices when multiple memcgs are available */ + unsigned int memcgs_need_aging:1; + unsigned int memcgs_need_swapping:1; + unsigned int memcgs_avoid_swapping:1; +#endif + /* Allocation order */ s8 order; @@ -4348,6 +4355,22 @@ static void lru_gen_age_node(struct pglist_data *pgdat, struct scan_control *sc) VM_BUG_ON(!current_is_kswapd()); + /* + * To reduce the chance of going into the aging path or swapping, which + * can be costly, optimistically skip them unless their corresponding + * flags were cleared in the eviction path. This improves the overall + * performance when multiple memcgs are available. + */ + if (!sc->memcgs_need_aging) { + sc->memcgs_need_aging = true; + sc->memcgs_avoid_swapping = !sc->memcgs_need_swapping; + sc->memcgs_need_swapping = true; + return; + } + + sc->memcgs_need_swapping = true; + sc->memcgs_avoid_swapping = true; + current->reclaim_state->mm_walk = &pgdat->mm_walk; memcg = mem_cgroup_iter(NULL, NULL, NULL); @@ -4750,7 +4773,8 @@ static int isolate_folios(struct lruvec *lruvec, struct scan_control *sc, int sw return scanned; } -static int evict_folios(struct lruvec *lruvec, struct scan_control *sc, int swappiness) +static int evict_folios(struct lruvec *lruvec, struct scan_control *sc, int swappiness, + bool *swapped) { int type; int scanned; @@ -4816,6 +4840,9 @@ static int evict_folios(struct lruvec *lruvec, struct scan_control *sc, int swap sc->nr_reclaimed += reclaimed; + if (type == LRU_GEN_ANON && swapped) + *swapped = true; + return scanned; } @@ -4844,8 +4871,10 @@ static long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *sc, bool if (!nr_to_scan) return 0; - if (!need_aging) + if (!need_aging) { + sc->memcgs_need_aging = false; return nr_to_scan; + } /* leave the work to lru_gen_age_node() */ if (current_is_kswapd()) @@ -4867,6 +4896,8 @@ static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc { struct blk_plug plug; long scanned = 0; + bool swapped = false; + unsigned long reclaimed = sc->nr_reclaimed; struct pglist_data *pgdat = lruvec_pgdat(lruvec); lru_add_drain(); @@ -4892,13 +4923,19 @@ static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc if (!nr_to_scan) break; - delta = evict_folios(lruvec, sc, swappiness); + delta = evict_folios(lruvec, sc, swappiness, &swapped); if (!delta) break; + if (sc->memcgs_avoid_swapping && swappiness < 200 && swapped) + break; + scanned += delta; - if (scanned >= nr_to_scan) + if (scanned >= nr_to_scan) { + if (!swapped && sc->nr_reclaimed - reclaimed >= MIN_LRU_BATCH) + sc->memcgs_need_swapping = false; break; + } cond_resched(); } -- 2.35.1.616.g0bdcbb4464-goog