shinys000114/linux
1
0
Fork 0
mirror of https://github.com/hardkernel/linux.git synced 2026-03-25 20:10:23 +09:00
Code Issues Packages Projects Releases Wiki Activity

FROMLIST: mm: multi-gen LRU: optimize multiple memcgs

Browse Source 
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): -[23, 25]%
                         IOPS         BW
      patch1-8:          2960k        11.3GiB/s
      patch1-9:          2248k        8783MiB/s

    memcached (anon): +[210, 214]%
                         Ops/sec      KB/sec
      patch1-8:          606940.09    23576.89
      patch1-9:          1895197.49   73619.93

  Mixed workloads:
    fio (buffered I/O): -[4, 6]%
                         IOPS         BW
      5.18-ed4643521e6a: 2369k        9255MiB/s
      patch1-9:          2248k        8783MiB/s

    memcached (anon): +[510, 516]%
                         Ops/sec      KB/sec
      5.18-ed4643521e6a: 309189.58    12010.61
      patch1-9:          1895197.49   73619.93

  Configurations:
    (changes since patch 6)

    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)

Link: https://lore.kernel.org/r/20220309021230.721028-10-yuzhao@google.com/
Signed-off-by: Yu Zhao <yuzhao@google.com>
Acked-by: Brian Geffon <bgeffon@google.com>
Acked-by: Jan Alexander Steffens (heftig) <heftig@archlinux.org>
Acked-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Acked-by: Steven Barrett <steven@liquorix.net>
Acked-by: Suleiman Souhlal <suleiman@google.com>
Tested-by: Daniel Byrne <djbyrne@mtu.edu>
Tested-by: Donald Carr <d@chaos-reins.com>
Tested-by: Holger Hoffstätte <holger@applied-asynchrony.com>
Tested-by: Konstantin Kharlamov <Hi-Angel@yandex.ru>
Tested-by: Shuang Zhai <szhai2@cs.rochester.edu>
Tested-by: Sofia Trinh <sofia.trinh@edi.works>
Tested-by: Vaibhav Jain <vaibhav@linux.ibm.com>
Bug: 227651406
Signed-off-by: Kalesh Singh <kaleshsingh@google.com>
Change-Id: I0641467dbd7c5ba0645602cec7fe8d6fdb750edb
This commit is contained in:
Yu Zhao
2022-01-27 19:59:54 -07:00
committed by Todd Kjos
parent 93c4f86793
commit 082bc8296a
1 changed files with 42 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

47
mm/vmscan.c
View File

@@ -131,6 +131,13 @@ struct scan_control {
/* The file pages on the current node are dangerously low */
unsigned int file_is_tiny: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;
@@ -3933,6 +3940,22 @@ 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);
@@ -4334,7 +4357,8 @@ static int isolate_pages(struct lruvec *lruvec, struct scan_control *sc, int swa
return scanned;
}
static int evict_pages(struct lruvec *lruvec, struct scan_control *sc, int swappiness)
static int evict_pages(struct lruvec *lruvec, struct scan_control *sc, int swappiness,
bool *swapped)
{
int type;
int scanned;
@@ -4399,6 +4423,9 @@ static int evict_pages(struct lruvec *lruvec, struct scan_control *sc, int swapp
sc->nr_reclaimed += reclaimed;
if (type == LRU_GEN_ANON && swapped)
*swapped = true;
return scanned;
}
@@ -4427,8 +4454,10 @@ 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())
@@ -4450,6 +4479,8 @@ 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();
@@ -4475,14 +4506,20 @@ static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc
if (!nr_to_scan)
break;
delta = evict_pages(lruvec, sc, swappiness);
delta = evict_pages(lruvec, sc, swappiness, &swapped);
if (!delta)
break;
scanned += delta;
if (scanned >= nr_to_scan)
if (sc->memcgs_avoid_swapping && swappiness < 200 && swapped)
break;
scanned += delta;
if (scanned >= nr_to_scan) {
if (!swapped && sc->nr_reclaimed - reclaimed >= MIN_LRU_BATCH)
sc->memcgs_need_swapping = false;
break;
}
cond_resched();
}