summaryrefslogtreecommitdiff
path: root/mm/workingset.c
diff options
context:
space:
mode:
authorYu Zhao <yuzhao@google.com>2022-09-18 02:00:03 -0600
committerAndrew Morton <akpm@linux-foundation.org>2022-09-26 19:46:09 -0700
commitac35a490237446b71e3b4b782b1596967edd0aa8 (patch)
tree19cf96f257e5dadd2324f260b60d9814a40c82a0 /mm/workingset.c
parentec1c86b25f4bdd9dce6436c0539d2a6ae676e1c4 (diff)
mm: multi-gen LRU: minimal implementation
To avoid confusion, the terms "promotion" and "demotion" will be applied to the multi-gen LRU, as a new convention; the terms "activation" and "deactivation" will be applied to the active/inactive LRU, as usual. The aging produces young generations. Given an lruvec, it increments max_seq when max_seq-min_seq+1 approaches MIN_NR_GENS. The aging promotes hot pages to the youngest generation when it finds them accessed through page tables; the demotion of cold pages happens consequently when it increments max_seq. Promotion in the aging path does not involve any LRU list operations, only the updates of the gen counter and lrugen->nr_pages[]; demotion, unless as the result of the increment of max_seq, requires LRU list operations, e.g., lru_deactivate_fn(). The aging has the complexity O(nr_hot_pages), since it is only interested in hot pages. The eviction consumes old generations. Given an lruvec, it increments min_seq when lrugen->lists[] indexed by min_seq%MAX_NR_GENS becomes empty. A feedback loop modeled after the PID controller monitors refaults over anon and file types and decides which type to evict when both types are available from the same generation. The protection of pages accessed multiple times through file descriptors takes place in the eviction path. Each generation is divided into multiple tiers. A page accessed N times through file descriptors is in tier order_base_2(N). Tiers do not have dedicated lrugen->lists[], only bits in folio->flags. The aforementioned feedback loop also monitors refaults over all tiers and decides when to protect pages in which tiers (N>1), using the first tier (N=0,1) as a baseline. The first tier contains single-use unmapped clean pages, which are most likely the best choices. In contrast to promotion in the aging path, the protection of a page in the eviction path is achieved by moving this page to the next generation, i.e., min_seq+1, if the feedback loop decides so. This approach has the following advantages: 1. It removes the cost of activation in the buffered access path by inferring whether pages accessed multiple times through file descriptors are statistically hot and thus worth protecting in the eviction path. 2. It takes pages accessed through page tables into account and avoids overprotecting pages accessed multiple times through file descriptors. (Pages accessed through page tables are in the first tier, since N=0.) 3. More tiers provide better protection for pages accessed more than twice through file descriptors, when under heavy buffered I/O workloads. Server benchmark results: Single workload: fio (buffered I/O): +[30, 32]% IOPS BW 5.19-rc1: 2673k 10.2GiB/s patch1-6: 3491k 13.3GiB/s Single workload: memcached (anon): -[4, 6]% Ops/sec KB/sec 5.19-rc1: 1161501.04 45177.25 patch1-6: 1106168.46 43025.04 Configurations: CPU: two Xeon 6154 Mem: total 256G Node 1 was only used as a ram disk to reduce the variance in the results. patch drivers/block/brd.c <<EOF 99,100c99,100 < gfp_flags = GFP_NOIO | __GFP_ZERO | __GFP_HIGHMEM; < page = alloc_page(gfp_flags); --- > gfp_flags = GFP_NOIO | __GFP_ZERO | __GFP_HIGHMEM | __GFP_THISNODE; > page = alloc_pages_node(1, gfp_flags, 0); EOF cat >>/etc/systemd/system.conf <<EOF CPUAffinity=numa NUMAPolicy=bind NUMAMask=0 EOF cat >>/etc/memcached.conf <<EOF -m 184320 -s /var/run/memcached/memcached.sock -a 0766 -t 36 -B binary EOF cat fio.sh modprobe brd rd_nr=1 rd_size=113246208 swapoff -a mkfs.ext4 /dev/ram0 mount -t ext4 /dev/ram0 /mnt mkdir /sys/fs/cgroup/user.slice/test echo 38654705664 >/sys/fs/cgroup/user.slice/test/memory.max echo $$ >/sys/fs/cgroup/user.slice/test/cgroup.procs fio -name=mglru --numjobs=72 --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=5m --group_reporting cat memcached.sh modprobe brd rd_nr=1 rd_size=113246208 swapoff -a mkswap /dev/ram0 swapon /dev/ram0 memtier_benchmark -S /var/run/memcached/memcached.sock \ -P memcache_binary -n allkeys --key-minimum=1 \ --key-maximum=65000000 --key-pattern=P:P -c 1 -t 36 \ --ratio 1:0 --pipeline 8 -d 2000 memtier_benchmark -S /var/run/memcached/memcached.sock \ -P memcache_binary -n allkeys --key-minimum=1 \ --key-maximum=65000000 --key-pattern=R:R -c 1 -t 36 \ --ratio 0:1 --pipeline 8 --randomize --distinct-client-seed Client benchmark results: kswapd profiles: 5.19-rc1 40.33% page_vma_mapped_walk (overhead) 21.80% lzo1x_1_do_compress (real work) 7.53% do_raw_spin_lock 3.95% _raw_spin_unlock_irq 2.52% vma_interval_tree_iter_next 2.37% folio_referenced_one 2.28% vma_interval_tree_subtree_search 1.97% anon_vma_interval_tree_iter_first 1.60% ptep_clear_flush 1.06% __zram_bvec_write patch1-6 39.03% lzo1x_1_do_compress (real work) 18.47% page_vma_mapped_walk (overhead) 6.74% _raw_spin_unlock_irq 3.97% do_raw_spin_lock 2.49% ptep_clear_flush 2.48% anon_vma_interval_tree_iter_first 1.92% folio_referenced_one 1.88% __zram_bvec_write 1.48% memmove 1.31% vma_interval_tree_iter_next Configurations: CPU: single Snapdragon 7c Mem: total 4G ChromeOS MemoryPressure [1] [1] https://chromium.googlesource.com/chromiumos/platform/tast-tests/ Link: https://lkml.kernel.org/r/20220918080010.2920238-7-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> Cc: Andi Kleen <ak@linux.intel.com> Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com> Cc: Barry Song <baohua@kernel.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Hillf Danton <hdanton@sina.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Matthew Wilcox <willy@infradead.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Michael Larabel <Michael@MichaelLarabel.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Mike Rapoport <rppt@kernel.org> Cc: Mike Rapoport <rppt@linux.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Qi Zheng <zhengqi.arch@bytedance.com> Cc: Tejun Heo <tj@kernel.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Will Deacon <will@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Diffstat (limited to 'mm/workingset.c')
-rw-r--r--mm/workingset.c110
1 files changed, 108 insertions, 2 deletions
diff --git a/mm/workingset.c b/mm/workingset.c
index a5e84862fc86..ae7e984b23c6 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -187,7 +187,6 @@ static unsigned int bucket_order __read_mostly;
static void *pack_shadow(int memcgid, pg_data_t *pgdat, unsigned long eviction,
bool workingset)
{
- eviction >>= bucket_order;
eviction &= EVICTION_MASK;
eviction = (eviction << MEM_CGROUP_ID_SHIFT) | memcgid;
eviction = (eviction << NODES_SHIFT) | pgdat->node_id;
@@ -212,10 +211,107 @@ static void unpack_shadow(void *shadow, int *memcgidp, pg_data_t **pgdat,
*memcgidp = memcgid;
*pgdat = NODE_DATA(nid);
- *evictionp = entry << bucket_order;
+ *evictionp = entry;
*workingsetp = workingset;
}
+#ifdef CONFIG_LRU_GEN
+
+static void *lru_gen_eviction(struct folio *folio)
+{
+ int hist;
+ unsigned long token;
+ unsigned long min_seq;
+ struct lruvec *lruvec;
+ struct lru_gen_struct *lrugen;
+ int type = folio_is_file_lru(folio);
+ int delta = folio_nr_pages(folio);
+ int refs = folio_lru_refs(folio);
+ int tier = lru_tier_from_refs(refs);
+ struct mem_cgroup *memcg = folio_memcg(folio);
+ struct pglist_data *pgdat = folio_pgdat(folio);
+
+ BUILD_BUG_ON(LRU_GEN_WIDTH + LRU_REFS_WIDTH > BITS_PER_LONG - EVICTION_SHIFT);
+
+ lruvec = mem_cgroup_lruvec(memcg, pgdat);
+ lrugen = &lruvec->lrugen;
+ min_seq = READ_ONCE(lrugen->min_seq[type]);
+ token = (min_seq << LRU_REFS_WIDTH) | max(refs - 1, 0);
+
+ hist = lru_hist_from_seq(min_seq);
+ atomic_long_add(delta, &lrugen->evicted[hist][type][tier]);
+
+ return pack_shadow(mem_cgroup_id(memcg), pgdat, token, refs);
+}
+
+static void lru_gen_refault(struct folio *folio, void *shadow)
+{
+ int hist, tier, refs;
+ int memcg_id;
+ bool workingset;
+ unsigned long token;
+ unsigned long min_seq;
+ struct lruvec *lruvec;
+ struct lru_gen_struct *lrugen;
+ struct mem_cgroup *memcg;
+ struct pglist_data *pgdat;
+ int type = folio_is_file_lru(folio);
+ int delta = folio_nr_pages(folio);
+
+ unpack_shadow(shadow, &memcg_id, &pgdat, &token, &workingset);
+
+ if (pgdat != folio_pgdat(folio))
+ return;
+
+ rcu_read_lock();
+
+ memcg = folio_memcg_rcu(folio);
+ if (memcg_id != mem_cgroup_id(memcg))
+ goto unlock;
+
+ lruvec = mem_cgroup_lruvec(memcg, pgdat);
+ lrugen = &lruvec->lrugen;
+
+ min_seq = READ_ONCE(lrugen->min_seq[type]);
+ if ((token >> LRU_REFS_WIDTH) != (min_seq & (EVICTION_MASK >> LRU_REFS_WIDTH)))
+ goto unlock;
+
+ hist = lru_hist_from_seq(min_seq);
+ /* see the comment in folio_lru_refs() */
+ refs = (token & (BIT(LRU_REFS_WIDTH) - 1)) + workingset;
+ tier = lru_tier_from_refs(refs);
+
+ atomic_long_add(delta, &lrugen->refaulted[hist][type][tier]);
+ mod_lruvec_state(lruvec, WORKINGSET_REFAULT_BASE + type, delta);
+
+ /*
+ * Count the following two cases as stalls:
+ * 1. For pages accessed through page tables, hotter pages pushed out
+ * hot pages which refaulted immediately.
+ * 2. For pages accessed multiple times through file descriptors,
+ * numbers of accesses might have been out of the range.
+ */
+ if (lru_gen_in_fault() || refs == BIT(LRU_REFS_WIDTH)) {
+ folio_set_workingset(folio);
+ mod_lruvec_state(lruvec, WORKINGSET_RESTORE_BASE + type, delta);
+ }
+unlock:
+ rcu_read_unlock();
+}
+
+#else /* !CONFIG_LRU_GEN */
+
+static void *lru_gen_eviction(struct folio *folio)
+{
+ return NULL;
+}
+
+static void lru_gen_refault(struct folio *folio, void *shadow)
+{
+}
+
+#endif /* CONFIG_LRU_GEN */
+
/**
* workingset_age_nonresident - age non-resident entries as LRU ages
* @lruvec: the lruvec that was aged
@@ -264,10 +360,14 @@ void *workingset_eviction(struct folio *folio, struct mem_cgroup *target_memcg)
VM_BUG_ON_FOLIO(folio_ref_count(folio), folio);
VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
+ if (lru_gen_enabled())
+ return lru_gen_eviction(folio);
+
lruvec = mem_cgroup_lruvec(target_memcg, pgdat);
/* XXX: target_memcg can be NULL, go through lruvec */
memcgid = mem_cgroup_id(lruvec_memcg(lruvec));
eviction = atomic_long_read(&lruvec->nonresident_age);
+ eviction >>= bucket_order;
workingset_age_nonresident(lruvec, folio_nr_pages(folio));
return pack_shadow(memcgid, pgdat, eviction,
folio_test_workingset(folio));
@@ -298,7 +398,13 @@ void workingset_refault(struct folio *folio, void *shadow)
int memcgid;
long nr;
+ if (lru_gen_enabled()) {
+ lru_gen_refault(folio, shadow);
+ return;
+ }
+
unpack_shadow(shadow, &memcgid, &pgdat, &eviction, &workingset);
+ eviction <<= bucket_order;
rcu_read_lock();
/*