mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-26 02:39:48 +00:00
![Yu Zhao](/assets/img/avatar_default.png)
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>
748 lines
24 KiB
C
748 lines
24 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
/*
|
|
* Workingset detection
|
|
*
|
|
* Copyright (C) 2013 Red Hat, Inc., Johannes Weiner
|
|
*/
|
|
|
|
#include <linux/memcontrol.h>
|
|
#include <linux/mm_inline.h>
|
|
#include <linux/writeback.h>
|
|
#include <linux/shmem_fs.h>
|
|
#include <linux/pagemap.h>
|
|
#include <linux/atomic.h>
|
|
#include <linux/module.h>
|
|
#include <linux/swap.h>
|
|
#include <linux/dax.h>
|
|
#include <linux/fs.h>
|
|
#include <linux/mm.h>
|
|
|
|
/*
|
|
* Double CLOCK lists
|
|
*
|
|
* Per node, two clock lists are maintained for file pages: the
|
|
* inactive and the active list. Freshly faulted pages start out at
|
|
* the head of the inactive list and page reclaim scans pages from the
|
|
* tail. Pages that are accessed multiple times on the inactive list
|
|
* are promoted to the active list, to protect them from reclaim,
|
|
* whereas active pages are demoted to the inactive list when the
|
|
* active list grows too big.
|
|
*
|
|
* fault ------------------------+
|
|
* |
|
|
* +--------------+ | +-------------+
|
|
* reclaim <- | inactive | <-+-- demotion | active | <--+
|
|
* +--------------+ +-------------+ |
|
|
* | |
|
|
* +-------------- promotion ------------------+
|
|
*
|
|
*
|
|
* Access frequency and refault distance
|
|
*
|
|
* A workload is thrashing when its pages are frequently used but they
|
|
* are evicted from the inactive list every time before another access
|
|
* would have promoted them to the active list.
|
|
*
|
|
* In cases where the average access distance between thrashing pages
|
|
* is bigger than the size of memory there is nothing that can be
|
|
* done - the thrashing set could never fit into memory under any
|
|
* circumstance.
|
|
*
|
|
* However, the average access distance could be bigger than the
|
|
* inactive list, yet smaller than the size of memory. In this case,
|
|
* the set could fit into memory if it weren't for the currently
|
|
* active pages - which may be used more, hopefully less frequently:
|
|
*
|
|
* +-memory available to cache-+
|
|
* | |
|
|
* +-inactive------+-active----+
|
|
* a b | c d e f g h i | J K L M N |
|
|
* +---------------+-----------+
|
|
*
|
|
* It is prohibitively expensive to accurately track access frequency
|
|
* of pages. But a reasonable approximation can be made to measure
|
|
* thrashing on the inactive list, after which refaulting pages can be
|
|
* activated optimistically to compete with the existing active pages.
|
|
*
|
|
* Approximating inactive page access frequency - Observations:
|
|
*
|
|
* 1. When a page is accessed for the first time, it is added to the
|
|
* head of the inactive list, slides every existing inactive page
|
|
* towards the tail by one slot, and pushes the current tail page
|
|
* out of memory.
|
|
*
|
|
* 2. When a page is accessed for the second time, it is promoted to
|
|
* the active list, shrinking the inactive list by one slot. This
|
|
* also slides all inactive pages that were faulted into the cache
|
|
* more recently than the activated page towards the tail of the
|
|
* inactive list.
|
|
*
|
|
* Thus:
|
|
*
|
|
* 1. The sum of evictions and activations between any two points in
|
|
* time indicate the minimum number of inactive pages accessed in
|
|
* between.
|
|
*
|
|
* 2. Moving one inactive page N page slots towards the tail of the
|
|
* list requires at least N inactive page accesses.
|
|
*
|
|
* Combining these:
|
|
*
|
|
* 1. When a page is finally evicted from memory, the number of
|
|
* inactive pages accessed while the page was in cache is at least
|
|
* the number of page slots on the inactive list.
|
|
*
|
|
* 2. In addition, measuring the sum of evictions and activations (E)
|
|
* at the time of a page's eviction, and comparing it to another
|
|
* reading (R) at the time the page faults back into memory tells
|
|
* the minimum number of accesses while the page was not cached.
|
|
* This is called the refault distance.
|
|
*
|
|
* Because the first access of the page was the fault and the second
|
|
* access the refault, we combine the in-cache distance with the
|
|
* out-of-cache distance to get the complete minimum access distance
|
|
* of this page:
|
|
*
|
|
* NR_inactive + (R - E)
|
|
*
|
|
* And knowing the minimum access distance of a page, we can easily
|
|
* tell if the page would be able to stay in cache assuming all page
|
|
* slots in the cache were available:
|
|
*
|
|
* NR_inactive + (R - E) <= NR_inactive + NR_active
|
|
*
|
|
* which can be further simplified to
|
|
*
|
|
* (R - E) <= NR_active
|
|
*
|
|
* Put into words, the refault distance (out-of-cache) can be seen as
|
|
* a deficit in inactive list space (in-cache). If the inactive list
|
|
* had (R - E) more page slots, the page would not have been evicted
|
|
* in between accesses, but activated instead. And on a full system,
|
|
* the only thing eating into inactive list space is active pages.
|
|
*
|
|
*
|
|
* Refaulting inactive pages
|
|
*
|
|
* All that is known about the active list is that the pages have been
|
|
* accessed more than once in the past. This means that at any given
|
|
* time there is actually a good chance that pages on the active list
|
|
* are no longer in active use.
|
|
*
|
|
* So when a refault distance of (R - E) is observed and there are at
|
|
* least (R - E) active pages, the refaulting page is activated
|
|
* optimistically in the hope that (R - E) active pages are actually
|
|
* used less frequently than the refaulting page - or even not used at
|
|
* all anymore.
|
|
*
|
|
* That means if inactive cache is refaulting with a suitable refault
|
|
* distance, we assume the cache workingset is transitioning and put
|
|
* pressure on the current active list.
|
|
*
|
|
* If this is wrong and demotion kicks in, the pages which are truly
|
|
* used more frequently will be reactivated while the less frequently
|
|
* used once will be evicted from memory.
|
|
*
|
|
* But if this is right, the stale pages will be pushed out of memory
|
|
* and the used pages get to stay in cache.
|
|
*
|
|
* Refaulting active pages
|
|
*
|
|
* If on the other hand the refaulting pages have recently been
|
|
* deactivated, it means that the active list is no longer protecting
|
|
* actively used cache from reclaim. The cache is NOT transitioning to
|
|
* a different workingset; the existing workingset is thrashing in the
|
|
* space allocated to the page cache.
|
|
*
|
|
*
|
|
* Implementation
|
|
*
|
|
* For each node's LRU lists, a counter for inactive evictions and
|
|
* activations is maintained (node->nonresident_age).
|
|
*
|
|
* On eviction, a snapshot of this counter (along with some bits to
|
|
* identify the node) is stored in the now empty page cache
|
|
* slot of the evicted page. This is called a shadow entry.
|
|
*
|
|
* On cache misses for which there are shadow entries, an eligible
|
|
* refault distance will immediately activate the refaulting page.
|
|
*/
|
|
|
|
#define WORKINGSET_SHIFT 1
|
|
#define EVICTION_SHIFT ((BITS_PER_LONG - BITS_PER_XA_VALUE) + \
|
|
WORKINGSET_SHIFT + NODES_SHIFT + \
|
|
MEM_CGROUP_ID_SHIFT)
|
|
#define EVICTION_MASK (~0UL >> EVICTION_SHIFT)
|
|
|
|
/*
|
|
* Eviction timestamps need to be able to cover the full range of
|
|
* actionable refaults. However, bits are tight in the xarray
|
|
* entry, and after storing the identifier for the lruvec there might
|
|
* not be enough left to represent every single actionable refault. In
|
|
* that case, we have to sacrifice granularity for distance, and group
|
|
* evictions into coarser buckets by shaving off lower timestamp bits.
|
|
*/
|
|
static unsigned int bucket_order __read_mostly;
|
|
|
|
static void *pack_shadow(int memcgid, pg_data_t *pgdat, unsigned long eviction,
|
|
bool workingset)
|
|
{
|
|
eviction &= EVICTION_MASK;
|
|
eviction = (eviction << MEM_CGROUP_ID_SHIFT) | memcgid;
|
|
eviction = (eviction << NODES_SHIFT) | pgdat->node_id;
|
|
eviction = (eviction << WORKINGSET_SHIFT) | workingset;
|
|
|
|
return xa_mk_value(eviction);
|
|
}
|
|
|
|
static void unpack_shadow(void *shadow, int *memcgidp, pg_data_t **pgdat,
|
|
unsigned long *evictionp, bool *workingsetp)
|
|
{
|
|
unsigned long entry = xa_to_value(shadow);
|
|
int memcgid, nid;
|
|
bool workingset;
|
|
|
|
workingset = entry & ((1UL << WORKINGSET_SHIFT) - 1);
|
|
entry >>= WORKINGSET_SHIFT;
|
|
nid = entry & ((1UL << NODES_SHIFT) - 1);
|
|
entry >>= NODES_SHIFT;
|
|
memcgid = entry & ((1UL << MEM_CGROUP_ID_SHIFT) - 1);
|
|
entry >>= MEM_CGROUP_ID_SHIFT;
|
|
|
|
*memcgidp = memcgid;
|
|
*pgdat = NODE_DATA(nid);
|
|
*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
|
|
* @nr_pages: the number of pages to count
|
|
*
|
|
* As in-memory pages are aged, non-resident pages need to be aged as
|
|
* well, in order for the refault distances later on to be comparable
|
|
* to the in-memory dimensions. This function allows reclaim and LRU
|
|
* operations to drive the non-resident aging along in parallel.
|
|
*/
|
|
void workingset_age_nonresident(struct lruvec *lruvec, unsigned long nr_pages)
|
|
{
|
|
/*
|
|
* Reclaiming a cgroup means reclaiming all its children in a
|
|
* round-robin fashion. That means that each cgroup has an LRU
|
|
* order that is composed of the LRU orders of its child
|
|
* cgroups; and every page has an LRU position not just in the
|
|
* cgroup that owns it, but in all of that group's ancestors.
|
|
*
|
|
* So when the physical inactive list of a leaf cgroup ages,
|
|
* the virtual inactive lists of all its parents, including
|
|
* the root cgroup's, age as well.
|
|
*/
|
|
do {
|
|
atomic_long_add(nr_pages, &lruvec->nonresident_age);
|
|
} while ((lruvec = parent_lruvec(lruvec)));
|
|
}
|
|
|
|
/**
|
|
* workingset_eviction - note the eviction of a folio from memory
|
|
* @target_memcg: the cgroup that is causing the reclaim
|
|
* @folio: the folio being evicted
|
|
*
|
|
* Return: a shadow entry to be stored in @folio->mapping->i_pages in place
|
|
* of the evicted @folio so that a later refault can be detected.
|
|
*/
|
|
void *workingset_eviction(struct folio *folio, struct mem_cgroup *target_memcg)
|
|
{
|
|
struct pglist_data *pgdat = folio_pgdat(folio);
|
|
unsigned long eviction;
|
|
struct lruvec *lruvec;
|
|
int memcgid;
|
|
|
|
/* Folio is fully exclusive and pins folio's memory cgroup pointer */
|
|
VM_BUG_ON_FOLIO(folio_test_lru(folio), folio);
|
|
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));
|
|
}
|
|
|
|
/**
|
|
* workingset_refault - Evaluate the refault of a previously evicted folio.
|
|
* @folio: The freshly allocated replacement folio.
|
|
* @shadow: Shadow entry of the evicted folio.
|
|
*
|
|
* Calculates and evaluates the refault distance of the previously
|
|
* evicted folio in the context of the node and the memcg whose memory
|
|
* pressure caused the eviction.
|
|
*/
|
|
void workingset_refault(struct folio *folio, void *shadow)
|
|
{
|
|
bool file = folio_is_file_lru(folio);
|
|
struct mem_cgroup *eviction_memcg;
|
|
struct lruvec *eviction_lruvec;
|
|
unsigned long refault_distance;
|
|
unsigned long workingset_size;
|
|
struct pglist_data *pgdat;
|
|
struct mem_cgroup *memcg;
|
|
unsigned long eviction;
|
|
struct lruvec *lruvec;
|
|
unsigned long refault;
|
|
bool workingset;
|
|
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();
|
|
/*
|
|
* Look up the memcg associated with the stored ID. It might
|
|
* have been deleted since the folio's eviction.
|
|
*
|
|
* Note that in rare events the ID could have been recycled
|
|
* for a new cgroup that refaults a shared folio. This is
|
|
* impossible to tell from the available data. However, this
|
|
* should be a rare and limited disturbance, and activations
|
|
* are always speculative anyway. Ultimately, it's the aging
|
|
* algorithm's job to shake out the minimum access frequency
|
|
* for the active cache.
|
|
*
|
|
* XXX: On !CONFIG_MEMCG, this will always return NULL; it
|
|
* would be better if the root_mem_cgroup existed in all
|
|
* configurations instead.
|
|
*/
|
|
eviction_memcg = mem_cgroup_from_id(memcgid);
|
|
if (!mem_cgroup_disabled() && !eviction_memcg)
|
|
goto out;
|
|
eviction_lruvec = mem_cgroup_lruvec(eviction_memcg, pgdat);
|
|
refault = atomic_long_read(&eviction_lruvec->nonresident_age);
|
|
|
|
/*
|
|
* Calculate the refault distance
|
|
*
|
|
* The unsigned subtraction here gives an accurate distance
|
|
* across nonresident_age overflows in most cases. There is a
|
|
* special case: usually, shadow entries have a short lifetime
|
|
* and are either refaulted or reclaimed along with the inode
|
|
* before they get too old. But it is not impossible for the
|
|
* nonresident_age to lap a shadow entry in the field, which
|
|
* can then result in a false small refault distance, leading
|
|
* to a false activation should this old entry actually
|
|
* refault again. However, earlier kernels used to deactivate
|
|
* unconditionally with *every* reclaim invocation for the
|
|
* longest time, so the occasional inappropriate activation
|
|
* leading to pressure on the active list is not a problem.
|
|
*/
|
|
refault_distance = (refault - eviction) & EVICTION_MASK;
|
|
|
|
/*
|
|
* The activation decision for this folio is made at the level
|
|
* where the eviction occurred, as that is where the LRU order
|
|
* during folio reclaim is being determined.
|
|
*
|
|
* However, the cgroup that will own the folio is the one that
|
|
* is actually experiencing the refault event.
|
|
*/
|
|
nr = folio_nr_pages(folio);
|
|
memcg = folio_memcg(folio);
|
|
lruvec = mem_cgroup_lruvec(memcg, pgdat);
|
|
|
|
mod_lruvec_state(lruvec, WORKINGSET_REFAULT_BASE + file, nr);
|
|
|
|
mem_cgroup_flush_stats_delayed();
|
|
/*
|
|
* Compare the distance to the existing workingset size. We
|
|
* don't activate pages that couldn't stay resident even if
|
|
* all the memory was available to the workingset. Whether
|
|
* workingset competition needs to consider anon or not depends
|
|
* on having swap.
|
|
*/
|
|
workingset_size = lruvec_page_state(eviction_lruvec, NR_ACTIVE_FILE);
|
|
if (!file) {
|
|
workingset_size += lruvec_page_state(eviction_lruvec,
|
|
NR_INACTIVE_FILE);
|
|
}
|
|
if (mem_cgroup_get_nr_swap_pages(memcg) > 0) {
|
|
workingset_size += lruvec_page_state(eviction_lruvec,
|
|
NR_ACTIVE_ANON);
|
|
if (file) {
|
|
workingset_size += lruvec_page_state(eviction_lruvec,
|
|
NR_INACTIVE_ANON);
|
|
}
|
|
}
|
|
if (refault_distance > workingset_size)
|
|
goto out;
|
|
|
|
folio_set_active(folio);
|
|
workingset_age_nonresident(lruvec, nr);
|
|
mod_lruvec_state(lruvec, WORKINGSET_ACTIVATE_BASE + file, nr);
|
|
|
|
/* Folio was active prior to eviction */
|
|
if (workingset) {
|
|
folio_set_workingset(folio);
|
|
/* XXX: Move to lru_cache_add() when it supports new vs putback */
|
|
lru_note_cost_folio(folio);
|
|
mod_lruvec_state(lruvec, WORKINGSET_RESTORE_BASE + file, nr);
|
|
}
|
|
out:
|
|
rcu_read_unlock();
|
|
}
|
|
|
|
/**
|
|
* workingset_activation - note a page activation
|
|
* @folio: Folio that is being activated.
|
|
*/
|
|
void workingset_activation(struct folio *folio)
|
|
{
|
|
struct mem_cgroup *memcg;
|
|
|
|
rcu_read_lock();
|
|
/*
|
|
* Filter non-memcg pages here, e.g. unmap can call
|
|
* mark_page_accessed() on VDSO pages.
|
|
*
|
|
* XXX: See workingset_refault() - this should return
|
|
* root_mem_cgroup even for !CONFIG_MEMCG.
|
|
*/
|
|
memcg = folio_memcg_rcu(folio);
|
|
if (!mem_cgroup_disabled() && !memcg)
|
|
goto out;
|
|
workingset_age_nonresident(folio_lruvec(folio), folio_nr_pages(folio));
|
|
out:
|
|
rcu_read_unlock();
|
|
}
|
|
|
|
/*
|
|
* Shadow entries reflect the share of the working set that does not
|
|
* fit into memory, so their number depends on the access pattern of
|
|
* the workload. In most cases, they will refault or get reclaimed
|
|
* along with the inode, but a (malicious) workload that streams
|
|
* through files with a total size several times that of available
|
|
* memory, while preventing the inodes from being reclaimed, can
|
|
* create excessive amounts of shadow nodes. To keep a lid on this,
|
|
* track shadow nodes and reclaim them when they grow way past the
|
|
* point where they would still be useful.
|
|
*/
|
|
|
|
struct list_lru shadow_nodes;
|
|
|
|
void workingset_update_node(struct xa_node *node)
|
|
{
|
|
struct address_space *mapping;
|
|
|
|
/*
|
|
* Track non-empty nodes that contain only shadow entries;
|
|
* unlink those that contain pages or are being freed.
|
|
*
|
|
* Avoid acquiring the list_lru lock when the nodes are
|
|
* already where they should be. The list_empty() test is safe
|
|
* as node->private_list is protected by the i_pages lock.
|
|
*/
|
|
mapping = container_of(node->array, struct address_space, i_pages);
|
|
lockdep_assert_held(&mapping->i_pages.xa_lock);
|
|
|
|
if (node->count && node->count == node->nr_values) {
|
|
if (list_empty(&node->private_list)) {
|
|
list_lru_add(&shadow_nodes, &node->private_list);
|
|
__inc_lruvec_kmem_state(node, WORKINGSET_NODES);
|
|
}
|
|
} else {
|
|
if (!list_empty(&node->private_list)) {
|
|
list_lru_del(&shadow_nodes, &node->private_list);
|
|
__dec_lruvec_kmem_state(node, WORKINGSET_NODES);
|
|
}
|
|
}
|
|
}
|
|
|
|
static unsigned long count_shadow_nodes(struct shrinker *shrinker,
|
|
struct shrink_control *sc)
|
|
{
|
|
unsigned long max_nodes;
|
|
unsigned long nodes;
|
|
unsigned long pages;
|
|
|
|
nodes = list_lru_shrink_count(&shadow_nodes, sc);
|
|
if (!nodes)
|
|
return SHRINK_EMPTY;
|
|
|
|
/*
|
|
* Approximate a reasonable limit for the nodes
|
|
* containing shadow entries. We don't need to keep more
|
|
* shadow entries than possible pages on the active list,
|
|
* since refault distances bigger than that are dismissed.
|
|
*
|
|
* The size of the active list converges toward 100% of
|
|
* overall page cache as memory grows, with only a tiny
|
|
* inactive list. Assume the total cache size for that.
|
|
*
|
|
* Nodes might be sparsely populated, with only one shadow
|
|
* entry in the extreme case. Obviously, we cannot keep one
|
|
* node for every eligible shadow entry, so compromise on a
|
|
* worst-case density of 1/8th. Below that, not all eligible
|
|
* refaults can be detected anymore.
|
|
*
|
|
* On 64-bit with 7 xa_nodes per page and 64 slots
|
|
* each, this will reclaim shadow entries when they consume
|
|
* ~1.8% of available memory:
|
|
*
|
|
* PAGE_SIZE / xa_nodes / node_entries * 8 / PAGE_SIZE
|
|
*/
|
|
#ifdef CONFIG_MEMCG
|
|
if (sc->memcg) {
|
|
struct lruvec *lruvec;
|
|
int i;
|
|
|
|
lruvec = mem_cgroup_lruvec(sc->memcg, NODE_DATA(sc->nid));
|
|
for (pages = 0, i = 0; i < NR_LRU_LISTS; i++)
|
|
pages += lruvec_page_state_local(lruvec,
|
|
NR_LRU_BASE + i);
|
|
pages += lruvec_page_state_local(
|
|
lruvec, NR_SLAB_RECLAIMABLE_B) >> PAGE_SHIFT;
|
|
pages += lruvec_page_state_local(
|
|
lruvec, NR_SLAB_UNRECLAIMABLE_B) >> PAGE_SHIFT;
|
|
} else
|
|
#endif
|
|
pages = node_present_pages(sc->nid);
|
|
|
|
max_nodes = pages >> (XA_CHUNK_SHIFT - 3);
|
|
|
|
if (nodes <= max_nodes)
|
|
return 0;
|
|
return nodes - max_nodes;
|
|
}
|
|
|
|
static enum lru_status shadow_lru_isolate(struct list_head *item,
|
|
struct list_lru_one *lru,
|
|
spinlock_t *lru_lock,
|
|
void *arg) __must_hold(lru_lock)
|
|
{
|
|
struct xa_node *node = container_of(item, struct xa_node, private_list);
|
|
struct address_space *mapping;
|
|
int ret;
|
|
|
|
/*
|
|
* Page cache insertions and deletions synchronously maintain
|
|
* the shadow node LRU under the i_pages lock and the
|
|
* lru_lock. Because the page cache tree is emptied before
|
|
* the inode can be destroyed, holding the lru_lock pins any
|
|
* address_space that has nodes on the LRU.
|
|
*
|
|
* We can then safely transition to the i_pages lock to
|
|
* pin only the address_space of the particular node we want
|
|
* to reclaim, take the node off-LRU, and drop the lru_lock.
|
|
*/
|
|
|
|
mapping = container_of(node->array, struct address_space, i_pages);
|
|
|
|
/* Coming from the list, invert the lock order */
|
|
if (!xa_trylock(&mapping->i_pages)) {
|
|
spin_unlock_irq(lru_lock);
|
|
ret = LRU_RETRY;
|
|
goto out;
|
|
}
|
|
|
|
if (!spin_trylock(&mapping->host->i_lock)) {
|
|
xa_unlock(&mapping->i_pages);
|
|
spin_unlock_irq(lru_lock);
|
|
ret = LRU_RETRY;
|
|
goto out;
|
|
}
|
|
|
|
list_lru_isolate(lru, item);
|
|
__dec_lruvec_kmem_state(node, WORKINGSET_NODES);
|
|
|
|
spin_unlock(lru_lock);
|
|
|
|
/*
|
|
* The nodes should only contain one or more shadow entries,
|
|
* no pages, so we expect to be able to remove them all and
|
|
* delete and free the empty node afterwards.
|
|
*/
|
|
if (WARN_ON_ONCE(!node->nr_values))
|
|
goto out_invalid;
|
|
if (WARN_ON_ONCE(node->count != node->nr_values))
|
|
goto out_invalid;
|
|
xa_delete_node(node, workingset_update_node);
|
|
__inc_lruvec_kmem_state(node, WORKINGSET_NODERECLAIM);
|
|
|
|
out_invalid:
|
|
xa_unlock_irq(&mapping->i_pages);
|
|
if (mapping_shrinkable(mapping))
|
|
inode_add_lru(mapping->host);
|
|
spin_unlock(&mapping->host->i_lock);
|
|
ret = LRU_REMOVED_RETRY;
|
|
out:
|
|
cond_resched();
|
|
spin_lock_irq(lru_lock);
|
|
return ret;
|
|
}
|
|
|
|
static unsigned long scan_shadow_nodes(struct shrinker *shrinker,
|
|
struct shrink_control *sc)
|
|
{
|
|
/* list_lru lock nests inside the IRQ-safe i_pages lock */
|
|
return list_lru_shrink_walk_irq(&shadow_nodes, sc, shadow_lru_isolate,
|
|
NULL);
|
|
}
|
|
|
|
static struct shrinker workingset_shadow_shrinker = {
|
|
.count_objects = count_shadow_nodes,
|
|
.scan_objects = scan_shadow_nodes,
|
|
.seeks = 0, /* ->count reports only fully expendable nodes */
|
|
.flags = SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE,
|
|
};
|
|
|
|
/*
|
|
* Our list_lru->lock is IRQ-safe as it nests inside the IRQ-safe
|
|
* i_pages lock.
|
|
*/
|
|
static struct lock_class_key shadow_nodes_key;
|
|
|
|
static int __init workingset_init(void)
|
|
{
|
|
unsigned int timestamp_bits;
|
|
unsigned int max_order;
|
|
int ret;
|
|
|
|
BUILD_BUG_ON(BITS_PER_LONG < EVICTION_SHIFT);
|
|
/*
|
|
* Calculate the eviction bucket size to cover the longest
|
|
* actionable refault distance, which is currently half of
|
|
* memory (totalram_pages/2). However, memory hotplug may add
|
|
* some more pages at runtime, so keep working with up to
|
|
* double the initial memory by using totalram_pages as-is.
|
|
*/
|
|
timestamp_bits = BITS_PER_LONG - EVICTION_SHIFT;
|
|
max_order = fls_long(totalram_pages() - 1);
|
|
if (max_order > timestamp_bits)
|
|
bucket_order = max_order - timestamp_bits;
|
|
pr_info("workingset: timestamp_bits=%d max_order=%d bucket_order=%u\n",
|
|
timestamp_bits, max_order, bucket_order);
|
|
|
|
ret = prealloc_shrinker(&workingset_shadow_shrinker, "mm-shadow");
|
|
if (ret)
|
|
goto err;
|
|
ret = __list_lru_init(&shadow_nodes, true, &shadow_nodes_key,
|
|
&workingset_shadow_shrinker);
|
|
if (ret)
|
|
goto err_list_lru;
|
|
register_shrinker_prepared(&workingset_shadow_shrinker);
|
|
return 0;
|
|
err_list_lru:
|
|
free_prealloced_shrinker(&workingset_shadow_shrinker);
|
|
err:
|
|
return ret;
|
|
}
|
|
module_init(workingset_init);
|