mirror of
https://github.com/torvalds/linux.git
synced 2026-09-12 12:34:02 +02:00
7b9f4e5f81
The anon/file scan balance in get_scan_count() is driven by two scalars in
struct lruvec, anon_cost and file_cost, accumulated by every reclaim
producer under lruvec->lru_lock. The acquisition sites for cost work
specifically are:
- shrink_inactive_list() re-takes lru_lock at function exit purely
to call lru_note_cost_unlock_irq() with (nr_pageout, nr_scanned -
nr_reclaimed). One acquisition per inactive shrink.
- shrink_active_list() does the same with (0, nr_rotated). One
acquisition per active shrink.
- workingset_refault() takes the lock via folio_lruvec_lock_irq()
purely to record the refault cost. One acquisition per refault.
- prepare_scan_control() takes lru_lock just to snapshot the two
scalars into sc->{anon,file}_cost.
- lru_note_cost_unlock_irq() itself walks parent_lruvec and
re-acquires lru_lock on each ancestor to propagate the update,
adding O(memcg-depth) acquisitions per producer call.
This hurts because lru_lock is already a heavy contention point on
memory-heavy workloads: every isolate_lru_folios(), move_folios_to_lru()
and folio_add_lru() takes it. The cost work itself is trivial (two scalar
bumps and one comparison), but it contends with and causes contention for
actual LRU manipulation. The parent_lruvec() walk also multiplies
cost-update overhead by memcg hierarchy depth.
The balance formula for anon and file, respectively, is this:
cost = nr_io * SWAP_CLUSTER_MAX + nr_rotated
Instead of recording cost and running averaging logic directly when these
events occur, snapshot running vmstat counters once per reclaim cycle and
derive the balance from event deltas since the last run.
Use PGROTATE_* from the preceding patch for the rotation input.
WORKINGSET_RESTORE_* and NR_VMSCAN_WRITE provide the remaining event
counters. Charge NR_VMSCAN_WRITE through lruvec stats so all inputs can
be sampled per lruvec and aggregated through the memcg hierarchy. This is
overall cheaper and has fewer lock acquisition sites.
Moving accumulation and decay to the reclaim side also improves the cost
model across reclaim gaps. With producer-side decay, events that happen
while reclaim is idle still age each other before reclaim ever samples the
costs. If a workload refaults a large anon set and then a smaller file
set before reclaim runs again, the later file activity can age the earlier
anon activity out of the cost model. The new scheme observes the whole
between-reclaim delta and decays anon and file proportionally, so the
scan-balance history better represents what happened since the last
reclaim pass.
A dedicated per-lruvec spinlock, cost_lock, serialises the delta
extraction, the cost->count update and the halving loop against concurrent
reclaimers in the same memcg+node.
NR_VMSCAN_WRITE is accounted at writeout(), so reclaim_stat.nr_pageout is
no longer needed and is removed.
memcg-v1's memory.stat anon_cost/file_cost is now sourced from
cost[].count instead of the removed lruvec anon_cost/file_cost fields.
The reported values only refresh when prepare_scan_control() runs and are
bounded at ~lrusize/4 by the halving loop; the scan-balance signal they
express is unchanged.
Under pure MGLRU the scan-balance signal itself is not consumed (both
prepare_scan_control() and get_scan_count() are short-circuited on the
MGLRU paths, and MGLRU's own type/tier selection comes from
read_ctrl_pos() on lrugen->{avg_refaulted,avg_total,refaulted,evicted},
not from anon_cost/file_cost). NR_VMSCAN_WRITE naturally covers writeout
from either reclaim implementation. The preceding patch also bumps
PGROTATE_{ANON,FILE} from evict_folios(), so rotation-driven reclaim work
is accounted consistently across both implementations.
Link: https://lore.kernel.org/20260727162550.2032-4-usama.arif@linux.dev
Signed-off-by: Usama Arif <usama.arif@linux.dev>
Acked-by: Shakeel Butt <shakeel.butt@linux.dev>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Vlastimil Babka (SUSE) <vbabka@kernel.org>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Baoquan He <baoquan.he@linux.dev>
Cc: Chris Li <chrisl@kernel.org>
Cc: David Hildenbrand <david@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Kairui Song <kasong@tencent.com>
Cc: Liam R. Howlett <liam@infradead.org>
Cc: Lorenzo Stoakes <ljs@kernel.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Nhat Pham <nphamcs@gmail.com>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Wei Xu <weixugc@google.com>
Cc: Yuanchu Xie <yuanchu@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
116 lines
2.7 KiB
C
116 lines
2.7 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
/*
|
|
* linux/mm/mmzone.c
|
|
*
|
|
* management codes for pgdats, zones and page flags
|
|
*/
|
|
|
|
|
|
#include <linux/stddef.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/mmzone.h>
|
|
|
|
struct pglist_data *first_online_pgdat(void)
|
|
{
|
|
return NODE_DATA(first_online_node);
|
|
}
|
|
|
|
struct pglist_data *next_online_pgdat(struct pglist_data *pgdat)
|
|
{
|
|
int nid = next_online_node(pgdat->node_id);
|
|
|
|
if (nid == MAX_NUMNODES)
|
|
return NULL;
|
|
return NODE_DATA(nid);
|
|
}
|
|
|
|
/*
|
|
* next_zone - helper magic for for_each_zone()
|
|
*/
|
|
struct zone *next_zone(struct zone *zone)
|
|
{
|
|
pg_data_t *pgdat = zone->zone_pgdat;
|
|
|
|
if (zone < pgdat->node_zones + MAX_NR_ZONES - 1)
|
|
zone++;
|
|
else {
|
|
pgdat = next_online_pgdat(pgdat);
|
|
if (pgdat)
|
|
zone = pgdat->node_zones;
|
|
else
|
|
zone = NULL;
|
|
}
|
|
return zone;
|
|
}
|
|
|
|
static inline int zref_in_nodemask(struct zoneref *zref,
|
|
const nodemask_t *nodes)
|
|
{
|
|
#ifdef CONFIG_NUMA
|
|
return node_isset(zonelist_node_idx(zref), *nodes);
|
|
#else
|
|
return 1;
|
|
#endif /* CONFIG_NUMA */
|
|
}
|
|
|
|
/* Returns the next zone at or below highest_zoneidx in a zonelist */
|
|
struct zoneref *__next_zones_zonelist(struct zoneref *z,
|
|
enum zone_type highest_zoneidx,
|
|
const nodemask_t *nodes)
|
|
{
|
|
/*
|
|
* Find the next suitable zone to use for the allocation.
|
|
* Only filter based on nodemask if it's set
|
|
*/
|
|
if (unlikely(nodes == NULL))
|
|
while (zonelist_zone_idx(z) > highest_zoneidx)
|
|
z++;
|
|
else
|
|
while (zonelist_zone_idx(z) > highest_zoneidx ||
|
|
(zonelist_zone(z) && !zref_in_nodemask(z, nodes)))
|
|
z++;
|
|
|
|
return z;
|
|
}
|
|
|
|
void lruvec_init(struct lruvec *lruvec)
|
|
{
|
|
enum lru_list lru;
|
|
|
|
memset(lruvec, 0, sizeof(struct lruvec));
|
|
spin_lock_init(&lruvec->lru_lock);
|
|
spin_lock_init(&lruvec->cost_lock);
|
|
zswap_lruvec_state_init(lruvec);
|
|
|
|
for_each_lru(lru)
|
|
INIT_LIST_HEAD(&lruvec->lists[lru]);
|
|
/*
|
|
* The "Unevictable LRU" is imaginary: though its size is maintained,
|
|
* it is never scanned, and unevictable pages are not threaded on it
|
|
* (so that their lru fields can be reused to hold mlock_count).
|
|
* Poison its list head, so that any operations on it would crash.
|
|
*/
|
|
list_del(&lruvec->lists[LRU_UNEVICTABLE]);
|
|
|
|
lru_gen_init_lruvec(lruvec);
|
|
}
|
|
|
|
#if defined(CONFIG_NUMA_BALANCING) && !defined(LAST_CPUPID_NOT_IN_PAGE_FLAGS)
|
|
int folio_xchg_last_cpupid(struct folio *folio, int cpupid)
|
|
{
|
|
unsigned long old_flags, flags;
|
|
int last_cpupid;
|
|
|
|
old_flags = READ_ONCE(folio->flags.f);
|
|
do {
|
|
flags = old_flags;
|
|
last_cpupid = (flags >> LAST_CPUPID_PGSHIFT) & LAST_CPUPID_MASK;
|
|
|
|
flags &= ~(LAST_CPUPID_MASK << LAST_CPUPID_PGSHIFT);
|
|
flags |= (cpupid & LAST_CPUPID_MASK) << LAST_CPUPID_PGSHIFT;
|
|
} while (unlikely(!try_cmpxchg(&folio->flags.f, &old_flags, flags)));
|
|
|
|
return last_cpupid;
|
|
}
|
|
#endif
|