mirror of
https://github.com/torvalds/linux.git
synced 2024-11-25 13:41:51 +00:00
ec1c86b25f
Evictable pages are divided into multiple generations for each lruvec. The youngest generation number is stored in lrugen->max_seq for both anon and file types as they are aged on an equal footing. The oldest generation numbers are stored in lrugen->min_seq[] separately for anon and file types as clean file pages can be evicted regardless of swap constraints. These three variables are monotonically increasing. Generation numbers are truncated into order_base_2(MAX_NR_GENS+1) bits in order to fit into the gen counter in folio->flags. Each truncated generation number is an index to lrugen->lists[]. The sliding window technique is used to track at least MIN_NR_GENS and at most MAX_NR_GENS generations. The gen counter stores a value within [1, MAX_NR_GENS] while a page is on one of lrugen->lists[]. Otherwise it stores 0. There are two conceptually independent procedures: "the aging", which produces young generations, and "the eviction", which consumes old generations. They form a closed-loop system, i.e., "the page reclaim". Both procedures can be invoked from userspace for the purposes of working set estimation and proactive reclaim. These techniques are commonly used to optimize job scheduling (bin packing) in data centers [1][2]. To avoid confusion, the terms "hot" and "cold" will be applied to the multi-gen LRU, as a new convention; the terms "active" and "inactive" will be applied to the active/inactive LRU, as usual. The protection of hot pages and the selection of cold pages are based on page access channels and patterns. There are two access channels: one through page tables and the other through file descriptors. The protection of the former channel is by design stronger because: 1. The uncertainty in determining the access patterns of the former channel is higher due to the approximation of the accessed bit. 2. The cost of evicting the former channel is higher due to the TLB flushes required and the likelihood of encountering the dirty bit. 3. The penalty of underprotecting the former channel is higher because applications usually do not prepare themselves for major page faults like they do for blocked I/O. E.g., GUI applications commonly use dedicated I/O threads to avoid blocking rendering threads. There are also two access patterns: one with temporal locality and the other without. For the reasons listed above, the former channel is assumed to follow the former pattern unless VM_SEQ_READ or VM_RAND_READ is present; the latter channel is assumed to follow the latter pattern unless outlying refaults have been observed [3][4]. The next patch will address the "outlying refaults". Three macros, i.e., LRU_REFS_WIDTH, LRU_REFS_PGOFF and LRU_REFS_MASK, used later are added in this patch to make the entire patchset less diffy. A page is added to the youngest generation on faulting. The aging needs to check the accessed bit at least twice before handing this page over to the eviction. The first check takes care of the accessed bit set on the initial fault; the second check makes sure this page has not been used since then. This protocol, AKA second chance, requires a minimum of two generations, hence MIN_NR_GENS. [1] https://dl.acm.org/doi/10.1145/3297858.3304053 [2] https://dl.acm.org/doi/10.1145/3503222.3507731 [3] https://lwn.net/Articles/495543/ [4] https://lwn.net/Articles/815342/ Link: https://lkml.kernel.org/r/20220918080010.2920238-6-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>
113 lines
2.5 KiB
C
113 lines
2.5 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, 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,
|
|
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 ||
|
|
(z->zone && !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);
|
|
|
|
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 page_cpupid_xchg_last(struct page *page, int cpupid)
|
|
{
|
|
unsigned long old_flags, flags;
|
|
int last_cpupid;
|
|
|
|
old_flags = READ_ONCE(page->flags);
|
|
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(&page->flags, &old_flags, flags)));
|
|
|
|
return last_cpupid;
|
|
}
|
|
#endif
|