Free_area是一个数组用做buddy系统,每一个数组代表固定大小的连续内存
struct free_area {
struct list_head free_list[MIGRATE_TYPES];
unsigned long nr_free;
};
如果一个页经常被用到可以看成是active的,inactive页则相反。在页面换出时active页会被尽可能的换出刷到磁盘上
active_list收集active页 inactive_list收集 inactive页
nr_scan_active 和nr_scan_inactive用于内存恢复时扫描有多少 active 和 inactive页
pages_scanned记录上一次页交换有多少页没被扫描到
flag 描述现在zone区域的状态
typedef enum {
ZONE_ALL_UNRECLAIMABLE, /* all pages pinned */
ZONE_RECLAIM_LOCKED, /* prevents concurrent reclaim */
ZONE_OOM_LOCKED, /* zone is in OOM killer zonelist */
} zone_flags_t;
内核使用三个函数测试和设置flag值
void zone_set_flag(struct zone *zone, zone_flags_t flag)
int zone_test_and_set_flag(struct zone *zone, zone_flags_t flag)
void zone_clear_flag(struct zone *zone, zone_flags_t flag)
static inline void zone_set_flag(struct zone *zone, zone_flags_t flag)
{
set_bit(flag, &zone->flags);
}
zone_page_state用于记录zone信息
static inline unsigned long zone_page_state(struct zone *zone,
enum zone_stat_item item)
{
long x = atomic_long_read(&zone->vm_stat[item]);
#ifdef CONFIG_SMP
if (x < 0)
x = 0;
#endif
return x;
}
144页
min_free_kbytes表示内核最低空闲内存值
min_free_kbytes = sqrt(lowmem_kbytes * 16)
通常初始化值是1024K(1M)
* 16MB: 512k
* 32MB: 724k
* 64MB: 1024k
* 128MB: 1448k
* 256MB: 2048k
* 512MB: 2896k
* 1024MB: 4096k
* 2048MB: 5792k
* 4096MB: 8192k
* 8192MB: 11584k
* 16384MB: 16384k
cat /proc/sys/vm/min_free_kbytes 可以看到
struct zone {
/* Fields commonly accessed by the page allocator */
unsigned long pages_min, pages_low, pages_high;
/*
* We don't know if the memory that we're going to allocate will be freeable
* or/and it will be released eventually, so to avoid totally wasting several
* GB of ram we must reserve some of the lower zone memory (otherwise we risk
* to run OOM on the lower zones despite there's tons of freeable ram
* on the higher zones). This array is recalculated at runtime if the
* sysctl_lowmem_reserve_ratio sysctl changes.
*/
unsigned long lowmem_reserve[MAX_NR_ZONES];
#ifdef CONFIG_NUMA
int node;
/*
* zone reclaim becomes active if more unmapped pages exist.
*/
unsigned long min_unmapped_pages;
unsigned long min_slab_pages;
struct per_cpu_pageset *pageset[NR_CPUS];
#else
struct per_cpu_pageset pageset[NR_CPUS];
#endif
/*
* free areas of different sizes
*/
spinlock_t lock;
#ifdef CONFIG_MEMORY_HOTPLUG
/* see spanned/present_pages for more description */
seqlock_t span_seqlock;
#endif
struct free_area free_area[MAX_ORDER];
#ifndef CONFIG_SPARSEMEM
/*
* Flags for a pageblock_nr_pages block. See pageblock-flags.h.
* In SPARSEMEM, this map is stored in struct mem_section
*/
unsigned long *pageblock_flags;
#endif /* CONFIG_SPARSEMEM */
ZONE_PADDING(_pad1_)
/* Fields commonly accessed by the page reclaim scanner */
spinlock_t lru_lock;
struct {
struct list_head list;
unsigned long nr_scan;
} lru[NR_LRU_LISTS];
struct zone_reclaim_stat reclaim_stat;
unsigned long pages_scanned; /* since last reclaim */
unsigned long flags; /* zone flags, see below */
/* Zone statistics */
atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS];
/*
* prev_priority holds the scanning priority for this zone. It is
* defined as the scanning priority at which we achieved our reclaim
* target at the previous try_to_free_pages() or balance_pgdat()
* invokation.
*
* We use prev_priority as a measure of how much stress page reclaim is
* under - it drives the swappiness decision: whether to unmap mapped
* pages.
*
* Access to both this field is quite racy even on uniprocessor. But
* it is expected to average out OK.
*/
int prev_priority;
/*
* The target ratio of ACTIVE_ANON to INACTIVE_ANON pages on
* this zone's LRU. Maintained by the pageout code.
*/
unsigned int inactive_ratio;
ZONE_PADDING(_pad2_)
/* Rarely used or read-mostly fields */
/*
* wait_table -- the array holding the hash table
* wait_table_hash_nr_entries -- the size of the hash table array
* wait_table_bits -- wait_table_size == (1 << wait_table_bits)
*
* The purpose of all these is to keep track of the people
* waiting for a page to become available and make them
* runnable again when possible. The trouble is that this
* consumes a lot of space, especially when so few things
* wait on pages at a given time. So instead of using
* per-page waitqueues, we use a waitqueue hash table.
*
* The bucket discipline is to sleep on the same queue when
* colliding and wake all in that wait queue when removing.
* When something wakes, it must check to be sure its page is
* truly available, a la thundering herd. The cost of a
* collision is great, but given the expected load of the
* table, they should be so rare as to be outweighed by the
* benefits from the saved space.
*
* __wait_on_page_locked() and unlock_page() in mm/filemap.c, are the
* primary users of these fields, and in mm/page_alloc.c
* free_area_init_core() performs the initialization of them.
*/
wait_queue_head_t * wait_table;
unsigned long wait_table_hash_nr_entries;
unsigned long wait_table_bits;
/*
* Discontig memory support fields.
*/
struct pglist_data *zone_pgdat;
/* zone_start_pfn == zone_start_paddr >> PAGE_SHIFT */
unsigned long zone_start_pfn;
/*
* zone_start_pfn, spanned_pages and present_pages are all
* protected by span_seqlock. It is a seqlock because it has
* to be read outside of zone->lock, and it is done in the main
* allocator path. But, it is written quite infrequently.
*
* The lock is declared along with zone->lock because it is
* frequently read in proximity to zone->lock. It's good to
* give them a chance of being in the same cacheline.
*/
unsigned long spanned_pages; /* total size, including holes */
unsigned long present_pages; /* amount of memory (excluding holes) */
/*
* rarely used fields:
*/
const char *name;
} ____cacheline_internodealigned_in_smp;
Zone 里的per_cpu_pageset用于实现hot-cold 分配,把hot page放到CPU的cache里处理148
Page frames(页帧)代表最小的内存单元,内核里用struct page结构体来表示内存里的页