1.相关概念
UMA(Uniform Memory Access): 一致性内存访问,所有CPU core访问内存速度一致;
NUMA(Non Uniform Memory Access):非一致性内存访问,不同CPU访问不同的内存区域速度是不一样的;不同的CPU分别挂载了属于自己本地的内存,所以CPU访问本地内存速度最快,
访问远端内存速度相对较慢;
linux中将NUMA 中内存访问速度一致的内存部分称为一个节点(node),用struct pglist_data
表示;
一个节点分成很多区zone,struct zone来表示;
一个zone里面包含很多page,struct page表示;
结构之间关系如图所示:
2. 数据结构详解:
typedef struct pglist_data {
//一个节点中zone区数组,一般有ZONE_DMA,ZONE_NORMAL
struct zone node_zones[MAX_NR_ZONES];
//分配内存时的顺序
struct zonelist node_zonelists[MAX_ZONELISTS];
int nr_zones;//节点中zone的个数
#ifdef CONFIG_FLAT_NODE_MEM_MAP /* means !SPARSEMEM */
//非稀疏内存模型才会有此变量,该节点第一个页面在page数组中的地址
struct page *node_mem_map;
#ifdef CONFIG_MEMCG
struct page_cgroup *node_page_cgroup;
#endif
#endif
#ifndef CONFIG_NO_BOOTMEM
struct bootmem_data *bdata;
#endif
#ifdef CONFIG_MEMORY_HOTPLUG
/*
* Must be held any time you expect node_start_pfn, node_present_pages
* or node_spanned_pages stay constant. Holding this will also
* guarantee that any pfn_valid() stays that way.
*
* pgdat_resize_lock() and pgdat_resize_unlock() are provided to
* manipulate node_size_lock without checking for CONFIG_MEMORY_HOTPLUG.
*
* Nests above zone->lock and zone->span_seqlock
*/
spinlock_t node_size_lock;
#endif
unsigned long node_start_pfn;//节点的起始页面号
unsigned long node_present_pages; //总的有效物理页面数
unsigned long node_spanned_pages; //所有物理页面数,包含了内存空洞
int node_id; //node id
wait_queue_head_t kswapd_wait;
wait_queue_head_t pfmemalloc_wait;
struct task_struct *kswapd; //页换出进程描述符
int kswapd_max_order;
enum zone_type classzone_idx;
#ifdef CONFIG_NUMA_BALANCING
/* Lock serializing the migrate rate limiting window */
spinlock_t numabalancing_migrate_lock;
/* Rate limiting time interval */
unsigned long numabalancing_migrate_next_window;
/* Number of pages migrated during the rate limiting time interval */
unsigned long numabalancing_migrate_nr_pages;
#endif
} pg_data_t;
struct zone {
/* Read-mostly fields */
<span style="font-family: Arial, Helvetica, sans-serif;"> //zone的水位标示数组,内存回收时参考不同的数位值</span></span>
unsigned long watermark[NR_WMARK];
/*
* 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.
*/
long lowmem_reserve[MAX_NR_ZONES];
#ifdef CONFIG_NUMA
int node;
#endif
/*
* The target ratio of ACTIVE_ANON to INACTIVE_ANON pages on
* this zone's LRU. Maintained by the pageout code.
*/
unsigned int inactive_ratio;
struct pglist_data *zone_pgdat;//zone 区所属的节点
struct per_cpu_pageset __percpu *pageset;
/*
* This is a per-zone reserve of pages that should not be
* considered dirtyable memory.
*/
unsigned long dirty_balance_reserve;
#ifdef CONFIG_CMA
bool cma_alloc;
#endif
#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 */
#ifdef CONFIG_NUMA
/*
* zone reclaim becomes active if more unmapped pages exist.
*/
unsigned long min_unmapped_pages;
unsigned long min_slab_pages;
#endif /* CONFIG_NUMA */
/* zone_start_pfn == zone_start_paddr >> PAGE_SHIFT */
unsigned long zone_start_pfn;
/*
* spanned_pages is the total pages spanned by the zone, including
* holes, which is calculated as:
* spanned_pages = zone_end_pfn - zone_start_pfn;
*
* present_pages is physical pages existing within the zone, which
* is calculated as:
* present_pages = spanned_pages - absent_pages(pages in holes);
*
* managed_pages is present pages managed by the buddy system, which
* is calculated as (reserved_pages includes pages allocated by the
* bootmem allocator):
* managed_pages = present_pages - reserved_pages;
*
* So present_pages may be used by memory hotplug or memory power
* management logic to figure out unmanaged pages by checking
* (present_pages - managed_pages). And managed_pages should be used
* by page allocator and vm scanner to calculate all kinds of watermarks
* and thresholds.
*
* Locking rules:
*
* zone_start_pfn and spanned_pages are 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 span_seq 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.
*
* Write access to present_pages at runtime should be protected by
* mem_hotplug_begin/end(). Any reader who can't tolerant drift of
* present_pages should get_online_mems() to get a stable value.
*
* Read access to managed_pages should be safe because it's unsigned
* long. Write access to zone->managed_pages and totalram_pages are
* protected by managed_page_count_lock at runtime. Idealy only
* adjust_managed_page_count() should be used instead of directly
* touching zone->managed_pages and totalram_pages.
*/
unsigned long managed_pages;
unsigned long spanned_pages; //zone 总物理页面数
unsigned long present_pages; //zone除去空洞后的页面数
const char *name;//zone name
/*
* Number of MIGRATE_RESEVE page block. To maintain for just
* optimization. Protected by zone->lock.
*/
int nr_migrate_reserve_block;
#ifdef CONFIG_MEMORY_ISOLATION
/*
* Number of isolated pageblock. It is used to solve incorrect
* freepage counting problem due to racy retrieving migratetype
* of pageblock. Protected by zone->lock.
*/
unsigned long nr_isolate_pageblock;
#endif
#ifdef CONFIG_MEMORY_HOTPLUG
/* see spanned/present_pages for more description */
seqlock_t span_seqlock;
#endif
/*
* 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;//进程等待队列,这些进程等待管理区中的某页
unsigned long wait_table_hash_nr_entries;
unsigned long wait_table_bits;
ZONE_PADDING(_pad1_)
/* Write-intensive fields used from the page allocator */
spinlock_t lock;
/* free areas of different sizes */
struct free_area free_area[MAX_ORDER]; //zone中的空闲页链表,二维数组结构进行管理
/* zone flags, see below */
unsigned long flags;
ZONE_PADDING(_pad2_)
/* Write-intensive fields used by page reclaim */
/* Fields commonly accessed by the page reclaim scanner */
spinlock_t lru_lock;
struct lruvec lruvec;
/* Evictions & activations on the inactive file list */
atomic_long_t inactive_age;
/*
* When free pages are below this point, additional steps are taken
* when reading the number of free pages to avoid per-cpu counter
* drift allowing watermarks to be breached
*/
unsigned long percpu_drift_mark;
#if defined CONFIG_COMPACTION || defined CONFIG_CMA
/* pfn where compaction free scanner should start */
unsigned long compact_cached_free_pfn;
/* pfn where async and sync compaction migration scanner should start */
unsigned long compact_cached_migrate_pfn[2];
#endif
#ifdef CONFIG_COMPACTION
/*
* On compaction failure, 1<<compact_defer_shift compactions
* are skipped before trying again. The number attempted since
* last failure is tracked with compact_considered.
*/
unsigned int compact_considered;
unsigned int compact_defer_shift;
int compact_order_failed;
#endif
#if defined CONFIG_COMPACTION || defined CONFIG_CMA
/* Set to true when the PG_migrate_skip bits should be cleared */
bool compact_blockskip_flush;
#endif
ZONE_PADDING(_pad3_)
/* Zone statistics */
atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS];
} ____cacheline_internodealigned_in_smp;
/*
* Each physical page in the system has a struct page associated with
* it to keep track of whatever it is we are using the page for at the
* moment. Note that we have no way to track which tasks are using
* a page, though if it is a pagecache page, rmap structures can tell us
* who is mapping it.
*
* The objects in struct page are organized in double word blocks in
* order to allows us to use atomic double word operations on portions
* of struct page. That is currently only used by slub but the arrangement
* allows the use of atomic double word operations on the flags/mapping
* and lru list pointers also.
*/
struct page {
/* First double word block */
unsigned long flags; //页面标志,具体含义参考enum pageflags
union {
struct address_space *mapping; /* If low bit clear, points to
* inode address_space, or NULL.
* If page mapped as anonymous
* memory, low bit is set, and
* it points to anon_vma object:
* see PAGE_MAPPING_ANON below.
*/
void *s_mem; /* slab first object */
};
/* Second double word */
struct {
union {
pgoff_t index; /* Our offset within mapping. */
void *freelist; /* sl[aou]b first free object */
bool pfmemalloc; /* If set by the page allocator,
* ALLOC_NO_WATERMARKS was set
* and the low watermark was not
* met implying that the system
* is under some pressure. The
* caller should try ensure
* this page is only used to
* free other pages.
*/
};
union {
#if defined(CONFIG_HAVE_CMPXCHG_DOUBLE) && \
defined(CONFIG_HAVE_ALIGNED_STRUCT_PAGE)
/* Used for cmpxchg_double in slub */
unsigned long counters;
#else
/*
* Keep _count separate from slub cmpxchg_double data.
* As the rest of the double word is protected by
* slab_lock but _count is not.
*/
unsigned counters;
#endif
struct {
union {
/*
* Count of ptes mapped in
* mms, to show when page is
* mapped & limit reverse map
* searches.
*
* Used also for tail pages
* refcounting instead of
* _count. Tail pages cannot
* be mapped and keeping the
* tail page _count zero at
* all times guarantees
* get_page_unless_zero() will
* never succeed on tail
* pages.
*/
atomic_t _mapcount;
struct { /* SLUB */
unsigned inuse:16;
unsigned objects:15;
unsigned frozen:1;
};
int units; /* SLOB */
};
atomic_t _count; /* Usage count, see below. */
};
unsigned int active; /* SLAB */
};
};
/* Third double word block */
union {
struct list_head lru; /* Pageout list, eg. active_list
* protected by zone->lru_lock !
* Can be used as a generic list
* by the page owner.
*/
struct { /* slub per cpu partial pages */
struct page *next; /* Next partial slab */
#ifdef CONFIG_64BIT
int pages; /* Nr of partial slabs left */
int pobjects; /* Approximate # of objects */
#else
short int pages;
short int pobjects;
#endif
};
struct slab *slab_page; /* slab fields */
struct rcu_head rcu_head; /* Used by SLAB
* when destroying via RCU
*/
#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && USE_SPLIT_PMD_PTLOCKS
pgtable_t pmd_huge_pte; /* protected by page->ptl */
#endif
};
/* Remainder is not double word aligned */
union {
unsigned long private; /* Mapping-private opaque data:
* usually used for buffer_heads
* if PagePrivate set; used for
* swp_entry_t if PageSwapCache;
* indicates order in the buddy
* system if PG_buddy is set.
*/
#if USE_SPLIT_PTE_PTLOCKS
#if ALLOC_SPLIT_PTLOCKS
spinlock_t *ptl;
#else
spinlock_t ptl;
#endif
#endif
struct kmem_cache *slab_cache; /* SL[AU]B: Pointer to slab */
struct page *first_page; /* Compound tail pages */
};
/*
* On machines where all RAM is mapped into kernel address space,
* we can simply calculate the virtual address. On machines with
* highmem some memory is mapped into kernel virtual memory
* dynamically, so we need a place to store that address.
* Note that this field could be 16 bits on x86 ... ;)
*
* Architectures with slow multiplication can define
* WANT_PAGE_VIRTUAL in asm/page.h
*/
#if defined(WANT_PAGE_VIRTUAL)
void *virtual; /* Kernel virtual address (NULL if
not kmapped, ie. highmem) */
#endif /* WANT_PAGE_VIRTUAL */
#ifdef CONFIG_WANT_PAGE_DEBUG_FLAGS
unsigned long debug_flags; /* Use atomic bitops on this */
#endif
#ifdef CONFIG_BLK_DEV_IO_TRACE
struct task_struct *tsk_dirty; /* task that sets this page dirty */
#endif
#ifdef CONFIG_KMEMCHECK
/*
* kmemcheck wants to track the status of each byte in a page; this
* is a pointer to such a status block. NULL if not tracked.
*/
void *shadow;
#endif
#ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS
int _last_cpupid;
#endif
#ifdef CONFIG_PAGE_OWNER
int order;
gfp_t gfp_mask;
struct stack_trace trace;
unsigned long trace_entries[8];
#endif
}
因为内核会为每一个物理页帧创建一个struct page的结构体,因此要保证page结构体足够的小,否则仅struct page就要占用大量的内存。
出于节省内存的考虑,struct page中使用了大量的联合体union。下面仅对常用的一些的字段做说明:
1) flags :描述page的状态和其他信息,如图:
主要分为4部分,其中标志位flag向高位增长,其余位字段向低位增长,中间存在空闲位。
section :主要用于稀疏内存模型SPARSEMEM,可忽略。
node :NUMA节点号,标识该page属于哪一个节点。
zone :内存域标志,标识该page属于哪一个zone。
flag :page的状态标识,常用的有:
PG_locked :page被锁定,说明有使用者正在操作该page。
PG_error :状态标志,表示涉及该page的IO操作发生了错误。
PG_referenced :表示page刚刚被访问过。
PG_active :page处于inactive LRU链表。PG_active和PG_referenced一起控制该page的活跃程度,这在内存回收时将会非常有用。
PG_uptodate :表示page的数据已经与后备存储器是同步的,是最新的。
PG_dirty :与后备存储器中的数据相比,该page的内容已经被修改。
PG_lru :表示该page处于LRU链表上。
PG_slab :该page属于slab分配器。
PG_reserved :设置该标志,防止该page被交换到swap。
PG_private :如果page中的private成员非空,则需要设置该标志。参考6)对private的解释。
PG_writeback :page中的数据正在被回写到后备存储器。
PG_swapcache :表示该page处于swap cache中。
PG_mappedtodisk :表示page中的数据在后备存储器中有对应。
PG_reclaim :表示该page要被回收。当PFRA决定要回收某个page后,需要设置该标志。
PG_swapbacked :该page的后备存储器是swap。
PG_unevictable :该page被锁住,不能交换,并会出现在LRU_UNEVICTABLE链表中,它包括的几种page:ramdisk或ramfs使用的页、
shm_locked、mlock锁定的页。
PG_mlocked :该page在vma中被锁定,一般是通过系统调用mlock()锁定了一段内存。
内核中提供了一些标准宏,用来检查、操作某些特定的比特位,如:
-> PageXXX(page):检查page是否设置了PG_XXX位
-> SetPageXXX(page):设置page的 PG_XXX位
-> ClearPageXXX(page):清除 page的 PG_XXX位
-> TestSetPageXXX(page ):设置 page的 PG_XXX位,并返回原值
-> TestClearPageXXX(page):清除 page的 PG_XXX位,并返回原值
2) _count :引用计数,表示内核中引用该page的次数,如果要操作该page,引用计数会+1,操作完成-1。当该值为0时,表示没有引用该page的位置,所以该page可以被解除映射,这往往在内存回收时是有用的。
3) _mapcount :被页表映射的次数,也就是说该page同时被多少个进程共享。初始值为-1,如果只被一个进程的页表映射了,该值为0 。如果该page处于伙伴系统中,该值为PAGE_BUDDY_MAPCOUNT_VALUE(-128),内核通过判断该值是否为PAGE_BUDDY_MAPCOUNT_VALUE来确定该page是否属于伙伴系统。
注意区分_count和_mapcount,_mapcount表示的是映射次数,而_count表示的是使用次数;被映射了不一定在使用,但要使用必须先映射。
4) mapping :有三种含义
a: 如果mapping = 0,说明该page属于交换缓存(swap cache);当需要使用地址空间时会指定交换分区的地址空间swapper_space。
b: 如果mapping != 0,bit[0] = 0,说明该page属于页缓存或文件映射,mapping指向文件的地址空间address_space。
c: 如果mapping != 0,bit[0] != 0,说明该page为匿名映射,mapping指向struct anon_vma对象。
通过mapping恢复anon_vma的方法:anon_vma = (struct anon_vma *)(mapping - PAGE_MAPPING_ANON)。
5) index :在映射的虚拟空间(vma_area)内的偏移;一个文件可能只映射一部分,假设映射了1M的空间,index指的是在1M空间内的偏移,而不是在整个文件内的偏移。
6) private :私有数据指针,由应用场景确定其具体的含义:
a:如果设置了PG_private标志,表示buffer_heads;
b:如果设置了PG_swapcache标志,private存储了该page在交换分区中对应的位置信息swp_entry_t。
c:如果_mapcount = PAGE_BUDDY_MAPCOUNT_VALUE,说明该page位于伙伴系统,private存储该伙伴的阶。
7) lru :链表头,主要有3个用途:
a:page处于伙伴系统中时,用于链接相同阶的伙伴(只使用伙伴中的第一个page的lru即可达到目的)。
b:page属于slab时,page->lru.next指向page驻留的的缓存的管理结构,page->lru.prec指向保存该page的slab的管理结构。
c:page被用户态使用或被当做页缓存使用时,用于将该page连入zone中相应的lru链表,供内存回收时使用。