linux物理內存描述 (二)
linux物理內存描述 (二) /*
* rarely used fields:
*/
const char *name;
} ____cacheline_internodealigned_in_smp;
struct zone {
/* Fields commonly accessed by the page allocator */
/* zone watermarks, access with *_wmark_pages(zone) macros */
/*本管理區的三個水線值:高水線(比較充足)、低水線、MIN水線。*/
unsigned long watermark;
/*
* 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.
*/
/**
* 當高端內存、normal內存區域中無法分配到內存時,需要從normal、DMA區域中分配內存。
* 為了避免DMA區域被消耗光,需要額外保留一些內存供驅動使用。
* 該欄位就是指從上級內存區退到回內存區時,需要額外保留的內存數量。
*/
unsigned long lowmem_reserve;
#ifdef CONFIG_NUMA
/*所屬的NUMA節點。*/
int node;
/*
* zone reclaim becomes active if more unmapped pages exist.
*/
/*當可回收的頁超過此值時,將進行頁面回收。*/
unsigned long min_unmapped_pages;
/*當管理區中,用於slab的可回收頁大於此值時,將回收slab中的緩存頁。*/
unsigned long min_slab_pages;
/*
* 每CPU的頁面緩存。
* 當分配單個頁面時,首先從該緩存中分配頁面。這樣可以:
*避免使用全局的鎖
* 避免同一個頁面反覆被不同的CPU分配,引起緩存行的失效。
* 避免將管理區中的大塊分割成碎片。
*/
struct per_cpu_pageset *pageset;
#else
struct per_cpu_pageset pageset;
#endif
/*
* free areas of different sizes
*/
/*該鎖用於保護夥伴系統數據結構。即保護free_area相關數據。*/
spinlock_t lock;
#ifdef CONFIG_MEMORY_HOTPLUG
/* see spanned/present_pages for more description */
/*用於保護spanned/present_pages等變數。這些變數幾乎不會發生變化,除非發生了內存熱插撥操作。
這幾個變數並不被lock欄位保護。並且主要用於讀,因此使用讀寫鎖。*/
seqlock_t span_seqlock;
#endif
/*夥伴系統的主要變數。這個數組定義了11個隊列,每個隊列中的元素都是大小為2^n的頁面*/
struct free_area free_area;
#ifndef CONFIG_SPARSEMEM
/*
* Flags for a pageblock_nr_pages block. See pageblock-flags.h.
* In SPARSEMEM, this map is stored in struct mem_section
*/
/*本管理區里的頁面標誌數組*/
unsigned long *pageblock_flags;
#endif /* CONFIG_SPARSEMEM */
/*填充的未用欄位,確保後面的欄位是緩存行對齊的*/
ZONE_PADDING(_pad1_)
/* Fields commonly accessed by the page reclaim scanner */
/*
* lru相關的欄位用於內存回收。這個欄位用於保護這幾個回收相關的欄位。
* lru用於確定哪些欄位是活躍的,哪些不是活躍的,並據此確定應當被寫回到磁碟以釋放內存。
*/
spinlock_t lru_lock;
/* 匿名活動頁、匿名不活動頁、文件活動頁、文件不活動頁鏈表頭*/
struct zone_lru {
struct list_head list;
} lru;
/*頁面回收狀態*/
struct zone_reclaim_stat reclaim_stat;
/*自從最後一次回收頁面以來,掃過的頁面數*/
unsigned long pages_scanned; /* since last reclaim */
unsigned long flags; /* zone flags, see below */
/* Zone statistics */
atomic_long_t vm_stat;
/*
* 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;
/*為cache對齊*/
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.
*/
/*管理區屬於的節點*/
struct pglist_data *zone_pgdat;
/* zone_start_pfn == zone_start_paddr >> PAGE_SHIFT */
/*管理區的頁面在mem_map中的偏移*/
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;沒有說明的地方,內核中的英文註釋已經寫得很清楚了。
頁面
系統中每個物理頁面都有一個相關聯的page用於記錄該頁面的狀態。view plaincopy to clipboardprint?/*
* 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.
*/
struct page {
unsigned long flags; /* Atomic flags, some possibly
* updated asynchronously */
atomic_t _count; /* Usage count, see below. */
union {
atomic_t _mapcount; /* Count of ptes mapped in mms,
* to show when page is mapped
* & limit reverse map searches.
*/
struct { /* SLUB */
u16 inuse;
u16 objects;
};
};
union {
struct {
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.
*/
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.
*/
};
#if USE_SPLIT_PTLOCKS
spinlock_t ptl;
#endif
struct kmem_cache *slab; /* SLUB: Pointer to slab */
/* 如果屬於夥伴系統,並且不是夥伴系統中的第一個頁
則指向第一個頁*/
struct page *first_page; /* Compound tail pages */
};
union {/*如果是文件映射,那麼表示本頁面在文件中的位置(偏移)*/
pgoff_t index; /* Our offset within mapping. */
void *freelist; /* SLUB: freelist req. slab lock */
};
struct list_head lru; /* Pageout list, eg. active_list
* protected by zone->lru_lock !
*/
/*
* 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_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
};
/*
* 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.
*/
struct page {
unsigned long flags; /* Atomic flags, some possibly
* updated asynchronously */
atomic_t _count; /* Usage count, see below. */
union {
atomic_t _mapcount; /* Count of ptes mapped in mms,
* to show when page is mapped
* & limit reverse map searches.
*/
struct { /* SLUB */
u16 inuse;
u16 objects;
};
};
union {
struct {
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.
*/
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.
*/
};
#if USE_SPLIT_PTLOCKS
spinlock_t ptl;
#endif
struct kmem_cache *slab; /* SLUB: Pointer to slab */
/* 如果屬於夥伴系統,並且不是夥伴系統中的第一個頁
則指向第一個頁*/
struct page *first_page; /* Compound tail pages */
};
union {/*如果是文件映射,那麼表示本頁面在文件中的位置(偏移)*/
pgoff_t index; /* Our offset within mapping. */
void *freelist; /* SLUB: freelist req. slab lock */
};
struct list_head lru; /* Pageout list, eg. active_list
* protected by zone->lru_lock !
*/
/*
* 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_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
};linux中主要的結構描述體現了linux物理內存管理的設計。後面會介紹linux內存管理的各個細節。
《解決方案》
謝謝分享
《解決方案》
感謝了。學習。