在Linux内核，对于进程的内存使用与Cgroup的内存使用统计有一些相同和不同的地方。
进程的内存统计一般来说，业务进程使用的内存主要有以下几种情况：
（1）用户空间的匿名映射页（Anonymous pages in User Mode address spaces），比如调用malloc分配的内存，以及使用MAP_ANONYMOUS的mmap；当系统内存不够时，内核可以将这部分内存交换出去；
（2）用户空间的文件映射页（Mapped pages in User Mode address spaces），包含map file和map tmpfs；前者比如指定文件的mmap，后者比如IPC共享内存；当系统内存不够时，内核可以回收这些页，但回收之前可能需要与文件同步数据；
（3）文件缓存（page in page cache of disk file）；发生在程序通过普通的read/write读写文件时，当系统内存不够时，内核可以回收这些页，但回收之前可能需要与文件同步数据；
（4）buffer pages，属于page cache；比如读取块设备文件。
其中（1）和（2）是算作进程的RSS，（3)和（4)属于page cache。
与进程内存统计相关的几个文件：
/proc/[pid]/stat
(23) vsize %lu Virtual memory size in bytes. (24) rss %ld Resident Set Size: number of pages the process has in real memory. This is just the pages which count toward text, data, or stack space. This does not include pages which have not been demand-loaded in, or which are swapped out.RSS的计算：
对应top的RSS列，do_task_stat
#define get_mm_rss(mm) \ (get_mm_counter(mm, file_rss) + get_mm_counter(mm, anon_rss))即RSS=file_rss + anon_rss
/proc/[pid]/statm
Provides information about memory usage, measured in pages. The columns are: size (1) total program size (same as VmSize in /proc/[pid]/status) resident (2) resident set size (same as VmRSS in /proc/[pid]/status) share (3) shared pages (i.e., backed by a file) text (4) text (code) lib (5) library (unused in Linux 2.6) data (6) data + stack dt (7) dirty pages (unused in Linux 2.6)见函数proc_pid_statm
int task_statm(struct mm_struct *mm, int *shared, int *text, int *data, int *resident) { *shared = get_mm_counter(mm, file_rss); *text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK)) >> PAGE_SHIFT; *data = mm->total_vm - mm->shared_vm; *resident = *shared + get_mm_counter(mm, anon_rss); return mm->total_vm; }top的SHR=file_rss。实际上，进程使用的共享内存，也是算到file_rss的，因为共享内存基于tmpfs。
anon_rss与file_rss的计算
static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, pmd_t *pmd, pgoff_t pgoff, unsigned int flags, pte_t orig_pte) { if (flags & FAULT_FLAG_WRITE) { if (!(vma->vm_flags & VM_SHARED)) { anon = 1;///anon page ... if (anon) { inc_mm_counter(mm, anon_rss); page_add_new_anon_rmap(page, vma, address); } else { inc_mm_counter(mm, file_rss); page_add_file_rmap(page); cgroup 的内存统计 stat filememory.stat file includes following statistics
# per-memory cgroup local status cache - # of bytes of page cache memory. rss - # of bytes of anonymous and swap cache memory (includes transparent hugepages). rss_huge - # of bytes of anonymous transparent hugepages. mapped_file - # of bytes of mapped file (includes tmpfs/shmem) pgpgin - # of charging events to the memory cgroup. The charging event happens each time a page is accounted as either mapped anon page(RSS) or cache page(Page Cache) to the cgroup. pgpgout - # of uncharging events to the memory cgroup. The uncharging event happens each time a page is unaccounted from the cgroup. swap - # of bytes of swap usage dirty - # of bytes that are waiting to get written back to the disk. writeback - # of bytes of file/anon cache that are queued for syncing to disk. inactive_anon - # of bytes of anonymous and swap cache memory on inactive LRU list. active_anon - # of bytes of anonymous and swap cache memory on active LRU list. inactive_file - # of bytes of file-backed memory on inactive LRU list. active_file - # of bytes of file-backed memory on active LRU list. unevictable - # of bytes of memory that cannot be reclaimed (mlocked etc).相关代码
static void mem_cgroup_get_local_stat(struct mem_cgroup *mem, struct mcs_total_stat *s) { s64 val; /* per cpu stat */ val = mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_CACHE); s->stat[MCS_CACHE] += val * PAGE_SIZE; val = mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_RSS); s->stat[MCS_RSS] += val * PAGE_SIZE; val = mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_FILE_MAPPED); s->stat[MCS_FILE_MAPPED] += val * PAGE_SIZE; val = mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_PGPGIN_COUNT); s->stat[MCS_PGPGIN] += val; val = mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_PGPGOUT_COUNT); s->stat[MCS_PGPGOUT] += val; if (do_swap_account) { val = mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_SWAPOUT); s->stat[MCS_SWAP] += val * PAGE_SIZE; } /* per zone stat */ val = mem_cgroup_get_local_zonestat(mem, LRU_INACTIVE_ANON); s->stat[MCS_INACTIVE_ANON] += val * PAGE_SIZE; val = mem_cgroup_get_local_zonestat(mem, LRU_ACTIVE_ANON); s->stat[MCS_ACTIVE_ANON] += val * PAGE_SIZE; val = mem_cgroup_get_local_zonestat(mem, LRU_INACTIVE_FILE); s->stat[MCS_INACTIVE_FILE] += val * PAGE_SIZE; val = mem_cgroup_get_local_zonestat(mem, LRU_ACTIVE_FILE); s->stat[MCS_ACTIVE_FILE] += val * PAGE_SIZE; val = mem_cgroup_get_local_zonestat(mem, LRU_UNEVICTABLE); s->stat[MCS_UNEVICTABLE] += val * PAGE_SIZE; } 数据结构 struct mem_cgroup { ... /* * statistics. This must be placed at the end of memcg. */ struct mem_cgroup_stat stat; ///统计数据 }; /* memory cgroup统计值 * Statistics for memory cgroup. */ enum mem_cgroup_stat_index { /* * For MEM_CONTAINER_TYPE_ALL, usage = pagecache + rss. */ MEM_CGROUP_STAT_CACHE, /* # of pages charged as cache */ MEM_CGROUP_STAT_RSS, /* # of pages charged as anon rss */ MEM_CGROUP_STAT_FILE_MAPPED, /* # of pages charged as file rss */ MEM_CGROUP_STAT_PGPGIN_COUNT, /* # of pages paged in */ MEM_CGROUP_STAT_PGPGOUT_COUNT, /* # of pages paged out */ MEM_CGROUP_STAT_EVENTS, /* sum of pagein + pageout for internal use */ MEM_CGROUP_STAT_SWAPOUT, /* # of pages, swapped out */ MEM_CGROUP_STAT_NSTATS, }; struct mem_cgroup_stat_cpu { s64 count[MEM_CGROUP_STAT_NSTATS]; } ____cacheline_aligned_in_smp; struct mem_cgroup_stat { struct mem_cgroup_stat_cpu cpustat[0]; }; rss and cache