Apakah penampan linux

static int meminfo_proc_show(struct seq_file *m, void *v)  
{  
……  
cached = global_page_state(NR_FILE_PAGES) -  
 total_swapcache_pages() - i.bufferram;  
if (cached < 0)  
 cached = 0;  
……  
 seq_printf(m,  
 "MemTotal: %8lu kB\n"  
 "MemFree: %8lu kB\n"  
 "Buffers: %8lu kB\n"  
 "Cached: %8lu kB\n"  
 ……  
 ,  
 K(i.totalram),  
 K(i.freeram),  
 K(i.bufferram),  
 K(cached),  
 ……  
 );  
……  
}

void si_meminfo(struct sysinfo *val) 
{ 
 val->totalram = totalram_pages; 
 val->sharedram = 0; 
 val->freeram = global_page_state(NR_FREE_PAGES); 
 val->bufferram = nr_blockdev_pages(); 
 val->totalhigh = totalhigh_pages; 
 val->freehigh = nr_free_highpages(); 
 val->mem_unit = PAGE_SIZE; 
}

long nr_blockdev_pages(void)  
{  
 struct block_device *bdev;  
 long ret = 0;  
 spin_lock(&bdev_lock);  
 list_for_each_entry(bdev, &all_bdevs, bd_list) {  
 ret += bdev->bd_inode->i_mapping->nrpages;  
 }  
 spin_unlock(&bdev_lock);  
 return ret;  
}

[root nfs_dir] # ll -h file_50MB.bin 
-rw-rw-r-- 1 4104 4106 50.0M Feb 24 2016 file_50MB.bin 
[root nfs_dir] # cat /proc/meminfo 
MemTotal: 90532 kB 
MemFree: 65696 kB 
Buffers: 0 kB 
Cached: 8148 kB 
…… 
[root@test nfs_dir] # cp file_50MB.bin / 
[root@test nfs_dir] # cat /proc/meminfo 
MemTotal: 90532 kB 
MemFree: 13012 kB 
Buffers: 0 kB 
Cached: 60488 kB

[0225_19:10:44:10s][root@test nfs_dir] # cat /proc/meminfo 
[0225_19:10:44:10s]MemTotal: 90532 kB  
[0225_19:10:44:10s]MemFree: 58988 kB  
[0225_19:10:44:10s]Buffers: 0 kB  
[0225_19:10:44:10s]Cached: 4144 kB  
...... ......  
[0225_19:11:13:11s][root@test nfs_dir] # dd if=/dev/zero of=/dev/h_sda bs=10M count=2000 &  
[0225_19:11:17:11s][root@test nfs_dir] # cat /proc/meminfo  
[0225_19:11:17:11s]MemTotal: 90532 kB  
[0225_19:11:17:11s]MemFree: 11852 kB  
[0225_19:11:17:11s]Buffers: 36224 kB  
[0225_19:11:17:11s]Cached: 4148 kB  
...... ......  
[0225_19:11:21:11s][root@test nfs_dir] # cat /proc/meminfo  
[0225_19:11:21:11s]MemTotal: 90532 kB  
[0225_19:11:21:11s]MemFree: 11356 kB  
[0225_19:11:21:11s]Buffers: 36732 kB  
[0225_19:11:21:11s]Cached: 4148kB  
...... ......  
[0225_19:11:41:11s][root@test nfs_dir] # cat /proc/meminfo  
[0225_19:11:41:11s]MemTotal: 90532 kB  
[0225_19:11:41:11s]MemFree: 11864 kB  
[0225_19:11:41:11s]Buffers: 36264 kB  
[0225_19:11:41:11s]Cached: 4148 kB  
….. ……

int posix_fadvise(int fd, off_t offset, off_t len, int advice);

/*  
 * POSIX_FADV_WILLNEED could set PG_Referenced, and POSIX_FADV_NOREUSE could  
 * deactivate the pages and clear PG_Referenced.  
 */  
SYSCALL_DEFINE4(fadvise64_64, int, fd, loff_t, offset, loff_t, len, int, advice)  
{  
 … … … …  
 /* => 将指定范围内的数据从page cache中换出 */  
 case POSIX_FADV_DONTNEED:  
 /* => 如果后备设备不忙的话，先调用__filemap_fdatawrite_range把脏页面刷掉 */  
 if (!bdi_write_congested(mapping->backing_dev_info))  
 /* => WB_SYNC_NONE: 不是同步等待页面刷新完成，只是提交了 */  
 /* => 而fsync和fdatasync是用WB_SYNC_ALL参数等到完成才返回的 */  
 __filemap_fdatawrite_range(mapping, offset, endbyte,  
 WB_SYNC_NONE);  
  
 
 /* First and last FULL page! */  
 start_index = (offset+(PAGE_CACHE_SIZE-1)) >> PAGE_CACHE_SHIFT;  
 end_index = (endbyte >> PAGE_CACHE_SHIFT);  
  
 
 /* => 接下来清除页面缓存 */ 
 if (end_index >= start_index) {  
 unsigned long count = invalidate_mapping_pages(mapping,  
 start_index, end_index); 
  
 
 /*  
 * If fewer pages were invalidated than expected then  
 * it is possible that some of the pages were on 
 * a per-cpu pagevec for a remote CPU. Drain all  
 * pagevecs and try again.  
 */  
 if (count < (end_index - start_index + 1)) {  
 lru_add_drain_all();  
 invalidate_mapping_pages(mapping, start_index,  
 end_index);  
 }  
 }  
 break;  
… … … …  
}

/* => 清除缓存页(除了脏页、上锁的、正在回写的或映射在页表中的)*/  
unsigned long invalidate_mapping_pages(struct address_space *mapping,  
 pgoff_t start, pgoff_t end)  
{  
 struct pagevec pvec;  
 pgoff_t index = start;  
 unsigned long ret;  
 unsigned long count = 0;  
 int i;  
  
 
 /*  
 * Note: this function may get called on a shmem/tmpfs mapping:  
 * pagevec_lookup() might then return 0 prematurely (because it  
 * got a gangful of swap entries); but it's hardly worth worrying  
 * about - it can rarely have anything to free from such a mapping  
 * (most pages are dirty), and already skips over any difficulties.  
 */  
  
 
 pagevec_init(&pvec, 0);  
 while (index <= end && pagevec_lookup(&pvec, mapping, index,  
 min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1)) {  
 mem_cgroup_uncharge_start();  
 for (i = 0; i < pagevec_count(&pvec); i++) {  
 struct page *page = pvec.pages[i];  
  
 
 /* We rely upon deletion not changing page->index */  
 index = page->index;  
 if (index > end)  
 break;  
  
 
 if (!trylock_page(page))  
 continue;  
 WARN_ON(page->index != index);  
 /* => 无效一个文件的缓存 */  
 ret = invalidate_inode_page(page);  
 unlock_page(page);  
 /*  
 * Invalidation is a hint that the page is no longer  
 * of interest and try to speed up its reclaim.  
 */  
 if (!ret)  
 deactivate_page(page);  
 count += ret;  
 }  
 pagevec_release(&pvec);  
 mem_cgroup_uncharge_end();  
 cond_resched();  
 index++;  
 }  
 return count;  
} 
   
 
/*  
 * Safely invalidate one page from its pagecache mapping.  
 * It only drops clean, unused pages. The page must be locked.  
 *  
 * Returns 1 if the page is successfully invalidated, otherwise 0.  
 */  
/* => 无效一个文件的缓存 */  
int invalidate_inode_page(struct page *page)  
{  
 struct address_space *mapping = page_mapping(page);  
 if (!mapping)  
 return 0;  
 /* => 若当前页是脏页或正在写回的页，直接返回 */  
 if (PageDirty(page) || PageWriteback(page))  
 return 0;  
 /* => 若已经被映射到页表了，则直接返回 */  
 if (page_mapped(page))  
 return 0;  
 /* => 如果满足了以上条件就调用invalidate_complete_page继续 */  
 return invalidate_complete_page(mapping, page);  
}  
从上面的代码可以看到清除相关的页面要满足二个条件： 1. 不脏且没在回写； 2. 未被使用。如果满足了这二个条件就调用invalidate_complete_page继续：  
/* => 无效一个完整的页 */  
static int  
invalidate_complete_page(struct address_space *mapping, struct page *page)  
{  
 int ret;  
  
 
 if (page->mapping != mapping)  
 return 0;  
  
 
 if (page_has_private(page) && !try_to_release_page(page, 0))  
 return 0;  
  
 
 /* => 若满足以上更多条件，则从地址空间中解除该页 */  
 ret = remove_mapping(mapping, page); 
   
 
 return ret;  
}  
  
 
/*  
 * Attempt to detach a locked page from its ->mapping. If it is dirty or if  
 * someone else has a ref on the page, abort and return 0. If it was  
 * successfully detached, return 1. Assumes the caller has a single ref on  
 * this page.  
 */  
/* => 从地址空间中解除该页 */  
int remove_mapping(struct address_space *mapping, struct page *page) 
{  
 if (__remove_mapping(mapping, page)) {  
 /*  
 * Unfreezing the refcount with 1 rather than 2 effectively  
 * drops the pagecache ref for us without requiring another  
 * atomic operation.  
 */  
 page_unfreeze_refs(page, 1);  
 return 1;  
 }  
 return 0;  
} 
   
 
/*  
 * Same as remove_mapping, but if the page is removed from the mapping, it  
 * gets returned with a refcount of 0.  
 */  
/* => 从地址空间中解除该页 */  
static int __remove_mapping(struct address_space *mapping, struct page *page)  
{  
 BUG_ON(!PageLocked(page));  
 BUG_ON(mapping != page_mapping(page));  
  
 
 spin_lock_irq(&mapping->tree_lock);  
 /*  
 * The non racy check for a busy page.  
 *  
 * Must be careful with the order of the tests. When someone has  
 * a ref to the page, it may be possible that they dirty it then  
 * drop the reference. So if PageDirty is tested before page_count 
 * here, then the following race may occur: 
 *  
 * get_user_pages(&page);  
 * [user mapping goes away]  
 * write_to(page);  
 * !PageDirty(page) [good]  
 * SetPageDirty(page); 
 * put_page(page); 
 * !page_count(page) [good, discard it]  
 *  
 * [oops, our write_to data is lost]  
 *  
 * Reversing the order of the tests ensures such a situation cannot  
 * escape unnoticed. The smp_rmb is needed to ensure the page->flags  
 * load is not satisfied before that of page->_count.  
 *  
 * Note that if SetPageDirty is always performed via set_page_dirty,  
 * and thus under tree_lock, then this ordering is not required. 
 */  
 if (!page_freeze_refs(page, 2))  
 goto cannot_free;  
 /* note: atomic_cmpxchg in page_freeze_refs provides the smp_rmb */  
 if (unlikely(PageDirty(page))) {  
 page_unfreeze_refs(page, 2);  
 goto cannot_free; 
 } 
  
 if (PageSwapCache(page)) {  
 swp_entry_t swap = { .val = page_private(page) }; 
 __delete_from_swap_cache(page);  
 spin_unlock_irq(&mapping->tree_lock);  
 swapcache_free(swap, page);  
 } else {  
 void (*freepage)(struct page *);  
  
 
 freepage = mapping->a_ops->freepage;  
  
  /* => 从页缓存中删除和释放该页 */ 
  __delete_from_page_cache(page); 
  spin_unlock_irq(&mapping->tree_lock); 
  mem_cgroup_uncharge_cache_page(page); 
   
  if (freepage != NULL) 
  freepage(page);  
 }  
  
  return 1;  
  
 
cannot_free:  
 spin_unlock_irq(&mapping->tree_lock);  
 return 0;  
}  
  
 /* 
 * Delete a page from the page cache and free it. Caller has to make  
 * sure the page is locked and that nobody else uses it - or that usage  
 * is safe. The caller must hold the mapping&#39;s tree_lock.  
 */  
/* => 从页缓存中删除和释放该页 */  
void __delete_from_page_cache(struct page *page)  
{  
 struct address_space *mapping = page->mapping;  
   
 trace_mm_filemap_delete_from_page_cache(page);  
 /*  
 * if we&#39;re uptodate, flush out into the cleancache, otherwise  
 * invalidate any existing cleancache entries. We can&#39;t leave  
 * stale data around in the cleancache once our page is gone  
 */  
 if (PageUptodate(page) && PageMappedToDisk(page))  
 cleancache_put_page(page);  
 else  
 cleancache_invalidate_page(mapping, page);  
  
 
 radix_tree_delete(&mapping->page_tree, page->index);  
 /* => 解除与之绑定的地址空间结构 */  
 page->mapping = NULL;  
 /* Leave page->index set: truncation lookup relies upon it */  
 /* => 减少地址空间中的页计数 */ 
 mapping->nrpages--; 
 __dec_zone_page_state(page, NR_FILE_PAGES);  
 if (PageSwapBacked(page))  
 __dec_zone_page_state(page, NR_SHMEM);  
 BUG_ON(page_mapped(page)); 
   
 
 /*  
 * Some filesystems seem to re-dirty the page even after  
 * the VM has canceled the dirty bit (eg ext3 journaling).  
 *  
 * Fix it up by doing a final dirty accounting check after  
 * having removed the page entirely.  
 */  
 if (PageDirty(page) && mapping_cap_account_dirty(mapping)) {  
 dec_zone_page_state(page, NR_FILE_DIRTY);  
 dec_bdi_stat(mapping->backing_dev_info, BDI_RECLAIMABLE); 
 } 
}

fdatasync(fd); 
posix_fadvise(fd, 0, 0, POSIX_FADV_DONTNEED);

$ git clone https://github.com/hoytech/vmtouch.git 
$ cd vmtouch 
$ make 
$ sudo make install

NAME 
 mincore - determine whether pages are resident in memory 
 
  
SYNOPSIS 
 #include <unistd.h> 
 #include <sys/mman.h> 
  
 
 int mincore(void *addr, size_t length, unsigned char *vec); 
 
  
 Feature Test Macro Requirements for glibc (see feature_test_macros(7)): 
 
  
 mincore(): _BSD_SOURCE || _SVID_SOURCE

[root@test nfs_dir] # mkdir /mnt/usb && mount /dev/msc /mnt/usb/  
[root@test usb] # vmtouch .  
 Files: 57  
 Directories: 2  
 Resident Pages: 0/278786 0/1G 0%  
 Elapsed: 0.023126 seconds

[root@test usb] # busybox_v400 tail -n 10 test.bin > /dev/null

[root@test usb] # vmtouch -v test.bin  
test.bin  
[ o] 240/25600  
  
 
 Files: 1  
 Directories: 0  
 Resident Pages: 240/25600 960K/100M 0.938%  
 Elapsed: 0.002019 seconds

[root@test usb] # vmtouch -vt test.bin  
test.bin  
[OOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOO] 25600/25600  
  
 
 Files: 1  
 Directories: 0  
 Touched Pages: 25600 (100M) 
 Elapsed: 39.049 seconds

[root@test usb] # vmtouch -ev test.bin  
Evicting test.bin  
  
 
 Files: 1  
 Directories: 0  
 Evicted Pages: 25600 (100M)  
 Elapsed: 0.01461 seconds

int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,  
 unsigned long arg)  
{  
 struct gendisk *disk = bdev->bd_disk;  
 struct backing_dev_info *bdi;  
 loff_t size;  
 int ret, n;  
  
 
 switch(cmd) {  
 case BLKFLSBUF:  
 if (!capable(CAP_SYS_ADMIN))  
 return -EACCES;  
  
 
 ret = __blkdev_driver_ioctl(bdev, mode, cmd, arg);  
 if (!is_unrecognized_ioctl(ret))  
 return ret;  
  
 
 fsync_bdev(bdev);  
 invalidate_bdev(bdev); 
 return 0;  
case ……:  
…………  
}  
  
 
/* Invalidate clean unused buffers and pagecache. */  
void invalidate_bdev(struct block_device *bdev)  
{  
 struct address_space *mapping = bdev->bd_inode->i_mapping;  
  
 
 if (mapping->nrpages == 0)  
 return;  
  
 
 invalidate_bh_lrus();  
 lru_add_drain_all(); /* make sure all lru add caches are flushed */  
 invalidate_mapping_pages(mapping, 0, -1);  
 /* 99% of the time, we don't need to flush the cleancache on the bdev.  
 * But, for the strange corners, lets be cautious  
 */  
 cleancache_invalidate_inode(mapping);  
}  
EXPORT_SYMBOL(invalidate_bdev);

[0225_19:10:25:10s][root@test nfs_dir] # cat /proc/meminfo  
[0225_19:10:25:10s]MemTotal: 90532 kB  
[0225_19:10:25:10s]MemFree: 12296 kB  
[0225_19:10:25:10s]Buffers: 46076 kB  
[0225_19:10:25:10s]Cached: 4136 kB  
…………  
[0225_19:10:42:10s][root@test nfs_dir] # /mnt/nfs_dir/a.out  
[0225_19:10:42:10s]ioctl cmd BLKFLSBUF ok!  
[0225_19:10:44:10s][root@test nfs_dir] # cat /proc/meminfo  
[0225_19:10:44:10s]MemTotal: 90532 kB  
[0225_19:10:44:10s]MemFree: 58988 kB  
[0225_19:10:44:10s]Buffers: 0 kB  
…………  
[0225_19:10:44:10s]Cached: 4144 kB

#include <stdio.h>  
#include <fcntl.h>  
#include <errno.h> 
#include <sys/ioctl.h> 
#define BLKFLSBUF _IO(0x12, 97) 
int main(int argc, char* argv[])  
{  
 int fd = -1;  
 fd = open("/dev/h_sda", O_RDWR); 
 if (fd < 0) 
 { 
 return -1; 
 }  
 if (ioctl(fd, BLKFLSBUF, 0))  
 {  
 printf("ioctl cmd BLKFLSBUF failed, errno:%d\n", errno);  
 } 
 close(fd); 
printf("ioctl cmd BLKFLSBUF ok!\n"); 
 return 0;  
}

int drop_caches_sysctl_handler(ctl_table *table, int write,  
 void __user *buffer, size_t *length, loff_t *ppos)  
{  
 int ret;  
  
 
 ret = proc_dointvec_minmax(table, write, buffer, length, ppos);  
 if (ret)  
 return ret;  
 if (write) {  
 /* => echo 1 > /proc/sys/vm/drop_caches 清理页缓存 */  
 if (sysctl_drop_caches & 1)  
 /* => 遍历所有的超级块，清理所有的缓存 */  
 iterate_supers(drop_pagecache_sb, NULL);  
 if (sysctl_drop_caches & 2)  
 drop_slab();  
 }  
 return 0;  
}  
  
 
/**  
 * iterate_supers - call function for all active superblocks  
 * @f: function to call  
 * @arg: argument to pass to it  
 *  
 * Scans the superblock list and calls given function, passing it  
 * locked superblock and given argument.  
 */  
void iterate_supers(void (*f)(struct super_block *, void *), void *arg)  
{  
 struct super_block *sb, *p = NULL;  
  
 
 spin_lock(&sb_lock);  
 list_for_each_entry(sb, &super_blocks, s_list) {  
 if (hlist_unhashed(&sb->s_instances))  
 continue;  
 sb->s_count++;  
 spin_unlock(&sb_lock);  
  
 
 down_read(&sb->s_umount); 
 if (sb->s_root && (sb->s_flags & MS_BORN))  
 f(sb, arg);  
 up_read(&sb->s_umount); 
  
 
 spin_lock(&sb_lock);  
 if (p) 
 __put_super(p);  
 p = sb;  
 }  
 if (p)  
 __put_super(p);  
 spin_unlock(&sb_lock); 
} 
  
 
/* => 清理文件系统(包括bdev伪文件系统)的页缓存 */  
static void drop_pagecache_sb(struct super_block *sb, void *unused)  
{  
 struct inode *inode, *toput_inode = NULL;  
  
 
 spin_lock(&inode_sb_list_lock);  
 /* => 遍历所有的inode */  
 list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {  
 spin_lock(&inode->i_lock);  
 /* 
 * => 若当前状态为(I_FREEING|I_WILL_FREE|I_NEW) 或  
 * => 若没有缓存页  
 * => 则跳过  
 */  
 if ((inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) ||  
 (inode->i_mapping->nrpages == 0)) { 
 spin_unlock(&inode->i_lock);  
 continue;  
 }  
 __iget(inode);  
 spin_unlock(&inode->i_lock);  
 spin_unlock(&inode_sb_list_lock);  
 /* => 清除缓存页(除了脏页、上锁的、正在回写的或映射在页表中的)*/  
 invalidate_mapping_pages(inode->i_mapping, 0, -1);  
 iput(toput_inode);  
 toput_inode = inode;  
 spin_lock(&inode_sb_list_lock);  
 } 
 spin_unlock(&inode_sb_list_lock);  
 iput(toput_inode);  
}

[root@test usb] # cat /proc/meminfo 
MemTotal: 90516 kB 
MemFree: 12396 kB 
Buffers: 96 kB 
Cached: 60756 kB 
[root@test usb] # busybox_v400 sync 
[root@test usb] # busybox_v400 sync 
[root@test usb] # busybox_v400 sync 
[root@test usb] # echo 1 > /proc/sys/vm/drop_caches 
[root@test usb] # cat /proc/meminfo 
MemTotal: 90516 kB 
MemFree: 68820 kB 
Buffers: 12 kB 
Cached: 4464 kB