Difference between Buffers and cached
$free -mtotal used free shared buffers cachedMem: 3777 3746 31 0 160 954-/+ buffers/cache: 2631 1145Swap: 753 1 751
Buffer Pages
Whenever the kernel must individually address a block, it refers to the buffer page that holds the block buffer and checks the corresponding buffer head.
Here are two common cases in which the kernel creates buffer pages:
· When reading or writing pages of a file that are not stored in contiguous disk blocks. This happens either because the filesystem has allocated noncontiguous blocks to the file, or because the file contains "holes"
· When accessing a single disk block (for instance, when reading a superblock or an inode block).
Raw disk operation such dd use buffers.
Read 10M of raw disk block
$dd if=/dev/sda6 of=/dev/zero bs=1024k count=1010+0 records in10+0 records out10485760 bytes (10 MB) copied, 0.209051 seconds, 50.2 MB/s
Buffers sized increased by 10MB( 170M-160M)
Dentry cache, inode cache and page cache in cached column.$free -mtotal used free shared buffers cachedMem: 3777 3754 23 0 170 952-/+ buffers/cache: 2631 1145Swap: 753 1 751
Dentry cache: Directory Entry Cache, pathname (filename) lookup cache.
Inode cache: Cache for inode, not actual data block.
Page cache: Cache for actual data block
[FROM: http://www.mjmwired.net/kernel/Documentation/filesystems/vfs.txt ]
The combined value of dentry and inode cache is not bigger than whole slab size
$grep -i slab /proc/meminfoSlab: 183896 kB
Examine in detail by checking /proc/slabinfo.
$ awk '/dentry|inode/ { print $1,$2,$3,$4}' /proc/slabinfonfs_inode_cache 122787 123312 984rpc_inode_cache 24 25 768ext3_inode_cache 9767 9770 776mqueue_inode_cache 1 4 896isofs_inode_cache 0 0 624minix_inode_cache 0 0 640hugetlbfs_inode_cache 1 7 576ext2_inode_cache 0 0 728shmem_inode_cache 441 455 776sock_inode_cache 231 235 704proc_inode_cache 670 756 608inode_cache 2415 2415 576dentry_cache 99060 110162 200#sum up them (bytes)$awk '/dentry|inode/ { x=x+$3*$4} END {print x }' /proc/slabinfo153348952
view live stats with slabtop by sorting by cache size
$slabtop -s cActive / Total Objects (% used) : 332028 / 361849 (91.8%)Active / Total Slabs (% used) : 45630 / 45631 (100.0%)Active / Total Caches (% used) : 102 / 139 (73.4%)Active / Total Size (% used) : 171443.16K / 175338.12K (97.8%)Minimum / Average / Maximum Object : 0.02K / 0.48K / 128.00KOBJS ACTIVE USE OBJ SIZE SLABS OBJ/SLAB CACHE SIZE NAME125948 125864 99% 0.96K 31487 4 125948K nfs_inode_cache113962 105262 92% 0.20K 5998 19 23992K dentry_cache14609 14460 98% 0.52K 2087 7 8348K radix_tree_node9770 9765 99% 0.76K 1954 5 7816K ext3_inode_cache59048 44057 74% 0.09K 1342 44 5368K buffer_head2415 2410 99% 0.56K 345 7 1380K inode_cache
I haven’t found to way to get page_cache size directly, It needs bit of calculation page_cache=~ cached – inode – dentry
alternatively observe the value change by releasing pagecache
#write dirty pages to disksync#To free pagecache:echo 1 > /proc/sys/vm/drop_caches#To free dentries and inodes:echo 2 > /proc/sys/vm/drop_caches#To free pagecache, dentries and inodes:echo 3 > /proc/sys/vm/drop_caches
As this is a non-destructive operation and dirty objects are not freeable, it is highly recommended to run command “sync” first.
#Suppress page cache usage.
sysctl -w vm.swappiness=0
vm.swappiness # value range: 0 - 100, lower value tends to shrink page cache to get free memory, higher value tends to use swap to get free memory
No comments:
Post a Comment
Note: Only a member of this blog may post a comment.