Commit 9d0243bc authored by Andrew Morton's avatar Andrew Morton Committed by Linus Torvalds
Browse files

[PATCH] drop-pagecache 



Add /proc/sys/vm/drop_caches.  When written to, this will cause the kernel to
discard as much pagecache and/or reclaimable slab objects as it can.  THis
operation requires root permissions.

It won't drop dirty data, so the user should run `sync' first.

Caveats:

a) Holds inode_lock for exorbitant amounts of time.

b) Needs to be taught about NUMA nodes: propagate these all the way through
   so the discarding can be controlled on a per-node basis.

This is a debugging feature: useful for getting consistent results between
filesystem benchmarks.  We could possibly put it under a config option, but
it's less than 300 bytes.

Signed-off-by: default avatarAndrew Morton <akpm@osdl.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@osdl.org>
parent bec6b0c8

Documentation/filesystems/proc.txt

+17 −0
Original line number Diff line number Diff line
@@ -1302,6 +1302,23 @@ VM has token based thrashing control mechanism and uses the token to prevent 
unnecessary page faults in thrashing situation. The unit of the value is

second. The value would be useful to tune thrashing behavior.



drop_caches

-----------



Writing to this will cause the kernel to drop clean caches, dentries and

inodes from memory, causing that memory to become free.



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, the

user should run `sync' first.





2.5 /proc/sys/dev - Device specific parameters

----------------------------------------------

Documentation/sysctl/vm.txt

+2 −1
Original line number Diff line number Diff line
@@ -26,12 +26,13 @@ Currently, these files are in /proc/sys/vm: 
- min_free_kbytes

- laptop_mode

- block_dump

- drop-caches



==============================================================



dirty_ratio, dirty_background_ratio, dirty_expire_centisecs,

dirty_writeback_centisecs, vfs_cache_pressure, laptop_mode,

block_dump, swap_token_timeout:

block_dump, swap_token_timeout, drop-caches:



See Documentation/filesystems/proc.txt

fs/Makefile

+1 −1
Original line number Diff line number Diff line
@@ -10,7 +10,7 @@ obj-y := open.o read_write.o file_table.o buffer.o bio.o super.o \ 
		ioctl.o readdir.o select.o fifo.o locks.o dcache.o inode.o \

		attr.o bad_inode.o file.o filesystems.o namespace.o aio.o \

		seq_file.o xattr.o libfs.o fs-writeback.o mpage.o direct-io.o \

		ioprio.o pnode.o

		ioprio.o pnode.o drop_caches.o



obj-$(CONFIG_INOTIFY)		+= inotify.o

obj-$(CONFIG_EPOLL)		+= eventpoll.o

fs/drop_caches.c

0 → 100644
+68 −0
Original line number Diff line number Diff line 
/*

 * Implement the manual drop-all-pagecache function

 */



#include <linux/kernel.h>

#include <linux/mm.h>

#include <linux/fs.h>

#include <linux/writeback.h>

#include <linux/sysctl.h>

#include <linux/gfp.h>



/* A global variable is a bit ugly, but it keeps the code simple */

int sysctl_drop_caches;



static void drop_pagecache_sb(struct super_block *sb)

{

	struct inode *inode;



	spin_lock(&inode_lock);

	list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {

		if (inode->i_state & (I_FREEING|I_WILL_FREE))

			continue;

		invalidate_inode_pages(inode->i_mapping);

	}

	spin_unlock(&inode_lock);

}



void drop_pagecache(void)

{

	struct super_block *sb;



	spin_lock(&sb_lock);

restart:

	list_for_each_entry(sb, &super_blocks, s_list) {

		sb->s_count++;

		spin_unlock(&sb_lock);

		down_read(&sb->s_umount);

		if (sb->s_root)

			drop_pagecache_sb(sb);

		up_read(&sb->s_umount);

		spin_lock(&sb_lock);

		if (__put_super_and_need_restart(sb))

			goto restart;

	}

	spin_unlock(&sb_lock);

}



void drop_slab(void)

{

	int nr_objects;



	do {

		nr_objects = shrink_slab(1000, GFP_KERNEL, 1000);

	} while (nr_objects > 10);

}



int drop_caches_sysctl_handler(ctl_table *table, int write,

	struct file *file, void __user *buffer, size_t *length, loff_t *ppos)

{

	proc_dointvec_minmax(table, write, file, buffer, length, ppos);

	if (write) {

		if (sysctl_drop_caches & 1)

			drop_pagecache();

		if (sysctl_drop_caches & 2)

			drop_slab();

	}

	return 0;

}

include/linux/mm.h

+7 −0
Original line number Diff line number Diff line
@@ -1036,5 +1036,12 @@ int in_gate_area_no_task(unsigned long addr); 
/* /proc/<pid>/oom_adj set to -17 protects from the oom-killer */

#define OOM_DISABLE -17



int drop_caches_sysctl_handler(struct ctl_table *, int, struct file *,

					void __user *, size_t *, loff_t *);

int shrink_slab(unsigned long scanned, gfp_t gfp_mask,

			unsigned long lru_pages);

void drop_pagecache(void);

void drop_slab(void);



#endif /* __KERNEL__ */

#endif /* _LINUX_MM_H */

CRA Git | Maintained and supported by SUSTech CRA and CCSE