alistair23-linux/include/linux/page_cgroup.h
KAMEZAWA Hiroyuki a3b2d69269 cgroups: use css id in swap cgroup for saving memory v5
Try to use CSS ID for records in swap_cgroup.  By this, on 64bit machine,
size of swap_cgroup goes down to 2 bytes from 8bytes.

This means, when 2GB of swap is equipped, (assume the page size is 4096bytes)

	From size of swap_cgroup = 2G/4k * 8 = 4Mbytes.
	To   size of swap_cgroup = 2G/4k * 2 = 1Mbytes.

Reduction is large.  Of course, there are trade-offs.  This CSS ID will
add overhead to swap-in/swap-out/swap-free.

But in general,
  - swap is a resource which the user tend to avoid use.
  - If swap is never used, swap_cgroup area is not used.
  - Reading traditional manuals, size of swap should be proportional to
    size of memory. Memory size of machine is increasing now.

I think reducing size of swap_cgroup makes sense.

Note:
  - ID->CSS lookup routine has no locks, it's under RCU-Read-Side.
  - memcg can be obsolete at rmdir() but not freed while refcnt from
    swap_cgroup is available.

Changelog v4->v5:
 - reworked on to memcg-charge-swapcache-to-proper-memcg.patch
Changlog ->v4:
 - fixed not configured case.
 - deleted unnecessary comments.
 - fixed NULL pointer bug.
 - fixed message in dmesg.

[nishimura@mxp.nes.nec.co.jp: css_tryget can be called twice in !PageCgroupUsed case]
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Balbir Singh <balbir@in.ibm.com>
Cc: Paul Menage <menage@google.com>
Cc: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-02 19:04:56 -07:00

126 lines
2.9 KiB
C

#ifndef __LINUX_PAGE_CGROUP_H
#define __LINUX_PAGE_CGROUP_H
#ifdef CONFIG_CGROUP_MEM_RES_CTLR
#include <linux/bit_spinlock.h>
/*
* Page Cgroup can be considered as an extended mem_map.
* A page_cgroup page is associated with every page descriptor. The
* page_cgroup helps us identify information about the cgroup
* All page cgroups are allocated at boot or memory hotplug event,
* then the page cgroup for pfn always exists.
*/
struct page_cgroup {
unsigned long flags;
struct mem_cgroup *mem_cgroup;
struct page *page;
struct list_head lru; /* per cgroup LRU list */
};
void __meminit pgdat_page_cgroup_init(struct pglist_data *pgdat);
void __init page_cgroup_init(void);
struct page_cgroup *lookup_page_cgroup(struct page *page);
enum {
/* flags for mem_cgroup */
PCG_LOCK, /* page cgroup is locked */
PCG_CACHE, /* charged as cache */
PCG_USED, /* this object is in use. */
};
#define TESTPCGFLAG(uname, lname) \
static inline int PageCgroup##uname(struct page_cgroup *pc) \
{ return test_bit(PCG_##lname, &pc->flags); }
#define SETPCGFLAG(uname, lname) \
static inline void SetPageCgroup##uname(struct page_cgroup *pc)\
{ set_bit(PCG_##lname, &pc->flags); }
#define CLEARPCGFLAG(uname, lname) \
static inline void ClearPageCgroup##uname(struct page_cgroup *pc) \
{ clear_bit(PCG_##lname, &pc->flags); }
/* Cache flag is set only once (at allocation) */
TESTPCGFLAG(Cache, CACHE)
TESTPCGFLAG(Used, USED)
CLEARPCGFLAG(Used, USED)
static inline int page_cgroup_nid(struct page_cgroup *pc)
{
return page_to_nid(pc->page);
}
static inline enum zone_type page_cgroup_zid(struct page_cgroup *pc)
{
return page_zonenum(pc->page);
}
static inline void lock_page_cgroup(struct page_cgroup *pc)
{
bit_spin_lock(PCG_LOCK, &pc->flags);
}
static inline int trylock_page_cgroup(struct page_cgroup *pc)
{
return bit_spin_trylock(PCG_LOCK, &pc->flags);
}
static inline void unlock_page_cgroup(struct page_cgroup *pc)
{
bit_spin_unlock(PCG_LOCK, &pc->flags);
}
#else /* CONFIG_CGROUP_MEM_RES_CTLR */
struct page_cgroup;
static inline void __meminit pgdat_page_cgroup_init(struct pglist_data *pgdat)
{
}
static inline struct page_cgroup *lookup_page_cgroup(struct page *page)
{
return NULL;
}
static inline void page_cgroup_init(void)
{
}
#endif
#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
#include <linux/swap.h>
extern unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id);
extern unsigned short lookup_swap_cgroup(swp_entry_t ent);
extern int swap_cgroup_swapon(int type, unsigned long max_pages);
extern void swap_cgroup_swapoff(int type);
#else
#include <linux/swap.h>
static inline
unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id)
{
return 0;
}
static inline
unsigned short lookup_swap_cgroup(swp_entry_t ent)
{
return 0;
}
static inline int
swap_cgroup_swapon(int type, unsigned long max_pages)
{
return 0;
}
static inline void swap_cgroup_swapoff(int type)
{
return;
}
#endif
#endif