8c7c6e34a1
This patch implements per cgroup limit for usage of memory+swap. However
there are SwapCache, double counting of swap-cache and swap-entry is
avoided.
Mem+Swap controller works as following.
- memory usage is limited by memory.limit_in_bytes.
- memory + swap usage is limited by memory.memsw_limit_in_bytes.
This has following benefits.
- A user can limit total resource usage of mem+swap.
Without this, because memory resource controller doesn't take care of
usage of swap, a process can exhaust all the swap (by memory leak.)
We can avoid this case.
And Swap is shared resource but it cannot be reclaimed (goes back to memory)
until it's used. This characteristic can be trouble when the memory
is divided into some parts by cpuset or memcg.
Assume group A and group B.
After some application executes, the system can be..
Group A -- very large free memory space but occupy 99% of swap.
Group B -- under memory shortage but cannot use swap...it's nearly full.
Ability to set appropriate swap limit for each group is required.
Maybe someone wonder "why not swap but mem+swap ?"
- The global LRU(kswapd) can swap out arbitrary pages. Swap-out means
to move account from memory to swap...there is no change in usage of
mem+swap.
In other words, when we want to limit the usage of swap without affecting
global LRU, mem+swap limit is better than just limiting swap.
Accounting target information is stored in swap_cgroup which is
per swap entry record.
Charge is done as following.
map
- charge page and memsw.
unmap
- uncharge page/memsw if not SwapCache.
swap-out (__delete_from_swap_cache)
- uncharge page
- record mem_cgroup information to swap_cgroup.
swap-in (do_swap_page)
- charged as page and memsw.
record in swap_cgroup is cleared.
memsw accounting is decremented.
swap-free (swap_free())
- if swap entry is freed, memsw is uncharged by PAGE_SIZE.
There are people work under never-swap environments and consider swap as
something bad. For such people, this mem+swap controller extension is just an
overhead. This overhead is avoided by config or boot option.
(see Kconfig. detail is not in this patch.)
TODO:
- maybe more optimization can be don in swap-in path. (but not very safe.)
But we just do simple accounting at this stage.
[nishimura@mxp.nes.nec.co.jp: make resize limit hold mutex]
[hugh@veritas.com: memswap controller core swapcache fixes]
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: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
196 lines
5.2 KiB
C
196 lines
5.2 KiB
C
/* memcontrol.h - Memory Controller
|
|
*
|
|
* Copyright IBM Corporation, 2007
|
|
* Author Balbir Singh <balbir@linux.vnet.ibm.com>
|
|
*
|
|
* Copyright 2007 OpenVZ SWsoft Inc
|
|
* Author: Pavel Emelianov <xemul@openvz.org>
|
|
*
|
|
* This program is free software; you can redistribute it and/or modify
|
|
* it under the terms of the GNU General Public License as published by
|
|
* the Free Software Foundation; either version 2 of the License, or
|
|
* (at your option) any later version.
|
|
*
|
|
* This program is distributed in the hope that it will be useful,
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
* GNU General Public License for more details.
|
|
*/
|
|
|
|
#ifndef _LINUX_MEMCONTROL_H
|
|
#define _LINUX_MEMCONTROL_H
|
|
|
|
struct mem_cgroup;
|
|
struct page_cgroup;
|
|
struct page;
|
|
struct mm_struct;
|
|
|
|
#ifdef CONFIG_CGROUP_MEM_RES_CTLR
|
|
|
|
extern int mem_cgroup_newpage_charge(struct page *page, struct mm_struct *mm,
|
|
gfp_t gfp_mask);
|
|
/* for swap handling */
|
|
extern int mem_cgroup_try_charge(struct mm_struct *mm,
|
|
gfp_t gfp_mask, struct mem_cgroup **ptr);
|
|
extern int mem_cgroup_try_charge_swapin(struct mm_struct *mm,
|
|
struct page *page, gfp_t mask, struct mem_cgroup **ptr);
|
|
extern void mem_cgroup_commit_charge_swapin(struct page *page,
|
|
struct mem_cgroup *ptr);
|
|
extern void mem_cgroup_cancel_charge_swapin(struct mem_cgroup *ptr);
|
|
|
|
extern int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
|
|
gfp_t gfp_mask);
|
|
extern void mem_cgroup_move_lists(struct page *page, enum lru_list lru);
|
|
extern void mem_cgroup_uncharge_page(struct page *page);
|
|
extern void mem_cgroup_uncharge_cache_page(struct page *page);
|
|
extern int mem_cgroup_shrink_usage(struct mm_struct *mm, gfp_t gfp_mask);
|
|
|
|
extern unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
|
|
struct list_head *dst,
|
|
unsigned long *scanned, int order,
|
|
int mode, struct zone *z,
|
|
struct mem_cgroup *mem_cont,
|
|
int active, int file);
|
|
extern void mem_cgroup_out_of_memory(struct mem_cgroup *mem, gfp_t gfp_mask);
|
|
int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *mem);
|
|
|
|
extern struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p);
|
|
|
|
#define mm_match_cgroup(mm, cgroup) \
|
|
((cgroup) == mem_cgroup_from_task((mm)->owner))
|
|
|
|
extern int
|
|
mem_cgroup_prepare_migration(struct page *page, struct mem_cgroup **ptr);
|
|
extern void mem_cgroup_end_migration(struct mem_cgroup *mem,
|
|
struct page *oldpage, struct page *newpage);
|
|
|
|
/*
|
|
* For memory reclaim.
|
|
*/
|
|
extern int mem_cgroup_calc_mapped_ratio(struct mem_cgroup *mem);
|
|
extern long mem_cgroup_reclaim_imbalance(struct mem_cgroup *mem);
|
|
|
|
extern int mem_cgroup_get_reclaim_priority(struct mem_cgroup *mem);
|
|
extern void mem_cgroup_note_reclaim_priority(struct mem_cgroup *mem,
|
|
int priority);
|
|
extern void mem_cgroup_record_reclaim_priority(struct mem_cgroup *mem,
|
|
int priority);
|
|
|
|
extern long mem_cgroup_calc_reclaim(struct mem_cgroup *mem, struct zone *zone,
|
|
int priority, enum lru_list lru);
|
|
|
|
#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
|
|
extern int do_swap_account;
|
|
#endif
|
|
#else /* CONFIG_CGROUP_MEM_RES_CTLR */
|
|
struct mem_cgroup;
|
|
|
|
static inline int mem_cgroup_newpage_charge(struct page *page,
|
|
struct mm_struct *mm, gfp_t gfp_mask)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline int mem_cgroup_cache_charge(struct page *page,
|
|
struct mm_struct *mm, gfp_t gfp_mask)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline int mem_cgroup_try_charge(struct mm_struct *mm,
|
|
gfp_t gfp_mask, struct mem_cgroup **ptr)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline int mem_cgroup_try_charge_swapin(struct mm_struct *mm,
|
|
struct page *page, gfp_t gfp_mask, struct mem_cgroup **ptr)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline void mem_cgroup_commit_charge_swapin(struct page *page,
|
|
struct mem_cgroup *ptr)
|
|
{
|
|
}
|
|
|
|
static inline void mem_cgroup_cancel_charge_swapin(struct mem_cgroup *ptr)
|
|
{
|
|
}
|
|
|
|
static inline void mem_cgroup_uncharge_page(struct page *page)
|
|
{
|
|
}
|
|
|
|
static inline void mem_cgroup_uncharge_cache_page(struct page *page)
|
|
{
|
|
}
|
|
|
|
static inline int mem_cgroup_shrink_usage(struct mm_struct *mm, gfp_t gfp_mask)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline void mem_cgroup_move_lists(struct page *page, bool active)
|
|
{
|
|
}
|
|
|
|
static inline int mm_match_cgroup(struct mm_struct *mm, struct mem_cgroup *mem)
|
|
{
|
|
return 1;
|
|
}
|
|
|
|
static inline int task_in_mem_cgroup(struct task_struct *task,
|
|
const struct mem_cgroup *mem)
|
|
{
|
|
return 1;
|
|
}
|
|
|
|
static inline int
|
|
mem_cgroup_prepare_migration(struct page *page, struct mem_cgroup **ptr)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline void mem_cgroup_end_migration(struct mem_cgroup *mem,
|
|
struct page *oldpage,
|
|
struct page *newpage)
|
|
{
|
|
}
|
|
|
|
static inline int mem_cgroup_calc_mapped_ratio(struct mem_cgroup *mem)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline int mem_cgroup_reclaim_imbalance(struct mem_cgroup *mem)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline int mem_cgroup_get_reclaim_priority(struct mem_cgroup *mem)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline void mem_cgroup_note_reclaim_priority(struct mem_cgroup *mem,
|
|
int priority)
|
|
{
|
|
}
|
|
|
|
static inline void mem_cgroup_record_reclaim_priority(struct mem_cgroup *mem,
|
|
int priority)
|
|
{
|
|
}
|
|
|
|
static inline long mem_cgroup_calc_reclaim(struct mem_cgroup *mem,
|
|
struct zone *zone, int priority,
|
|
enum lru_list lru)
|
|
{
|
|
return 0;
|
|
}
|
|
#endif /* CONFIG_CGROUP_MEM_CONT */
|
|
|
|
#endif /* _LINUX_MEMCONTROL_H */
|
|
|