linux_dsm_epyc7002/include/linux/memcontrol.h

189 lines
4.9 KiB
C
Raw Normal View History

/* 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
memcg: introduce charge-commit-cancel style of functions There is a small race in do_swap_page(). When the page swapped-in is charged, the mapcount can be greater than 0. But, at the same time some process (shares it ) call unmap and make mapcount 1->0 and the page is uncharged. CPUA CPUB mapcount == 1. (1) charge if mapcount==0 zap_pte_range() (2) mapcount 1 => 0. (3) uncharge(). (success) (4) set page's rmap() mapcount 0=>1 Then, this swap page's account is leaked. For fixing this, I added a new interface. - charge account to res_counter by PAGE_SIZE and try to free pages if necessary. - commit register page_cgroup and add to LRU if necessary. - cancel uncharge PAGE_SIZE because of do_swap_page failure. CPUA (1) charge (always) (2) set page's rmap (mapcount > 0) (3) commit charge was necessary or not after set_pte(). This protocol uses PCG_USED bit on page_cgroup for avoiding over accounting. Usual mem_cgroup_charge_common() does charge -> commit at a time. And this patch also adds following function to clarify all charges. - mem_cgroup_newpage_charge() ....replacement for mem_cgroup_charge() called against newly allocated anon pages. - mem_cgroup_charge_migrate_fixup() called only from remove_migration_ptes(). we'll have to rewrite this later.(this patch just keeps old behavior) This function will be removed by additional patch to make migration clearer. Good for clarifying "what we do" Then, we have 4 following charge points. - newpage - swap-in - add-to-cache. - migration. [akpm@linux-foundation.org: add missing inline directives to stubs] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Reviewed-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Cc: Balbir Singh <balbir@in.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-08 09:07:48 +07:00
extern int mem_cgroup_newpage_charge(struct page *page, struct mm_struct *mm,
gfp_t gfp_mask);
memcg: introduce charge-commit-cancel style of functions There is a small race in do_swap_page(). When the page swapped-in is charged, the mapcount can be greater than 0. But, at the same time some process (shares it ) call unmap and make mapcount 1->0 and the page is uncharged. CPUA CPUB mapcount == 1. (1) charge if mapcount==0 zap_pte_range() (2) mapcount 1 => 0. (3) uncharge(). (success) (4) set page's rmap() mapcount 0=>1 Then, this swap page's account is leaked. For fixing this, I added a new interface. - charge account to res_counter by PAGE_SIZE and try to free pages if necessary. - commit register page_cgroup and add to LRU if necessary. - cancel uncharge PAGE_SIZE because of do_swap_page failure. CPUA (1) charge (always) (2) set page's rmap (mapcount > 0) (3) commit charge was necessary or not after set_pte(). This protocol uses PCG_USED bit on page_cgroup for avoiding over accounting. Usual mem_cgroup_charge_common() does charge -> commit at a time. And this patch also adds following function to clarify all charges. - mem_cgroup_newpage_charge() ....replacement for mem_cgroup_charge() called against newly allocated anon pages. - mem_cgroup_charge_migrate_fixup() called only from remove_migration_ptes(). we'll have to rewrite this later.(this patch just keeps old behavior) This function will be removed by additional patch to make migration clearer. Good for clarifying "what we do" Then, we have 4 following charge points. - newpage - swap-in - add-to-cache. - migration. [akpm@linux-foundation.org: add missing inline directives to stubs] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Reviewed-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Cc: Balbir Singh <balbir@in.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-08 09:07:48 +07:00
/* for swap handling */
extern int mem_cgroup_try_charge(struct mm_struct *mm,
gfp_t gfp_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);
Unevictable LRU Infrastructure When the system contains lots of mlocked or otherwise unevictable pages, the pageout code (kswapd) can spend lots of time scanning over these pages. Worse still, the presence of lots of unevictable pages can confuse kswapd into thinking that more aggressive pageout modes are required, resulting in all kinds of bad behaviour. Infrastructure to manage pages excluded from reclaim--i.e., hidden from vmscan. Based on a patch by Larry Woodman of Red Hat. Reworked to maintain "unevictable" pages on a separate per-zone LRU list, to "hide" them from vmscan. Kosaki Motohiro added the support for the memory controller unevictable lru list. Pages on the unevictable list have both PG_unevictable and PG_lru set. Thus, PG_unevictable is analogous to and mutually exclusive with PG_active--it specifies which LRU list the page is on. The unevictable infrastructure is enabled by a new mm Kconfig option [CONFIG_]UNEVICTABLE_LRU. A new function 'page_evictable(page, vma)' in vmscan.c tests whether or not a page may be evictable. Subsequent patches will add the various !evictable tests. We'll want to keep these tests light-weight for use in shrink_active_list() and, possibly, the fault path. To avoid races between tasks putting pages [back] onto an LRU list and tasks that might be moving the page from non-evictable to evictable state, the new function 'putback_lru_page()' -- inverse to 'isolate_lru_page()' -- tests the "evictability" of a page after placing it on the LRU, before dropping the reference. If the page has become unevictable, putback_lru_page() will redo the 'putback', thus moving the page to the unevictable list. This way, we avoid "stranding" evictable pages on the unevictable list. [akpm@linux-foundation.org: fix fallout from out-of-order merge] [riel@redhat.com: fix UNEVICTABLE_LRU and !PROC_PAGE_MONITOR build] [nishimura@mxp.nes.nec.co.jp: remove redundant mapping check] [kosaki.motohiro@jp.fujitsu.com: unevictable-lru-infrastructure: putback_lru_page()/unevictable page handling rework] [kosaki.motohiro@jp.fujitsu.com: kill unnecessary lock_page() in vmscan.c] [kosaki.motohiro@jp.fujitsu.com: revert migration change of unevictable lru infrastructure] [kosaki.motohiro@jp.fujitsu.com: revert to unevictable-lru-infrastructure-kconfig-fix.patch] [kosaki.motohiro@jp.fujitsu.com: restore patch failure of vmstat-unevictable-and-mlocked-pages-vm-events.patch] Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Debugged-by: Benjamin Kidwell <benjkidwell@yahoo.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 10:26:39 +07:00
extern void mem_cgroup_move_lists(struct page *page, enum lru_list lru);
extern void mem_cgroup_uncharge_page(struct page *page);
memcg: remove refcnt from page_cgroup memcg: performance improvements Patch Description 1/5 ... remove refcnt fron page_cgroup patch (shmem handling is fixed) 2/5 ... swapcache handling patch 3/5 ... add helper function for shmem's memory reclaim patch 4/5 ... optimize by likely/unlikely ppatch 5/5 ... remove redundunt check patch (shmem handling is fixed.) Unix bench result. == 2.6.26-rc2-mm1 + memory resource controller Execl Throughput 2915.4 lps (29.6 secs, 3 samples) C Compiler Throughput 1019.3 lpm (60.0 secs, 3 samples) Shell Scripts (1 concurrent) 5796.0 lpm (60.0 secs, 3 samples) Shell Scripts (8 concurrent) 1097.7 lpm (60.0 secs, 3 samples) Shell Scripts (16 concurrent) 565.3 lpm (60.0 secs, 3 samples) File Read 1024 bufsize 2000 maxblocks 1022128.0 KBps (30.0 secs, 3 samples) File Write 1024 bufsize 2000 maxblocks 544057.0 KBps (30.0 secs, 3 samples) File Copy 1024 bufsize 2000 maxblocks 346481.0 KBps (30.0 secs, 3 samples) File Read 256 bufsize 500 maxblocks 319325.0 KBps (30.0 secs, 3 samples) File Write 256 bufsize 500 maxblocks 148788.0 KBps (30.0 secs, 3 samples) File Copy 256 bufsize 500 maxblocks 99051.0 KBps (30.0 secs, 3 samples) File Read 4096 bufsize 8000 maxblocks 2058917.0 KBps (30.0 secs, 3 samples) File Write 4096 bufsize 8000 maxblocks 1606109.0 KBps (30.0 secs, 3 samples) File Copy 4096 bufsize 8000 maxblocks 854789.0 KBps (30.0 secs, 3 samples) Dc: sqrt(2) to 99 decimal places 126145.2 lpm (30.0 secs, 3 samples) INDEX VALUES TEST BASELINE RESULT INDEX Execl Throughput 43.0 2915.4 678.0 File Copy 1024 bufsize 2000 maxblocks 3960.0 346481.0 875.0 File Copy 256 bufsize 500 maxblocks 1655.0 99051.0 598.5 File Copy 4096 bufsize 8000 maxblocks 5800.0 854789.0 1473.8 Shell Scripts (8 concurrent) 6.0 1097.7 1829.5 ========= FINAL SCORE 991.3 == 2.6.26-rc2-mm1 + this set == Execl Throughput 3012.9 lps (29.9 secs, 3 samples) C Compiler Throughput 981.0 lpm (60.0 secs, 3 samples) Shell Scripts (1 concurrent) 5872.0 lpm (60.0 secs, 3 samples) Shell Scripts (8 concurrent) 1120.3 lpm (60.0 secs, 3 samples) Shell Scripts (16 concurrent) 578.0 lpm (60.0 secs, 3 samples) File Read 1024 bufsize 2000 maxblocks 1003993.0 KBps (30.0 secs, 3 samples) File Write 1024 bufsize 2000 maxblocks 550452.0 KBps (30.0 secs, 3 samples) File Copy 1024 bufsize 2000 maxblocks 347159.0 KBps (30.0 secs, 3 samples) File Read 256 bufsize 500 maxblocks 314644.0 KBps (30.0 secs, 3 samples) File Write 256 bufsize 500 maxblocks 151852.0 KBps (30.0 secs, 3 samples) File Copy 256 bufsize 500 maxblocks 101000.0 KBps (30.0 secs, 3 samples) File Read 4096 bufsize 8000 maxblocks 2033256.0 KBps (30.0 secs, 3 samples) File Write 4096 bufsize 8000 maxblocks 1611814.0 KBps (30.0 secs, 3 samples) File Copy 4096 bufsize 8000 maxblocks 847979.0 KBps (30.0 secs, 3 samples) Dc: sqrt(2) to 99 decimal places 128148.7 lpm (30.0 secs, 3 samples) INDEX VALUES TEST BASELINE RESULT INDEX Execl Throughput 43.0 3012.9 700.7 File Copy 1024 bufsize 2000 maxblocks 3960.0 347159.0 876.7 File Copy 256 bufsize 500 maxblocks 1655.0 101000.0 610.3 File Copy 4096 bufsize 8000 maxblocks 5800.0 847979.0 1462.0 Shell Scripts (8 concurrent) 6.0 1120.3 1867.2 ========= FINAL SCORE 1004.6 This patch: Remove refcnt from page_cgroup(). After this, * A page is charged only when !page_mapped() && no page_cgroup is assigned. * Anon page is newly mapped. * File page is added to mapping->tree. * A page is uncharged only when * Anon page is fully unmapped. * File page is removed from LRU. There is no change in behavior from user's view. This patch also removes unnecessary calls in rmap.c which was used only for refcnt mangement. [akpm@linux-foundation.org: fix warning] [hugh@veritas.com: fix shmem_unuse_inode charging] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Balbir Singh <balbir@in.ibm.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Pavel Emelyanov <xemul@openvz.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Hugh Dickins <hugh@veritas.com> Cc: YAMAMOTO Takashi <yamamoto@valinux.co.jp> Cc: Paul Menage <menage@google.com> Cc: David Rientjes <rientjes@google.com> 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>
2008-07-25 15:47:14 +07:00
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,
vmscan: split LRU lists into anon & file sets Split the LRU lists in two, one set for pages that are backed by real file systems ("file") and one for pages that are backed by memory and swap ("anon"). The latter includes tmpfs. The advantage of doing this is that the VM will not have to scan over lots of anonymous pages (which we generally do not want to swap out), just to find the page cache pages that it should evict. This patch has the infrastructure and a basic policy to balance how much we scan the anon lists and how much we scan the file lists. The big policy changes are in separate patches. [lee.schermerhorn@hp.com: collect lru meminfo statistics from correct offset] [kosaki.motohiro@jp.fujitsu.com: prevent incorrect oom under split_lru] [kosaki.motohiro@jp.fujitsu.com: fix pagevec_move_tail() doesn't treat unevictable page] [hugh@veritas.com: memcg swapbacked pages active] [hugh@veritas.com: splitlru: BDI_CAP_SWAP_BACKED] [akpm@linux-foundation.org: fix /proc/vmstat units] [nishimura@mxp.nes.nec.co.jp: memcg: fix handling of shmem migration] [kosaki.motohiro@jp.fujitsu.com: adjust Quicklists field of /proc/meminfo] [kosaki.motohiro@jp.fujitsu.com: fix style issue of get_scan_ratio()] Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <Lee.Schermerhorn@hp.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: 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>
2008-10-19 10:26:32 +07:00
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);
cgroups: add an owner to the mm_struct Remove the mem_cgroup member from mm_struct and instead adds an owner. This approach was suggested by Paul Menage. The advantage of this approach is that, once the mm->owner is known, using the subsystem id, the cgroup can be determined. It also allows several control groups that are virtually grouped by mm_struct, to exist independent of the memory controller i.e., without adding mem_cgroup's for each controller, to mm_struct. A new config option CONFIG_MM_OWNER is added and the memory resource controller selects this config option. This patch also adds cgroup callbacks to notify subsystems when mm->owner changes. The mm_cgroup_changed callback is called with the task_lock() of the new task held and is called just prior to changing the mm->owner. I am indebted to Paul Menage for the several reviews of this patchset and helping me make it lighter and simpler. This patch was tested on a powerpc box, it was compiled with both the MM_OWNER config turned on and off. After the thread group leader exits, it's moved to init_css_state by cgroup_exit(), thus all future charges from runnings threads would be redirected to the init_css_set's subsystem. Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Hugh Dickins <hugh@veritas.com> Cc: Sudhir Kumar <skumar@linux.vnet.ibm.com> Cc: YAMAMOTO Takashi <yamamoto@valinux.co.jp> Cc: Hirokazu Takahashi <taka@valinux.co.jp> Cc: David Rientjes <rientjes@google.com>, Cc: Balbir Singh <balbir@linux.vnet.ibm.com> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Reviewed-by: Paul Menage <menage@google.com> Cc: Oleg Nesterov <oleg@tv-sign.ru> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-29 15:00:16 +07:00
extern struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p);
#define mm_match_cgroup(mm, cgroup) \
cgroups: add an owner to the mm_struct Remove the mem_cgroup member from mm_struct and instead adds an owner. This approach was suggested by Paul Menage. The advantage of this approach is that, once the mm->owner is known, using the subsystem id, the cgroup can be determined. It also allows several control groups that are virtually grouped by mm_struct, to exist independent of the memory controller i.e., without adding mem_cgroup's for each controller, to mm_struct. A new config option CONFIG_MM_OWNER is added and the memory resource controller selects this config option. This patch also adds cgroup callbacks to notify subsystems when mm->owner changes. The mm_cgroup_changed callback is called with the task_lock() of the new task held and is called just prior to changing the mm->owner. I am indebted to Paul Menage for the several reviews of this patchset and helping me make it lighter and simpler. This patch was tested on a powerpc box, it was compiled with both the MM_OWNER config turned on and off. After the thread group leader exits, it's moved to init_css_state by cgroup_exit(), thus all future charges from runnings threads would be redirected to the init_css_set's subsystem. Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Hugh Dickins <hugh@veritas.com> Cc: Sudhir Kumar <skumar@linux.vnet.ibm.com> Cc: YAMAMOTO Takashi <yamamoto@valinux.co.jp> Cc: Hirokazu Takahashi <taka@valinux.co.jp> Cc: David Rientjes <rientjes@google.com>, Cc: Balbir Singh <balbir@linux.vnet.ibm.com> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Reviewed-by: Paul Menage <menage@google.com> Cc: Oleg Nesterov <oleg@tv-sign.ru> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-29 15:00:16 +07:00
((cgroup) == mem_cgroup_from_task((mm)->owner))
Memory controller: memory accounting Add the accounting hooks. The accounting is carried out for RSS and Page Cache (unmapped) pages. There is now a common limit and accounting for both. The RSS accounting is accounted at page_add_*_rmap() and page_remove_rmap() time. Page cache is accounted at add_to_page_cache(), __delete_from_page_cache(). Swap cache is also accounted for. Each page's page_cgroup is protected with the last bit of the page_cgroup pointer, this makes handling of race conditions involving simultaneous mappings of a page easier. A reference count is kept in the page_cgroup to deal with cases where a page might be unmapped from the RSS of all tasks, but still lives in the page cache. Credits go to Vaidyanathan Srinivasan for helping with reference counting work of the page cgroup. Almost all of the page cache accounting code has help from Vaidyanathan Srinivasan. [hugh@veritas.com: fix swapoff breakage] [akpm@linux-foundation.org: fix locking] Signed-off-by: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Paul Menage <menage@google.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Kirill Korotaev <dev@sw.ru> Cc: Herbert Poetzl <herbert@13thfloor.at> Cc: David Rientjes <rientjes@google.com> Cc: <Valdis.Kletnieks@vt.edu> 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>
2008-02-07 15:13:53 +07:00
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);
bugfix for memory cgroup controller: migration under memory controller fix While using memory control cgroup, page-migration under it works as following. == 1. uncharge all refs at try to unmap. 2. charge regs again remove_migration_ptes() == This is simple but has following problems. == The page is uncharged and charged back again if *mapped*. - This means that cgroup before migration can be different from one after migration - If page is not mapped but charged as page cache, charge is just ignored (because not mapped, it will not be uncharged before migration) This is memory leak. == This patch tries to keep memory cgroup at page migration by increasing one refcnt during it. 3 functions are added. mem_cgroup_prepare_migration() --- increase refcnt of page->page_cgroup mem_cgroup_end_migration() --- decrease refcnt of page->page_cgroup mem_cgroup_page_migration() --- copy page->page_cgroup from old page to new page. During migration - old page is under PG_locked. - new page is under PG_locked, too. - both old page and new page is not on LRU. These 3 facts guarantee that page_cgroup() migration has no race. Tested and worked well in x86_64/fake-NUMA box. Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Balbir Singh <balbir@linux.vnet.ibm.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Paul Menage <menage@google.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Kirill Korotaev <dev@sw.ru> Cc: Herbert Poetzl <herbert@13thfloor.at> Cc: David Rientjes <rientjes@google.com> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-07 15:14:10 +07:00
/*
* 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 */
memcg: introduce charge-commit-cancel style of functions There is a small race in do_swap_page(). When the page swapped-in is charged, the mapcount can be greater than 0. But, at the same time some process (shares it ) call unmap and make mapcount 1->0 and the page is uncharged. CPUA CPUB mapcount == 1. (1) charge if mapcount==0 zap_pte_range() (2) mapcount 1 => 0. (3) uncharge(). (success) (4) set page's rmap() mapcount 0=>1 Then, this swap page's account is leaked. For fixing this, I added a new interface. - charge account to res_counter by PAGE_SIZE and try to free pages if necessary. - commit register page_cgroup and add to LRU if necessary. - cancel uncharge PAGE_SIZE because of do_swap_page failure. CPUA (1) charge (always) (2) set page's rmap (mapcount > 0) (3) commit charge was necessary or not after set_pte(). This protocol uses PCG_USED bit on page_cgroup for avoiding over accounting. Usual mem_cgroup_charge_common() does charge -> commit at a time. And this patch also adds following function to clarify all charges. - mem_cgroup_newpage_charge() ....replacement for mem_cgroup_charge() called against newly allocated anon pages. - mem_cgroup_charge_migrate_fixup() called only from remove_migration_ptes(). we'll have to rewrite this later.(this patch just keeps old behavior) This function will be removed by additional patch to make migration clearer. Good for clarifying "what we do" Then, we have 4 following charge points. - newpage - swap-in - add-to-cache. - migration. [akpm@linux-foundation.org: add missing inline directives to stubs] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Reviewed-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Cc: Balbir Singh <balbir@in.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-08 09:07:48 +07:00
struct mem_cgroup;
static inline int mem_cgroup_newpage_charge(struct page *page,
struct mm_struct *mm, gfp_t gfp_mask)
Memory controller: memory accounting Add the accounting hooks. The accounting is carried out for RSS and Page Cache (unmapped) pages. There is now a common limit and accounting for both. The RSS accounting is accounted at page_add_*_rmap() and page_remove_rmap() time. Page cache is accounted at add_to_page_cache(), __delete_from_page_cache(). Swap cache is also accounted for. Each page's page_cgroup is protected with the last bit of the page_cgroup pointer, this makes handling of race conditions involving simultaneous mappings of a page easier. A reference count is kept in the page_cgroup to deal with cases where a page might be unmapped from the RSS of all tasks, but still lives in the page cache. Credits go to Vaidyanathan Srinivasan for helping with reference counting work of the page cgroup. Almost all of the page cache accounting code has help from Vaidyanathan Srinivasan. [hugh@veritas.com: fix swapoff breakage] [akpm@linux-foundation.org: fix locking] Signed-off-by: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Paul Menage <menage@google.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Kirill Korotaev <dev@sw.ru> Cc: Herbert Poetzl <herbert@13thfloor.at> Cc: David Rientjes <rientjes@google.com> Cc: <Valdis.Kletnieks@vt.edu> 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>
2008-02-07 15:13:53 +07:00
{
return 0;
}
static inline int mem_cgroup_cache_charge(struct page *page,
struct mm_struct *mm, gfp_t gfp_mask)
Memory controller: memory accounting Add the accounting hooks. The accounting is carried out for RSS and Page Cache (unmapped) pages. There is now a common limit and accounting for both. The RSS accounting is accounted at page_add_*_rmap() and page_remove_rmap() time. Page cache is accounted at add_to_page_cache(), __delete_from_page_cache(). Swap cache is also accounted for. Each page's page_cgroup is protected with the last bit of the page_cgroup pointer, this makes handling of race conditions involving simultaneous mappings of a page easier. A reference count is kept in the page_cgroup to deal with cases where a page might be unmapped from the RSS of all tasks, but still lives in the page cache. Credits go to Vaidyanathan Srinivasan for helping with reference counting work of the page cgroup. Almost all of the page cache accounting code has help from Vaidyanathan Srinivasan. [hugh@veritas.com: fix swapoff breakage] [akpm@linux-foundation.org: fix locking] Signed-off-by: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Paul Menage <menage@google.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Kirill Korotaev <dev@sw.ru> Cc: Herbert Poetzl <herbert@13thfloor.at> Cc: David Rientjes <rientjes@google.com> Cc: <Valdis.Kletnieks@vt.edu> 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>
2008-02-07 15:13:53 +07:00
{
return 0;
Memory controller: memory accounting Add the accounting hooks. The accounting is carried out for RSS and Page Cache (unmapped) pages. There is now a common limit and accounting for both. The RSS accounting is accounted at page_add_*_rmap() and page_remove_rmap() time. Page cache is accounted at add_to_page_cache(), __delete_from_page_cache(). Swap cache is also accounted for. Each page's page_cgroup is protected with the last bit of the page_cgroup pointer, this makes handling of race conditions involving simultaneous mappings of a page easier. A reference count is kept in the page_cgroup to deal with cases where a page might be unmapped from the RSS of all tasks, but still lives in the page cache. Credits go to Vaidyanathan Srinivasan for helping with reference counting work of the page cgroup. Almost all of the page cache accounting code has help from Vaidyanathan Srinivasan. [hugh@veritas.com: fix swapoff breakage] [akpm@linux-foundation.org: fix locking] Signed-off-by: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Paul Menage <menage@google.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Kirill Korotaev <dev@sw.ru> Cc: Herbert Poetzl <herbert@13thfloor.at> Cc: David Rientjes <rientjes@google.com> Cc: <Valdis.Kletnieks@vt.edu> 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>
2008-02-07 15:13:53 +07:00
}
memcg: introduce charge-commit-cancel style of functions There is a small race in do_swap_page(). When the page swapped-in is charged, the mapcount can be greater than 0. But, at the same time some process (shares it ) call unmap and make mapcount 1->0 and the page is uncharged. CPUA CPUB mapcount == 1. (1) charge if mapcount==0 zap_pte_range() (2) mapcount 1 => 0. (3) uncharge(). (success) (4) set page's rmap() mapcount 0=>1 Then, this swap page's account is leaked. For fixing this, I added a new interface. - charge account to res_counter by PAGE_SIZE and try to free pages if necessary. - commit register page_cgroup and add to LRU if necessary. - cancel uncharge PAGE_SIZE because of do_swap_page failure. CPUA (1) charge (always) (2) set page's rmap (mapcount > 0) (3) commit charge was necessary or not after set_pte(). This protocol uses PCG_USED bit on page_cgroup for avoiding over accounting. Usual mem_cgroup_charge_common() does charge -> commit at a time. And this patch also adds following function to clarify all charges. - mem_cgroup_newpage_charge() ....replacement for mem_cgroup_charge() called against newly allocated anon pages. - mem_cgroup_charge_migrate_fixup() called only from remove_migration_ptes(). we'll have to rewrite this later.(this patch just keeps old behavior) This function will be removed by additional patch to make migration clearer. Good for clarifying "what we do" Then, we have 4 following charge points. - newpage - swap-in - add-to-cache. - migration. [akpm@linux-foundation.org: add missing inline directives to stubs] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Reviewed-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Cc: Balbir Singh <balbir@in.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-08 09:07:48 +07:00
static inline int mem_cgroup_try_charge(struct mm_struct *mm,
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)
{
}
Memory controller: memory accounting Add the accounting hooks. The accounting is carried out for RSS and Page Cache (unmapped) pages. There is now a common limit and accounting for both. The RSS accounting is accounted at page_add_*_rmap() and page_remove_rmap() time. Page cache is accounted at add_to_page_cache(), __delete_from_page_cache(). Swap cache is also accounted for. Each page's page_cgroup is protected with the last bit of the page_cgroup pointer, this makes handling of race conditions involving simultaneous mappings of a page easier. A reference count is kept in the page_cgroup to deal with cases where a page might be unmapped from the RSS of all tasks, but still lives in the page cache. Credits go to Vaidyanathan Srinivasan for helping with reference counting work of the page cgroup. Almost all of the page cache accounting code has help from Vaidyanathan Srinivasan. [hugh@veritas.com: fix swapoff breakage] [akpm@linux-foundation.org: fix locking] Signed-off-by: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Paul Menage <menage@google.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Kirill Korotaev <dev@sw.ru> Cc: Herbert Poetzl <herbert@13thfloor.at> Cc: David Rientjes <rientjes@google.com> Cc: <Valdis.Kletnieks@vt.edu> 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>
2008-02-07 15:13:53 +07:00
static inline void mem_cgroup_uncharge_page(struct page *page)
{
}
memcg: remove refcnt from page_cgroup memcg: performance improvements Patch Description 1/5 ... remove refcnt fron page_cgroup patch (shmem handling is fixed) 2/5 ... swapcache handling patch 3/5 ... add helper function for shmem's memory reclaim patch 4/5 ... optimize by likely/unlikely ppatch 5/5 ... remove redundunt check patch (shmem handling is fixed.) Unix bench result. == 2.6.26-rc2-mm1 + memory resource controller Execl Throughput 2915.4 lps (29.6 secs, 3 samples) C Compiler Throughput 1019.3 lpm (60.0 secs, 3 samples) Shell Scripts (1 concurrent) 5796.0 lpm (60.0 secs, 3 samples) Shell Scripts (8 concurrent) 1097.7 lpm (60.0 secs, 3 samples) Shell Scripts (16 concurrent) 565.3 lpm (60.0 secs, 3 samples) File Read 1024 bufsize 2000 maxblocks 1022128.0 KBps (30.0 secs, 3 samples) File Write 1024 bufsize 2000 maxblocks 544057.0 KBps (30.0 secs, 3 samples) File Copy 1024 bufsize 2000 maxblocks 346481.0 KBps (30.0 secs, 3 samples) File Read 256 bufsize 500 maxblocks 319325.0 KBps (30.0 secs, 3 samples) File Write 256 bufsize 500 maxblocks 148788.0 KBps (30.0 secs, 3 samples) File Copy 256 bufsize 500 maxblocks 99051.0 KBps (30.0 secs, 3 samples) File Read 4096 bufsize 8000 maxblocks 2058917.0 KBps (30.0 secs, 3 samples) File Write 4096 bufsize 8000 maxblocks 1606109.0 KBps (30.0 secs, 3 samples) File Copy 4096 bufsize 8000 maxblocks 854789.0 KBps (30.0 secs, 3 samples) Dc: sqrt(2) to 99 decimal places 126145.2 lpm (30.0 secs, 3 samples) INDEX VALUES TEST BASELINE RESULT INDEX Execl Throughput 43.0 2915.4 678.0 File Copy 1024 bufsize 2000 maxblocks 3960.0 346481.0 875.0 File Copy 256 bufsize 500 maxblocks 1655.0 99051.0 598.5 File Copy 4096 bufsize 8000 maxblocks 5800.0 854789.0 1473.8 Shell Scripts (8 concurrent) 6.0 1097.7 1829.5 ========= FINAL SCORE 991.3 == 2.6.26-rc2-mm1 + this set == Execl Throughput 3012.9 lps (29.9 secs, 3 samples) C Compiler Throughput 981.0 lpm (60.0 secs, 3 samples) Shell Scripts (1 concurrent) 5872.0 lpm (60.0 secs, 3 samples) Shell Scripts (8 concurrent) 1120.3 lpm (60.0 secs, 3 samples) Shell Scripts (16 concurrent) 578.0 lpm (60.0 secs, 3 samples) File Read 1024 bufsize 2000 maxblocks 1003993.0 KBps (30.0 secs, 3 samples) File Write 1024 bufsize 2000 maxblocks 550452.0 KBps (30.0 secs, 3 samples) File Copy 1024 bufsize 2000 maxblocks 347159.0 KBps (30.0 secs, 3 samples) File Read 256 bufsize 500 maxblocks 314644.0 KBps (30.0 secs, 3 samples) File Write 256 bufsize 500 maxblocks 151852.0 KBps (30.0 secs, 3 samples) File Copy 256 bufsize 500 maxblocks 101000.0 KBps (30.0 secs, 3 samples) File Read 4096 bufsize 8000 maxblocks 2033256.0 KBps (30.0 secs, 3 samples) File Write 4096 bufsize 8000 maxblocks 1611814.0 KBps (30.0 secs, 3 samples) File Copy 4096 bufsize 8000 maxblocks 847979.0 KBps (30.0 secs, 3 samples) Dc: sqrt(2) to 99 decimal places 128148.7 lpm (30.0 secs, 3 samples) INDEX VALUES TEST BASELINE RESULT INDEX Execl Throughput 43.0 3012.9 700.7 File Copy 1024 bufsize 2000 maxblocks 3960.0 347159.0 876.7 File Copy 256 bufsize 500 maxblocks 1655.0 101000.0 610.3 File Copy 4096 bufsize 8000 maxblocks 5800.0 847979.0 1462.0 Shell Scripts (8 concurrent) 6.0 1120.3 1867.2 ========= FINAL SCORE 1004.6 This patch: Remove refcnt from page_cgroup(). After this, * A page is charged only when !page_mapped() && no page_cgroup is assigned. * Anon page is newly mapped. * File page is added to mapping->tree. * A page is uncharged only when * Anon page is fully unmapped. * File page is removed from LRU. There is no change in behavior from user's view. This patch also removes unnecessary calls in rmap.c which was used only for refcnt mangement. [akpm@linux-foundation.org: fix warning] [hugh@veritas.com: fix shmem_unuse_inode charging] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Balbir Singh <balbir@in.ibm.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Pavel Emelyanov <xemul@openvz.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Hugh Dickins <hugh@veritas.com> Cc: YAMAMOTO Takashi <yamamoto@valinux.co.jp> Cc: Paul Menage <menage@google.com> Cc: David Rientjes <rientjes@google.com> 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>
2008-07-25 15:47:14 +07:00
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)
bugfix for memory cgroup controller: migration under memory controller fix While using memory control cgroup, page-migration under it works as following. == 1. uncharge all refs at try to unmap. 2. charge regs again remove_migration_ptes() == This is simple but has following problems. == The page is uncharged and charged back again if *mapped*. - This means that cgroup before migration can be different from one after migration - If page is not mapped but charged as page cache, charge is just ignored (because not mapped, it will not be uncharged before migration) This is memory leak. == This patch tries to keep memory cgroup at page migration by increasing one refcnt during it. 3 functions are added. mem_cgroup_prepare_migration() --- increase refcnt of page->page_cgroup mem_cgroup_end_migration() --- decrease refcnt of page->page_cgroup mem_cgroup_page_migration() --- copy page->page_cgroup from old page to new page. During migration - old page is under PG_locked. - new page is under PG_locked, too. - both old page and new page is not on LRU. These 3 facts guarantee that page_cgroup() migration has no race. Tested and worked well in x86_64/fake-NUMA box. Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Balbir Singh <balbir@linux.vnet.ibm.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Paul Menage <menage@google.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Kirill Korotaev <dev@sw.ru> Cc: Herbert Poetzl <herbert@13thfloor.at> Cc: David Rientjes <rientjes@google.com> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-07 15:14:10 +07:00
{
return 0;
}
static inline void mem_cgroup_end_migration(struct mem_cgroup *mem,
struct page *oldpage,
struct page *newpage)
bugfix for memory cgroup controller: migration under memory controller fix While using memory control cgroup, page-migration under it works as following. == 1. uncharge all refs at try to unmap. 2. charge regs again remove_migration_ptes() == This is simple but has following problems. == The page is uncharged and charged back again if *mapped*. - This means that cgroup before migration can be different from one after migration - If page is not mapped but charged as page cache, charge is just ignored (because not mapped, it will not be uncharged before migration) This is memory leak. == This patch tries to keep memory cgroup at page migration by increasing one refcnt during it. 3 functions are added. mem_cgroup_prepare_migration() --- increase refcnt of page->page_cgroup mem_cgroup_end_migration() --- decrease refcnt of page->page_cgroup mem_cgroup_page_migration() --- copy page->page_cgroup from old page to new page. During migration - old page is under PG_locked. - new page is under PG_locked, too. - both old page and new page is not on LRU. These 3 facts guarantee that page_cgroup() migration has no race. Tested and worked well in x86_64/fake-NUMA box. Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Balbir Singh <balbir@linux.vnet.ibm.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Paul Menage <menage@google.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Kirill Korotaev <dev@sw.ru> Cc: Herbert Poetzl <herbert@13thfloor.at> Cc: David Rientjes <rientjes@google.com> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-07 15:14:10 +07:00
{
}
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 */