linux/mm/memcontrol.c

1212 lines
30 KiB
C
Raw Normal View History

/* memcontrol.c - 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.
*/
#include <linux/res_counter.h>
#include <linux/memcontrol.h>
#include <linux/cgroup.h>
#include <linux/mm.h>
memory cgroup enhancements: add status accounting function for memory cgroup Add statistics account infrastructure for memory controller. All account information is stored per-cpu and caller will not have to take lock or use atomic ops. This will be used by memory.stat file later. CACHE includes swapcache now. I'd like to divide it to PAGECACHE and SWAPCACHE later. This patch adds 3 functions for accounting. * __mem_cgroup_stat_add() ... for usual routine. * __mem_cgroup_stat_add_safe ... for calling under irq_disabled section. * mem_cgroup_read_stat() ... for reading stat value. * renamed PAGECACHE to CACHE (because it may include swapcache *now*) [akpm@linux-foundation.org: coding-style fixes] [akpm@linux-foundation.org: fix smp_processor_id-in-preemptible] [akpm@linux-foundation.org: uninline things] [akpm@linux-foundation.org: remove dead code] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: YAMAMOTO Takashi <yamamoto@valinux.co.jp> 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> Cc: Kirill Korotaev <dev@sw.ru> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Paul Menage <menage@google.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Cc: YAMAMOTO Takashi <yamamoto@valinux.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-07 16:14:24 +08:00
#include <linux/smp.h>
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 16:13:53 +08:00
#include <linux/page-flags.h>
#include <linux/backing-dev.h>
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 16:13:53 +08:00
#include <linux/bit_spinlock.h>
#include <linux/rcupdate.h>
#include <linux/slab.h>
#include <linux/swap.h>
#include <linux/spinlock.h>
#include <linux/fs.h>
#include <linux/seq_file.h>
#include <linux/vmalloc.h>
#include <asm/uaccess.h>
struct cgroup_subsys mem_cgroup_subsys __read_mostly;
static struct kmem_cache *page_cgroup_cache __read_mostly;
#define MEM_CGROUP_RECLAIM_RETRIES 5
memory cgroup enhancements: add status accounting function for memory cgroup Add statistics account infrastructure for memory controller. All account information is stored per-cpu and caller will not have to take lock or use atomic ops. This will be used by memory.stat file later. CACHE includes swapcache now. I'd like to divide it to PAGECACHE and SWAPCACHE later. This patch adds 3 functions for accounting. * __mem_cgroup_stat_add() ... for usual routine. * __mem_cgroup_stat_add_safe ... for calling under irq_disabled section. * mem_cgroup_read_stat() ... for reading stat value. * renamed PAGECACHE to CACHE (because it may include swapcache *now*) [akpm@linux-foundation.org: coding-style fixes] [akpm@linux-foundation.org: fix smp_processor_id-in-preemptible] [akpm@linux-foundation.org: uninline things] [akpm@linux-foundation.org: remove dead code] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: YAMAMOTO Takashi <yamamoto@valinux.co.jp> 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> Cc: Kirill Korotaev <dev@sw.ru> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Paul Menage <menage@google.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Cc: YAMAMOTO Takashi <yamamoto@valinux.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-07 16:14:24 +08:00
/*
* Statistics for memory cgroup.
*/
enum mem_cgroup_stat_index {
/*
* For MEM_CONTAINER_TYPE_ALL, usage = pagecache + rss.
*/
MEM_CGROUP_STAT_CACHE, /* # of pages charged as cache */
MEM_CGROUP_STAT_RSS, /* # of pages charged as rss */
MEM_CGROUP_STAT_PGPGIN_COUNT, /* # of pages paged in */
MEM_CGROUP_STAT_PGPGOUT_COUNT, /* # of pages paged out */
memory cgroup enhancements: add status accounting function for memory cgroup Add statistics account infrastructure for memory controller. All account information is stored per-cpu and caller will not have to take lock or use atomic ops. This will be used by memory.stat file later. CACHE includes swapcache now. I'd like to divide it to PAGECACHE and SWAPCACHE later. This patch adds 3 functions for accounting. * __mem_cgroup_stat_add() ... for usual routine. * __mem_cgroup_stat_add_safe ... for calling under irq_disabled section. * mem_cgroup_read_stat() ... for reading stat value. * renamed PAGECACHE to CACHE (because it may include swapcache *now*) [akpm@linux-foundation.org: coding-style fixes] [akpm@linux-foundation.org: fix smp_processor_id-in-preemptible] [akpm@linux-foundation.org: uninline things] [akpm@linux-foundation.org: remove dead code] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: YAMAMOTO Takashi <yamamoto@valinux.co.jp> 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> Cc: Kirill Korotaev <dev@sw.ru> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Paul Menage <menage@google.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Cc: YAMAMOTO Takashi <yamamoto@valinux.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-07 16:14:24 +08:00
MEM_CGROUP_STAT_NSTATS,
};
struct mem_cgroup_stat_cpu {
s64 count[MEM_CGROUP_STAT_NSTATS];
} ____cacheline_aligned_in_smp;
struct mem_cgroup_stat {
struct mem_cgroup_stat_cpu cpustat[NR_CPUS];
};
/*
* For accounting under irq disable, no need for increment preempt count.
*/
static void __mem_cgroup_stat_add_safe(struct mem_cgroup_stat *stat,
enum mem_cgroup_stat_index idx, int val)
{
int cpu = smp_processor_id();
stat->cpustat[cpu].count[idx] += val;
}
static s64 mem_cgroup_read_stat(struct mem_cgroup_stat *stat,
enum mem_cgroup_stat_index idx)
{
int cpu;
s64 ret = 0;
for_each_possible_cpu(cpu)
ret += stat->cpustat[cpu].count[idx];
return ret;
}
/*
* per-zone information in memory controller.
*/
enum mem_cgroup_zstat_index {
MEM_CGROUP_ZSTAT_ACTIVE,
MEM_CGROUP_ZSTAT_INACTIVE,
NR_MEM_CGROUP_ZSTAT,
};
struct mem_cgroup_per_zone {
/*
* spin_lock to protect the per cgroup LRU
*/
spinlock_t lru_lock;
struct list_head active_list;
struct list_head inactive_list;
unsigned long count[NR_MEM_CGROUP_ZSTAT];
};
/* Macro for accessing counter */
#define MEM_CGROUP_ZSTAT(mz, idx) ((mz)->count[(idx)])
struct mem_cgroup_per_node {
struct mem_cgroup_per_zone zoneinfo[MAX_NR_ZONES];
};
struct mem_cgroup_lru_info {
struct mem_cgroup_per_node *nodeinfo[MAX_NUMNODES];
};
/*
* The memory controller data structure. The memory controller controls both
* page cache and RSS per cgroup. We would eventually like to provide
* statistics based on the statistics developed by Rik Van Riel for clock-pro,
* to help the administrator determine what knobs to tune.
*
* TODO: Add a water mark for the memory controller. Reclaim will begin when
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 16:13:53 +08:00
* we hit the water mark. May be even add a low water mark, such that
* no reclaim occurs from a cgroup at it's low water mark, this is
* a feature that will be implemented much later in the future.
*/
struct mem_cgroup {
struct cgroup_subsys_state css;
/*
* the counter to account for memory usage
*/
struct res_counter res;
/*
* Per cgroup active and inactive list, similar to the
* per zone LRU lists.
*/
struct mem_cgroup_lru_info info;
int prev_priority; /* for recording reclaim priority */
memory cgroup enhancements: add status accounting function for memory cgroup Add statistics account infrastructure for memory controller. All account information is stored per-cpu and caller will not have to take lock or use atomic ops. This will be used by memory.stat file later. CACHE includes swapcache now. I'd like to divide it to PAGECACHE and SWAPCACHE later. This patch adds 3 functions for accounting. * __mem_cgroup_stat_add() ... for usual routine. * __mem_cgroup_stat_add_safe ... for calling under irq_disabled section. * mem_cgroup_read_stat() ... for reading stat value. * renamed PAGECACHE to CACHE (because it may include swapcache *now*) [akpm@linux-foundation.org: coding-style fixes] [akpm@linux-foundation.org: fix smp_processor_id-in-preemptible] [akpm@linux-foundation.org: uninline things] [akpm@linux-foundation.org: remove dead code] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: YAMAMOTO Takashi <yamamoto@valinux.co.jp> 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> Cc: Kirill Korotaev <dev@sw.ru> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Paul Menage <menage@google.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Cc: YAMAMOTO Takashi <yamamoto@valinux.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-07 16:14:24 +08:00
/*
* statistics.
*/
struct mem_cgroup_stat stat;
};
static struct mem_cgroup init_mem_cgroup;
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 16:13:53 +08:00
/*
* We use the lower bit of the page->page_cgroup pointer as a bit spin
* lock. We need to ensure that page->page_cgroup is at least two
* byte aligned (based on comments from Nick Piggin). But since
* bit_spin_lock doesn't actually set that lock bit in a non-debug
* uniprocessor kernel, we should avoid setting it here too.
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 16:13:53 +08:00
*/
#define PAGE_CGROUP_LOCK_BIT 0x0
#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK)
#define PAGE_CGROUP_LOCK (1 << PAGE_CGROUP_LOCK_BIT)
#else
#define PAGE_CGROUP_LOCK 0x0
#endif
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 16:13:53 +08:00
/*
* A page_cgroup page is associated with every page descriptor. The
* page_cgroup helps us identify information about the cgroup
*/
struct page_cgroup {
struct list_head lru; /* per cgroup LRU list */
struct page *page;
struct mem_cgroup *mem_cgroup;
int flags;
};
#define PAGE_CGROUP_FLAG_CACHE (0x1) /* charged as cache */
#define PAGE_CGROUP_FLAG_ACTIVE (0x2) /* page is active in this cgroup */
static int page_cgroup_nid(struct page_cgroup *pc)
{
return page_to_nid(pc->page);
}
static enum zone_type page_cgroup_zid(struct page_cgroup *pc)
{
return page_zonenum(pc->page);
}
enum charge_type {
MEM_CGROUP_CHARGE_TYPE_CACHE = 0,
MEM_CGROUP_CHARGE_TYPE_MAPPED,
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 16:47:14 +08:00
MEM_CGROUP_CHARGE_TYPE_FORCE, /* used by force_empty */
};
memory cgroup enhancements: add status accounting function for memory cgroup Add statistics account infrastructure for memory controller. All account information is stored per-cpu and caller will not have to take lock or use atomic ops. This will be used by memory.stat file later. CACHE includes swapcache now. I'd like to divide it to PAGECACHE and SWAPCACHE later. This patch adds 3 functions for accounting. * __mem_cgroup_stat_add() ... for usual routine. * __mem_cgroup_stat_add_safe ... for calling under irq_disabled section. * mem_cgroup_read_stat() ... for reading stat value. * renamed PAGECACHE to CACHE (because it may include swapcache *now*) [akpm@linux-foundation.org: coding-style fixes] [akpm@linux-foundation.org: fix smp_processor_id-in-preemptible] [akpm@linux-foundation.org: uninline things] [akpm@linux-foundation.org: remove dead code] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: YAMAMOTO Takashi <yamamoto@valinux.co.jp> 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> Cc: Kirill Korotaev <dev@sw.ru> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Paul Menage <menage@google.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Cc: YAMAMOTO Takashi <yamamoto@valinux.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-07 16:14:24 +08:00
/*
* Always modified under lru lock. Then, not necessary to preempt_disable()
*/
static void mem_cgroup_charge_statistics(struct mem_cgroup *mem, int flags,
bool charge)
{
int val = (charge)? 1 : -1;
struct mem_cgroup_stat *stat = &mem->stat;
VM_BUG_ON(!irqs_disabled());
memory cgroup enhancements: add status accounting function for memory cgroup Add statistics account infrastructure for memory controller. All account information is stored per-cpu and caller will not have to take lock or use atomic ops. This will be used by memory.stat file later. CACHE includes swapcache now. I'd like to divide it to PAGECACHE and SWAPCACHE later. This patch adds 3 functions for accounting. * __mem_cgroup_stat_add() ... for usual routine. * __mem_cgroup_stat_add_safe ... for calling under irq_disabled section. * mem_cgroup_read_stat() ... for reading stat value. * renamed PAGECACHE to CACHE (because it may include swapcache *now*) [akpm@linux-foundation.org: coding-style fixes] [akpm@linux-foundation.org: fix smp_processor_id-in-preemptible] [akpm@linux-foundation.org: uninline things] [akpm@linux-foundation.org: remove dead code] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: YAMAMOTO Takashi <yamamoto@valinux.co.jp> 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> Cc: Kirill Korotaev <dev@sw.ru> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Paul Menage <menage@google.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Cc: YAMAMOTO Takashi <yamamoto@valinux.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-07 16:14:24 +08:00
if (flags & PAGE_CGROUP_FLAG_CACHE)
__mem_cgroup_stat_add_safe(stat, MEM_CGROUP_STAT_CACHE, val);
memory cgroup enhancements: add status accounting function for memory cgroup Add statistics account infrastructure for memory controller. All account information is stored per-cpu and caller will not have to take lock or use atomic ops. This will be used by memory.stat file later. CACHE includes swapcache now. I'd like to divide it to PAGECACHE and SWAPCACHE later. This patch adds 3 functions for accounting. * __mem_cgroup_stat_add() ... for usual routine. * __mem_cgroup_stat_add_safe ... for calling under irq_disabled section. * mem_cgroup_read_stat() ... for reading stat value. * renamed PAGECACHE to CACHE (because it may include swapcache *now*) [akpm@linux-foundation.org: coding-style fixes] [akpm@linux-foundation.org: fix smp_processor_id-in-preemptible] [akpm@linux-foundation.org: uninline things] [akpm@linux-foundation.org: remove dead code] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: YAMAMOTO Takashi <yamamoto@valinux.co.jp> 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> Cc: Kirill Korotaev <dev@sw.ru> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Paul Menage <menage@google.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Cc: YAMAMOTO Takashi <yamamoto@valinux.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-07 16:14:24 +08:00
else
__mem_cgroup_stat_add_safe(stat, MEM_CGROUP_STAT_RSS, val);
if (charge)
__mem_cgroup_stat_add_safe(stat,
MEM_CGROUP_STAT_PGPGIN_COUNT, 1);
else
__mem_cgroup_stat_add_safe(stat,
MEM_CGROUP_STAT_PGPGOUT_COUNT, 1);
}
static struct mem_cgroup_per_zone *
mem_cgroup_zoneinfo(struct mem_cgroup *mem, int nid, int zid)
{
return &mem->info.nodeinfo[nid]->zoneinfo[zid];
}
static struct mem_cgroup_per_zone *
page_cgroup_zoneinfo(struct page_cgroup *pc)
{
struct mem_cgroup *mem = pc->mem_cgroup;
int nid = page_cgroup_nid(pc);
int zid = page_cgroup_zid(pc);
memory cgroup enhancements: add status accounting function for memory cgroup Add statistics account infrastructure for memory controller. All account information is stored per-cpu and caller will not have to take lock or use atomic ops. This will be used by memory.stat file later. CACHE includes swapcache now. I'd like to divide it to PAGECACHE and SWAPCACHE later. This patch adds 3 functions for accounting. * __mem_cgroup_stat_add() ... for usual routine. * __mem_cgroup_stat_add_safe ... for calling under irq_disabled section. * mem_cgroup_read_stat() ... for reading stat value. * renamed PAGECACHE to CACHE (because it may include swapcache *now*) [akpm@linux-foundation.org: coding-style fixes] [akpm@linux-foundation.org: fix smp_processor_id-in-preemptible] [akpm@linux-foundation.org: uninline things] [akpm@linux-foundation.org: remove dead code] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: YAMAMOTO Takashi <yamamoto@valinux.co.jp> 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> Cc: Kirill Korotaev <dev@sw.ru> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Paul Menage <menage@google.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Cc: YAMAMOTO Takashi <yamamoto@valinux.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-07 16:14:24 +08:00
return mem_cgroup_zoneinfo(mem, nid, zid);
}
static unsigned long mem_cgroup_get_all_zonestat(struct mem_cgroup *mem,
enum mem_cgroup_zstat_index idx)
{
int nid, zid;
struct mem_cgroup_per_zone *mz;
u64 total = 0;
for_each_online_node(nid)
for (zid = 0; zid < MAX_NR_ZONES; zid++) {
mz = mem_cgroup_zoneinfo(mem, nid, zid);
total += MEM_CGROUP_ZSTAT(mz, idx);
}
return total;
memory cgroup enhancements: add status accounting function for memory cgroup Add statistics account infrastructure for memory controller. All account information is stored per-cpu and caller will not have to take lock or use atomic ops. This will be used by memory.stat file later. CACHE includes swapcache now. I'd like to divide it to PAGECACHE and SWAPCACHE later. This patch adds 3 functions for accounting. * __mem_cgroup_stat_add() ... for usual routine. * __mem_cgroup_stat_add_safe ... for calling under irq_disabled section. * mem_cgroup_read_stat() ... for reading stat value. * renamed PAGECACHE to CACHE (because it may include swapcache *now*) [akpm@linux-foundation.org: coding-style fixes] [akpm@linux-foundation.org: fix smp_processor_id-in-preemptible] [akpm@linux-foundation.org: uninline things] [akpm@linux-foundation.org: remove dead code] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: YAMAMOTO Takashi <yamamoto@valinux.co.jp> 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> Cc: Kirill Korotaev <dev@sw.ru> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Paul Menage <menage@google.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Cc: YAMAMOTO Takashi <yamamoto@valinux.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-07 16:14:24 +08:00
}
static struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont)
{
return container_of(cgroup_subsys_state(cont,
mem_cgroup_subsys_id), struct mem_cgroup,
css);
}
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 16:00:16 +08:00
struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p)
{
mm owner: fix race between swapoff and exit There's a race between mm->owner assignment and swapoff, more easily seen when task slab poisoning is turned on. The condition occurs when try_to_unuse() runs in parallel with an exiting task. A similar race can occur with callers of get_task_mm(), such as /proc/<pid>/<mmstats> or ptrace or page migration. CPU0 CPU1 try_to_unuse looks at mm = task0->mm increments mm->mm_users task 0 exits mm->owner needs to be updated, but no new owner is found (mm_users > 1, but no other task has task->mm = task0->mm) mm_update_next_owner() leaves mmput(mm) decrements mm->mm_users task0 freed dereferencing mm->owner fails The fix is to notify the subsystem via mm_owner_changed callback(), if no new owner is found, by specifying the new task as NULL. Jiri Slaby: mm->owner was set to NULL prior to calling cgroup_mm_owner_callbacks(), but must be set after that, so as not to pass NULL as old owner causing oops. Daisuke Nishimura: mm_update_next_owner() may set mm->owner to NULL, but mem_cgroup_from_task() and its callers need to take account of this situation to avoid oops. Hugh Dickins: Lockdep warning and hang below exec_mmap() when testing these patches. exit_mm() up_reads mmap_sem before calling mm_update_next_owner(), so exec_mmap() now needs to do the same. And with that repositioning, there's now no point in mm_need_new_owner() allowing for NULL mm. Reported-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com> Signed-off-by: Jiri Slaby <jirislaby@gmail.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Hugh Dickins <hugh@veritas.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Paul Menage <menage@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-09-29 06:09:31 +08:00
/*
* mm_update_next_owner() may clear mm->owner to NULL
* if it races with swapoff, page migration, etc.
* So this can be called with p == NULL.
*/
if (unlikely(!p))
return NULL;
return container_of(task_subsys_state(p, mem_cgroup_subsys_id),
struct mem_cgroup, css);
}
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 16:13:53 +08:00
static inline int page_cgroup_locked(struct page *page)
{
return bit_spin_is_locked(PAGE_CGROUP_LOCK_BIT, &page->page_cgroup);
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 16:13:53 +08:00
}
static void page_assign_page_cgroup(struct page *page, struct page_cgroup *pc)
{
VM_BUG_ON(!page_cgroup_locked(page));
page->page_cgroup = ((unsigned long)pc | PAGE_CGROUP_LOCK);
}
struct page_cgroup *page_get_page_cgroup(struct page *page)
{
return (struct page_cgroup *) (page->page_cgroup & ~PAGE_CGROUP_LOCK);
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 16:13:53 +08:00
}
static void lock_page_cgroup(struct page *page)
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 16:13:53 +08:00
{
bit_spin_lock(PAGE_CGROUP_LOCK_BIT, &page->page_cgroup);
}
static int try_lock_page_cgroup(struct page *page)
{
return bit_spin_trylock(PAGE_CGROUP_LOCK_BIT, &page->page_cgroup);
}
static void unlock_page_cgroup(struct page *page)
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 16:13:53 +08:00
{
bit_spin_unlock(PAGE_CGROUP_LOCK_BIT, &page->page_cgroup);
}
static void __mem_cgroup_remove_list(struct mem_cgroup_per_zone *mz,
struct page_cgroup *pc)
{
int from = pc->flags & PAGE_CGROUP_FLAG_ACTIVE;
if (from)
MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_ACTIVE) -= 1;
else
MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_INACTIVE) -= 1;
mem_cgroup_charge_statistics(pc->mem_cgroup, pc->flags, false);
list_del(&pc->lru);
}
static void __mem_cgroup_add_list(struct mem_cgroup_per_zone *mz,
struct page_cgroup *pc)
{
int to = pc->flags & PAGE_CGROUP_FLAG_ACTIVE;
if (!to) {
MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_INACTIVE) += 1;
list_add(&pc->lru, &mz->inactive_list);
} else {
MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_ACTIVE) += 1;
list_add(&pc->lru, &mz->active_list);
}
mem_cgroup_charge_statistics(pc->mem_cgroup, pc->flags, true);
}
static void __mem_cgroup_move_lists(struct page_cgroup *pc, bool active)
{
int from = pc->flags & PAGE_CGROUP_FLAG_ACTIVE;
struct mem_cgroup_per_zone *mz = page_cgroup_zoneinfo(pc);
if (from)
MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_ACTIVE) -= 1;
else
MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_INACTIVE) -= 1;
if (active) {
MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_ACTIVE) += 1;
pc->flags |= PAGE_CGROUP_FLAG_ACTIVE;
list_move(&pc->lru, &mz->active_list);
} else {
MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_INACTIVE) += 1;
pc->flags &= ~PAGE_CGROUP_FLAG_ACTIVE;
list_move(&pc->lru, &mz->inactive_list);
}
}
int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *mem)
{
int ret;
task_lock(task);
ret = task->mm && mm_match_cgroup(task->mm, mem);
task_unlock(task);
return ret;
}
/*
* This routine assumes that the appropriate zone's lru lock is already held
*/
void mem_cgroup_move_lists(struct page *page, bool active)
{
struct page_cgroup *pc;
struct mem_cgroup_per_zone *mz;
unsigned long flags;
if (mem_cgroup_subsys.disabled)
return;
/*
* We cannot lock_page_cgroup while holding zone's lru_lock,
* because other holders of lock_page_cgroup can be interrupted
* with an attempt to rotate_reclaimable_page. But we cannot
* safely get to page_cgroup without it, so just try_lock it:
* mem_cgroup_isolate_pages allows for page left on wrong list.
*/
if (!try_lock_page_cgroup(page))
return;
pc = page_get_page_cgroup(page);
if (pc) {
mz = page_cgroup_zoneinfo(pc);
spin_lock_irqsave(&mz->lru_lock, flags);
__mem_cgroup_move_lists(pc, active);
spin_unlock_irqrestore(&mz->lru_lock, flags);
}
unlock_page_cgroup(page);
}
/*
* Calculate mapped_ratio under memory controller. This will be used in
* vmscan.c for deteremining we have to reclaim mapped pages.
*/
int mem_cgroup_calc_mapped_ratio(struct mem_cgroup *mem)
{
long total, rss;
/*
* usage is recorded in bytes. But, here, we assume the number of
* physical pages can be represented by "long" on any arch.
*/
total = (long) (mem->res.usage >> PAGE_SHIFT) + 1L;
rss = (long)mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_RSS);
return (int)((rss * 100L) / total);
}
/*
* This function is called from vmscan.c. In page reclaiming loop. balance
* between active and inactive list is calculated. For memory controller
* page reclaiming, we should use using mem_cgroup's imbalance rather than
* zone's global lru imbalance.
*/
long mem_cgroup_reclaim_imbalance(struct mem_cgroup *mem)
{
unsigned long active, inactive;
/* active and inactive are the number of pages. 'long' is ok.*/
active = mem_cgroup_get_all_zonestat(mem, MEM_CGROUP_ZSTAT_ACTIVE);
inactive = mem_cgroup_get_all_zonestat(mem, MEM_CGROUP_ZSTAT_INACTIVE);
return (long) (active / (inactive + 1));
}
/*
* prev_priority control...this will be used in memory reclaim path.
*/
int mem_cgroup_get_reclaim_priority(struct mem_cgroup *mem)
{
return mem->prev_priority;
}
void mem_cgroup_note_reclaim_priority(struct mem_cgroup *mem, int priority)
{
if (priority < mem->prev_priority)
mem->prev_priority = priority;
}
void mem_cgroup_record_reclaim_priority(struct mem_cgroup *mem, int priority)
{
mem->prev_priority = priority;
}
/*
* Calculate # of pages to be scanned in this priority/zone.
* See also vmscan.c
*
* priority starts from "DEF_PRIORITY" and decremented in each loop.
* (see include/linux/mmzone.h)
*/
long mem_cgroup_calc_reclaim_active(struct mem_cgroup *mem,
struct zone *zone, int priority)
{
long nr_active;
int nid = zone->zone_pgdat->node_id;
int zid = zone_idx(zone);
struct mem_cgroup_per_zone *mz = mem_cgroup_zoneinfo(mem, nid, zid);
nr_active = MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_ACTIVE);
return (nr_active >> priority);
}
long mem_cgroup_calc_reclaim_inactive(struct mem_cgroup *mem,
struct zone *zone, int priority)
{
long nr_inactive;
int nid = zone->zone_pgdat->node_id;
int zid = zone_idx(zone);
struct mem_cgroup_per_zone *mz = mem_cgroup_zoneinfo(mem, nid, zid);
nr_inactive = MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_INACTIVE);
return (nr_inactive >> priority);
}
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)
{
unsigned long nr_taken = 0;
struct page *page;
unsigned long scan;
LIST_HEAD(pc_list);
struct list_head *src;
struct page_cgroup *pc, *tmp;
int nid = z->zone_pgdat->node_id;
int zid = zone_idx(z);
struct mem_cgroup_per_zone *mz;
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 16:00:16 +08:00
BUG_ON(!mem_cont);
mz = mem_cgroup_zoneinfo(mem_cont, nid, zid);
if (active)
src = &mz->active_list;
else
src = &mz->inactive_list;
spin_lock(&mz->lru_lock);
scan = 0;
list_for_each_entry_safe_reverse(pc, tmp, src, lru) {
memcgroup: fix zone isolation OOM mem_cgroup_charge_common shows a tendency to OOM without good reason, when a memhog goes well beyond its rss limit but with plenty of swap available. Seen on x86 but not on PowerPC; seen when the next patch omits swapcache from memcgroup, but we presume it can happen without. mem_cgroup_isolate_pages is not quite satisfying reclaim's criteria for OOM avoidance. Already it has to scan beyond the nr_to_scan limit when it finds a !LRU page or an active page when handling inactive or an inactive page when handling active. It needs to do exactly the same when it finds a page from the wrong zone (the x86 tests had two zones, the PowerPC tests had only one). Don't increment scan and then decrement it in these cases, just move the incrementation down. Fix recent off-by-one when checking against nr_to_scan. Cut out "Check if the meta page went away from under us", presumably left over from early debugging: no amount of such checks could save us if this list really were being updated without locking. This change does make the unlimited scan while holding two spinlocks even worse - bad for latency and bad for containment; but that's a separate issue which is better left to be fixed a little later. Signed-off-by: Hugh Dickins <hugh@veritas.com> Cc: Pavel Emelianov <xemul@openvz.org> Acked-by: Balbir Singh <balbir@linux.vnet.ibm.com> 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 16:14:12 +08:00
if (scan >= nr_to_scan)
break;
page = pc->page;
memcgroup: fix zone isolation OOM mem_cgroup_charge_common shows a tendency to OOM without good reason, when a memhog goes well beyond its rss limit but with plenty of swap available. Seen on x86 but not on PowerPC; seen when the next patch omits swapcache from memcgroup, but we presume it can happen without. mem_cgroup_isolate_pages is not quite satisfying reclaim's criteria for OOM avoidance. Already it has to scan beyond the nr_to_scan limit when it finds a !LRU page or an active page when handling inactive or an inactive page when handling active. It needs to do exactly the same when it finds a page from the wrong zone (the x86 tests had two zones, the PowerPC tests had only one). Don't increment scan and then decrement it in these cases, just move the incrementation down. Fix recent off-by-one when checking against nr_to_scan. Cut out "Check if the meta page went away from under us", presumably left over from early debugging: no amount of such checks could save us if this list really were being updated without locking. This change does make the unlimited scan while holding two spinlocks even worse - bad for latency and bad for containment; but that's a separate issue which is better left to be fixed a little later. Signed-off-by: Hugh Dickins <hugh@veritas.com> Cc: Pavel Emelianov <xemul@openvz.org> Acked-by: Balbir Singh <balbir@linux.vnet.ibm.com> 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 16:14:12 +08:00
if (unlikely(!PageLRU(page)))
continue;
if (PageActive(page) && !active) {
__mem_cgroup_move_lists(pc, true);
continue;
}
if (!PageActive(page) && active) {
__mem_cgroup_move_lists(pc, false);
continue;
}
memcgroup: fix zone isolation OOM mem_cgroup_charge_common shows a tendency to OOM without good reason, when a memhog goes well beyond its rss limit but with plenty of swap available. Seen on x86 but not on PowerPC; seen when the next patch omits swapcache from memcgroup, but we presume it can happen without. mem_cgroup_isolate_pages is not quite satisfying reclaim's criteria for OOM avoidance. Already it has to scan beyond the nr_to_scan limit when it finds a !LRU page or an active page when handling inactive or an inactive page when handling active. It needs to do exactly the same when it finds a page from the wrong zone (the x86 tests had two zones, the PowerPC tests had only one). Don't increment scan and then decrement it in these cases, just move the incrementation down. Fix recent off-by-one when checking against nr_to_scan. Cut out "Check if the meta page went away from under us", presumably left over from early debugging: no amount of such checks could save us if this list really were being updated without locking. This change does make the unlimited scan while holding two spinlocks even worse - bad for latency and bad for containment; but that's a separate issue which is better left to be fixed a little later. Signed-off-by: Hugh Dickins <hugh@veritas.com> Cc: Pavel Emelianov <xemul@openvz.org> Acked-by: Balbir Singh <balbir@linux.vnet.ibm.com> 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 16:14:12 +08:00
scan++;
list_move(&pc->lru, &pc_list);
if (__isolate_lru_page(page, mode) == 0) {
list_move(&page->lru, dst);
nr_taken++;
}
}
list_splice(&pc_list, src);
spin_unlock(&mz->lru_lock);
*scanned = scan;
return nr_taken;
}
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 16:13:53 +08:00
/*
* Charge the memory controller for page usage.
* Return
* 0 if the charge was successful
* < 0 if the cgroup is over its limit
*/
static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm,
gfp_t gfp_mask, enum charge_type ctype,
struct mem_cgroup *memcg)
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 16:13:53 +08:00
{
struct mem_cgroup *mem;
struct page_cgroup *pc;
unsigned long flags;
unsigned long nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
struct mem_cgroup_per_zone *mz;
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 16:13:53 +08:00
pc = kmem_cache_alloc(page_cgroup_cache, gfp_mask);
if (unlikely(pc == NULL))
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 16:13:53 +08:00
goto err;
/*
* We always charge the cgroup the mm_struct belongs to.
* The mm_struct's mem_cgroup changes on task migration if the
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 16:13:53 +08:00
* thread group leader migrates. It's possible that mm is not
* set, if so charge the init_mm (happens for pagecache usage).
*/
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 16:47:14 +08:00
if (likely(!memcg)) {
rcu_read_lock();
mem = mem_cgroup_from_task(rcu_dereference(mm->owner));
mm owner: fix race between swapoff and exit There's a race between mm->owner assignment and swapoff, more easily seen when task slab poisoning is turned on. The condition occurs when try_to_unuse() runs in parallel with an exiting task. A similar race can occur with callers of get_task_mm(), such as /proc/<pid>/<mmstats> or ptrace or page migration. CPU0 CPU1 try_to_unuse looks at mm = task0->mm increments mm->mm_users task 0 exits mm->owner needs to be updated, but no new owner is found (mm_users > 1, but no other task has task->mm = task0->mm) mm_update_next_owner() leaves mmput(mm) decrements mm->mm_users task0 freed dereferencing mm->owner fails The fix is to notify the subsystem via mm_owner_changed callback(), if no new owner is found, by specifying the new task as NULL. Jiri Slaby: mm->owner was set to NULL prior to calling cgroup_mm_owner_callbacks(), but must be set after that, so as not to pass NULL as old owner causing oops. Daisuke Nishimura: mm_update_next_owner() may set mm->owner to NULL, but mem_cgroup_from_task() and its callers need to take account of this situation to avoid oops. Hugh Dickins: Lockdep warning and hang below exec_mmap() when testing these patches. exit_mm() up_reads mmap_sem before calling mm_update_next_owner(), so exec_mmap() now needs to do the same. And with that repositioning, there's now no point in mm_need_new_owner() allowing for NULL mm. Reported-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com> Signed-off-by: Jiri Slaby <jirislaby@gmail.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Hugh Dickins <hugh@veritas.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Paul Menage <menage@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-09-29 06:09:31 +08:00
if (unlikely(!mem)) {
rcu_read_unlock();
kmem_cache_free(page_cgroup_cache, pc);
return 0;
}
/*
* For every charge from the cgroup, increment reference count
*/
css_get(&mem->css);
rcu_read_unlock();
} else {
mem = memcg;
css_get(&memcg->css);
}
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 16:13:53 +08:00
while (res_counter_charge(&mem->res, PAGE_SIZE)) {
if (!(gfp_mask & __GFP_WAIT))
goto out;
if (try_to_free_mem_cgroup_pages(mem, gfp_mask))
continue;
/*
* try_to_free_mem_cgroup_pages() might not give us a full
* picture of reclaim. Some pages are reclaimed and might be
* moved to swap cache or just unmapped from the cgroup.
* Check the limit again to see if the reclaim reduced the
* current usage of the cgroup before giving up
*/
if (res_counter_check_under_limit(&mem->res))
continue;
if (!nr_retries--) {
mem_cgroup_out_of_memory(mem, gfp_mask);
goto out;
}
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 16:13:53 +08:00
}
pc->mem_cgroup = mem;
pc->page = page;
/*
* If a page is accounted as a page cache, insert to inactive list.
* If anon, insert to active list.
*/
if (ctype == MEM_CGROUP_CHARGE_TYPE_CACHE)
pc->flags = PAGE_CGROUP_FLAG_CACHE;
else
pc->flags = PAGE_CGROUP_FLAG_ACTIVE;
lock_page_cgroup(page);
if (unlikely(page_get_page_cgroup(page))) {
unlock_page_cgroup(page);
res_counter_uncharge(&mem->res, PAGE_SIZE);
css_put(&mem->css);
kmem_cache_free(page_cgroup_cache, pc);
goto done;
}
page_assign_page_cgroup(page, pc);
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 16:13:53 +08:00
mz = page_cgroup_zoneinfo(pc);
spin_lock_irqsave(&mz->lru_lock, flags);
__mem_cgroup_add_list(mz, pc);
spin_unlock_irqrestore(&mz->lru_lock, flags);
memcg: fix oops on NULL lru list While testing force_empty, during an exit_mmap, __mem_cgroup_remove_list called from mem_cgroup_uncharge_page oopsed on a NULL pointer in the lru list. I couldn't see what racing tasks on other cpus were doing, but surmise that another must have been in mem_cgroup_charge_common on the same page, between its unlock_page_cgroup and spin_lock_irqsave near done (thanks to that kzalloc which I'd almost changed to a kmalloc). Normally such a race cannot happen, the ref_cnt prevents it, the final uncharge cannot race with the initial charge. But force_empty buggers the ref_cnt, that's what it's all about; and thereafter forced pages are vulnerable to races such as this (just think of a shared page also mapped into an mm of another mem_cgroup than that just emptied). And remain vulnerable until they're freed indefinitely later. This patch just fixes the oops by moving the unlock_page_cgroups down below adding to and removing from the list (only possible given the previous patch); and while we're at it, we might as well make it an invariant that page->page_cgroup is always set while pc is on lru. But this behaviour of force_empty seems highly unsatisfactory to me: why have a ref_cnt if we always have to cope with it being violated (as in the earlier page migration patch). We may prefer force_empty to move pages to an orphan mem_cgroup (could be the root, but better not), from which other cgroups could recover them; we might need to reverse the locking again; but no time now for such concerns. 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>
2008-03-05 06:29:16 +08:00
unlock_page_cgroup(page);
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 16:13:53 +08:00
done:
return 0;
out:
css_put(&mem->css);
kmem_cache_free(page_cgroup_cache, pc);
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 16:13:53 +08:00
err:
return -ENOMEM;
}
int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask)
{
if (mem_cgroup_subsys.disabled)
return 0;
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 16:47:14 +08:00
/*
* If already mapped, we don't have to account.
* If page cache, page->mapping has address_space.
* But page->mapping may have out-of-use anon_vma pointer,
* detecit it by PageAnon() check. newly-mapped-anon's page->mapping
* is NULL.
*/
if (page_mapped(page) || (page->mapping && !PageAnon(page)))
return 0;
if (unlikely(!mm))
mm = &init_mm;
return mem_cgroup_charge_common(page, mm, gfp_mask,
MEM_CGROUP_CHARGE_TYPE_MAPPED, NULL);
}
int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
gfp_t gfp_mask)
{
if (mem_cgroup_subsys.disabled)
return 0;
/*
* Corner case handling. This is called from add_to_page_cache()
* in usual. But some FS (shmem) precharges this page before calling it
* and call add_to_page_cache() with GFP_NOWAIT.
*
* For GFP_NOWAIT case, the page may be pre-charged before calling
* add_to_page_cache(). (See shmem.c) check it here and avoid to call
* charge twice. (It works but has to pay a bit larger cost.)
*/
if (!(gfp_mask & __GFP_WAIT)) {
struct page_cgroup *pc;
lock_page_cgroup(page);
pc = page_get_page_cgroup(page);
if (pc) {
VM_BUG_ON(pc->page != page);
VM_BUG_ON(!pc->mem_cgroup);
unlock_page_cgroup(page);
return 0;
}
unlock_page_cgroup(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 16:47:14 +08:00
if (unlikely(!mm))
mm = &init_mm;
return mem_cgroup_charge_common(page, mm, gfp_mask,
MEM_CGROUP_CHARGE_TYPE_CACHE, NULL);
}
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 16:13:53 +08:00
/*
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 16:47:14 +08:00
* uncharge if !page_mapped(page)
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 16:13:53 +08:00
*/
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 16:47:14 +08:00
static void
__mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype)
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 16:13:53 +08:00
{
struct page_cgroup *pc;
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 16:13:53 +08:00
struct mem_cgroup *mem;
struct mem_cgroup_per_zone *mz;
unsigned long flags;
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 16:13:53 +08:00
if (mem_cgroup_subsys.disabled)
return;
/*
* Check if our page_cgroup is valid
*/
lock_page_cgroup(page);
pc = page_get_page_cgroup(page);
if (unlikely(!pc))
goto unlock;
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 16:13:53 +08:00
VM_BUG_ON(pc->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 16:47:14 +08:00
if ((ctype == MEM_CGROUP_CHARGE_TYPE_MAPPED)
&& ((pc->flags & PAGE_CGROUP_FLAG_CACHE)
|| page_mapped(page)))
goto unlock;
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 16:47:14 +08:00
mz = page_cgroup_zoneinfo(pc);
spin_lock_irqsave(&mz->lru_lock, flags);
__mem_cgroup_remove_list(mz, pc);
spin_unlock_irqrestore(&mz->lru_lock, flags);
memcg: fix oops on NULL lru list While testing force_empty, during an exit_mmap, __mem_cgroup_remove_list called from mem_cgroup_uncharge_page oopsed on a NULL pointer in the lru list. I couldn't see what racing tasks on other cpus were doing, but surmise that another must have been in mem_cgroup_charge_common on the same page, between its unlock_page_cgroup and spin_lock_irqsave near done (thanks to that kzalloc which I'd almost changed to a kmalloc). Normally such a race cannot happen, the ref_cnt prevents it, the final uncharge cannot race with the initial charge. But force_empty buggers the ref_cnt, that's what it's all about; and thereafter forced pages are vulnerable to races such as this (just think of a shared page also mapped into an mm of another mem_cgroup than that just emptied). And remain vulnerable until they're freed indefinitely later. This patch just fixes the oops by moving the unlock_page_cgroups down below adding to and removing from the list (only possible given the previous patch); and while we're at it, we might as well make it an invariant that page->page_cgroup is always set while pc is on lru. But this behaviour of force_empty seems highly unsatisfactory to me: why have a ref_cnt if we always have to cope with it being violated (as in the earlier page migration patch). We may prefer force_empty to move pages to an orphan mem_cgroup (could be the root, but better not), from which other cgroups could recover them; we might need to reverse the locking again; but no time now for such concerns. 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>
2008-03-05 06:29:16 +08:00
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 16:47:14 +08:00
page_assign_page_cgroup(page, NULL);
unlock_page_cgroup(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 16:47:14 +08:00
mem = pc->mem_cgroup;
res_counter_uncharge(&mem->res, PAGE_SIZE);
css_put(&mem->css);
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 16:47:14 +08:00
kmem_cache_free(page_cgroup_cache, pc);
return;
unlock:
unlock_page_cgroup(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 16:47:14 +08:00
void mem_cgroup_uncharge_page(struct page *page)
{
__mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_MAPPED);
}
void mem_cgroup_uncharge_cache_page(struct page *page)
{
VM_BUG_ON(page_mapped(page));
__mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_CACHE);
}
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 16:14:10 +08:00
/*
* Before starting migration, account against new page.
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 16:14:10 +08:00
*/
int mem_cgroup_prepare_migration(struct page *page, 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 16:14:10 +08:00
{
struct page_cgroup *pc;
struct mem_cgroup *mem = NULL;
enum charge_type ctype = MEM_CGROUP_CHARGE_TYPE_MAPPED;
int ret = 0;
if (mem_cgroup_subsys.disabled)
return 0;
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 16:14:10 +08:00
lock_page_cgroup(page);
pc = page_get_page_cgroup(page);
if (pc) {
mem = pc->mem_cgroup;
css_get(&mem->css);
if (pc->flags & PAGE_CGROUP_FLAG_CACHE)
ctype = MEM_CGROUP_CHARGE_TYPE_CACHE;
}
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 16:14:10 +08:00
unlock_page_cgroup(page);
if (mem) {
ret = mem_cgroup_charge_common(newpage, NULL, GFP_KERNEL,
ctype, mem);
css_put(&mem->css);
}
return ret;
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 16:14:10 +08:00
}
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 16:47:14 +08:00
/* remove redundant charge if migration failed*/
void mem_cgroup_end_migration(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 16:14:10 +08:00
{
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 16:47:14 +08:00
/*
* At success, page->mapping is not NULL.
* special rollback care is necessary when
* 1. at migration failure. (newpage->mapping is cleared in this case)
* 2. the newpage was moved but not remapped again because the task
* exits and the newpage is obsolete. In this case, the new page
* may be a swapcache. So, we just call mem_cgroup_uncharge_page()
* always for avoiding mess. The page_cgroup will be removed if
* unnecessary. File cache pages is still on radix-tree. Don't
* care it.
*/
if (!newpage->mapping)
__mem_cgroup_uncharge_common(newpage,
MEM_CGROUP_CHARGE_TYPE_FORCE);
else if (PageAnon(newpage))
mem_cgroup_uncharge_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 16:14:10 +08:00
}
/*
* A call to try to shrink memory usage under specified resource controller.
* This is typically used for page reclaiming for shmem for reducing side
* effect of page allocation from shmem, which is used by some mem_cgroup.
*/
int mem_cgroup_shrink_usage(struct mm_struct *mm, gfp_t gfp_mask)
{
struct mem_cgroup *mem;
int progress = 0;
int retry = MEM_CGROUP_RECLAIM_RETRIES;
if (mem_cgroup_subsys.disabled)
return 0;
if (!mm)
return 0;
rcu_read_lock();
mem = mem_cgroup_from_task(rcu_dereference(mm->owner));
mm owner: fix race between swapoff and exit There's a race between mm->owner assignment and swapoff, more easily seen when task slab poisoning is turned on. The condition occurs when try_to_unuse() runs in parallel with an exiting task. A similar race can occur with callers of get_task_mm(), such as /proc/<pid>/<mmstats> or ptrace or page migration. CPU0 CPU1 try_to_unuse looks at mm = task0->mm increments mm->mm_users task 0 exits mm->owner needs to be updated, but no new owner is found (mm_users > 1, but no other task has task->mm = task0->mm) mm_update_next_owner() leaves mmput(mm) decrements mm->mm_users task0 freed dereferencing mm->owner fails The fix is to notify the subsystem via mm_owner_changed callback(), if no new owner is found, by specifying the new task as NULL. Jiri Slaby: mm->owner was set to NULL prior to calling cgroup_mm_owner_callbacks(), but must be set after that, so as not to pass NULL as old owner causing oops. Daisuke Nishimura: mm_update_next_owner() may set mm->owner to NULL, but mem_cgroup_from_task() and its callers need to take account of this situation to avoid oops. Hugh Dickins: Lockdep warning and hang below exec_mmap() when testing these patches. exit_mm() up_reads mmap_sem before calling mm_update_next_owner(), so exec_mmap() now needs to do the same. And with that repositioning, there's now no point in mm_need_new_owner() allowing for NULL mm. Reported-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com> Signed-off-by: Jiri Slaby <jirislaby@gmail.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Hugh Dickins <hugh@veritas.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Paul Menage <menage@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-09-29 06:09:31 +08:00
if (unlikely(!mem)) {
rcu_read_unlock();
return 0;
}
css_get(&mem->css);
rcu_read_unlock();
do {
progress = try_to_free_mem_cgroup_pages(mem, gfp_mask);
progress += res_counter_check_under_limit(&mem->res);
} while (!progress && --retry);
css_put(&mem->css);
if (!retry)
return -ENOMEM;
return 0;
}
int mem_cgroup_resize_limit(struct mem_cgroup *memcg, unsigned long long val)
{
int retry_count = MEM_CGROUP_RECLAIM_RETRIES;
int progress;
int ret = 0;
while (res_counter_set_limit(&memcg->res, val)) {
if (signal_pending(current)) {
ret = -EINTR;
break;
}
if (!retry_count) {
ret = -EBUSY;
break;
}
progress = try_to_free_mem_cgroup_pages(memcg, GFP_KERNEL);
if (!progress)
retry_count--;
}
return ret;
}
/*
* This routine traverse page_cgroup in given list and drop them all.
* *And* this routine doesn't reclaim page itself, just removes page_cgroup.
*/
#define FORCE_UNCHARGE_BATCH (128)
static void mem_cgroup_force_empty_list(struct mem_cgroup *mem,
struct mem_cgroup_per_zone *mz,
int active)
{
struct page_cgroup *pc;
struct page *page;
int count = FORCE_UNCHARGE_BATCH;
unsigned long flags;
struct list_head *list;
if (active)
list = &mz->active_list;
else
list = &mz->inactive_list;
spin_lock_irqsave(&mz->lru_lock, flags);
while (!list_empty(list)) {
pc = list_entry(list->prev, struct page_cgroup, lru);
page = pc->page;
get_page(page);
spin_unlock_irqrestore(&mz->lru_lock, flags);
/*
* Check if this page is on LRU. !LRU page can be found
* if it's under page migration.
*/
if (PageLRU(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 16:47:14 +08:00
__mem_cgroup_uncharge_common(page,
MEM_CGROUP_CHARGE_TYPE_FORCE);
put_page(page);
if (--count <= 0) {
count = FORCE_UNCHARGE_BATCH;
cond_resched();
}
} else
cond_resched();
spin_lock_irqsave(&mz->lru_lock, flags);
}
spin_unlock_irqrestore(&mz->lru_lock, flags);
}
/*
* make mem_cgroup's charge to be 0 if there is no task.
* This enables deleting this mem_cgroup.
*/
static int mem_cgroup_force_empty(struct mem_cgroup *mem)
{
int ret = -EBUSY;
int node, zid;
css_get(&mem->css);
/*
* page reclaim code (kswapd etc..) will move pages between
* active_list <-> inactive_list while we don't take a lock.
* So, we have to do loop here until all lists are empty.
*/
while (mem->res.usage > 0) {
if (atomic_read(&mem->css.cgroup->count) > 0)
goto out;
for_each_node_state(node, N_POSSIBLE)
for (zid = 0; zid < MAX_NR_ZONES; zid++) {
struct mem_cgroup_per_zone *mz;
mz = mem_cgroup_zoneinfo(mem, node, zid);
/* drop all page_cgroup in active_list */
mem_cgroup_force_empty_list(mem, mz, 1);
/* drop all page_cgroup in inactive_list */
mem_cgroup_force_empty_list(mem, mz, 0);
}
}
ret = 0;
out:
css_put(&mem->css);
return ret;
}
static u64 mem_cgroup_read(struct cgroup *cont, struct cftype *cft)
{
return res_counter_read_u64(&mem_cgroup_from_cont(cont)->res,
cft->private);
}
/*
* The user of this function is...
* RES_LIMIT.
*/
static int mem_cgroup_write(struct cgroup *cont, struct cftype *cft,
const char *buffer)
{
struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
unsigned long long val;
int ret;
switch (cft->private) {
case RES_LIMIT:
/* This function does all necessary parse...reuse it */
ret = res_counter_memparse_write_strategy(buffer, &val);
if (!ret)
ret = mem_cgroup_resize_limit(memcg, val);
break;
default:
ret = -EINVAL; /* should be BUG() ? */
break;
}
return ret;
}
static int mem_cgroup_reset(struct cgroup *cont, unsigned int event)
{
struct mem_cgroup *mem;
mem = mem_cgroup_from_cont(cont);
switch (event) {
case RES_MAX_USAGE:
res_counter_reset_max(&mem->res);
break;
case RES_FAILCNT:
res_counter_reset_failcnt(&mem->res);
break;
}
return 0;
}
static int mem_force_empty_write(struct cgroup *cont, unsigned int event)
{
return mem_cgroup_force_empty(mem_cgroup_from_cont(cont));
}
static const struct mem_cgroup_stat_desc {
const char *msg;
u64 unit;
} mem_cgroup_stat_desc[] = {
[MEM_CGROUP_STAT_CACHE] = { "cache", PAGE_SIZE, },
[MEM_CGROUP_STAT_RSS] = { "rss", PAGE_SIZE, },
[MEM_CGROUP_STAT_PGPGIN_COUNT] = {"pgpgin", 1, },
[MEM_CGROUP_STAT_PGPGOUT_COUNT] = {"pgpgout", 1, },
};
static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft,
struct cgroup_map_cb *cb)
{
struct mem_cgroup *mem_cont = mem_cgroup_from_cont(cont);
struct mem_cgroup_stat *stat = &mem_cont->stat;
int i;
for (i = 0; i < ARRAY_SIZE(stat->cpustat[0].count); i++) {
s64 val;
val = mem_cgroup_read_stat(stat, i);
val *= mem_cgroup_stat_desc[i].unit;
cb->fill(cb, mem_cgroup_stat_desc[i].msg, val);
}
/* showing # of active pages */
{
unsigned long active, inactive;
inactive = mem_cgroup_get_all_zonestat(mem_cont,
MEM_CGROUP_ZSTAT_INACTIVE);
active = mem_cgroup_get_all_zonestat(mem_cont,
MEM_CGROUP_ZSTAT_ACTIVE);
cb->fill(cb, "active", (active) * PAGE_SIZE);
cb->fill(cb, "inactive", (inactive) * PAGE_SIZE);
}
return 0;
}
static struct cftype mem_cgroup_files[] = {
{
.name = "usage_in_bytes",
.private = RES_USAGE,
.read_u64 = mem_cgroup_read,
},
{
.name = "max_usage_in_bytes",
.private = RES_MAX_USAGE,
.trigger = mem_cgroup_reset,
.read_u64 = mem_cgroup_read,
},
{
.name = "limit_in_bytes",
.private = RES_LIMIT,
.write_string = mem_cgroup_write,
.read_u64 = mem_cgroup_read,
},
{
.name = "failcnt",
.private = RES_FAILCNT,
.trigger = mem_cgroup_reset,
.read_u64 = mem_cgroup_read,
},
{
.name = "force_empty",
.trigger = mem_force_empty_write,
},
{
.name = "stat",
.read_map = mem_control_stat_show,
},
};
static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *mem, int node)
{
struct mem_cgroup_per_node *pn;
struct mem_cgroup_per_zone *mz;
int zone, tmp = node;
/*
* This routine is called against possible nodes.
* But it's BUG to call kmalloc() against offline node.
*
* TODO: this routine can waste much memory for nodes which will
* never be onlined. It's better to use memory hotplug callback
* function.
*/
if (!node_state(node, N_NORMAL_MEMORY))
tmp = -1;
pn = kmalloc_node(sizeof(*pn), GFP_KERNEL, tmp);
if (!pn)
return 1;
mem->info.nodeinfo[node] = pn;
memset(pn, 0, sizeof(*pn));
for (zone = 0; zone < MAX_NR_ZONES; zone++) {
mz = &pn->zoneinfo[zone];
INIT_LIST_HEAD(&mz->active_list);
INIT_LIST_HEAD(&mz->inactive_list);
spin_lock_init(&mz->lru_lock);
}
return 0;
}
static void free_mem_cgroup_per_zone_info(struct mem_cgroup *mem, int node)
{
kfree(mem->info.nodeinfo[node]);
}
static struct mem_cgroup *mem_cgroup_alloc(void)
{
struct mem_cgroup *mem;
if (sizeof(*mem) < PAGE_SIZE)
mem = kmalloc(sizeof(*mem), GFP_KERNEL);
else
mem = vmalloc(sizeof(*mem));
if (mem)
memset(mem, 0, sizeof(*mem));
return mem;
}
static void mem_cgroup_free(struct mem_cgroup *mem)
{
if (sizeof(*mem) < PAGE_SIZE)
kfree(mem);
else
vfree(mem);
}
static struct cgroup_subsys_state *
mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
{
struct mem_cgroup *mem;
int node;
if (unlikely((cont->parent) == NULL)) {
mem = &init_mem_cgroup;
page_cgroup_cache = KMEM_CACHE(page_cgroup, SLAB_PANIC);
} else {
mem = mem_cgroup_alloc();
if (!mem)
return ERR_PTR(-ENOMEM);
}
res_counter_init(&mem->res);
for_each_node_state(node, N_POSSIBLE)
if (alloc_mem_cgroup_per_zone_info(mem, node))
goto free_out;
return &mem->css;
free_out:
for_each_node_state(node, N_POSSIBLE)
free_mem_cgroup_per_zone_info(mem, node);
if (cont->parent != NULL)
mem_cgroup_free(mem);
return ERR_PTR(-ENOMEM);
}
static void mem_cgroup_pre_destroy(struct cgroup_subsys *ss,
struct cgroup *cont)
{
struct mem_cgroup *mem = mem_cgroup_from_cont(cont);
mem_cgroup_force_empty(mem);
}
static void mem_cgroup_destroy(struct cgroup_subsys *ss,
struct cgroup *cont)
{
int node;
struct mem_cgroup *mem = mem_cgroup_from_cont(cont);
for_each_node_state(node, N_POSSIBLE)
free_mem_cgroup_per_zone_info(mem, node);
mem_cgroup_free(mem_cgroup_from_cont(cont));
}
static int mem_cgroup_populate(struct cgroup_subsys *ss,
struct cgroup *cont)
{
return cgroup_add_files(cont, ss, mem_cgroup_files,
ARRAY_SIZE(mem_cgroup_files));
}
static void mem_cgroup_move_task(struct cgroup_subsys *ss,
struct cgroup *cont,
struct cgroup *old_cont,
struct task_struct *p)
{
struct mm_struct *mm;
struct mem_cgroup *mem, *old_mem;
mm = get_task_mm(p);
if (mm == NULL)
return;
mem = mem_cgroup_from_cont(cont);
old_mem = mem_cgroup_from_cont(old_cont);
/*
* Only thread group leaders are allowed to migrate, the mm_struct is
* in effect owned by the leader
*/
if (!thread_group_leader(p))
goto out;
out:
mmput(mm);
}
struct cgroup_subsys mem_cgroup_subsys = {
.name = "memory",
.subsys_id = mem_cgroup_subsys_id,
.create = mem_cgroup_create,
.pre_destroy = mem_cgroup_pre_destroy,
.destroy = mem_cgroup_destroy,
.populate = mem_cgroup_populate,
.attach = mem_cgroup_move_task,
.early_init = 0,
};