From bb2a0de92c891b8feeedc0178acb3ae009d899a8 Mon Sep 17 00:00:00 2001
From: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Date: Tue, 26 Jul 2011 16:08:22 -0700
Subject: memcg: consolidate memory cgroup lru stat functions
In mm/memcontrol.c, there are many lru stat functions as..
mem_cgroup_zone_nr_lru_pages
mem_cgroup_node_nr_file_lru_pages
mem_cgroup_nr_file_lru_pages
mem_cgroup_node_nr_anon_lru_pages
mem_cgroup_nr_anon_lru_pages
mem_cgroup_node_nr_unevictable_lru_pages
mem_cgroup_nr_unevictable_lru_pages
mem_cgroup_node_nr_lru_pages
mem_cgroup_nr_lru_pages
mem_cgroup_get_local_zonestat
Some of them are under #ifdef MAX_NUMNODES >1 and others are not.
This seems bad. This patch consolidates all functions into
mem_cgroup_zone_nr_lru_pages()
mem_cgroup_node_nr_lru_pages()
mem_cgroup_nr_lru_pages()
For these functions, "which LRU?" information is passed by a mask.
example:
mem_cgroup_nr_lru_pages(mem, BIT(LRU_ACTIVE_ANON))
And I added some macro as ALL_LRU, ALL_LRU_FILE, ALL_LRU_ANON.
example:
mem_cgroup_nr_lru_pages(mem, ALL_LRU)
BTW, considering layout of NUMA memory placement of counters, this patch seems
to be better.
Now, when we gather all LRU information, we scan in following orer
for_each_lru -> for_each_node -> for_each_zone.
This means we'll touch cache lines in different node in turn.
After patch, we'll scan
for_each_node -> for_each_zone -> for_each_lru(mask)
Then, we'll gather information in the same cacheline at once.
[akpm@linux-foundation.org: fix warnigns, build error]
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Cc: Balbir Singh <bsingharora@gmail.com>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Ying Han <yinghan@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
include/linux/memcontrol.h | 7 +++----
1 file changed, 3 insertions(+), 4 deletions(-)
(limited to 'include/linux/memcontrol.h')
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 50940da6adf..affd5b19b86 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -111,8 +111,7 @@ int mem_cgroup_inactive_anon_is_low(struct mem_cgroup *memcg);
int mem_cgroup_inactive_file_is_low(struct mem_cgroup *memcg);
int mem_cgroup_select_victim_node(struct mem_cgroup *memcg);
unsigned long mem_cgroup_zone_nr_lru_pages(struct mem_cgroup *memcg,
- struct zone *zone,
- enum lru_list lru);
+ int nid, int zid, unsigned int lrumask);
struct zone_reclaim_stat *mem_cgroup_get_reclaim_stat(struct mem_cgroup *memcg,
struct zone *zone);
struct zone_reclaim_stat*
@@ -313,8 +312,8 @@ mem_cgroup_inactive_file_is_low(struct mem_cgroup *memcg)
}
static inline unsigned long
-mem_cgroup_zone_nr_lru_pages(struct mem_cgroup *memcg, struct zone *zone,
- enum lru_list lru)
+mem_cgroup_zone_nr_lru_pages(struct mem_cgroup *memcg, int nid, int zid,
+ unsigned int lru_mask)
{
return 0;
}
--
cgit v1.2.3-70-g09d2
From 82f9d486e59f588c7d100865c36510644abda356 Mon Sep 17 00:00:00 2001
From: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Date: Tue, 26 Jul 2011 16:08:26 -0700
Subject: memcg: add memory.vmscan_stat
The commit log of 0ae5e89c60c9 ("memcg: count the soft_limit reclaim
in...") says it adds scanning stats to memory.stat file. But it doesn't
because we considered we needed to make a concensus for such new APIs.
This patch is a trial to add memory.scan_stat. This shows
- the number of scanned pages(total, anon, file)
- the number of rotated pages(total, anon, file)
- the number of freed pages(total, anon, file)
- the number of elaplsed time (including sleep/pause time)
for both of direct/soft reclaim.
The biggest difference with oringinal Ying's one is that this file
can be reset by some write, as
# echo 0 ...../memory.scan_stat
Example of output is here. This is a result after make -j 6 kernel
under 300M limit.
[kamezawa@bluextal ~]$ cat /cgroup/memory/A/memory.scan_stat
[kamezawa@bluextal ~]$ cat /cgroup/memory/A/memory.vmscan_stat
scanned_pages_by_limit 9471864
scanned_anon_pages_by_limit 6640629
scanned_file_pages_by_limit 2831235
rotated_pages_by_limit 4243974
rotated_anon_pages_by_limit 3971968
rotated_file_pages_by_limit 272006
freed_pages_by_limit 2318492
freed_anon_pages_by_limit 962052
freed_file_pages_by_limit 1356440
elapsed_ns_by_limit 351386416101
scanned_pages_by_system 0
scanned_anon_pages_by_system 0
scanned_file_pages_by_system 0
rotated_pages_by_system 0
rotated_anon_pages_by_system 0
rotated_file_pages_by_system 0
freed_pages_by_system 0
freed_anon_pages_by_system 0
freed_file_pages_by_system 0
elapsed_ns_by_system 0
scanned_pages_by_limit_under_hierarchy 9471864
scanned_anon_pages_by_limit_under_hierarchy 6640629
scanned_file_pages_by_limit_under_hierarchy 2831235
rotated_pages_by_limit_under_hierarchy 4243974
rotated_anon_pages_by_limit_under_hierarchy 3971968
rotated_file_pages_by_limit_under_hierarchy 272006
freed_pages_by_limit_under_hierarchy 2318492
freed_anon_pages_by_limit_under_hierarchy 962052
freed_file_pages_by_limit_under_hierarchy 1356440
elapsed_ns_by_limit_under_hierarchy 351386416101
scanned_pages_by_system_under_hierarchy 0
scanned_anon_pages_by_system_under_hierarchy 0
scanned_file_pages_by_system_under_hierarchy 0
rotated_pages_by_system_under_hierarchy 0
rotated_anon_pages_by_system_under_hierarchy 0
rotated_file_pages_by_system_under_hierarchy 0
freed_pages_by_system_under_hierarchy 0
freed_anon_pages_by_system_under_hierarchy 0
freed_file_pages_by_system_under_hierarchy 0
elapsed_ns_by_system_under_hierarchy 0
total_xxxx is for hierarchy management.
This will be useful for further memcg developments and need to be
developped before we do some complicated rework on LRU/softlimit
management.
This patch adds a new struct memcg_scanrecord into scan_control struct.
sc->nr_scanned at el is not designed for exporting information. For
example, nr_scanned is reset frequentrly and incremented +2 at scanning
mapped pages.
To avoid complexity, I added a new param in scan_control which is for
exporting scanning score.
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Ying Han <yinghan@google.com>
Cc: Andrew Bresticker <abrestic@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
Documentation/cgroups/memory.txt | 85 ++++++++++++++++++-
include/linux/memcontrol.h | 19 +++++
include/linux/swap.h | 6 --
mm/memcontrol.c | 172 +++++++++++++++++++++++++++++++++++++--
mm/vmscan.c | 39 +++++++--
5 files changed, 303 insertions(+), 18 deletions(-)
(limited to 'include/linux/memcontrol.h')
diff --git a/Documentation/cgroups/memory.txt b/Documentation/cgroups/memory.txt
index 06eb6d957c8..6f3c598971f 100644
--- a/Documentation/cgroups/memory.txt
+++ b/Documentation/cgroups/memory.txt
@@ -380,7 +380,7 @@ will be charged as a new owner of it.
5.2 stat file
-memory.stat file includes following statistics
+5.2.1 memory.stat file includes following statistics
# per-memory cgroup local status
cache - # of bytes of page cache memory.
@@ -438,6 +438,89 @@ Note:
file_mapped is accounted only when the memory cgroup is owner of page
cache.)
+5.2.2 memory.vmscan_stat
+
+memory.vmscan_stat includes statistics information for memory scanning and
+freeing, reclaiming. The statistics shows memory scanning information since
+memory cgroup creation and can be reset to 0 by writing 0 as
+
+ #echo 0 > ../memory.vmscan_stat
+
+This file contains following statistics.
+
+[param]_[file_or_anon]_pages_by_[reason]_[under_heararchy]
+[param]_elapsed_ns_by_[reason]_[under_hierarchy]
+
+For example,
+
+ scanned_file_pages_by_limit indicates the number of scanned
+ file pages at vmscan.
+
+Now, 3 parameters are supported
+
+ scanned - the number of pages scanned by vmscan
+ rotated - the number of pages activated at vmscan
+ freed - the number of pages freed by vmscan
+
+If "rotated" is high against scanned/freed, the memcg seems busy.
+
+Now, 2 reason are supported
+
+ limit - the memory cgroup's limit
+ system - global memory pressure + softlimit
+ (global memory pressure not under softlimit is not handled now)
+
+When under_hierarchy is added in the tail, the number indicates the
+total memcg scan of its children and itself.
+
+elapsed_ns is a elapsed time in nanosecond. This may include sleep time
+and not indicates CPU usage. So, please take this as just showing
+latency.
+
+Here is an example.
+
+# cat /cgroup/memory/A/memory.vmscan_stat
+scanned_pages_by_limit 9471864
+scanned_anon_pages_by_limit 6640629
+scanned_file_pages_by_limit 2831235
+rotated_pages_by_limit 4243974
+rotated_anon_pages_by_limit 3971968
+rotated_file_pages_by_limit 272006
+freed_pages_by_limit 2318492
+freed_anon_pages_by_limit 962052
+freed_file_pages_by_limit 1356440
+elapsed_ns_by_limit 351386416101
+scanned_pages_by_system 0
+scanned_anon_pages_by_system 0
+scanned_file_pages_by_system 0
+rotated_pages_by_system 0
+rotated_anon_pages_by_system 0
+rotated_file_pages_by_system 0
+freed_pages_by_system 0
+freed_anon_pages_by_system 0
+freed_file_pages_by_system 0
+elapsed_ns_by_system 0
+scanned_pages_by_limit_under_hierarchy 9471864
+scanned_anon_pages_by_limit_under_hierarchy 6640629
+scanned_file_pages_by_limit_under_hierarchy 2831235
+rotated_pages_by_limit_under_hierarchy 4243974
+rotated_anon_pages_by_limit_under_hierarchy 3971968
+rotated_file_pages_by_limit_under_hierarchy 272006
+freed_pages_by_limit_under_hierarchy 2318492
+freed_anon_pages_by_limit_under_hierarchy 962052
+freed_file_pages_by_limit_under_hierarchy 1356440
+elapsed_ns_by_limit_under_hierarchy 351386416101
+scanned_pages_by_system_under_hierarchy 0
+scanned_anon_pages_by_system_under_hierarchy 0
+scanned_file_pages_by_system_under_hierarchy 0
+rotated_pages_by_system_under_hierarchy 0
+rotated_anon_pages_by_system_under_hierarchy 0
+rotated_file_pages_by_system_under_hierarchy 0
+freed_pages_by_system_under_hierarchy 0
+freed_anon_pages_by_system_under_hierarchy 0
+freed_file_pages_by_system_under_hierarchy 0
+elapsed_ns_by_system_under_hierarchy 0
+
5.3 swappiness
Similar to /proc/sys/vm/swappiness, but affecting a hierarchy of groups only.
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index affd5b19b86..b9660078691 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -39,6 +39,16 @@ extern unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
struct mem_cgroup *mem_cont,
int active, int file);
+struct memcg_scanrecord {
+ struct mem_cgroup *mem; /* scanend memory cgroup */
+ struct mem_cgroup *root; /* scan target hierarchy root */
+ int context; /* scanning context (see memcontrol.c) */
+ unsigned long nr_scanned[2]; /* the number of scanned pages */
+ unsigned long nr_rotated[2]; /* the number of rotated pages */
+ unsigned long nr_freed[2]; /* the number of freed pages */
+ unsigned long elapsed; /* nsec of time elapsed while scanning */
+};
+
#ifdef CONFIG_CGROUP_MEM_RES_CTLR
/*
* All "charge" functions with gfp_mask should use GFP_KERNEL or
@@ -119,6 +129,15 @@ mem_cgroup_get_reclaim_stat_from_page(struct page *page);
extern void mem_cgroup_print_oom_info(struct mem_cgroup *memcg,
struct task_struct *p);
+extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem,
+ gfp_t gfp_mask, bool noswap,
+ struct memcg_scanrecord *rec);
+extern unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem,
+ gfp_t gfp_mask, bool noswap,
+ struct zone *zone,
+ struct memcg_scanrecord *rec,
+ unsigned long *nr_scanned);
+
#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
extern int do_swap_account;
#endif
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 44558b600ee..91d5fcc8311 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -251,12 +251,6 @@ static inline void lru_cache_add_file(struct page *page)
/* linux/mm/vmscan.c */
extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
gfp_t gfp_mask, nodemask_t *mask);
-extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem,
- gfp_t gfp_mask, bool noswap);
-extern unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem,
- gfp_t gfp_mask, bool noswap,
- struct zone *zone,
- unsigned long *nr_scanned);
extern int __isolate_lru_page(struct page *page, int mode, int file);
extern unsigned long shrink_all_memory(unsigned long nr_pages);
extern int vm_swappiness;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index dfeca594fd7..04e505bfd7d 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -205,6 +205,50 @@ struct mem_cgroup_eventfd_list {
static void mem_cgroup_threshold(struct mem_cgroup *mem);
static void mem_cgroup_oom_notify(struct mem_cgroup *mem);
+enum {
+ SCAN_BY_LIMIT,
+ SCAN_BY_SYSTEM,
+ NR_SCAN_CONTEXT,
+ SCAN_BY_SHRINK, /* not recorded now */
+};
+
+enum {
+ SCAN,
+ SCAN_ANON,
+ SCAN_FILE,
+ ROTATE,
+ ROTATE_ANON,
+ ROTATE_FILE,
+ FREED,
+ FREED_ANON,
+ FREED_FILE,
+ ELAPSED,
+ NR_SCANSTATS,
+};
+
+struct scanstat {
+ spinlock_t lock;
+ unsigned long stats[NR_SCAN_CONTEXT][NR_SCANSTATS];
+ unsigned long rootstats[NR_SCAN_CONTEXT][NR_SCANSTATS];
+};
+
+const char *scanstat_string[NR_SCANSTATS] = {
+ "scanned_pages",
+ "scanned_anon_pages",
+ "scanned_file_pages",
+ "rotated_pages",
+ "rotated_anon_pages",
+ "rotated_file_pages",
+ "freed_pages",
+ "freed_anon_pages",
+ "freed_file_pages",
+ "elapsed_ns",
+};
+#define SCANSTAT_WORD_LIMIT "_by_limit"
+#define SCANSTAT_WORD_SYSTEM "_by_system"
+#define SCANSTAT_WORD_HIERARCHY "_under_hierarchy"
+
+
/*
* The memory controller data structure. The memory controller controls both
* page cache and RSS per cgroup. We would eventually like to provide
@@ -270,7 +314,8 @@ struct mem_cgroup {
/* For oom notifier event fd */
struct list_head oom_notify;
-
+ /* For recording LRU-scan statistics */
+ struct scanstat scanstat;
/*
* Should we move charges of a task when a task is moved into this
* mem_cgroup ? And what type of charges should we move ?
@@ -1623,6 +1668,44 @@ bool mem_cgroup_reclaimable(struct mem_cgroup *mem, bool noswap)
}
#endif
+static void __mem_cgroup_record_scanstat(unsigned long *stats,
+ struct memcg_scanrecord *rec)
+{
+
+ stats[SCAN] += rec->nr_scanned[0] + rec->nr_scanned[1];
+ stats[SCAN_ANON] += rec->nr_scanned[0];
+ stats[SCAN_FILE] += rec->nr_scanned[1];
+
+ stats[ROTATE] += rec->nr_rotated[0] + rec->nr_rotated[1];
+ stats[ROTATE_ANON] += rec->nr_rotated[0];
+ stats[ROTATE_FILE] += rec->nr_rotated[1];
+
+ stats[FREED] += rec->nr_freed[0] + rec->nr_freed[1];
+ stats[FREED_ANON] += rec->nr_freed[0];
+ stats[FREED_FILE] += rec->nr_freed[1];
+
+ stats[ELAPSED] += rec->elapsed;
+}
+
+static void mem_cgroup_record_scanstat(struct memcg_scanrecord *rec)
+{
+ struct mem_cgroup *mem;
+ int context = rec->context;
+
+ if (context >= NR_SCAN_CONTEXT)
+ return;
+
+ mem = rec->mem;
+ spin_lock(&mem->scanstat.lock);
+ __mem_cgroup_record_scanstat(mem->scanstat.stats[context], rec);
+ spin_unlock(&mem->scanstat.lock);
+
+ mem = rec->root;
+ spin_lock(&mem->scanstat.lock);
+ __mem_cgroup_record_scanstat(mem->scanstat.rootstats[context], rec);
+ spin_unlock(&mem->scanstat.lock);
+}
+
/*
* Scan the hierarchy if needed to reclaim memory. We remember the last child
* we reclaimed from, so that we don't end up penalizing one child extensively
@@ -1647,8 +1730,9 @@ static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_mem,
bool noswap = reclaim_options & MEM_CGROUP_RECLAIM_NOSWAP;
bool shrink = reclaim_options & MEM_CGROUP_RECLAIM_SHRINK;
bool check_soft = reclaim_options & MEM_CGROUP_RECLAIM_SOFT;
+ struct memcg_scanrecord rec;
unsigned long excess;
- unsigned long nr_scanned;
+ unsigned long scanned;
excess = res_counter_soft_limit_excess(&root_mem->res) >> PAGE_SHIFT;
@@ -1656,6 +1740,15 @@ static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_mem,
if (!check_soft && !shrink && root_mem->memsw_is_minimum)
noswap = true;
+ if (shrink)
+ rec.context = SCAN_BY_SHRINK;
+ else if (check_soft)
+ rec.context = SCAN_BY_SYSTEM;
+ else
+ rec.context = SCAN_BY_LIMIT;
+
+ rec.root = root_mem;
+
while (1) {
victim = mem_cgroup_select_victim(root_mem);
if (victim == root_mem) {
@@ -1696,14 +1789,23 @@ static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_mem,
css_put(&victim->css);
continue;
}
+ rec.mem = victim;
+ rec.nr_scanned[0] = 0;
+ rec.nr_scanned[1] = 0;
+ rec.nr_rotated[0] = 0;
+ rec.nr_rotated[1] = 0;
+ rec.nr_freed[0] = 0;
+ rec.nr_freed[1] = 0;
+ rec.elapsed = 0;
/* we use swappiness of local cgroup */
if (check_soft) {
ret = mem_cgroup_shrink_node_zone(victim, gfp_mask,
- noswap, zone, &nr_scanned);
- *total_scanned += nr_scanned;
+ noswap, zone, &rec, &scanned);
+ *total_scanned += scanned;
} else
ret = try_to_free_mem_cgroup_pages(victim, gfp_mask,
- noswap);
+ noswap, &rec);
+ mem_cgroup_record_scanstat(&rec);
css_put(&victim->css);
/*
* At shrinking usage, we can't check we should stop here or
@@ -3792,14 +3894,18 @@ try_to_free:
/* try to free all pages in this cgroup */
shrink = 1;
while (nr_retries && mem->res.usage > 0) {
+ struct memcg_scanrecord rec;
int progress;
if (signal_pending(current)) {
ret = -EINTR;
goto out;
}
+ rec.context = SCAN_BY_SHRINK;
+ rec.mem = mem;
+ rec.root = mem;
progress = try_to_free_mem_cgroup_pages(mem, GFP_KERNEL,
- false);
+ false, &rec);
if (!progress) {
nr_retries--;
/* maybe some writeback is necessary */
@@ -4643,6 +4749,54 @@ static int mem_control_numa_stat_open(struct inode *unused, struct file *file)
}
#endif /* CONFIG_NUMA */
+static int mem_cgroup_vmscan_stat_read(struct cgroup *cgrp,
+ struct cftype *cft,
+ struct cgroup_map_cb *cb)
+{
+ struct mem_cgroup *mem = mem_cgroup_from_cont(cgrp);
+ char string[64];
+ int i;
+
+ for (i = 0; i < NR_SCANSTATS; i++) {
+ strcpy(string, scanstat_string[i]);
+ strcat(string, SCANSTAT_WORD_LIMIT);
+ cb->fill(cb, string, mem->scanstat.stats[SCAN_BY_LIMIT][i]);
+ }
+
+ for (i = 0; i < NR_SCANSTATS; i++) {
+ strcpy(string, scanstat_string[i]);
+ strcat(string, SCANSTAT_WORD_SYSTEM);
+ cb->fill(cb, string, mem->scanstat.stats[SCAN_BY_SYSTEM][i]);
+ }
+
+ for (i = 0; i < NR_SCANSTATS; i++) {
+ strcpy(string, scanstat_string[i]);
+ strcat(string, SCANSTAT_WORD_LIMIT);
+ strcat(string, SCANSTAT_WORD_HIERARCHY);
+ cb->fill(cb, string, mem->scanstat.rootstats[SCAN_BY_LIMIT][i]);
+ }
+ for (i = 0; i < NR_SCANSTATS; i++) {
+ strcpy(string, scanstat_string[i]);
+ strcat(string, SCANSTAT_WORD_SYSTEM);
+ strcat(string, SCANSTAT_WORD_HIERARCHY);
+ cb->fill(cb, string, mem->scanstat.rootstats[SCAN_BY_SYSTEM][i]);
+ }
+ return 0;
+}
+
+static int mem_cgroup_reset_vmscan_stat(struct cgroup *cgrp,
+ unsigned int event)
+{
+ struct mem_cgroup *mem = mem_cgroup_from_cont(cgrp);
+
+ spin_lock(&mem->scanstat.lock);
+ memset(&mem->scanstat.stats, 0, sizeof(mem->scanstat.stats));
+ memset(&mem->scanstat.rootstats, 0, sizeof(mem->scanstat.rootstats));
+ spin_unlock(&mem->scanstat.lock);
+ return 0;
+}
+
+
static struct cftype mem_cgroup_files[] = {
{
.name = "usage_in_bytes",
@@ -4713,6 +4867,11 @@ static struct cftype mem_cgroup_files[] = {
.mode = S_IRUGO,
},
#endif
+ {
+ .name = "vmscan_stat",
+ .read_map = mem_cgroup_vmscan_stat_read,
+ .trigger = mem_cgroup_reset_vmscan_stat,
+ },
};
#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
@@ -4976,6 +5135,7 @@ mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
atomic_set(&mem->refcnt, 1);
mem->move_charge_at_immigrate = 0;
mutex_init(&mem->thresholds_lock);
+ spin_lock_init(&mem->scanstat.lock);
return &mem->css;
free_out:
__mem_cgroup_free(mem);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index f87702a376d..7ef69124fa3 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -105,6 +105,7 @@ struct scan_control {
/* Which cgroup do we reclaim from */
struct mem_cgroup *mem_cgroup;
+ struct memcg_scanrecord *memcg_record;
/*
* Nodemask of nodes allowed by the caller. If NULL, all nodes
@@ -1348,6 +1349,8 @@ putback_lru_pages(struct zone *zone, struct scan_control *sc,
int file = is_file_lru(lru);
int numpages = hpage_nr_pages(page);
reclaim_stat->recent_rotated[file] += numpages;
+ if (!scanning_global_lru(sc))
+ sc->memcg_record->nr_rotated[file] += numpages;
}
if (!pagevec_add(&pvec, page)) {
spin_unlock_irq(&zone->lru_lock);
@@ -1391,6 +1394,10 @@ static noinline_for_stack void update_isolated_counts(struct zone *zone,
reclaim_stat->recent_scanned[0] += *nr_anon;
reclaim_stat->recent_scanned[1] += *nr_file;
+ if (!scanning_global_lru(sc)) {
+ sc->memcg_record->nr_scanned[0] += *nr_anon;
+ sc->memcg_record->nr_scanned[1] += *nr_file;
+ }
}
/*
@@ -1504,6 +1511,9 @@ shrink_inactive_list(unsigned long nr_to_scan, struct zone *zone,
nr_reclaimed += shrink_page_list(&page_list, zone, sc);
}
+ if (!scanning_global_lru(sc))
+ sc->memcg_record->nr_freed[file] += nr_reclaimed;
+
local_irq_disable();
if (current_is_kswapd())
__count_vm_events(KSWAPD_STEAL, nr_reclaimed);
@@ -1603,6 +1613,8 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
}
reclaim_stat->recent_scanned[file] += nr_taken;
+ if (!scanning_global_lru(sc))
+ sc->memcg_record->nr_scanned[file] += nr_taken;
__count_zone_vm_events(PGREFILL, zone, pgscanned);
if (file)
@@ -1654,6 +1666,8 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
* get_scan_ratio.
*/
reclaim_stat->recent_rotated[file] += nr_rotated;
+ if (!scanning_global_lru(sc))
+ sc->memcg_record->nr_rotated[file] += nr_rotated;
move_active_pages_to_lru(zone, &l_active,
LRU_ACTIVE + file * LRU_FILE);
@@ -2254,9 +2268,10 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
#ifdef CONFIG_CGROUP_MEM_RES_CTLR
unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem,
- gfp_t gfp_mask, bool noswap,
- struct zone *zone,
- unsigned long *nr_scanned)
+ gfp_t gfp_mask, bool noswap,
+ struct zone *zone,
+ struct memcg_scanrecord *rec,
+ unsigned long *scanned)
{
struct scan_control sc = {
.nr_scanned = 0,
@@ -2266,7 +2281,9 @@ unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem,
.may_swap = !noswap,
.order = 0,
.mem_cgroup = mem,
+ .memcg_record = rec,
};
+ unsigned long start, end;
sc.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) |
(GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK);
@@ -2275,6 +2292,7 @@ unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem,
sc.may_writepage,
sc.gfp_mask);
+ start = sched_clock();
/*
* NOTE: Although we can get the priority field, using it
* here is not a good idea, since it limits the pages we can scan.
@@ -2283,19 +2301,25 @@ unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem,
* the priority and make it zero.
*/
shrink_zone(0, zone, &sc);
+ end = sched_clock();
+
+ if (rec)
+ rec->elapsed += end - start;
+ *scanned = sc.nr_scanned;
trace_mm_vmscan_memcg_softlimit_reclaim_end(sc.nr_reclaimed);
- *nr_scanned = sc.nr_scanned;
return sc.nr_reclaimed;
}
unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont,
gfp_t gfp_mask,
- bool noswap)
+ bool noswap,
+ struct memcg_scanrecord *rec)
{
struct zonelist *zonelist;
unsigned long nr_reclaimed;
+ unsigned long start, end;
int nid;
struct scan_control sc = {
.may_writepage = !laptop_mode,
@@ -2304,6 +2328,7 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont,
.nr_to_reclaim = SWAP_CLUSTER_MAX,
.order = 0,
.mem_cgroup = mem_cont,
+ .memcg_record = rec,
.nodemask = NULL, /* we don't care the placement */
.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) |
(GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK),
@@ -2312,6 +2337,7 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont,
.gfp_mask = sc.gfp_mask,
};
+ start = sched_clock();
/*
* Unlike direct reclaim via alloc_pages(), memcg's reclaim doesn't
* take care of from where we get pages. So the node where we start the
@@ -2326,6 +2352,9 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont,
sc.gfp_mask);
nr_reclaimed = do_try_to_free_pages(zonelist, &sc, &shrink);
+ end = sched_clock();
+ if (rec)
+ rec->elapsed += end - start;
trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed);
--
cgit v1.2.3-70-g09d2
From aa3b189551ad8e5cc1d9c663735c131650238278 Mon Sep 17 00:00:00 2001
From: Hugh Dickins <hughd@google.com>
Date: Wed, 3 Aug 2011 16:21:24 -0700
Subject: tmpfs: convert mem_cgroup shmem to radix-swap
Remove mem_cgroup_shmem_charge_fallback(): it was only required when we
had to move swappage to filecache with GFP_NOWAIT.
Remove the GFP_NOWAIT special case from mem_cgroup_cache_charge(), by
moving its call out from shmem_add_to_page_cache() to two of thats three
callers. But leave it doing mem_cgroup_uncharge_cache_page() on error:
although asymmetrical, it's easier for all 3 callers to handle.
These two changes would also be appropriate if anyone were to start
using shmem_read_mapping_page_gfp() with GFP_NOWAIT.
Remove mem_cgroup_get_shmem_target(): mc_handle_file_pte() can test
radix_tree_exceptional_entry() to get what it needs for itself.
Signed-off-by: Hugh Dickins <hughd@google.com>
Acked-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
include/linux/memcontrol.h | 8 -----
include/linux/shmem_fs.h | 2 --
mm/memcontrol.c | 66 +++++-------------------------------
mm/shmem.c | 83 ++++++----------------------------------------
4 files changed, 20 insertions(+), 139 deletions(-)
(limited to 'include/linux/memcontrol.h')
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index b9660078691..3b535db00a9 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -86,8 +86,6 @@ extern void mem_cgroup_uncharge_end(void);
extern void mem_cgroup_uncharge_page(struct page *page);
extern void mem_cgroup_uncharge_cache_page(struct page *page);
-extern int mem_cgroup_shmem_charge_fallback(struct page *page,
- struct mm_struct *mm, gfp_t gfp_mask);
extern void mem_cgroup_out_of_memory(struct mem_cgroup *mem, gfp_t gfp_mask);
int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *mem);
@@ -225,12 +223,6 @@ static inline void mem_cgroup_uncharge_cache_page(struct page *page)
{
}
-static inline int mem_cgroup_shmem_charge_fallback(struct page *page,
- struct mm_struct *mm, gfp_t gfp_mask)
-{
- return 0;
-}
-
static inline void mem_cgroup_add_lru_list(struct page *page, int lru)
{
}
diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h
index 3f05795dcf7..0c8e952df59 100644
--- a/include/linux/shmem_fs.h
+++ b/include/linux/shmem_fs.h
@@ -57,8 +57,6 @@ extern struct page *shmem_read_mapping_page_gfp(struct address_space *mapping,
pgoff_t index, gfp_t gfp_mask);
extern void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end);
extern int shmem_unuse(swp_entry_t entry, struct page *page);
-extern void mem_cgroup_get_shmem_target(struct inode *inode, pgoff_t pgoff,
- struct page **pagep, swp_entry_t *ent);
static inline struct page *shmem_read_mapping_page(
struct address_space *mapping, pgoff_t index)
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 5f84d2351dd..f4ec4e7ca4c 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -35,7 +35,6 @@
#include <linux/limits.h>
#include <linux/mutex.h>
#include <linux/rbtree.h>
-#include <linux/shmem_fs.h>
#include <linux/slab.h>
#include <linux/swap.h>
#include <linux/swapops.h>
@@ -2873,30 +2872,6 @@ int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
return 0;
if (PageCompound(page))
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.)
- * And when the page is SwapCache, it should take swap information
- * into account. This is under lock_page() now.
- */
- if (!(gfp_mask & __GFP_WAIT)) {
- struct page_cgroup *pc;
-
- pc = lookup_page_cgroup(page);
- if (!pc)
- return 0;
- lock_page_cgroup(pc);
- if (PageCgroupUsed(pc)) {
- unlock_page_cgroup(pc);
- return 0;
- }
- unlock_page_cgroup(pc);
- }
if (unlikely(!mm))
mm = &init_mm;
@@ -3486,31 +3461,6 @@ void mem_cgroup_end_migration(struct mem_cgroup *mem,
cgroup_release_and_wakeup_rmdir(&mem->css);
}
-/*
- * A call to try to shrink memory usage on charge failure at shmem's swapin.
- * Calling hierarchical_reclaim is not enough because we should update
- * last_oom_jiffies to prevent pagefault_out_of_memory from invoking global OOM.
- * Moreover considering hierarchy, we should reclaim from the mem_over_limit,
- * not from the memcg which this page would be charged to.
- * try_charge_swapin does all of these works properly.
- */
-int mem_cgroup_shmem_charge_fallback(struct page *page,
- struct mm_struct *mm,
- gfp_t gfp_mask)
-{
- struct mem_cgroup *mem;
- int ret;
-
- if (mem_cgroup_disabled())
- return 0;
-
- ret = mem_cgroup_try_charge_swapin(mm, page, gfp_mask, &mem);
- if (!ret)
- mem_cgroup_cancel_charge_swapin(mem); /* it does !mem check */
-
- return ret;
-}
-
#ifdef CONFIG_DEBUG_VM
static struct page_cgroup *lookup_page_cgroup_used(struct page *page)
{
@@ -5330,15 +5280,17 @@ static struct page *mc_handle_file_pte(struct vm_area_struct *vma,
pgoff = pte_to_pgoff(ptent);
/* page is moved even if it's not RSS of this task(page-faulted). */
- if (!mapping_cap_swap_backed(mapping)) { /* normal file */
- page = find_get_page(mapping, pgoff);
- } else { /* shmem/tmpfs file. we should take account of swap too. */
- swp_entry_t ent;
- mem_cgroup_get_shmem_target(inode, pgoff, &page, &ent);
+ page = find_get_page(mapping, pgoff);
+
+#ifdef CONFIG_SWAP
+ /* shmem/tmpfs may report page out on swap: account for that too. */
+ if (radix_tree_exceptional_entry(page)) {
+ swp_entry_t swap = radix_to_swp_entry(page);
if (do_swap_account)
- entry->val = ent.val;
+ *entry = swap;
+ page = find_get_page(&swapper_space, swap.val);
}
-
+#endif
return page;
}
diff --git a/mm/shmem.c b/mm/shmem.c
index 92f01d7cc15..13ef2d7e912 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -262,15 +262,11 @@ static int shmem_add_to_page_cache(struct page *page,
struct address_space *mapping,
pgoff_t index, gfp_t gfp, void *expected)
{
- int error;
+ int error = 0;
VM_BUG_ON(!PageLocked(page));
VM_BUG_ON(!PageSwapBacked(page));
- error = mem_cgroup_cache_charge(page, current->mm,
- gfp & GFP_RECLAIM_MASK);
- if (error)
- goto out;
if (!expected)
error = radix_tree_preload(gfp & GFP_RECLAIM_MASK);
if (!error) {
@@ -300,7 +296,6 @@ static int shmem_add_to_page_cache(struct page *page,
}
if (error)
mem_cgroup_uncharge_cache_page(page);
-out:
return error;
}
@@ -660,7 +655,6 @@ int shmem_unuse(swp_entry_t swap, struct page *page)
* Charge page using GFP_KERNEL while we can wait, before taking
* the shmem_swaplist_mutex which might hold up shmem_writepage().
* Charged back to the user (not to caller) when swap account is used.
- * shmem_add_to_page_cache() will be called with GFP_NOWAIT.
*/
error = mem_cgroup_cache_charge(page, current->mm, GFP_KERNEL);
if (error)
@@ -954,8 +948,11 @@ repeat:
goto failed;
}
- error = shmem_add_to_page_cache(page, mapping, index,
- gfp, swp_to_radix_entry(swap));
+ error = mem_cgroup_cache_charge(page, current->mm,
+ gfp & GFP_RECLAIM_MASK);
+ if (!error)
+ error = shmem_add_to_page_cache(page, mapping, index,
+ gfp, swp_to_radix_entry(swap));
if (error)
goto failed;
@@ -990,8 +987,11 @@ repeat:
SetPageSwapBacked(page);
__set_page_locked(page);
- error = shmem_add_to_page_cache(page, mapping, index,
- gfp, NULL);
+ error = mem_cgroup_cache_charge(page, current->mm,
+ gfp & GFP_RECLAIM_MASK);
+ if (!error)
+ error = shmem_add_to_page_cache(page, mapping, index,
+ gfp, NULL);
if (error)
goto decused;
lru_cache_add_anon(page);
@@ -2442,42 +2442,6 @@ out4:
return error;
}
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR
-/**
- * mem_cgroup_get_shmem_target - find page or swap assigned to the shmem file
- * @inode: the inode to be searched
- * @index: the page offset to be searched
- * @pagep: the pointer for the found page to be stored
- * @swapp: the pointer for the found swap entry to be stored
- *
- * If a page is found, refcount of it is incremented. Callers should handle
- * these refcount.
- */
-void mem_cgroup_get_shmem_target(struct inode *inode, pgoff_t index,
- struct page **pagep, swp_entry_t *swapp)
-{
- struct shmem_inode_info *info = SHMEM_I(inode);
- struct page *page = NULL;
- swp_entry_t swap = {0};
-
- if ((index << PAGE_CACHE_SHIFT) >= i_size_read(inode))
- goto out;
-
- spin_lock(&info->lock);
-#ifdef CONFIG_SWAP
- swap = shmem_get_swap(info, index);
- if (swap.val)
- page = find_get_page(&swapper_space, swap.val);
- else
-#endif
- page = find_get_page(inode->i_mapping, index);
- spin_unlock(&info->lock);
-out:
- *pagep = page;
- *swapp = swap;
-}
-#endif
-
#else /* !CONFIG_SHMEM */
/*
@@ -2523,31 +2487,6 @@ void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend)
}
EXPORT_SYMBOL_GPL(shmem_truncate_range);
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR
-/**
- * mem_cgroup_get_shmem_target - find page or swap assigned to the shmem file
- * @inode: the inode to be searched
- * @index: the page offset to be searched
- * @pagep: the pointer for the found page to be stored
- * @swapp: the pointer for the found swap entry to be stored
- *
- * If a page is found, refcount of it is incremented. Callers should handle
- * these refcount.
- */
-void mem_cgroup_get_shmem_target(struct inode *inode, pgoff_t index,
- struct page **pagep, swp_entry_t *swapp)
-{
- struct page *page = NULL;
-
- if ((index << PAGE_CACHE_SHIFT) >= i_size_read(inode))
- goto out;
- page = find_get_page(inode->i_mapping, index);
-out:
- *pagep = page;
- *swapp = (swp_entry_t){0};
-}
-#endif
-
#define shmem_vm_ops generic_file_vm_ops
#define shmem_file_operations ramfs_file_operations
#define shmem_get_inode(sb, dir, mode, dev, flags) ramfs_get_inode(sb, dir, mode, dev)
--
cgit v1.2.3-70-g09d2
From 185efc0f9a1f2d6ad6d4782c5d9e529f3290567f Mon Sep 17 00:00:00 2001
From: Johannes Weiner <jweiner@redhat.com>
Date: Wed, 14 Sep 2011 16:21:58 -0700
Subject: memcg: Revert "memcg: add memory.vmscan_stat"
Revert the post-3.0 commit 82f9d486e59f5 ("memcg: add
memory.vmscan_stat").
The implementation of per-memcg reclaim statistics violates how memcg
hierarchies usually behave: hierarchically.
The reclaim statistics are accounted to child memcgs and the parent
hitting the limit, but not to hierarchy levels in between. Usually,
hierarchical statistics are perfectly recursive, with each level
representing the sum of itself and all its children.
Since this exports statistics to userspace, this may lead to confusion
and problems with changing things after the release, so revert it now,
we can try again later.
Signed-off-by: Johannes Weiner <jweiner@redhat.com>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Ying Han <yinghan@google.com>
Cc: Balbir Singh <bsingharora@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
Documentation/cgroups/memory.txt | 85 +------------------
include/linux/memcontrol.h | 19 -----
include/linux/swap.h | 6 ++
mm/memcontrol.c | 172 ++-------------------------------------
mm/vmscan.c | 39 ++-------
5 files changed, 18 insertions(+), 303 deletions(-)
(limited to 'include/linux/memcontrol.h')
diff --git a/Documentation/cgroups/memory.txt b/Documentation/cgroups/memory.txt
index 6f3c598971f..06eb6d957c8 100644
--- a/Documentation/cgroups/memory.txt
+++ b/Documentation/cgroups/memory.txt
@@ -380,7 +380,7 @@ will be charged as a new owner of it.
5.2 stat file
-5.2.1 memory.stat file includes following statistics
+memory.stat file includes following statistics
# per-memory cgroup local status
cache - # of bytes of page cache memory.
@@ -438,89 +438,6 @@ Note:
file_mapped is accounted only when the memory cgroup is owner of page
cache.)
-5.2.2 memory.vmscan_stat
-
-memory.vmscan_stat includes statistics information for memory scanning and
-freeing, reclaiming. The statistics shows memory scanning information since
-memory cgroup creation and can be reset to 0 by writing 0 as
-
- #echo 0 > ../memory.vmscan_stat
-
-This file contains following statistics.
-
-[param]_[file_or_anon]_pages_by_[reason]_[under_heararchy]
-[param]_elapsed_ns_by_[reason]_[under_hierarchy]
-
-For example,
-
- scanned_file_pages_by_limit indicates the number of scanned
- file pages at vmscan.
-
-Now, 3 parameters are supported
-
- scanned - the number of pages scanned by vmscan
- rotated - the number of pages activated at vmscan
- freed - the number of pages freed by vmscan
-
-If "rotated" is high against scanned/freed, the memcg seems busy.
-
-Now, 2 reason are supported
-
- limit - the memory cgroup's limit
- system - global memory pressure + softlimit
- (global memory pressure not under softlimit is not handled now)
-
-When under_hierarchy is added in the tail, the number indicates the
-total memcg scan of its children and itself.
-
-elapsed_ns is a elapsed time in nanosecond. This may include sleep time
-and not indicates CPU usage. So, please take this as just showing
-latency.
-
-Here is an example.
-
-# cat /cgroup/memory/A/memory.vmscan_stat
-scanned_pages_by_limit 9471864
-scanned_anon_pages_by_limit 6640629
-scanned_file_pages_by_limit 2831235
-rotated_pages_by_limit 4243974
-rotated_anon_pages_by_limit 3971968
-rotated_file_pages_by_limit 272006
-freed_pages_by_limit 2318492
-freed_anon_pages_by_limit 962052
-freed_file_pages_by_limit 1356440
-elapsed_ns_by_limit 351386416101
-scanned_pages_by_system 0
-scanned_anon_pages_by_system 0
-scanned_file_pages_by_system 0
-rotated_pages_by_system 0
-rotated_anon_pages_by_system 0
-rotated_file_pages_by_system 0
-freed_pages_by_system 0
-freed_anon_pages_by_system 0
-freed_file_pages_by_system 0
-elapsed_ns_by_system 0
-scanned_pages_by_limit_under_hierarchy 9471864
-scanned_anon_pages_by_limit_under_hierarchy 6640629
-scanned_file_pages_by_limit_under_hierarchy 2831235
-rotated_pages_by_limit_under_hierarchy 4243974
-rotated_anon_pages_by_limit_under_hierarchy 3971968
-rotated_file_pages_by_limit_under_hierarchy 272006
-freed_pages_by_limit_under_hierarchy 2318492
-freed_anon_pages_by_limit_under_hierarchy 962052
-freed_file_pages_by_limit_under_hierarchy 1356440
-elapsed_ns_by_limit_under_hierarchy 351386416101
-scanned_pages_by_system_under_hierarchy 0
-scanned_anon_pages_by_system_under_hierarchy 0
-scanned_file_pages_by_system_under_hierarchy 0
-rotated_pages_by_system_under_hierarchy 0
-rotated_anon_pages_by_system_under_hierarchy 0
-rotated_file_pages_by_system_under_hierarchy 0
-freed_pages_by_system_under_hierarchy 0
-freed_anon_pages_by_system_under_hierarchy 0
-freed_file_pages_by_system_under_hierarchy 0
-elapsed_ns_by_system_under_hierarchy 0
-
5.3 swappiness
Similar to /proc/sys/vm/swappiness, but affecting a hierarchy of groups only.
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 3b535db00a9..343bd7661f2 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -39,16 +39,6 @@ extern unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
struct mem_cgroup *mem_cont,
int active, int file);
-struct memcg_scanrecord {
- struct mem_cgroup *mem; /* scanend memory cgroup */
- struct mem_cgroup *root; /* scan target hierarchy root */
- int context; /* scanning context (see memcontrol.c) */
- unsigned long nr_scanned[2]; /* the number of scanned pages */
- unsigned long nr_rotated[2]; /* the number of rotated pages */
- unsigned long nr_freed[2]; /* the number of freed pages */
- unsigned long elapsed; /* nsec of time elapsed while scanning */
-};
-
#ifdef CONFIG_CGROUP_MEM_RES_CTLR
/*
* All "charge" functions with gfp_mask should use GFP_KERNEL or
@@ -127,15 +117,6 @@ mem_cgroup_get_reclaim_stat_from_page(struct page *page);
extern void mem_cgroup_print_oom_info(struct mem_cgroup *memcg,
struct task_struct *p);
-extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem,
- gfp_t gfp_mask, bool noswap,
- struct memcg_scanrecord *rec);
-extern unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem,
- gfp_t gfp_mask, bool noswap,
- struct zone *zone,
- struct memcg_scanrecord *rec,
- unsigned long *nr_scanned);
-
#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
extern int do_swap_account;
#endif
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 14d62490922..c71f84bb62e 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -252,6 +252,12 @@ static inline void lru_cache_add_file(struct page *page)
extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
gfp_t gfp_mask, nodemask_t *mask);
extern int __isolate_lru_page(struct page *page, int mode, int file);
+extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem,
+ gfp_t gfp_mask, bool noswap);
+extern unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem,
+ gfp_t gfp_mask, bool noswap,
+ struct zone *zone,
+ unsigned long *nr_scanned);
extern unsigned long shrink_all_memory(unsigned long nr_pages);
extern int vm_swappiness;
extern int remove_mapping(struct address_space *mapping, struct page *page);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index ebd1e86bef1..3508777837c 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -204,50 +204,6 @@ struct mem_cgroup_eventfd_list {
static void mem_cgroup_threshold(struct mem_cgroup *mem);
static void mem_cgroup_oom_notify(struct mem_cgroup *mem);
-enum {
- SCAN_BY_LIMIT,
- SCAN_BY_SYSTEM,
- NR_SCAN_CONTEXT,
- SCAN_BY_SHRINK, /* not recorded now */
-};
-
-enum {
- SCAN,
- SCAN_ANON,
- SCAN_FILE,
- ROTATE,
- ROTATE_ANON,
- ROTATE_FILE,
- FREED,
- FREED_ANON,
- FREED_FILE,
- ELAPSED,
- NR_SCANSTATS,
-};
-
-struct scanstat {
- spinlock_t lock;
- unsigned long stats[NR_SCAN_CONTEXT][NR_SCANSTATS];
- unsigned long rootstats[NR_SCAN_CONTEXT][NR_SCANSTATS];
-};
-
-const char *scanstat_string[NR_SCANSTATS] = {
- "scanned_pages",
- "scanned_anon_pages",
- "scanned_file_pages",
- "rotated_pages",
- "rotated_anon_pages",
- "rotated_file_pages",
- "freed_pages",
- "freed_anon_pages",
- "freed_file_pages",
- "elapsed_ns",
-};
-#define SCANSTAT_WORD_LIMIT "_by_limit"
-#define SCANSTAT_WORD_SYSTEM "_by_system"
-#define SCANSTAT_WORD_HIERARCHY "_under_hierarchy"
-
-
/*
* The memory controller data structure. The memory controller controls both
* page cache and RSS per cgroup. We would eventually like to provide
@@ -313,8 +269,7 @@ struct mem_cgroup {
/* For oom notifier event fd */
struct list_head oom_notify;
- /* For recording LRU-scan statistics */
- struct scanstat scanstat;
+
/*
* Should we move charges of a task when a task is moved into this
* mem_cgroup ? And what type of charges should we move ?
@@ -1678,44 +1633,6 @@ bool mem_cgroup_reclaimable(struct mem_cgroup *mem, bool noswap)
}
#endif
-static void __mem_cgroup_record_scanstat(unsigned long *stats,
- struct memcg_scanrecord *rec)
-{
-
- stats[SCAN] += rec->nr_scanned[0] + rec->nr_scanned[1];
- stats[SCAN_ANON] += rec->nr_scanned[0];
- stats[SCAN_FILE] += rec->nr_scanned[1];
-
- stats[ROTATE] += rec->nr_rotated[0] + rec->nr_rotated[1];
- stats[ROTATE_ANON] += rec->nr_rotated[0];
- stats[ROTATE_FILE] += rec->nr_rotated[1];
-
- stats[FREED] += rec->nr_freed[0] + rec->nr_freed[1];
- stats[FREED_ANON] += rec->nr_freed[0];
- stats[FREED_FILE] += rec->nr_freed[1];
-
- stats[ELAPSED] += rec->elapsed;
-}
-
-static void mem_cgroup_record_scanstat(struct memcg_scanrecord *rec)
-{
- struct mem_cgroup *mem;
- int context = rec->context;
-
- if (context >= NR_SCAN_CONTEXT)
- return;
-
- mem = rec->mem;
- spin_lock(&mem->scanstat.lock);
- __mem_cgroup_record_scanstat(mem->scanstat.stats[context], rec);
- spin_unlock(&mem->scanstat.lock);
-
- mem = rec->root;
- spin_lock(&mem->scanstat.lock);
- __mem_cgroup_record_scanstat(mem->scanstat.rootstats[context], rec);
- spin_unlock(&mem->scanstat.lock);
-}
-
/*
* Scan the hierarchy if needed to reclaim memory. We remember the last child
* we reclaimed from, so that we don't end up penalizing one child extensively
@@ -1740,9 +1657,8 @@ static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_mem,
bool noswap = reclaim_options & MEM_CGROUP_RECLAIM_NOSWAP;
bool shrink = reclaim_options & MEM_CGROUP_RECLAIM_SHRINK;
bool check_soft = reclaim_options & MEM_CGROUP_RECLAIM_SOFT;
- struct memcg_scanrecord rec;
unsigned long excess;
- unsigned long scanned;
+ unsigned long nr_scanned;
excess = res_counter_soft_limit_excess(&root_mem->res) >> PAGE_SHIFT;
@@ -1750,15 +1666,6 @@ static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_mem,
if (!check_soft && !shrink && root_mem->memsw_is_minimum)
noswap = true;
- if (shrink)
- rec.context = SCAN_BY_SHRINK;
- else if (check_soft)
- rec.context = SCAN_BY_SYSTEM;
- else
- rec.context = SCAN_BY_LIMIT;
-
- rec.root = root_mem;
-
while (1) {
victim = mem_cgroup_select_victim(root_mem);
if (victim == root_mem) {
@@ -1799,23 +1706,14 @@ static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_mem,
css_put(&victim->css);
continue;
}
- rec.mem = victim;
- rec.nr_scanned[0] = 0;
- rec.nr_scanned[1] = 0;
- rec.nr_rotated[0] = 0;
- rec.nr_rotated[1] = 0;
- rec.nr_freed[0] = 0;
- rec.nr_freed[1] = 0;
- rec.elapsed = 0;
/* we use swappiness of local cgroup */
if (check_soft) {
ret = mem_cgroup_shrink_node_zone(victim, gfp_mask,
- noswap, zone, &rec, &scanned);
- *total_scanned += scanned;
+ noswap, zone, &nr_scanned);
+ *total_scanned += nr_scanned;
} else
ret = try_to_free_mem_cgroup_pages(victim, gfp_mask,
- noswap, &rec);
- mem_cgroup_record_scanstat(&rec);
+ noswap);
css_put(&victim->css);
/*
* At shrinking usage, we can't check we should stop here or
@@ -3854,18 +3752,14 @@ try_to_free:
/* try to free all pages in this cgroup */
shrink = 1;
while (nr_retries && mem->res.usage > 0) {
- struct memcg_scanrecord rec;
int progress;
if (signal_pending(current)) {
ret = -EINTR;
goto out;
}
- rec.context = SCAN_BY_SHRINK;
- rec.mem = mem;
- rec.root = mem;
progress = try_to_free_mem_cgroup_pages(mem, GFP_KERNEL,
- false, &rec);
+ false);
if (!progress) {
nr_retries--;
/* maybe some writeback is necessary */
@@ -4709,54 +4603,6 @@ static int mem_control_numa_stat_open(struct inode *unused, struct file *file)
}
#endif /* CONFIG_NUMA */
-static int mem_cgroup_vmscan_stat_read(struct cgroup *cgrp,
- struct cftype *cft,
- struct cgroup_map_cb *cb)
-{
- struct mem_cgroup *mem = mem_cgroup_from_cont(cgrp);
- char string[64];
- int i;
-
- for (i = 0; i < NR_SCANSTATS; i++) {
- strcpy(string, scanstat_string[i]);
- strcat(string, SCANSTAT_WORD_LIMIT);
- cb->fill(cb, string, mem->scanstat.stats[SCAN_BY_LIMIT][i]);
- }
-
- for (i = 0; i < NR_SCANSTATS; i++) {
- strcpy(string, scanstat_string[i]);
- strcat(string, SCANSTAT_WORD_SYSTEM);
- cb->fill(cb, string, mem->scanstat.stats[SCAN_BY_SYSTEM][i]);
- }
-
- for (i = 0; i < NR_SCANSTATS; i++) {
- strcpy(string, scanstat_string[i]);
- strcat(string, SCANSTAT_WORD_LIMIT);
- strcat(string, SCANSTAT_WORD_HIERARCHY);
- cb->fill(cb, string, mem->scanstat.rootstats[SCAN_BY_LIMIT][i]);
- }
- for (i = 0; i < NR_SCANSTATS; i++) {
- strcpy(string, scanstat_string[i]);
- strcat(string, SCANSTAT_WORD_SYSTEM);
- strcat(string, SCANSTAT_WORD_HIERARCHY);
- cb->fill(cb, string, mem->scanstat.rootstats[SCAN_BY_SYSTEM][i]);
- }
- return 0;
-}
-
-static int mem_cgroup_reset_vmscan_stat(struct cgroup *cgrp,
- unsigned int event)
-{
- struct mem_cgroup *mem = mem_cgroup_from_cont(cgrp);
-
- spin_lock(&mem->scanstat.lock);
- memset(&mem->scanstat.stats, 0, sizeof(mem->scanstat.stats));
- memset(&mem->scanstat.rootstats, 0, sizeof(mem->scanstat.rootstats));
- spin_unlock(&mem->scanstat.lock);
- return 0;
-}
-
-
static struct cftype mem_cgroup_files[] = {
{
.name = "usage_in_bytes",
@@ -4827,11 +4673,6 @@ static struct cftype mem_cgroup_files[] = {
.mode = S_IRUGO,
},
#endif
- {
- .name = "vmscan_stat",
- .read_map = mem_cgroup_vmscan_stat_read,
- .trigger = mem_cgroup_reset_vmscan_stat,
- },
};
#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
@@ -5095,7 +4936,6 @@ mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
atomic_set(&mem->refcnt, 1);
mem->move_charge_at_immigrate = 0;
mutex_init(&mem->thresholds_lock);
- spin_lock_init(&mem->scanstat.lock);
return &mem->css;
free_out:
__mem_cgroup_free(mem);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index e49bcb6d494..b55699cd906 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -105,7 +105,6 @@ struct scan_control {
/* Which cgroup do we reclaim from */
struct mem_cgroup *mem_cgroup;
- struct memcg_scanrecord *memcg_record;
/*
* Nodemask of nodes allowed by the caller. If NULL, all nodes
@@ -1349,8 +1348,6 @@ putback_lru_pages(struct zone *zone, struct scan_control *sc,
int file = is_file_lru(lru);
int numpages = hpage_nr_pages(page);
reclaim_stat->recent_rotated[file] += numpages;
- if (!scanning_global_lru(sc))
- sc->memcg_record->nr_rotated[file] += numpages;
}
if (!pagevec_add(&pvec, page)) {
spin_unlock_irq(&zone->lru_lock);
@@ -1394,10 +1391,6 @@ static noinline_for_stack void update_isolated_counts(struct zone *zone,
reclaim_stat->recent_scanned[0] += *nr_anon;
reclaim_stat->recent_scanned[1] += *nr_file;
- if (!scanning_global_lru(sc)) {
- sc->memcg_record->nr_scanned[0] += *nr_anon;
- sc->memcg_record->nr_scanned[1] += *nr_file;
- }
}
/*
@@ -1511,9 +1504,6 @@ shrink_inactive_list(unsigned long nr_to_scan, struct zone *zone,
nr_reclaimed += shrink_page_list(&page_list, zone, sc);
}
- if (!scanning_global_lru(sc))
- sc->memcg_record->nr_freed[file] += nr_reclaimed;
-
local_irq_disable();
if (current_is_kswapd())
__count_vm_events(KSWAPD_STEAL, nr_reclaimed);
@@ -1613,8 +1603,6 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
}
reclaim_stat->recent_scanned[file] += nr_taken;
- if (!scanning_global_lru(sc))
- sc->memcg_record->nr_scanned[file] += nr_taken;
__count_zone_vm_events(PGREFILL, zone, pgscanned);
if (file)
@@ -1666,8 +1654,6 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
* get_scan_ratio.
*/
reclaim_stat->recent_rotated[file] += nr_rotated;
- if (!scanning_global_lru(sc))
- sc->memcg_record->nr_rotated[file] += nr_rotated;
move_active_pages_to_lru(zone, &l_active,
LRU_ACTIVE + file * LRU_FILE);
@@ -2265,10 +2251,9 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
#ifdef CONFIG_CGROUP_MEM_RES_CTLR
unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem,
- gfp_t gfp_mask, bool noswap,
- struct zone *zone,
- struct memcg_scanrecord *rec,
- unsigned long *scanned)
+ gfp_t gfp_mask, bool noswap,
+ struct zone *zone,
+ unsigned long *nr_scanned)
{
struct scan_control sc = {
.nr_scanned = 0,
@@ -2278,9 +2263,7 @@ unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem,
.may_swap = !noswap,
.order = 0,
.mem_cgroup = mem,
- .memcg_record = rec,
};
- ktime_t start, end;
sc.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) |
(GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK);
@@ -2289,7 +2272,6 @@ unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem,
sc.may_writepage,
sc.gfp_mask);
- start = ktime_get();
/*
* NOTE: Although we can get the priority field, using it
* here is not a good idea, since it limits the pages we can scan.
@@ -2298,25 +2280,19 @@ unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem,
* the priority and make it zero.
*/
shrink_zone(0, zone, &sc);
- end = ktime_get();
-
- if (rec)
- rec->elapsed += ktime_to_ns(ktime_sub(end, start));
- *scanned = sc.nr_scanned;
trace_mm_vmscan_memcg_softlimit_reclaim_end(sc.nr_reclaimed);
+ *nr_scanned = sc.nr_scanned;
return sc.nr_reclaimed;
}
unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont,
gfp_t gfp_mask,
- bool noswap,
- struct memcg_scanrecord *rec)
+ bool noswap)
{
struct zonelist *zonelist;
unsigned long nr_reclaimed;
- ktime_t start, end;
int nid;
struct scan_control sc = {
.may_writepage = !laptop_mode,
@@ -2325,7 +2301,6 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont,
.nr_to_reclaim = SWAP_CLUSTER_MAX,
.order = 0,
.mem_cgroup = mem_cont,
- .memcg_record = rec,
.nodemask = NULL, /* we don't care the placement */
.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) |
(GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK),
@@ -2334,7 +2309,6 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont,
.gfp_mask = sc.gfp_mask,
};
- start = ktime_get();
/*
* Unlike direct reclaim via alloc_pages(), memcg's reclaim doesn't
* take care of from where we get pages. So the node where we start the
@@ -2349,9 +2323,6 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont,
sc.gfp_mask);
nr_reclaimed = do_try_to_free_pages(zonelist, &sc, &shrink);
- end = ktime_get();
- if (rec)
- rec->elapsed += ktime_to_ns(ktime_sub(end, start));
trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed);
--
cgit v1.2.3-70-g09d2