mm: change the call sites of numa statistics items
Patch series "Separate NUMA statistics from zone statistics", v2. Each page allocation updates a set of per-zone statistics with a call to zone_statistics(). As discussed in 2017 MM summit, these are a substantial source of overhead in the page allocator and are very rarely consumed. This significant overhead in cache bouncing caused by zone counters (NUMA associated counters) update in parallel in multi-threaded page allocation (pointed out by Dave Hansen). A link to the MM summit slides: http://people.netfilter.org/hawk/presentations/MM-summit2017/MM-summit2017-JesperBrouer.pdf To mitigate this overhead, this patchset separates NUMA statistics from zone statistics framework, and update NUMA counter threshold to a fixed size of MAX_U16 - 2, as a small threshold greatly increases the update frequency of the global counter from local per cpu counter (suggested by Ying Huang). The rationality is that these statistics counters don't need to be read often, unlike other VM counters, so it's not a problem to use a large threshold and make readers more expensive. With this patchset, we see 31.3% drop of CPU cycles(537-->369, see below) for per single page allocation and reclaim on Jesper's page_bench03 benchmark. Meanwhile, this patchset keeps the same style of virtual memory statistics with little end-user-visible effects (only move the numa stats to show behind zone page stats, see the first patch for details). I did an experiment of single page allocation and reclaim concurrently using Jesper's page_bench03 benchmark on a 2-Socket Broadwell-based server (88 processors with 126G memory) with different size of threshold of pcp counter. Benchmark provided by Jesper D Brouer(increase loop times to 10000000): https://github.com/netoptimizer/prototype-kernel/tree/master/kernel/mm/bench Threshold CPU cycles Throughput(88 threads) 32 799 241760478 64 640 301628829 125 537 358906028 <==> system by default 256 468 412397590 512 428 450550704 4096 399 482520943 20000 394 489009617 30000 395 488017817 65533 369(-31.3%) 521661345(+45.3%) <==> with this patchset N/A 342(-36.3%) 562900157(+56.8%) <==> disable zone_statistics This patch (of 3): In this patch, NUMA statistics is separated from zone statistics framework, all the call sites of NUMA stats are changed to use numa-stats-specific functions, it does not have any functionality change except that the number of NUMA stats is shown behind zone page stats when users *read* the zone info. E.g. cat /proc/zoneinfo ***Base*** ***With this patch*** nr_free_pages 3976 nr_free_pages 3976 nr_zone_inactive_anon 0 nr_zone_inactive_anon 0 nr_zone_active_anon 0 nr_zone_active_anon 0 nr_zone_inactive_file 0 nr_zone_inactive_file 0 nr_zone_active_file 0 nr_zone_active_file 0 nr_zone_unevictable 0 nr_zone_unevictable 0 nr_zone_write_pending 0 nr_zone_write_pending 0 nr_mlock 0 nr_mlock 0 nr_page_table_pages 0 nr_page_table_pages 0 nr_kernel_stack 0 nr_kernel_stack 0 nr_bounce 0 nr_bounce 0 nr_zspages 0 nr_zspages 0 numa_hit 0 *nr_free_cma 0* numa_miss 0 numa_hit 0 numa_foreign 0 numa_miss 0 numa_interleave 0 numa_foreign 0 numa_local 0 numa_interleave 0 numa_other 0 numa_local 0 *nr_free_cma 0* numa_other 0 ... ... vm stats threshold: 10 vm stats threshold: 10 ... ... The next patch updates the numa stats counter size and threshold. [akpm@linux-foundation.org: coding-style fixes] Link: http://lkml.kernel.org/r/1503568801-21305-2-git-send-email-kemi.wang@intel.com Signed-off-by: Kemi Wang <kemi.wang@intel.com> Reported-by: Jesper Dangaard Brouer <brouer@redhat.com> Acked-by: Mel Gorman <mgorman@techsingularity.net> Cc: Michal Hocko <mhocko@suse.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Christopher Lameter <cl@linux.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Andi Kleen <andi.kleen@intel.com> Cc: Ying Huang <ying.huang@intel.com> Cc: Aaron Lu <aaron.lu@intel.com> Cc: Tim Chen <tim.c.chen@intel.com> Cc: Dave Hansen <dave.hansen@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This commit is contained in:
Kemi Wang
Linus Torvalds
Родитель
fde26bed58
Коммит
3a321d2a3d
|
|
@ -160,12 +160,12 @@ static ssize_t node_read_numastat(struct device *dev,
|
|||
"interleave_hit %lu\n"
|
||||
"local_node %lu\n"
|
||||
"other_node %lu\n",
|
||||
sum_zone_node_page_state(dev->id, NUMA_HIT),
|
||||
sum_zone_node_page_state(dev->id, NUMA_MISS),
|
||||
sum_zone_node_page_state(dev->id, NUMA_FOREIGN),
|
||||
sum_zone_node_page_state(dev->id, NUMA_INTERLEAVE_HIT),
|
||||
sum_zone_node_page_state(dev->id, NUMA_LOCAL),
|
||||
sum_zone_node_page_state(dev->id, NUMA_OTHER));
|
||||
sum_zone_numa_state(dev->id, NUMA_HIT),
|
||||
sum_zone_numa_state(dev->id, NUMA_MISS),
|
||||
sum_zone_numa_state(dev->id, NUMA_FOREIGN),
|
||||
sum_zone_numa_state(dev->id, NUMA_INTERLEAVE_HIT),
|
||||
sum_zone_numa_state(dev->id, NUMA_LOCAL),
|
||||
sum_zone_numa_state(dev->id, NUMA_OTHER));
|
||||
}
|
||||
static DEVICE_ATTR(numastat, S_IRUGO, node_read_numastat, NULL);
|
||||
|
||||
|
|
@ -181,9 +181,17 @@ static ssize_t node_read_vmstat(struct device *dev,
|
|||
n += sprintf(buf+n, "%s %lu\n", vmstat_text[i],
|
||||
sum_zone_node_page_state(nid, i));
|
||||
|
||||
for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++)
|
||||
#ifdef CONFIG_NUMA
|
||||
for (i = 0; i < NR_VM_NUMA_STAT_ITEMS; i++)
|
||||
n += sprintf(buf+n, "%s %lu\n",
|
||||
vmstat_text[i + NR_VM_ZONE_STAT_ITEMS],
|
||||
sum_zone_numa_state(nid, i));
|
||||
#endif
|
||||
|
||||
for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++)
|
||||
n += sprintf(buf+n, "%s %lu\n",
|
||||
vmstat_text[i + NR_VM_ZONE_STAT_ITEMS +
|
||||
NR_VM_NUMA_STAT_ITEMS],
|
||||
node_page_state(pgdat, i));
|
||||
|
||||
return n;
|
||||
|
|
|
|||
|
|
@ -114,6 +114,20 @@ struct zone_padding {
|
|||
#define ZONE_PADDING(name)
|
||||
#endif
|
||||
|
||||
#ifdef CONFIG_NUMA
|
||||
enum numa_stat_item {
|
||||
NUMA_HIT, /* allocated in intended node */
|
||||
NUMA_MISS, /* allocated in non intended node */
|
||||
NUMA_FOREIGN, /* was intended here, hit elsewhere */
|
||||
NUMA_INTERLEAVE_HIT, /* interleaver preferred this zone */
|
||||
NUMA_LOCAL, /* allocation from local node */
|
||||
NUMA_OTHER, /* allocation from other node */
|
||||
NR_VM_NUMA_STAT_ITEMS
|
||||
};
|
||||
#else
|
||||
#define NR_VM_NUMA_STAT_ITEMS 0
|
||||
#endif
|
||||
|
||||
enum zone_stat_item {
|
||||
/* First 128 byte cacheline (assuming 64 bit words) */
|
||||
NR_FREE_PAGES,
|
||||
|
|
@ -131,14 +145,6 @@ enum zone_stat_item {
|
|||
NR_BOUNCE,
|
||||
#if IS_ENABLED(CONFIG_ZSMALLOC)
|
||||
NR_ZSPAGES, /* allocated in zsmalloc */
|
||||
#endif
|
||||
#ifdef CONFIG_NUMA
|
||||
NUMA_HIT, /* allocated in intended node */
|
||||
NUMA_MISS, /* allocated in non intended node */
|
||||
NUMA_FOREIGN, /* was intended here, hit elsewhere */
|
||||
NUMA_INTERLEAVE_HIT, /* interleaver preferred this zone */
|
||||
NUMA_LOCAL, /* allocation from local node */
|
||||
NUMA_OTHER, /* allocation from other node */
|
||||
#endif
|
||||
NR_FREE_CMA_PAGES,
|
||||
NR_VM_ZONE_STAT_ITEMS };
|
||||
|
|
@ -276,6 +282,8 @@ struct per_cpu_pageset {
|
|||
struct per_cpu_pages pcp;
|
||||
#ifdef CONFIG_NUMA
|
||||
s8 expire;
|
||||
s8 numa_stat_threshold;
|
||||
s8 vm_numa_stat_diff[NR_VM_NUMA_STAT_ITEMS];
|
||||
#endif
|
||||
#ifdef CONFIG_SMP
|
||||
s8 stat_threshold;
|
||||
|
|
@ -496,6 +504,7 @@ struct zone {
|
|||
ZONE_PADDING(_pad3_)
|
||||
/* Zone statistics */
|
||||
atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS];
|
||||
atomic_long_t vm_numa_stat[NR_VM_NUMA_STAT_ITEMS];
|
||||
} ____cacheline_internodealigned_in_smp;
|
||||
|
||||
enum pgdat_flags {
|
||||
|
|
|
|||
|
|
@ -107,8 +107,33 @@ static inline void vm_events_fold_cpu(int cpu)
|
|||
* Zone and node-based page accounting with per cpu differentials.
|
||||
*/
|
||||
extern atomic_long_t vm_zone_stat[NR_VM_ZONE_STAT_ITEMS];
|
||||
extern atomic_long_t vm_numa_stat[NR_VM_NUMA_STAT_ITEMS];
|
||||
extern atomic_long_t vm_node_stat[NR_VM_NODE_STAT_ITEMS];
|
||||
|
||||
#ifdef CONFIG_NUMA
|
||||
static inline void zone_numa_state_add(long x, struct zone *zone,
|
||||
enum numa_stat_item item)
|
||||
{
|
||||
atomic_long_add(x, &zone->vm_numa_stat[item]);
|
||||
atomic_long_add(x, &vm_numa_stat[item]);
|
||||
}
|
||||
|
||||
static inline unsigned long global_numa_state(enum numa_stat_item item)
|
||||
{
|
||||
long x = atomic_long_read(&vm_numa_stat[item]);
|
||||
|
||||
return x;
|
||||
}
|
||||
|
||||
static inline unsigned long zone_numa_state(struct zone *zone,
|
||||
enum numa_stat_item item)
|
||||
{
|
||||
long x = atomic_long_read(&zone->vm_numa_stat[item]);
|
||||
|
||||
return x;
|
||||
}
|
||||
#endif /* CONFIG_NUMA */
|
||||
|
||||
static inline void zone_page_state_add(long x, struct zone *zone,
|
||||
enum zone_stat_item item)
|
||||
{
|
||||
|
|
@ -194,8 +219,10 @@ static inline unsigned long node_page_state_snapshot(pg_data_t *pgdat,
|
|||
|
||||
|
||||
#ifdef CONFIG_NUMA
|
||||
extern void __inc_numa_state(struct zone *zone, enum numa_stat_item item);
|
||||
extern unsigned long sum_zone_node_page_state(int node,
|
||||
enum zone_stat_item item);
|
||||
extern unsigned long sum_zone_numa_state(int node, enum numa_stat_item item);
|
||||
extern unsigned long node_page_state(struct pglist_data *pgdat,
|
||||
enum node_stat_item item);
|
||||
#else
|
||||
|
|
|
|||
|
|
@ -2741,18 +2741,18 @@ int __isolate_free_page(struct page *page, unsigned int order)
|
|||
static inline void zone_statistics(struct zone *preferred_zone, struct zone *z)
|
||||
{
|
||||
#ifdef CONFIG_NUMA
|
||||
enum zone_stat_item local_stat = NUMA_LOCAL;
|
||||
enum numa_stat_item local_stat = NUMA_LOCAL;
|
||||
|
||||
if (z->node != numa_node_id())
|
||||
local_stat = NUMA_OTHER;
|
||||
|
||||
if (z->node == preferred_zone->node)
|
||||
__inc_zone_state(z, NUMA_HIT);
|
||||
__inc_numa_state(z, NUMA_HIT);
|
||||
else {
|
||||
__inc_zone_state(z, NUMA_MISS);
|
||||
__inc_zone_state(preferred_zone, NUMA_FOREIGN);
|
||||
__inc_numa_state(z, NUMA_MISS);
|
||||
__inc_numa_state(preferred_zone, NUMA_FOREIGN);
|
||||
}
|
||||
__inc_zone_state(z, local_stat);
|
||||
__inc_numa_state(z, local_stat);
|
||||
#endif
|
||||
}
|
||||
|
||||
|
|
|
|||
161
mm/vmstat.c
161
mm/vmstat.c
|
|
@ -87,8 +87,10 @@ void vm_events_fold_cpu(int cpu)
|
|||
* vm_stat contains the global counters
|
||||
*/
|
||||
atomic_long_t vm_zone_stat[NR_VM_ZONE_STAT_ITEMS] __cacheline_aligned_in_smp;
|
||||
atomic_long_t vm_numa_stat[NR_VM_NUMA_STAT_ITEMS] __cacheline_aligned_in_smp;
|
||||
atomic_long_t vm_node_stat[NR_VM_NODE_STAT_ITEMS] __cacheline_aligned_in_smp;
|
||||
EXPORT_SYMBOL(vm_zone_stat);
|
||||
EXPORT_SYMBOL(vm_numa_stat);
|
||||
EXPORT_SYMBOL(vm_node_stat);
|
||||
|
||||
#ifdef CONFIG_SMP
|
||||
|
|
@ -192,7 +194,10 @@ void refresh_zone_stat_thresholds(void)
|
|||
|
||||
per_cpu_ptr(zone->pageset, cpu)->stat_threshold
|
||||
= threshold;
|
||||
|
||||
#ifdef CONFIG_NUMA
|
||||
per_cpu_ptr(zone->pageset, cpu)->numa_stat_threshold
|
||||
= threshold;
|
||||
#endif
|
||||
/* Base nodestat threshold on the largest populated zone. */
|
||||
pgdat_threshold = per_cpu_ptr(pgdat->per_cpu_nodestats, cpu)->stat_threshold;
|
||||
per_cpu_ptr(pgdat->per_cpu_nodestats, cpu)->stat_threshold
|
||||
|
|
@ -226,9 +231,14 @@ void set_pgdat_percpu_threshold(pg_data_t *pgdat,
|
|||
continue;
|
||||
|
||||
threshold = (*calculate_pressure)(zone);
|
||||
for_each_online_cpu(cpu)
|
||||
for_each_online_cpu(cpu) {
|
||||
per_cpu_ptr(zone->pageset, cpu)->stat_threshold
|
||||
= threshold;
|
||||
#ifdef CONFIG_NUMA
|
||||
per_cpu_ptr(zone->pageset, cpu)->numa_stat_threshold
|
||||
= threshold;
|
||||
#endif
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
|
|
@ -604,6 +614,32 @@ EXPORT_SYMBOL(dec_node_page_state);
|
|||
* Fold a differential into the global counters.
|
||||
* Returns the number of counters updated.
|
||||
*/
|
||||
#ifdef CONFIG_NUMA
|
||||
static int fold_diff(int *zone_diff, int *numa_diff, int *node_diff)
|
||||
{
|
||||
int i;
|
||||
int changes = 0;
|
||||
|
||||
for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
|
||||
if (zone_diff[i]) {
|
||||
atomic_long_add(zone_diff[i], &vm_zone_stat[i]);
|
||||
changes++;
|
||||
}
|
||||
|
||||
for (i = 0; i < NR_VM_NUMA_STAT_ITEMS; i++)
|
||||
if (numa_diff[i]) {
|
||||
atomic_long_add(numa_diff[i], &vm_numa_stat[i]);
|
||||
changes++;
|
||||
}
|
||||
|
||||
for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++)
|
||||
if (node_diff[i]) {
|
||||
atomic_long_add(node_diff[i], &vm_node_stat[i]);
|
||||
changes++;
|
||||
}
|
||||
return changes;
|
||||
}
|
||||
#else
|
||||
static int fold_diff(int *zone_diff, int *node_diff)
|
||||
{
|
||||
int i;
|
||||
|
|
@ -622,6 +658,7 @@ static int fold_diff(int *zone_diff, int *node_diff)
|
|||
}
|
||||
return changes;
|
||||
}
|
||||
#endif /* CONFIG_NUMA */
|
||||
|
||||
/*
|
||||
* Update the zone counters for the current cpu.
|
||||
|
|
@ -645,6 +682,9 @@ static int refresh_cpu_vm_stats(bool do_pagesets)
|
|||
struct zone *zone;
|
||||
int i;
|
||||
int global_zone_diff[NR_VM_ZONE_STAT_ITEMS] = { 0, };
|
||||
#ifdef CONFIG_NUMA
|
||||
int global_numa_diff[NR_VM_NUMA_STAT_ITEMS] = { 0, };
|
||||
#endif
|
||||
int global_node_diff[NR_VM_NODE_STAT_ITEMS] = { 0, };
|
||||
int changes = 0;
|
||||
|
||||
|
|
@ -666,6 +706,18 @@ static int refresh_cpu_vm_stats(bool do_pagesets)
|
|||
}
|
||||
}
|
||||
#ifdef CONFIG_NUMA
|
||||
for (i = 0; i < NR_VM_NUMA_STAT_ITEMS; i++) {
|
||||
int v;
|
||||
|
||||
v = this_cpu_xchg(p->vm_numa_stat_diff[i], 0);
|
||||
if (v) {
|
||||
|
||||
atomic_long_add(v, &zone->vm_numa_stat[i]);
|
||||
global_numa_diff[i] += v;
|
||||
__this_cpu_write(p->expire, 3);
|
||||
}
|
||||
}
|
||||
|
||||
if (do_pagesets) {
|
||||
cond_resched();
|
||||
/*
|
||||
|
|
@ -712,7 +764,12 @@ static int refresh_cpu_vm_stats(bool do_pagesets)
|
|||
}
|
||||
}
|
||||
|
||||
#ifdef CONFIG_NUMA
|
||||
changes += fold_diff(global_zone_diff, global_numa_diff,
|
||||
global_node_diff);
|
||||
#else
|
||||
changes += fold_diff(global_zone_diff, global_node_diff);
|
||||
#endif
|
||||
return changes;
|
||||
}
|
||||
|
||||
|
|
@ -727,6 +784,9 @@ void cpu_vm_stats_fold(int cpu)
|
|||
struct zone *zone;
|
||||
int i;
|
||||
int global_zone_diff[NR_VM_ZONE_STAT_ITEMS] = { 0, };
|
||||
#ifdef CONFIG_NUMA
|
||||
int global_numa_diff[NR_VM_NUMA_STAT_ITEMS] = { 0, };
|
||||
#endif
|
||||
int global_node_diff[NR_VM_NODE_STAT_ITEMS] = { 0, };
|
||||
|
||||
for_each_populated_zone(zone) {
|
||||
|
|
@ -743,6 +803,18 @@ void cpu_vm_stats_fold(int cpu)
|
|||
atomic_long_add(v, &zone->vm_stat[i]);
|
||||
global_zone_diff[i] += v;
|
||||
}
|
||||
|
||||
#ifdef CONFIG_NUMA
|
||||
for (i = 0; i < NR_VM_NUMA_STAT_ITEMS; i++)
|
||||
if (p->vm_numa_stat_diff[i]) {
|
||||
int v;
|
||||
|
||||
v = p->vm_numa_stat_diff[i];
|
||||
p->vm_numa_stat_diff[i] = 0;
|
||||
atomic_long_add(v, &zone->vm_numa_stat[i]);
|
||||
global_numa_diff[i] += v;
|
||||
}
|
||||
#endif
|
||||
}
|
||||
|
||||
for_each_online_pgdat(pgdat) {
|
||||
|
|
@ -761,7 +833,11 @@ void cpu_vm_stats_fold(int cpu)
|
|||
}
|
||||
}
|
||||
|
||||
#ifdef CONFIG_NUMA
|
||||
fold_diff(global_zone_diff, global_numa_diff, global_node_diff);
|
||||
#else
|
||||
fold_diff(global_zone_diff, global_node_diff);
|
||||
#endif
|
||||
}
|
||||
|
||||
/*
|
||||
|
|
@ -779,10 +855,38 @@ void drain_zonestat(struct zone *zone, struct per_cpu_pageset *pset)
|
|||
atomic_long_add(v, &zone->vm_stat[i]);
|
||||
atomic_long_add(v, &vm_zone_stat[i]);
|
||||
}
|
||||
|
||||
#ifdef CONFIG_NUMA
|
||||
for (i = 0; i < NR_VM_NUMA_STAT_ITEMS; i++)
|
||||
if (pset->vm_numa_stat_diff[i]) {
|
||||
int v = pset->vm_numa_stat_diff[i];
|
||||
|
||||
pset->vm_numa_stat_diff[i] = 0;
|
||||
atomic_long_add(v, &zone->vm_numa_stat[i]);
|
||||
atomic_long_add(v, &vm_numa_stat[i]);
|
||||
}
|
||||
#endif
|
||||
}
|
||||
#endif
|
||||
|
||||
#ifdef CONFIG_NUMA
|
||||
void __inc_numa_state(struct zone *zone,
|
||||
enum numa_stat_item item)
|
||||
{
|
||||
struct per_cpu_pageset __percpu *pcp = zone->pageset;
|
||||
s8 __percpu *p = pcp->vm_numa_stat_diff + item;
|
||||
s8 v, t;
|
||||
|
||||
v = __this_cpu_inc_return(*p);
|
||||
t = __this_cpu_read(pcp->numa_stat_threshold);
|
||||
if (unlikely(v > t)) {
|
||||
s8 overstep = t >> 1;
|
||||
|
||||
zone_numa_state_add(v + overstep, zone, item);
|
||||
__this_cpu_write(*p, -overstep);
|
||||
}
|
||||
}
|
||||
|
||||
/*
|
||||
* Determine the per node value of a stat item. This function
|
||||
* is called frequently in a NUMA machine, so try to be as
|
||||
|
|
@ -801,6 +905,19 @@ unsigned long sum_zone_node_page_state(int node,
|
|||
return count;
|
||||
}
|
||||
|
||||
unsigned long sum_zone_numa_state(int node,
|
||||
enum numa_stat_item item)
|
||||
{
|
||||
struct zone *zones = NODE_DATA(node)->node_zones;
|
||||
int i;
|
||||
unsigned long count = 0;
|
||||
|
||||
for (i = 0; i < MAX_NR_ZONES; i++)
|
||||
count += zone_numa_state(zones + i, item);
|
||||
|
||||
return count;
|
||||
}
|
||||
|
||||
/*
|
||||
* Determine the per node value of a stat item.
|
||||
*/
|
||||
|
|
@ -937,6 +1054,9 @@ const char * const vmstat_text[] = {
|
|||
#if IS_ENABLED(CONFIG_ZSMALLOC)
|
||||
"nr_zspages",
|
||||
#endif
|
||||
"nr_free_cma",
|
||||
|
||||
/* enum numa_stat_item counters */
|
||||
#ifdef CONFIG_NUMA
|
||||
"numa_hit",
|
||||
"numa_miss",
|
||||
|
|
@ -945,7 +1065,6 @@ const char * const vmstat_text[] = {
|
|||
"numa_local",
|
||||
"numa_other",
|
||||
#endif
|
||||
"nr_free_cma",
|
||||
|
||||
/* Node-based counters */
|
||||
"nr_inactive_anon",
|
||||
|
|
@ -1106,7 +1225,6 @@ const char * const vmstat_text[] = {
|
|||
};
|
||||
#endif /* CONFIG_PROC_FS || CONFIG_SYSFS || CONFIG_NUMA */
|
||||
|
||||
|
||||
#if (defined(CONFIG_DEBUG_FS) && defined(CONFIG_COMPACTION)) || \
|
||||
defined(CONFIG_PROC_FS)
|
||||
static void *frag_start(struct seq_file *m, loff_t *pos)
|
||||
|
|
@ -1384,7 +1502,8 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat,
|
|||
seq_printf(m, "\n per-node stats");
|
||||
for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) {
|
||||
seq_printf(m, "\n %-12s %lu",
|
||||
vmstat_text[i + NR_VM_ZONE_STAT_ITEMS],
|
||||
vmstat_text[i + NR_VM_ZONE_STAT_ITEMS +
|
||||
NR_VM_NUMA_STAT_ITEMS],
|
||||
node_page_state(pgdat, i));
|
||||
}
|
||||
}
|
||||
|
|
@ -1421,6 +1540,13 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat,
|
|||
seq_printf(m, "\n %-12s %lu", vmstat_text[i],
|
||||
zone_page_state(zone, i));
|
||||
|
||||
#ifdef CONFIG_NUMA
|
||||
for (i = 0; i < NR_VM_NUMA_STAT_ITEMS; i++)
|
||||
seq_printf(m, "\n %-12s %lu",
|
||||
vmstat_text[i + NR_VM_ZONE_STAT_ITEMS],
|
||||
zone_numa_state(zone, i));
|
||||
#endif
|
||||
|
||||
seq_printf(m, "\n pagesets");
|
||||
for_each_online_cpu(i) {
|
||||
struct per_cpu_pageset *pageset;
|
||||
|
|
@ -1497,6 +1623,7 @@ static void *vmstat_start(struct seq_file *m, loff_t *pos)
|
|||
if (*pos >= ARRAY_SIZE(vmstat_text))
|
||||
return NULL;
|
||||
stat_items_size = NR_VM_ZONE_STAT_ITEMS * sizeof(unsigned long) +
|
||||
NR_VM_NUMA_STAT_ITEMS * sizeof(unsigned long) +
|
||||
NR_VM_NODE_STAT_ITEMS * sizeof(unsigned long) +
|
||||
NR_VM_WRITEBACK_STAT_ITEMS * sizeof(unsigned long);
|
||||
|
||||
|
|
@ -1512,6 +1639,12 @@ static void *vmstat_start(struct seq_file *m, loff_t *pos)
|
|||
v[i] = global_zone_page_state(i);
|
||||
v += NR_VM_ZONE_STAT_ITEMS;
|
||||
|
||||
#ifdef CONFIG_NUMA
|
||||
for (i = 0; i < NR_VM_NUMA_STAT_ITEMS; i++)
|
||||
v[i] = global_numa_state(i);
|
||||
v += NR_VM_NUMA_STAT_ITEMS;
|
||||
#endif
|
||||
|
||||
for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++)
|
||||
v[i] = global_node_page_state(i);
|
||||
v += NR_VM_NODE_STAT_ITEMS;
|
||||
|
|
@ -1613,6 +1746,16 @@ int vmstat_refresh(struct ctl_table *table, int write,
|
|||
err = -EINVAL;
|
||||
}
|
||||
}
|
||||
#ifdef CONFIG_NUMA
|
||||
for (i = 0; i < NR_VM_NUMA_STAT_ITEMS; i++) {
|
||||
val = atomic_long_read(&vm_numa_stat[i]);
|
||||
if (val < 0) {
|
||||
pr_warn("%s: %s %ld\n",
|
||||
__func__, vmstat_text[i + NR_VM_ZONE_STAT_ITEMS], val);
|
||||
err = -EINVAL;
|
||||
}
|
||||
}
|
||||
#endif
|
||||
if (err)
|
||||
return err;
|
||||
if (write)
|
||||
|
|
@ -1654,13 +1797,19 @@ static bool need_update(int cpu)
|
|||
struct per_cpu_pageset *p = per_cpu_ptr(zone->pageset, cpu);
|
||||
|
||||
BUILD_BUG_ON(sizeof(p->vm_stat_diff[0]) != 1);
|
||||
#ifdef CONFIG_NUMA
|
||||
BUILD_BUG_ON(sizeof(p->vm_numa_stat_diff[0]) != 1);
|
||||
#endif
|
||||
/*
|
||||
* The fast way of checking if there are any vmstat diffs.
|
||||
* This works because the diffs are byte sized items.
|
||||
*/
|
||||
if (memchr_inv(p->vm_stat_diff, 0, NR_VM_ZONE_STAT_ITEMS))
|
||||
return true;
|
||||
|
||||
#ifdef CONFIG_NUMA
|
||||
if (memchr_inv(p->vm_numa_stat_diff, 0, NR_VM_NUMA_STAT_ITEMS))
|
||||
return true;
|
||||
#endif
|
||||
}
|
||||
return false;
|
||||
}
|
||||
|
|
|
|||
Загрузка…
Ссылка в новой задаче