mirror of
https://github.com/edk2-porting/linux-next.git
synced 2024-12-26 22:24:09 +08:00
03c5a6e163
It is tricky to quantify the basic cost of automatic NUMA placement in a meaningful manner. This patch adds some vmstats that can be used as part of a basic costing model. u = basic unit = sizeof(void *) Ca = cost of struct page access = sizeof(struct page) / u Cpte = Cost PTE access = Ca Cupdate = Cost PTE update = (2 * Cpte) + (2 * Wlock) where Cpte is incurred twice for a read and a write and Wlock is a constant representing the cost of taking or releasing a lock Cnumahint = Cost of a minor page fault = some high constant e.g. 1000 Cpagerw = Cost to read or write a full page = Ca + PAGE_SIZE/u Ci = Cost of page isolation = Ca + Wi where Wi is a constant that should reflect the approximate cost of the locking operation Cpagecopy = Cpagerw + (Cpagerw * Wnuma) + Ci + (Ci * Wnuma) where Wnuma is the approximate NUMA factor. 1 is local. 1.2 would imply that remote accesses are 20% more expensive Balancing cost = Cpte * numa_pte_updates + Cnumahint * numa_hint_faults + Ci * numa_pages_migrated + Cpagecopy * numa_pages_migrated Note that numa_pages_migrated is used as a measure of how many pages were isolated even though it would miss pages that failed to migrate. A vmstat counter could have been added for it but the isolation cost is pretty marginal in comparison to the overall cost so it seemed overkill. The ideal way to measure automatic placement benefit would be to count the number of remote accesses versus local accesses and do something like benefit = (remote_accesses_before - remove_access_after) * Wnuma but the information is not readily available. As a workload converges, the expection would be that the number of remote numa hints would reduce to 0. convergence = numa_hint_faults_local / numa_hint_faults where this is measured for the last N number of numa hints recorded. When the workload is fully converged the value is 1. This can measure if the placement policy is converging and how fast it is doing it. Signed-off-by: Mel Gorman <mgorman@suse.de> Acked-by: Rik van Riel <riel@redhat.com>
279 lines
7.3 KiB
C
279 lines
7.3 KiB
C
#ifndef _LINUX_VMSTAT_H
|
|
#define _LINUX_VMSTAT_H
|
|
|
|
#include <linux/types.h>
|
|
#include <linux/percpu.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/mmzone.h>
|
|
#include <linux/vm_event_item.h>
|
|
#include <linux/atomic.h>
|
|
|
|
extern int sysctl_stat_interval;
|
|
|
|
#ifdef CONFIG_VM_EVENT_COUNTERS
|
|
/*
|
|
* Light weight per cpu counter implementation.
|
|
*
|
|
* Counters should only be incremented and no critical kernel component
|
|
* should rely on the counter values.
|
|
*
|
|
* Counters are handled completely inline. On many platforms the code
|
|
* generated will simply be the increment of a global address.
|
|
*/
|
|
|
|
struct vm_event_state {
|
|
unsigned long event[NR_VM_EVENT_ITEMS];
|
|
};
|
|
|
|
DECLARE_PER_CPU(struct vm_event_state, vm_event_states);
|
|
|
|
static inline void __count_vm_event(enum vm_event_item item)
|
|
{
|
|
__this_cpu_inc(vm_event_states.event[item]);
|
|
}
|
|
|
|
static inline void count_vm_event(enum vm_event_item item)
|
|
{
|
|
this_cpu_inc(vm_event_states.event[item]);
|
|
}
|
|
|
|
static inline void __count_vm_events(enum vm_event_item item, long delta)
|
|
{
|
|
__this_cpu_add(vm_event_states.event[item], delta);
|
|
}
|
|
|
|
static inline void count_vm_events(enum vm_event_item item, long delta)
|
|
{
|
|
this_cpu_add(vm_event_states.event[item], delta);
|
|
}
|
|
|
|
extern void all_vm_events(unsigned long *);
|
|
#ifdef CONFIG_HOTPLUG
|
|
extern void vm_events_fold_cpu(int cpu);
|
|
#else
|
|
static inline void vm_events_fold_cpu(int cpu)
|
|
{
|
|
}
|
|
#endif
|
|
|
|
#else
|
|
|
|
/* Disable counters */
|
|
static inline void count_vm_event(enum vm_event_item item)
|
|
{
|
|
}
|
|
static inline void count_vm_events(enum vm_event_item item, long delta)
|
|
{
|
|
}
|
|
static inline void __count_vm_event(enum vm_event_item item)
|
|
{
|
|
}
|
|
static inline void __count_vm_events(enum vm_event_item item, long delta)
|
|
{
|
|
}
|
|
static inline void all_vm_events(unsigned long *ret)
|
|
{
|
|
}
|
|
static inline void vm_events_fold_cpu(int cpu)
|
|
{
|
|
}
|
|
|
|
#endif /* CONFIG_VM_EVENT_COUNTERS */
|
|
|
|
#ifdef CONFIG_NUMA_BALANCING
|
|
#define count_vm_numa_event(x) count_vm_event(x)
|
|
#define count_vm_numa_events(x, y) count_vm_events(x, y)
|
|
#else
|
|
#define count_vm_numa_event(x) do {} while (0)
|
|
#define count_vm_numa_events(x, y) do {} while (0)
|
|
#endif /* CONFIG_NUMA_BALANCING */
|
|
|
|
#define __count_zone_vm_events(item, zone, delta) \
|
|
__count_vm_events(item##_NORMAL - ZONE_NORMAL + \
|
|
zone_idx(zone), delta)
|
|
|
|
/*
|
|
* Zone based page accounting with per cpu differentials.
|
|
*/
|
|
extern atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS];
|
|
|
|
static inline void zone_page_state_add(long x, struct zone *zone,
|
|
enum zone_stat_item item)
|
|
{
|
|
atomic_long_add(x, &zone->vm_stat[item]);
|
|
atomic_long_add(x, &vm_stat[item]);
|
|
}
|
|
|
|
static inline unsigned long global_page_state(enum zone_stat_item item)
|
|
{
|
|
long x = atomic_long_read(&vm_stat[item]);
|
|
#ifdef CONFIG_SMP
|
|
if (x < 0)
|
|
x = 0;
|
|
#endif
|
|
return x;
|
|
}
|
|
|
|
static inline unsigned long zone_page_state(struct zone *zone,
|
|
enum zone_stat_item item)
|
|
{
|
|
long x = atomic_long_read(&zone->vm_stat[item]);
|
|
#ifdef CONFIG_SMP
|
|
if (x < 0)
|
|
x = 0;
|
|
#endif
|
|
return x;
|
|
}
|
|
|
|
/*
|
|
* More accurate version that also considers the currently pending
|
|
* deltas. For that we need to loop over all cpus to find the current
|
|
* deltas. There is no synchronization so the result cannot be
|
|
* exactly accurate either.
|
|
*/
|
|
static inline unsigned long zone_page_state_snapshot(struct zone *zone,
|
|
enum zone_stat_item item)
|
|
{
|
|
long x = atomic_long_read(&zone->vm_stat[item]);
|
|
|
|
#ifdef CONFIG_SMP
|
|
int cpu;
|
|
for_each_online_cpu(cpu)
|
|
x += per_cpu_ptr(zone->pageset, cpu)->vm_stat_diff[item];
|
|
|
|
if (x < 0)
|
|
x = 0;
|
|
#endif
|
|
return x;
|
|
}
|
|
|
|
extern unsigned long global_reclaimable_pages(void);
|
|
extern unsigned long zone_reclaimable_pages(struct zone *zone);
|
|
|
|
#ifdef CONFIG_NUMA
|
|
/*
|
|
* Determine the per node value of a stat item. This function
|
|
* is called frequently in a NUMA machine, so try to be as
|
|
* frugal as possible.
|
|
*/
|
|
static inline unsigned long node_page_state(int node,
|
|
enum zone_stat_item item)
|
|
{
|
|
struct zone *zones = NODE_DATA(node)->node_zones;
|
|
|
|
return
|
|
#ifdef CONFIG_ZONE_DMA
|
|
zone_page_state(&zones[ZONE_DMA], item) +
|
|
#endif
|
|
#ifdef CONFIG_ZONE_DMA32
|
|
zone_page_state(&zones[ZONE_DMA32], item) +
|
|
#endif
|
|
#ifdef CONFIG_HIGHMEM
|
|
zone_page_state(&zones[ZONE_HIGHMEM], item) +
|
|
#endif
|
|
zone_page_state(&zones[ZONE_NORMAL], item) +
|
|
zone_page_state(&zones[ZONE_MOVABLE], item);
|
|
}
|
|
|
|
extern void zone_statistics(struct zone *, struct zone *, gfp_t gfp);
|
|
|
|
#else
|
|
|
|
#define node_page_state(node, item) global_page_state(item)
|
|
#define zone_statistics(_zl, _z, gfp) do { } while (0)
|
|
|
|
#endif /* CONFIG_NUMA */
|
|
|
|
#define add_zone_page_state(__z, __i, __d) mod_zone_page_state(__z, __i, __d)
|
|
#define sub_zone_page_state(__z, __i, __d) mod_zone_page_state(__z, __i, -(__d))
|
|
|
|
extern void inc_zone_state(struct zone *, enum zone_stat_item);
|
|
|
|
#ifdef CONFIG_SMP
|
|
void __mod_zone_page_state(struct zone *, enum zone_stat_item item, int);
|
|
void __inc_zone_page_state(struct page *, enum zone_stat_item);
|
|
void __dec_zone_page_state(struct page *, enum zone_stat_item);
|
|
|
|
void mod_zone_page_state(struct zone *, enum zone_stat_item, int);
|
|
void inc_zone_page_state(struct page *, enum zone_stat_item);
|
|
void dec_zone_page_state(struct page *, enum zone_stat_item);
|
|
|
|
extern void inc_zone_state(struct zone *, enum zone_stat_item);
|
|
extern void __inc_zone_state(struct zone *, enum zone_stat_item);
|
|
extern void dec_zone_state(struct zone *, enum zone_stat_item);
|
|
extern void __dec_zone_state(struct zone *, enum zone_stat_item);
|
|
|
|
void refresh_cpu_vm_stats(int);
|
|
void refresh_zone_stat_thresholds(void);
|
|
|
|
void drain_zonestat(struct zone *zone, struct per_cpu_pageset *);
|
|
|
|
int calculate_pressure_threshold(struct zone *zone);
|
|
int calculate_normal_threshold(struct zone *zone);
|
|
void set_pgdat_percpu_threshold(pg_data_t *pgdat,
|
|
int (*calculate_pressure)(struct zone *));
|
|
#else /* CONFIG_SMP */
|
|
|
|
/*
|
|
* We do not maintain differentials in a single processor configuration.
|
|
* The functions directly modify the zone and global counters.
|
|
*/
|
|
static inline void __mod_zone_page_state(struct zone *zone,
|
|
enum zone_stat_item item, int delta)
|
|
{
|
|
zone_page_state_add(delta, zone, item);
|
|
}
|
|
|
|
static inline void __inc_zone_state(struct zone *zone, enum zone_stat_item item)
|
|
{
|
|
atomic_long_inc(&zone->vm_stat[item]);
|
|
atomic_long_inc(&vm_stat[item]);
|
|
}
|
|
|
|
static inline void __inc_zone_page_state(struct page *page,
|
|
enum zone_stat_item item)
|
|
{
|
|
__inc_zone_state(page_zone(page), item);
|
|
}
|
|
|
|
static inline void __dec_zone_state(struct zone *zone, enum zone_stat_item item)
|
|
{
|
|
atomic_long_dec(&zone->vm_stat[item]);
|
|
atomic_long_dec(&vm_stat[item]);
|
|
}
|
|
|
|
static inline void __dec_zone_page_state(struct page *page,
|
|
enum zone_stat_item item)
|
|
{
|
|
__dec_zone_state(page_zone(page), item);
|
|
}
|
|
|
|
/*
|
|
* We only use atomic operations to update counters. So there is no need to
|
|
* disable interrupts.
|
|
*/
|
|
#define inc_zone_page_state __inc_zone_page_state
|
|
#define dec_zone_page_state __dec_zone_page_state
|
|
#define mod_zone_page_state __mod_zone_page_state
|
|
|
|
#define set_pgdat_percpu_threshold(pgdat, callback) { }
|
|
|
|
static inline void refresh_cpu_vm_stats(int cpu) { }
|
|
static inline void refresh_zone_stat_thresholds(void) { }
|
|
|
|
static inline void drain_zonestat(struct zone *zone,
|
|
struct per_cpu_pageset *pset) { }
|
|
#endif /* CONFIG_SMP */
|
|
|
|
static inline void __mod_zone_freepage_state(struct zone *zone, int nr_pages,
|
|
int migratetype)
|
|
{
|
|
__mod_zone_page_state(zone, NR_FREE_PAGES, nr_pages);
|
|
if (is_migrate_cma(migratetype))
|
|
__mod_zone_page_state(zone, NR_FREE_CMA_PAGES, nr_pages);
|
|
}
|
|
|
|
extern const char * const vmstat_text[];
|
|
|
|
#endif /* _LINUX_VMSTAT_H */
|