mm/page_alloc.c: calculate 'available' memory in a separate function

Add a new field, VIRTIO_BALLOON_S_AVAIL, to virtio_balloon memory
statistics protocol, corresponding to 'Available' in /proc/meminfo.

It indicates to the hypervisor how big the balloon can be inflated
without pushing the guest system to swap.  This metric would be very
useful in VM orchestration software to improve memory management of
different VMs under overcommit.

This patch (of 2):

Factor out calculation of the available memory counter into a separate
exportable function, in order to be able to use it in other parts of the
kernel.

In particular, it appears a relevant metric to report to the hypervisor
via virtio-balloon statistics interface (in a followup patch).

Signed-off-by: Igor Redko <redkoi@virtuozzo.com>
Signed-off-by: Denis V. Lunev <den@openvz.org>
Reviewed-by: Roman Kagan <rkagan@virtuozzo.com>
Cc: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This commit is contained in:
Igor Redko 2016-03-17 14:19:05 -07:00 коммит произвёл Linus Torvalds
Родитель 7eb50292d7
Коммит d02bd27bd3
3 изменённых файлов: 45 добавлений и 30 удалений

Просмотреть файл

@ -29,10 +29,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
unsigned long committed; unsigned long committed;
long cached; long cached;
long available; long available;
unsigned long pagecache;
unsigned long wmark_low = 0;
unsigned long pages[NR_LRU_LISTS]; unsigned long pages[NR_LRU_LISTS];
struct zone *zone;
int lru; int lru;
/* /*
@ -51,33 +48,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
for (lru = LRU_BASE; lru < NR_LRU_LISTS; lru++) for (lru = LRU_BASE; lru < NR_LRU_LISTS; lru++)
pages[lru] = global_page_state(NR_LRU_BASE + lru); pages[lru] = global_page_state(NR_LRU_BASE + lru);
for_each_zone(zone) available = si_mem_available();
wmark_low += zone->watermark[WMARK_LOW];
/*
* Estimate the amount of memory available for userspace allocations,
* without causing swapping.
*/
available = i.freeram - totalreserve_pages;
/*
* Not all the page cache can be freed, otherwise the system will
* start swapping. Assume at least half of the page cache, or the
* low watermark worth of cache, needs to stay.
*/
pagecache = pages[LRU_ACTIVE_FILE] + pages[LRU_INACTIVE_FILE];
pagecache -= min(pagecache / 2, wmark_low);
available += pagecache;
/*
* Part of the reclaimable slab consists of items that are in use,
* and cannot be freed. Cap this estimate at the low watermark.
*/
available += global_page_state(NR_SLAB_RECLAIMABLE) -
min(global_page_state(NR_SLAB_RECLAIMABLE) / 2, wmark_low);
if (available < 0)
available = 0;
/* /*
* Tagged format, for easy grepping and expansion. * Tagged format, for easy grepping and expansion.

Просмотреть файл

@ -1875,6 +1875,7 @@ extern int __meminit init_per_zone_wmark_min(void);
extern void mem_init(void); extern void mem_init(void);
extern void __init mmap_init(void); extern void __init mmap_init(void);
extern void show_mem(unsigned int flags); extern void show_mem(unsigned int flags);
extern long si_mem_available(void);
extern void si_meminfo(struct sysinfo * val); extern void si_meminfo(struct sysinfo * val);
extern void si_meminfo_node(struct sysinfo *val, int nid); extern void si_meminfo_node(struct sysinfo *val, int nid);

Просмотреть файл

@ -3713,6 +3713,49 @@ static inline void show_node(struct zone *zone)
printk("Node %d ", zone_to_nid(zone)); printk("Node %d ", zone_to_nid(zone));
} }
long si_mem_available(void)
{
long available;
unsigned long pagecache;
unsigned long wmark_low = 0;
unsigned long pages[NR_LRU_LISTS];
struct zone *zone;
int lru;
for (lru = LRU_BASE; lru < NR_LRU_LISTS; lru++)
pages[lru] = global_page_state(NR_LRU_BASE + lru);
for_each_zone(zone)
wmark_low += zone->watermark[WMARK_LOW];
/*
* Estimate the amount of memory available for userspace allocations,
* without causing swapping.
*/
available = global_page_state(NR_FREE_PAGES) - totalreserve_pages;
/*
* Not all the page cache can be freed, otherwise the system will
* start swapping. Assume at least half of the page cache, or the
* low watermark worth of cache, needs to stay.
*/
pagecache = pages[LRU_ACTIVE_FILE] + pages[LRU_INACTIVE_FILE];
pagecache -= min(pagecache / 2, wmark_low);
available += pagecache;
/*
* Part of the reclaimable slab consists of items that are in use,
* and cannot be freed. Cap this estimate at the low watermark.
*/
available += global_page_state(NR_SLAB_RECLAIMABLE) -
min(global_page_state(NR_SLAB_RECLAIMABLE) / 2, wmark_low);
if (available < 0)
available = 0;
return available;
}
EXPORT_SYMBOL_GPL(si_mem_available);
void si_meminfo(struct sysinfo *val) void si_meminfo(struct sysinfo *val)
{ {
val->totalram = totalram_pages; val->totalram = totalram_pages;