/* Can mapped pages be reclaimed? */
int may_unmap;
+ /* Can pages be swapped as part of reclaim? */
+ int may_swap;
+
/* This context's SWAP_CLUSTER_MAX. If freeing memory for
* suspend, we effectively ignore SWAP_CLUSTER_MAX.
* In this context, it doesn't matter that we scan the
swp_entry_t swap = { .val = page_private(page) };
__delete_from_swap_cache(page);
spin_unlock_irq(&mapping->tree_lock);
+ mem_cgroup_uncharge_swapcache(page, swap);
swap_free(swap);
} else {
__remove_from_page_cache(page);
spin_unlock_irq(&mapping->tree_lock);
+ mem_cgroup_uncharge_cache_page(page);
}
return 1;
unsigned long nr_scanned = 0;
unsigned long nr_reclaimed = 0;
struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc);
+ int lumpy_reclaim = 0;
+
+ /*
+ * If we need a large contiguous chunk of memory, or have
+ * trouble getting a small set of contiguous pages, we
+ * will reclaim both active and inactive pages.
+ *
+ * We use the same threshold as pageout congestion_wait below.
+ */
+ if (sc->order > PAGE_ALLOC_COSTLY_ORDER)
+ lumpy_reclaim = 1;
+ else if (sc->order && priority < DEF_PRIORITY - 2)
+ lumpy_reclaim = 1;
pagevec_init(&pvec, 1);
unsigned long nr_freed;
unsigned long nr_active;
unsigned int count[NR_LRU_LISTS] = { 0, };
- int mode = ISOLATE_INACTIVE;
-
- /*
- * If we need a large contiguous chunk of memory, or have
- * trouble getting a small set of contiguous pages, we
- * will reclaim both active and inactive pages.
- *
- * We use the same threshold as pageout congestion_wait below.
- */
- if (sc->order > PAGE_ALLOC_COSTLY_ORDER)
- mode = ISOLATE_BOTH;
- else if (sc->order && priority < DEF_PRIORITY - 2)
- mode = ISOLATE_BOTH;
+ int mode = lumpy_reclaim ? ISOLATE_BOTH : ISOLATE_INACTIVE;
nr_taken = sc->isolate_pages(sc->swap_cluster_max,
&page_list, &nr_scan, sc->order, mode,
* but that should be acceptable to the caller
*/
if (nr_freed < nr_taken && !current_is_kswapd() &&
- sc->order > PAGE_ALLOC_COSTLY_ORDER) {
+ lumpy_reclaim) {
congestion_wait(WRITE, HZ/10);
/*
struct scan_control *sc, int priority, int file)
{
unsigned long pgmoved;
- int pgdeactivate = 0;
unsigned long pgscanned;
LIST_HEAD(l_hold); /* The pages which were snipped off */
LIST_HEAD(l_inactive);
__mod_zone_page_state(zone, NR_ACTIVE_ANON, -pgmoved);
spin_unlock_irq(&zone->lru_lock);
- pgmoved = 0;
+ pgmoved = 0; /* count referenced (mapping) mapped pages */
while (!list_empty(&l_hold)) {
cond_resched();
page = lru_to_page(&l_hold);
*/
reclaim_stat->recent_rotated[!!file] += pgmoved;
- pgmoved = 0;
+ pgmoved = 0; /* count pages moved to inactive list */
while (!list_empty(&l_inactive)) {
page = lru_to_page(&l_inactive);
prefetchw_prev_lru_page(page, &l_inactive, flags);
mem_cgroup_add_lru_list(page, lru);
pgmoved++;
if (!pagevec_add(&pvec, page)) {
- __mod_zone_page_state(zone, NR_LRU_BASE + lru, pgmoved);
spin_unlock_irq(&zone->lru_lock);
- pgdeactivate += pgmoved;
- pgmoved = 0;
if (buffer_heads_over_limit)
pagevec_strip(&pvec);
__pagevec_release(&pvec);
}
}
__mod_zone_page_state(zone, NR_LRU_BASE + lru, pgmoved);
- pgdeactivate += pgmoved;
__count_zone_vm_events(PGREFILL, zone, pgscanned);
- __count_vm_events(PGDEACTIVATE, pgdeactivate);
+ __count_vm_events(PGDEACTIVATE, pgmoved);
spin_unlock_irq(&zone->lru_lock);
if (buffer_heads_over_limit)
pagevec_strip(&pvec);
return low;
}
+static int inactive_file_is_low_global(struct zone *zone)
+{
+ unsigned long active, inactive;
+
+ active = zone_page_state(zone, NR_ACTIVE_FILE);
+ inactive = zone_page_state(zone, NR_INACTIVE_FILE);
+
+ return (active > inactive);
+}
+
+/**
+ * inactive_file_is_low - check if file pages need to be deactivated
+ * @zone: zone to check
+ * @sc: scan control of this context
+ *
+ * When the system is doing streaming IO, memory pressure here
+ * ensures that active file pages get deactivated, until more
+ * than half of the file pages are on the inactive list.
+ *
+ * Once we get to that situation, protect the system's working
+ * set from being evicted by disabling active file page aging.
+ *
+ * This uses a different ratio than the anonymous pages, because
+ * the page cache uses a use-once replacement algorithm.
+ */
+static int inactive_file_is_low(struct zone *zone, struct scan_control *sc)
+{
+ int low;
+
+ if (scanning_global_lru(sc))
+ low = inactive_file_is_low_global(zone);
+ else
+ low = mem_cgroup_inactive_file_is_low(sc->mem_cgroup);
+ return low;
+}
+
static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan,
struct zone *zone, struct scan_control *sc, int priority)
{
int file = is_file_lru(lru);
- if (lru == LRU_ACTIVE_FILE) {
+ if (lru == LRU_ACTIVE_FILE && inactive_file_is_low(zone, sc)) {
shrink_active_list(nr_to_scan, zone, sc, priority, file);
return 0;
}
struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc);
/* If we have no swap space, do not bother scanning anon pages. */
- if (nr_swap_pages <= 0) {
+ if (!sc->may_swap || (nr_swap_pages <= 0)) {
percent[0] = 0;
percent[1] = 100;
return;
free = zone_page_state(zone, NR_FREE_PAGES);
/* If we have very few page cache pages,
force-scan anon pages. */
- if (unlikely(file + free <= zone->pages_high)) {
+ if (unlikely(file + free <= high_wmark_pages(zone))) {
percent[0] = 100;
percent[1] = 0;
return;
percent[1] = 100 - percent[0];
}
+/*
+ * Smallish @nr_to_scan's are deposited in @nr_saved_scan,
+ * until we collected @swap_cluster_max pages to scan.
+ */
+static unsigned long nr_scan_try_batch(unsigned long nr_to_scan,
+ unsigned long *nr_saved_scan,
+ unsigned long swap_cluster_max)
+{
+ unsigned long nr;
+
+ *nr_saved_scan += nr_to_scan;
+ nr = *nr_saved_scan;
+
+ if (nr >= swap_cluster_max)
+ *nr_saved_scan = 0;
+ else
+ nr = 0;
+
+ return nr;
+}
/*
* This is a basic per-zone page freer. Used by both kswapd and direct reclaim.
for_each_evictable_lru(l) {
int file = is_file_lru(l);
- int scan;
+ unsigned long scan;
scan = zone_nr_pages(zone, sc, l);
if (priority) {
scan >>= priority;
scan = (scan * percent[file]) / 100;
}
- if (scanning_global_lru(sc)) {
- zone->lru[l].nr_scan += scan;
- nr[l] = zone->lru[l].nr_scan;
- if (nr[l] >= swap_cluster_max)
- zone->lru[l].nr_scan = 0;
- else
- nr[l] = 0;
- } else
+ if (scanning_global_lru(sc))
+ nr[l] = nr_scan_try_batch(scan,
+ &zone->lru[l].nr_saved_scan,
+ swap_cluster_max);
+ else
nr[l] = scan;
}
* try to reclaim pages from zones which will satisfy the caller's allocation
* request.
*
- * We reclaim from a zone even if that zone is over pages_high. Because:
+ * We reclaim from a zone even if that zone is over high_wmark_pages(zone).
+ * Because:
* a) The caller may be trying to free *extra* pages to satisfy a higher-order
* allocation or
- * b) The zones may be over pages_high but they must go *over* pages_high to
- * satisfy the `incremental min' zone defense algorithm.
+ * b) The target zone may be at high_wmark_pages(zone) but the lower zones
+ * must go *over* high_wmark_pages(zone) to satisfy the `incremental min'
+ * zone defense algorithm.
*
* If a zone is deemed to be full of pinned pages then just give it a light
* scan then give up on it.
.may_writepage = !laptop_mode,
.swap_cluster_max = SWAP_CLUSTER_MAX,
.may_unmap = 1,
+ .may_swap = 1,
.swappiness = vm_swappiness,
.order = order,
.mem_cgroup = NULL,
struct scan_control sc = {
.may_writepage = !laptop_mode,
.may_unmap = 1,
+ .may_swap = !noswap,
.swap_cluster_max = SWAP_CLUSTER_MAX,
.swappiness = swappiness,
.order = 0,
};
struct zonelist *zonelist;
- if (noswap)
- sc.may_unmap = 0;
-
sc.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) |
(GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK);
zonelist = NODE_DATA(numa_node_id())->node_zonelists;
/*
* For kswapd, balance_pgdat() will work across all this node's zones until
- * they are all at pages_high.
+ * they are all at high_wmark_pages(zone).
*
* Returns the number of pages which were actually freed.
*
* the zone for when the problem goes away.
*
* kswapd scans the zones in the highmem->normal->dma direction. It skips
- * zones which have free_pages > pages_high, but once a zone is found to have
- * free_pages <= pages_high, we scan that zone and the lower zones regardless
- * of the number of free pages in the lower zones. This interoperates with
- * the page allocator fallback scheme to ensure that aging of pages is balanced
- * across the zones.
+ * zones which have free_pages > high_wmark_pages(zone), but once a zone is
+ * found to have free_pages <= high_wmark_pages(zone), we scan that zone and the
+ * lower zones regardless of the number of free pages in the lower zones. This
+ * interoperates with the page allocator fallback scheme to ensure that aging
+ * of pages is balanced across the zones.
*/
static unsigned long balance_pgdat(pg_data_t *pgdat, int order)
{
struct scan_control sc = {
.gfp_mask = GFP_KERNEL,
.may_unmap = 1,
+ .may_swap = 1,
.swap_cluster_max = SWAP_CLUSTER_MAX,
.swappiness = vm_swappiness,
.order = order,
};
/*
* temp_priority is used to remember the scanning priority at which
- * this zone was successfully refilled to free_pages == pages_high.
+ * this zone was successfully refilled to
+ * free_pages == high_wmark_pages(zone).
*/
int temp_priority[MAX_NR_ZONES];
shrink_active_list(SWAP_CLUSTER_MAX, zone,
&sc, priority, 0);
- if (!zone_watermark_ok(zone, order, zone->pages_high,
- 0, 0)) {
+ if (!zone_watermark_ok(zone, order,
+ high_wmark_pages(zone), 0, 0)) {
end_zone = i;
break;
}
priority != DEF_PRIORITY)
continue;
- if (!zone_watermark_ok(zone, order, zone->pages_high,
- end_zone, 0))
+ if (!zone_watermark_ok(zone, order,
+ high_wmark_pages(zone), end_zone, 0))
all_zones_ok = 0;
temp_priority[i] = priority;
sc.nr_scanned = 0;
* We put equal pressure on every zone, unless one
* zone has way too many pages free already.
*/
- if (!zone_watermark_ok(zone, order, 8*zone->pages_high,
- end_zone, 0))
+ if (!zone_watermark_ok(zone, order,
+ 8*high_wmark_pages(zone), end_zone, 0))
shrink_zone(priority, zone, &sc);
reclaim_state->reclaimed_slab = 0;
nr_slab = shrink_slab(sc.nr_scanned, GFP_KERNEL,
return;
pgdat = zone->zone_pgdat;
- if (zone_watermark_ok(zone, order, zone->pages_low, 0, 0))
+ if (zone_watermark_ok(zone, order, low_wmark_pages(zone), 0, 0))
return;
if (pgdat->kswapd_max_order < order)
pgdat->kswapd_max_order = order;
+ global_page_state(NR_INACTIVE_FILE);
}
-#ifdef CONFIG_PM
+#ifdef CONFIG_HIBERNATION
/*
* Helper function for shrink_all_memory(). Tries to reclaim 'nr_pages' pages
* from LRU lists system-wide, for given pass and priority.
l == LRU_ACTIVE_FILE))
continue;
- zone->lru[l].nr_scan += (lru_pages >> prio) + 1;
- if (zone->lru[l].nr_scan >= nr_pages || pass > 3) {
+ zone->lru[l].nr_saved_scan += (lru_pages >> prio) + 1;
+ if (zone->lru[l].nr_saved_scan >= nr_pages || pass > 3) {
unsigned long nr_to_scan;
- zone->lru[l].nr_scan = 0;
+ zone->lru[l].nr_saved_scan = 0;
nr_to_scan = min(nr_pages, lru_pages);
nr_reclaimed += shrink_list(l, nr_to_scan, zone,
sc, prio);
if (nr_reclaimed >= nr_pages) {
- sc->nr_reclaimed = nr_reclaimed;
+ sc->nr_reclaimed += nr_reclaimed;
return;
}
}
}
}
- sc->nr_reclaimed = nr_reclaimed;
+ sc->nr_reclaimed += nr_reclaimed;
}
/*
.may_unmap = 0,
.may_writepage = 1,
.isolate_pages = isolate_pages_global,
+ .nr_reclaimed = 0,
};
current->reclaim_state = &reclaim_state;
return sc.nr_reclaimed;
}
-#endif
+#endif /* CONFIG_HIBERNATION */
/* It's optimal to keep kswapds on the same CPUs as their memory, but
not required for correctness. So if the last cpu in a node goes
struct scan_control sc = {
.may_writepage = !!(zone_reclaim_mode & RECLAIM_WRITE),
.may_unmap = !!(zone_reclaim_mode & RECLAIM_SWAP),
+ .may_swap = 1,
.swap_cluster_max = max_t(unsigned long, nr_pages,
SWAP_CLUSTER_MAX),
.gfp_mask = gfp_mask,
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff