#include <linux/pagemap.h>
#include <linux/init.h>
#include <linux/highmem.h>
+#include <linux/vmstat.h>
#include <linux/file.h>
#include <linux/writeback.h>
#include <linux/blkdev.h>
#include <linux/notifier.h>
#include <linux/rwsem.h>
#include <linux/delay.h>
+#include <linux/kthread.h>
+#include <linux/freezer.h>
#include <asm/tlbflush.h>
#include <asm/div64.h>
/* Incremented by the number of inactive pages that were scanned */
unsigned long nr_scanned;
- unsigned long nr_mapped; /* From page_state */
-
/* This context's GFP mask */
gfp_t gfp_mask;
* In this context, it doesn't matter that we scan the
* whole list at once. */
int swap_cluster_max;
+
+ int swappiness;
+
+ int all_unreclaimable;
};
/*
* From 0 .. 100. Higher means more swappy.
*/
int vm_swappiness = 60;
-static long total_memory;
+long vm_total_pages; /* The total number of pages which the VM controls */
static LIST_HEAD(shrinker_list);
static DECLARE_RWSEM(shrinker_rwsem);
break;
if (shrink_ret < nr_before)
ret += nr_before - shrink_ret;
- mod_page_state(slabs_scanned, this_scan);
+ count_vm_events(SLABS_SCANNED, this_scan);
total_scan -= this_scan;
cond_resched();
unlock_page(page);
}
+/* possible outcome of pageout() */
+typedef enum {
+ /* failed to write page out, page is locked */
+ PAGE_KEEP,
+ /* move page to the active list, page is locked */
+ PAGE_ACTIVATE,
+ /* page has been sent to the disk successfully, page is unlocked */
+ PAGE_SUCCESS,
+ /* page is clean and locked */
+ PAGE_CLEAN,
+} pageout_t;
+
/*
* pageout is called by shrink_page_list() for each dirty page.
* Calls ->writepage().
*/
-pageout_t pageout(struct page *page, struct address_space *mapping)
+static pageout_t pageout(struct page *page, struct address_space *mapping)
{
/*
* If the page is dirty, only perform writeback if that write
struct writeback_control wbc = {
.sync_mode = WB_SYNC_NONE,
.nr_to_write = SWAP_CLUSTER_MAX,
+ .range_start = 0,
+ .range_end = LLONG_MAX,
.nonblocking = 1,
.for_reclaim = 1,
};
/* synchronous write or broken a_ops? */
ClearPageReclaim(page);
}
-
+ inc_zone_page_state(page, NR_VMSCAN_WRITE);
return PAGE_SUCCESS;
}
return PAGE_CLEAN;
}
+/*
+ * Attempt to detach a locked page from its ->mapping. If it is dirty or if
+ * someone else has a ref on the page, abort and return 0. If it was
+ * successfully detached, return 1. Assumes the caller has a single ref on
+ * this page.
+ */
int remove_mapping(struct address_space *mapping, struct page *page)
{
- if (!mapping)
- return 0; /* truncate got there first */
+ BUG_ON(!PageLocked(page));
+ BUG_ON(mapping != page_mapping(page));
write_lock_irq(&mapping->tree_lock);
-
/*
- * The non-racy check for busy page. It is critical to check
- * PageDirty _after_ making sure that the page is freeable and
- * not in use by anybody. (pagecache + us == 2)
+ * The non racy check for a busy page.
+ *
+ * Must be careful with the order of the tests. When someone has
+ * a ref to the page, it may be possible that they dirty it then
+ * drop the reference. So if PageDirty is tested before page_count
+ * here, then the following race may occur:
+ *
+ * get_user_pages(&page);
+ * [user mapping goes away]
+ * write_to(page);
+ * !PageDirty(page) [good]
+ * SetPageDirty(page);
+ * put_page(page);
+ * !page_count(page) [good, discard it]
+ *
+ * [oops, our write_to data is lost]
+ *
+ * Reversing the order of the tests ensures such a situation cannot
+ * escape unnoticed. The smp_rmb is needed to ensure the page->flags
+ * load is not satisfied before that of page->_count.
+ *
+ * Note that if SetPageDirty is always performed via set_page_dirty,
+ * and thus under tree_lock, then this ordering is not required.
*/
if (unlikely(page_count(page) != 2))
goto cannot_free;
if (TestSetPageLocked(page))
goto keep;
- BUG_ON(PageActive(page));
+ VM_BUG_ON(PageActive(page));
sc->nr_scanned++;
goto free_it;
}
- if (!remove_mapping(mapping, page))
+ if (!mapping || !remove_mapping(mapping, page))
goto keep_locked;
free_it:
unlock_page(page);
keep:
list_add(&page->lru, &ret_pages);
- BUG_ON(PageLRU(page));
+ VM_BUG_ON(PageLRU(page));
}
list_splice(&ret_pages, page_list);
if (pagevec_count(&freed_pvec))
__pagevec_release_nonlru(&freed_pvec);
- mod_page_state(pgactivate, pgactivate);
+ count_vm_events(PGACTIVATE, pgactivate);
return nr_reclaimed;
}
page = lru_to_page(src);
prefetchw_prev_lru_page(page, src, flags);
- BUG_ON(!PageLRU(page));
+ VM_BUG_ON(!PageLRU(page));
list_del(&page->lru);
target = src;
nr_reclaimed += nr_freed;
local_irq_disable();
if (current_is_kswapd()) {
- __mod_page_state_zone(zone, pgscan_kswapd, nr_scan);
- __mod_page_state(kswapd_steal, nr_freed);
+ __count_zone_vm_events(PGSCAN_KSWAPD, zone, nr_scan);
+ __count_vm_events(KSWAPD_STEAL, nr_freed);
} else
- __mod_page_state_zone(zone, pgscan_direct, nr_scan);
- __mod_page_state_zone(zone, pgsteal, nr_freed);
+ __count_zone_vm_events(PGSCAN_DIRECT, zone, nr_scan);
+ __count_zone_vm_events(PGSTEAL, zone, nr_freed);
if (nr_taken == 0)
goto done;
*/
while (!list_empty(&page_list)) {
page = lru_to_page(&page_list);
- BUG_ON(PageLRU(page));
+ VM_BUG_ON(PageLRU(page));
SetPageLRU(page);
list_del(&page->lru);
if (PageActive(page))
return nr_reclaimed;
}
+/*
+ * We are about to scan this zone at a certain priority level. If that priority
+ * level is smaller (ie: more urgent) than the previous priority, then note
+ * that priority level within the zone. This is done so that when the next
+ * process comes in to scan this zone, it will immediately start out at this
+ * priority level rather than having to build up its own scanning priority.
+ * Here, this priority affects only the reclaim-mapped threshold.
+ */
+static inline void note_zone_scanning_priority(struct zone *zone, int priority)
+{
+ if (priority < zone->prev_priority)
+ zone->prev_priority = priority;
+}
+
+static inline int zone_is_near_oom(struct zone *zone)
+{
+ return zone->pages_scanned >= (zone->nr_active + zone->nr_inactive)*3;
+}
+
/*
* This moves pages from the active list to the inactive list.
*
* But we had to alter page->flags anyway.
*/
static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
- struct scan_control *sc)
+ struct scan_control *sc, int priority)
{
unsigned long pgmoved;
int pgdeactivate = 0;
long distress;
long swap_tendency;
+ if (zone_is_near_oom(zone))
+ goto force_reclaim_mapped;
+
/*
* `distress' is a measure of how much trouble we're having
* reclaiming pages. 0 -> no problems. 100 -> great trouble.
*/
- distress = 100 >> zone->prev_priority;
+ distress = 100 >> min(zone->prev_priority, priority);
/*
* The point of this algorithm is to decide when to start
* how much memory
* is mapped.
*/
- mapped_ratio = (sc->nr_mapped * 100) / total_memory;
+ mapped_ratio = ((global_page_state(NR_FILE_MAPPED) +
+ global_page_state(NR_ANON_PAGES)) * 100) /
+ vm_total_pages;
/*
* Now decide how much we really want to unmap some pages. The
* A 100% value of vm_swappiness overrides this algorithm
* altogether.
*/
- swap_tendency = mapped_ratio / 2 + distress + vm_swappiness;
+ swap_tendency = mapped_ratio / 2 + distress + sc->swappiness;
/*
* Now use this metric to decide whether to start moving mapped
* memory onto the inactive list.
*/
if (swap_tendency >= 100)
+force_reclaim_mapped:
reclaim_mapped = 1;
}
while (!list_empty(&l_inactive)) {
page = lru_to_page(&l_inactive);
prefetchw_prev_lru_page(page, &l_inactive, flags);
- BUG_ON(PageLRU(page));
+ VM_BUG_ON(PageLRU(page));
SetPageLRU(page);
- BUG_ON(!PageActive(page));
+ VM_BUG_ON(!PageActive(page));
ClearPageActive(page);
list_move(&page->lru, &zone->inactive_list);
while (!list_empty(&l_active)) {
page = lru_to_page(&l_active);
prefetchw_prev_lru_page(page, &l_active, flags);
- BUG_ON(PageLRU(page));
+ VM_BUG_ON(PageLRU(page));
SetPageLRU(page);
- BUG_ON(!PageActive(page));
+ VM_BUG_ON(!PageActive(page));
list_move(&page->lru, &zone->active_list);
pgmoved++;
if (!pagevec_add(&pvec, page)) {
}
}
zone->nr_active += pgmoved;
- spin_unlock(&zone->lru_lock);
- __mod_page_state_zone(zone, pgrefill, pgscanned);
- __mod_page_state(pgdeactivate, pgdeactivate);
- local_irq_enable();
+ __count_zone_vm_events(PGREFILL, zone, pgscanned);
+ __count_vm_events(PGDEACTIVATE, pgdeactivate);
+ spin_unlock_irq(&zone->lru_lock);
pagevec_release(&pvec);
}
nr_to_scan = min(nr_active,
(unsigned long)sc->swap_cluster_max);
nr_active -= nr_to_scan;
- shrink_active_list(nr_to_scan, zone, sc);
+ shrink_active_list(nr_to_scan, zone, sc, priority);
}
if (nr_inactive) {
}
}
- throttle_vm_writeout();
+ throttle_vm_writeout(sc->gfp_mask);
atomic_dec(&zone->reclaim_in_progress);
return nr_reclaimed;
unsigned long nr_reclaimed = 0;
int i;
+ sc->all_unreclaimable = 1;
for (i = 0; zones[i] != NULL; i++) {
struct zone *zone = zones[i];
if (!populated_zone(zone))
continue;
- if (!cpuset_zone_allowed(zone, __GFP_HARDWALL))
+ if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
continue;
- zone->temp_priority = priority;
- if (zone->prev_priority > priority)
- zone->prev_priority = priority;
+ note_zone_scanning_priority(zone, priority);
if (zone->all_unreclaimable && priority != DEF_PRIORITY)
continue; /* Let kswapd poll it */
+ sc->all_unreclaimable = 0;
+
nr_reclaimed += shrink_zone(priority, zone, sc);
}
return nr_reclaimed;
.may_writepage = !laptop_mode,
.swap_cluster_max = SWAP_CLUSTER_MAX,
.may_swap = 1,
+ .swappiness = vm_swappiness,
};
- inc_page_state(allocstall);
+ count_vm_event(ALLOCSTALL);
for (i = 0; zones[i] != NULL; i++) {
struct zone *zone = zones[i];
- if (!cpuset_zone_allowed(zone, __GFP_HARDWALL))
+ if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
continue;
- zone->temp_priority = DEF_PRIORITY;
lru_pages += zone->nr_active + zone->nr_inactive;
}
for (priority = DEF_PRIORITY; priority >= 0; priority--) {
- sc.nr_mapped = read_page_state(nr_mapped);
sc.nr_scanned = 0;
if (!priority)
disable_swap_token();
/* Take a nap, wait for some writeback to complete */
if (sc.nr_scanned && priority < DEF_PRIORITY - 2)
- blk_congestion_wait(WRITE, HZ/10);
+ congestion_wait(WRITE, HZ/10);
}
+ /* top priority shrink_caches still had more to do? don't OOM, then */
+ if (!sc.all_unreclaimable)
+ ret = 1;
out:
+ /*
+ * Now that we've scanned all the zones at this priority level, note
+ * that level within the zone so that the next thread which performs
+ * scanning of this zone will immediately start out at this priority
+ * level. This affects only the decision whether or not to bring
+ * mapped pages onto the inactive list.
+ */
+ if (priority < 0)
+ priority = 0;
for (i = 0; zones[i] != 0; i++) {
struct zone *zone = zones[i];
- if (!cpuset_zone_allowed(zone, __GFP_HARDWALL))
+ if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
continue;
- zone->prev_priority = zone->temp_priority;
+ zone->prev_priority = priority;
}
return ret;
}
* For kswapd, balance_pgdat() will work across all this node's zones until
* they are all at pages_high.
*
- * If `nr_pages' is non-zero then it is the number of pages which are to be
- * reclaimed, regardless of the zone occupancies. This is a software suspend
- * special.
- *
* Returns the number of pages which were actually freed.
*
* There is special handling here for zones which are full of pinned pages.
* 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, unsigned long nr_pages,
- int order)
+static unsigned long balance_pgdat(pg_data_t *pgdat, int order)
{
- unsigned long to_free = nr_pages;
int all_zones_ok;
int priority;
int i;
struct scan_control sc = {
.gfp_mask = GFP_KERNEL,
.may_swap = 1,
- .swap_cluster_max = nr_pages ? nr_pages : SWAP_CLUSTER_MAX,
+ .swap_cluster_max = SWAP_CLUSTER_MAX,
+ .swappiness = vm_swappiness,
};
+ /*
+ * temp_priority is used to remember the scanning priority at which
+ * this zone was successfully refilled to free_pages == pages_high.
+ */
+ int temp_priority[MAX_NR_ZONES];
loop_again:
total_scanned = 0;
nr_reclaimed = 0;
sc.may_writepage = !laptop_mode;
- sc.nr_mapped = read_page_state(nr_mapped);
-
- inc_page_state(pageoutrun);
-
- for (i = 0; i < pgdat->nr_zones; i++) {
- struct zone *zone = pgdat->node_zones + i;
+ count_vm_event(PAGEOUTRUN);
- zone->temp_priority = DEF_PRIORITY;
- }
+ for (i = 0; i < pgdat->nr_zones; i++)
+ temp_priority[i] = DEF_PRIORITY;
for (priority = DEF_PRIORITY; priority >= 0; priority--) {
int end_zone = 0; /* Inclusive. 0 = ZONE_DMA */
all_zones_ok = 1;
- if (nr_pages == 0) {
- /*
- * Scan in the highmem->dma direction for the highest
- * zone which needs scanning
- */
- for (i = pgdat->nr_zones - 1; i >= 0; i--) {
- struct zone *zone = pgdat->node_zones + i;
+ /*
+ * Scan in the highmem->dma direction for the highest
+ * zone which needs scanning
+ */
+ for (i = pgdat->nr_zones - 1; i >= 0; i--) {
+ struct zone *zone = pgdat->node_zones + i;
- if (!populated_zone(zone))
- continue;
+ if (!populated_zone(zone))
+ continue;
- if (zone->all_unreclaimable &&
- priority != DEF_PRIORITY)
- continue;
+ if (zone->all_unreclaimable && priority != DEF_PRIORITY)
+ continue;
- if (!zone_watermark_ok(zone, order,
- zone->pages_high, 0, 0)) {
- end_zone = i;
- goto scan;
- }
+ if (!zone_watermark_ok(zone, order, zone->pages_high,
+ 0, 0)) {
+ end_zone = i;
+ break;
}
- goto out;
- } else {
- end_zone = pgdat->nr_zones - 1;
}
-scan:
+ if (i < 0)
+ goto out;
+
for (i = 0; i <= end_zone; i++) {
struct zone *zone = pgdat->node_zones + i;
if (zone->all_unreclaimable && priority != DEF_PRIORITY)
continue;
- if (nr_pages == 0) { /* Not software suspend */
- if (!zone_watermark_ok(zone, order,
- zone->pages_high, end_zone, 0))
- all_zones_ok = 0;
- }
- zone->temp_priority = priority;
- if (zone->prev_priority > priority)
- zone->prev_priority = priority;
+ if (!zone_watermark_ok(zone, order, zone->pages_high,
+ end_zone, 0))
+ all_zones_ok = 0;
+ temp_priority[i] = priority;
sc.nr_scanned = 0;
+ note_zone_scanning_priority(zone, priority);
nr_reclaimed += shrink_zone(priority, zone, &sc);
reclaim_state->reclaimed_slab = 0;
nr_slab = shrink_slab(sc.nr_scanned, GFP_KERNEL,
if (zone->all_unreclaimable)
continue;
if (nr_slab == 0 && zone->pages_scanned >=
- (zone->nr_active + zone->nr_inactive) * 4)
+ (zone->nr_active + zone->nr_inactive) * 6)
zone->all_unreclaimable = 1;
/*
* If we've done a decent amount of scanning and
total_scanned > nr_reclaimed + nr_reclaimed / 2)
sc.may_writepage = 1;
}
- if (nr_pages && to_free > nr_reclaimed)
- continue; /* swsusp: need to do more work */
if (all_zones_ok)
break; /* kswapd: all done */
/*
* another pass across the zones.
*/
if (total_scanned && priority < DEF_PRIORITY - 2)
- blk_congestion_wait(WRITE, HZ/10);
+ congestion_wait(WRITE, HZ/10);
/*
* We do this so kswapd doesn't build up large priorities for
* matches the direct reclaim path behaviour in terms of impact
* on zone->*_priority.
*/
- if ((nr_reclaimed >= SWAP_CLUSTER_MAX) && !nr_pages)
+ if (nr_reclaimed >= SWAP_CLUSTER_MAX)
break;
}
out:
+ /*
+ * Note within each zone the priority level at which this zone was
+ * brought into a happy state. So that the next thread which scans this
+ * zone will start out at that priority level.
+ */
for (i = 0; i < pgdat->nr_zones; i++) {
struct zone *zone = pgdat->node_zones + i;
- zone->prev_priority = zone->temp_priority;
+ zone->prev_priority = temp_priority[i];
}
if (!all_zones_ok) {
cond_resched();
+
+ try_to_freeze();
+
goto loop_again;
}
};
cpumask_t cpumask;
- daemonize("kswapd%d", pgdat->node_id);
cpumask = node_to_cpumask(pgdat->node_id);
if (!cpus_empty(cpumask))
set_cpus_allowed(tsk, cpumask);
}
finish_wait(&pgdat->kswapd_wait, &wait);
- balance_pgdat(pgdat, 0, order);
+ balance_pgdat(pgdat, order);
}
return 0;
}
return;
if (pgdat->kswapd_max_order < order)
pgdat->kswapd_max_order = order;
- if (!cpuset_zone_allowed(zone, __GFP_HARDWALL))
+ if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
return;
if (!waitqueue_active(&pgdat->kswapd_wait))
return;
#ifdef CONFIG_PM
/*
- * Try to free `nr_pages' of memory, system-wide. Returns the number of freed
- * pages.
+ * Helper function for shrink_all_memory(). Tries to reclaim 'nr_pages' pages
+ * from LRU lists system-wide, for given pass and priority, and returns the
+ * number of reclaimed pages
+ *
+ * For pass > 3 we also try to shrink the LRU lists that contain a few pages
+ */
+static unsigned long shrink_all_zones(unsigned long nr_pages, int prio,
+ int pass, struct scan_control *sc)
+{
+ struct zone *zone;
+ unsigned long nr_to_scan, ret = 0;
+
+ for_each_zone(zone) {
+
+ if (!populated_zone(zone))
+ continue;
+
+ if (zone->all_unreclaimable && prio != DEF_PRIORITY)
+ continue;
+
+ /* For pass = 0 we don't shrink the active list */
+ if (pass > 0) {
+ zone->nr_scan_active += (zone->nr_active >> prio) + 1;
+ if (zone->nr_scan_active >= nr_pages || pass > 3) {
+ zone->nr_scan_active = 0;
+ nr_to_scan = min(nr_pages, zone->nr_active);
+ shrink_active_list(nr_to_scan, zone, sc, prio);
+ }
+ }
+
+ zone->nr_scan_inactive += (zone->nr_inactive >> prio) + 1;
+ if (zone->nr_scan_inactive >= nr_pages || pass > 3) {
+ zone->nr_scan_inactive = 0;
+ nr_to_scan = min(nr_pages, zone->nr_inactive);
+ ret += shrink_inactive_list(nr_to_scan, zone, sc);
+ if (ret >= nr_pages)
+ return ret;
+ }
+ }
+
+ return ret;
+}
+
+static unsigned long count_lru_pages(void)
+{
+ struct zone *zone;
+ unsigned long ret = 0;
+
+ for_each_zone(zone)
+ ret += zone->nr_active + zone->nr_inactive;
+ return ret;
+}
+
+/*
+ * Try to free `nr_pages' of memory, system-wide, and return the number of
+ * freed pages.
+ *
+ * Rather than trying to age LRUs the aim is to preserve the overall
+ * LRU order by reclaiming preferentially
+ * inactive > active > active referenced > active mapped
*/
unsigned long shrink_all_memory(unsigned long nr_pages)
{
- pg_data_t *pgdat;
- unsigned long nr_to_free = nr_pages;
+ unsigned long lru_pages, nr_slab;
unsigned long ret = 0;
- unsigned retry = 2;
- struct reclaim_state reclaim_state = {
- .reclaimed_slab = 0,
+ int pass;
+ struct reclaim_state reclaim_state;
+ struct scan_control sc = {
+ .gfp_mask = GFP_KERNEL,
+ .may_swap = 0,
+ .swap_cluster_max = nr_pages,
+ .may_writepage = 1,
+ .swappiness = vm_swappiness,
};
current->reclaim_state = &reclaim_state;
-repeat:
- for_each_online_pgdat(pgdat) {
- unsigned long freed;
-
- freed = balance_pgdat(pgdat, nr_to_free, 0);
- ret += freed;
- nr_to_free -= freed;
- if ((long)nr_to_free <= 0)
+
+ lru_pages = count_lru_pages();
+ nr_slab = global_page_state(NR_SLAB_RECLAIMABLE);
+ /* If slab caches are huge, it's better to hit them first */
+ while (nr_slab >= lru_pages) {
+ reclaim_state.reclaimed_slab = 0;
+ shrink_slab(nr_pages, sc.gfp_mask, lru_pages);
+ if (!reclaim_state.reclaimed_slab)
break;
+
+ ret += reclaim_state.reclaimed_slab;
+ if (ret >= nr_pages)
+ goto out;
+
+ nr_slab -= reclaim_state.reclaimed_slab;
}
- if (retry-- && ret < nr_pages) {
- blk_congestion_wait(WRITE, HZ/5);
- goto repeat;
+
+ /*
+ * We try to shrink LRUs in 5 passes:
+ * 0 = Reclaim from inactive_list only
+ * 1 = Reclaim from active list but don't reclaim mapped
+ * 2 = 2nd pass of type 1
+ * 3 = Reclaim mapped (normal reclaim)
+ * 4 = 2nd pass of type 3
+ */
+ for (pass = 0; pass < 5; pass++) {
+ int prio;
+
+ /* Force reclaiming mapped pages in the passes #3 and #4 */
+ if (pass > 2) {
+ sc.may_swap = 1;
+ sc.swappiness = 100;
+ }
+
+ for (prio = DEF_PRIORITY; prio >= 0; prio--) {
+ unsigned long nr_to_scan = nr_pages - ret;
+
+ sc.nr_scanned = 0;
+ ret += shrink_all_zones(nr_to_scan, prio, pass, &sc);
+ if (ret >= nr_pages)
+ goto out;
+
+ reclaim_state.reclaimed_slab = 0;
+ shrink_slab(sc.nr_scanned, sc.gfp_mask,
+ count_lru_pages());
+ ret += reclaim_state.reclaimed_slab;
+ if (ret >= nr_pages)
+ goto out;
+
+ if (sc.nr_scanned && prio < DEF_PRIORITY - 2)
+ congestion_wait(WRITE, HZ / 10);
+ }
}
+
+ /*
+ * If ret = 0, we could not shrink LRUs, but there may be something
+ * in slab caches
+ */
+ if (!ret) {
+ do {
+ reclaim_state.reclaimed_slab = 0;
+ shrink_slab(nr_pages, sc.gfp_mask, count_lru_pages());
+ ret += reclaim_state.reclaimed_slab;
+ } while (ret < nr_pages && reclaim_state.reclaimed_slab > 0);
+ }
+
+out:
current->reclaim_state = NULL;
+
return ret;
}
#endif
-#ifdef CONFIG_HOTPLUG_CPU
/* 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
away, we get changed to run anywhere: as the first one comes back,
restore their cpu bindings. */
-static int cpu_callback(struct notifier_block *nfb,
+static int __devinit cpu_callback(struct notifier_block *nfb,
unsigned long action, void *hcpu)
{
pg_data_t *pgdat;
}
return NOTIFY_OK;
}
-#endif /* CONFIG_HOTPLUG_CPU */
+
+/*
+ * This kswapd start function will be called by init and node-hot-add.
+ * On node-hot-add, kswapd will moved to proper cpus if cpus are hot-added.
+ */
+int kswapd_run(int nid)
+{
+ pg_data_t *pgdat = NODE_DATA(nid);
+ int ret = 0;
+
+ if (pgdat->kswapd)
+ return 0;
+
+ pgdat->kswapd = kthread_run(kswapd, pgdat, "kswapd%d", nid);
+ if (IS_ERR(pgdat->kswapd)) {
+ /* failure at boot is fatal */
+ BUG_ON(system_state == SYSTEM_BOOTING);
+ printk("Failed to start kswapd on node %d\n",nid);
+ ret = -1;
+ }
+ return ret;
+}
static int __init kswapd_init(void)
{
- pg_data_t *pgdat;
+ int nid;
swap_setup();
- for_each_online_pgdat(pgdat) {
- pid_t pid;
-
- pid = kernel_thread(kswapd, pgdat, CLONE_KERNEL);
- BUG_ON(pid < 0);
- read_lock(&tasklist_lock);
- pgdat->kswapd = find_task_by_real_pid(pid);
- read_unlock(&tasklist_lock);
- }
- total_memory = nr_free_pagecache_pages();
+ for_each_online_node(nid)
+ kswapd_run(nid);
hotcpu_notifier(cpu_callback, 0);
return 0;
}
*
* If non-zero call zone_reclaim when the number of free pages falls below
* the watermarks.
- *
- * In the future we may add flags to the mode. However, the page allocator
- * should only have to check that zone_reclaim_mode != 0 before calling
- * zone_reclaim().
*/
int zone_reclaim_mode __read_mostly;
#define RECLAIM_ZONE (1<<0) /* Run shrink_cache on the zone */
#define RECLAIM_WRITE (1<<1) /* Writeout pages during reclaim */
#define RECLAIM_SWAP (1<<2) /* Swap pages out during reclaim */
-#define RECLAIM_SLAB (1<<3) /* Do a global slab shrink if the zone is out of memory */
-
-/*
- * Mininum time between zone reclaim scans
- */
-int zone_reclaim_interval __read_mostly = 30*HZ;
/*
* Priority for ZONE_RECLAIM. This determines the fraction of pages
*/
#define ZONE_RECLAIM_PRIORITY 4
+/*
+ * Percentage of pages in a zone that must be unmapped for zone_reclaim to
+ * occur.
+ */
+int sysctl_min_unmapped_ratio = 1;
+
+/*
+ * If the number of slab pages in a zone grows beyond this percentage then
+ * slab reclaim needs to occur.
+ */
+int sysctl_min_slab_ratio = 5;
+
/*
* Try to free up some pages from this zone through reclaim.
*/
struct scan_control sc = {
.may_writepage = !!(zone_reclaim_mode & RECLAIM_WRITE),
.may_swap = !!(zone_reclaim_mode & RECLAIM_SWAP),
- .nr_mapped = read_page_state(nr_mapped),
.swap_cluster_max = max_t(unsigned long, nr_pages,
SWAP_CLUSTER_MAX),
.gfp_mask = gfp_mask,
+ .swappiness = vm_swappiness,
};
+ unsigned long slab_reclaimable;
disable_swap_token();
cond_resched();
reclaim_state.reclaimed_slab = 0;
p->reclaim_state = &reclaim_state;
- /*
- * Free memory by calling shrink zone with increasing priorities
- * until we have enough memory freed.
- */
- priority = ZONE_RECLAIM_PRIORITY;
- do {
- nr_reclaimed += shrink_zone(priority, zone, &sc);
- priority--;
- } while (priority >= 0 && nr_reclaimed < nr_pages);
+ if (zone_page_state(zone, NR_FILE_PAGES) -
+ zone_page_state(zone, NR_FILE_MAPPED) >
+ zone->min_unmapped_pages) {
+ /*
+ * Free memory by calling shrink zone with increasing
+ * priorities until we have enough memory freed.
+ */
+ priority = ZONE_RECLAIM_PRIORITY;
+ do {
+ note_zone_scanning_priority(zone, priority);
+ nr_reclaimed += shrink_zone(priority, zone, &sc);
+ priority--;
+ } while (priority >= 0 && nr_reclaimed < nr_pages);
+ }
- if (nr_reclaimed < nr_pages && (zone_reclaim_mode & RECLAIM_SLAB)) {
+ slab_reclaimable = zone_page_state(zone, NR_SLAB_RECLAIMABLE);
+ if (slab_reclaimable > zone->min_slab_pages) {
/*
* shrink_slab() does not currently allow us to determine how
- * many pages were freed in this zone. So we just shake the slab
- * a bit and then go off node for this particular allocation
- * despite possibly having freed enough memory to allocate in
- * this zone. If we freed local memory then the next
- * allocations will be local again.
+ * many pages were freed in this zone. So we take the current
+ * number of slab pages and shake the slab until it is reduced
+ * by the same nr_pages that we used for reclaiming unmapped
+ * pages.
*
- * shrink_slab will free memory on all zones and may take
- * a long time.
+ * Note that shrink_slab will free memory on all zones and may
+ * take a long time.
*/
- shrink_slab(sc.nr_scanned, gfp_mask, order);
- }
+ while (shrink_slab(sc.nr_scanned, gfp_mask, order) &&
+ zone_page_state(zone, NR_SLAB_RECLAIMABLE) >
+ slab_reclaimable - nr_pages)
+ ;
- p->reclaim_state = NULL;
- current->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE);
-
- if (nr_reclaimed == 0) {
/*
- * We were unable to reclaim enough pages to stay on node. We
- * now allow off node accesses for a certain time period before
- * trying again to reclaim pages from the local zone.
+ * Update nr_reclaimed by the number of slab pages we
+ * reclaimed from this zone.
*/
- zone->last_unsuccessful_zone_reclaim = jiffies;
+ nr_reclaimed += slab_reclaimable -
+ zone_page_state(zone, NR_SLAB_RECLAIMABLE);
}
+ p->reclaim_state = NULL;
+ current->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE);
return nr_reclaimed >= nr_pages;
}
int node_id;
/*
- * Do not reclaim if there was a recent unsuccessful attempt at zone
- * reclaim. In that case we let allocations go off node for the
- * zone_reclaim_interval. Otherwise we would scan for each off-node
- * page allocation.
+ * Zone reclaim reclaims unmapped file backed pages and
+ * slab pages if we are over the defined limits.
+ *
+ * A small portion of unmapped file backed pages is needed for
+ * file I/O otherwise pages read by file I/O will be immediately
+ * thrown out if the zone is overallocated. So we do not reclaim
+ * if less than a specified percentage of the zone is used by
+ * unmapped file backed pages.
*/
- if (time_before(jiffies,
- zone->last_unsuccessful_zone_reclaim + zone_reclaim_interval))
- return 0;
+ if (zone_page_state(zone, NR_FILE_PAGES) -
+ zone_page_state(zone, NR_FILE_MAPPED) <= zone->min_unmapped_pages
+ && zone_page_state(zone, NR_SLAB_RECLAIMABLE)
+ <= zone->min_slab_pages)
+ return 0;
/*
* Avoid concurrent zone reclaims, do not reclaim in a zone that does
* over remote processors and spread off node memory allocations
* as wide as possible.
*/
- node_id = zone->zone_pgdat->node_id;
+ node_id = zone_to_nid(zone);
mask = node_to_cpumask(node_id);
if (!cpus_empty(mask) && node_id != numa_node_id())
return 0;