#include <linux/notifier.h>
#include <linux/rwsem.h>
#include <linux/delay.h>
+#include <linux/kthread.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;
* 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
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;
}
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_vm_events(PGACTIVATE, nr_freed);
if (nr_taken == 0)
goto done;
* 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
}
}
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);
}
.swappiness = vm_swappiness,
};
- inc_page_state(allocstall);
+ count_vm_event(ALLOCSTALL);
for (i = 0; zones[i] != NULL; i++) {
struct zone *zone = zones[i];
}
for (priority = DEF_PRIORITY; priority >= 0; priority--) {
- sc.nr_mapped = read_page_state(nr_mapped);
sc.nr_scanned = 0;
if (!priority)
disable_swap_token();
total_scanned = 0;
nr_reclaimed = 0;
sc.may_writepage = !laptop_mode;
- sc.nr_mapped = read_page_state(nr_mapped);
-
- inc_page_state(pageoutrun);
+ count_vm_event(PAGEOUTRUN);
for (i = 0; i < pgdat->nr_zones; i++) {
struct zone *zone = pgdat->node_zones + i;
};
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);
for_each_zone(zone)
lru_pages += zone->nr_active + zone->nr_inactive;
- nr_slab = read_page_state(nr_slab);
+ nr_slab = global_page_state(NR_SLAB);
/* If slab caches are huge, it's better to hit them first */
while (nr_slab >= lru_pages) {
reclaim_state.reclaimed_slab = 0;
for (prio = DEF_PRIORITY; prio >= 0; prio--) {
unsigned long nr_to_scan = nr_pages - ret;
- sc.nr_mapped = read_page_state(nr_mapped);
sc.nr_scanned = 0;
-
ret += shrink_all_zones(nr_to_scan, prio, pass, &sc);
if (ret >= nr_pages)
goto out;
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;
}
#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_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_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
* of a node considered for each zone_reclaim. 4 scans 1/16th of
*/
#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;
+
/*
* 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,
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.
- */
- zone->last_unsuccessful_zone_reclaim = jiffies;
- }
-
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.
+ *
+ * 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_ratio)
+ return 0;
/*
* Avoid concurrent zone reclaims, do not reclaim in a zone that does
git.samba.org / sfrench / cifs-2.6.git / blobdiff