* Copyright (C) 2006 Silicon Graphics, Inc.,
* Christoph Lameter <christoph@lameter.com>
*/
-
+#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/err.h>
#include <linux/module.h>
+#include <linux/slab.h>
#include <linux/cpu.h>
#include <linux/vmstat.h>
#include <linux/sched.h>
+#include <linux/math64.h>
#ifdef CONFIG_VM_EVENT_COUNTERS
DEFINE_PER_CPU(struct vm_event_state, vm_event_states) = {{0}};
EXPORT_PER_CPU_SYMBOL(vm_event_states);
-static void sum_vm_events(unsigned long *ret, cpumask_t *cpumask)
+static void sum_vm_events(unsigned long *ret, const struct cpumask *cpumask)
{
int cpu;
int i;
memset(ret, 0, NR_VM_EVENT_ITEMS * sizeof(unsigned long));
- for_each_cpu_mask_nr(cpu, *cpumask) {
+ for_each_cpu(cpu, cpumask) {
struct vm_event_state *this = &per_cpu(vm_event_states, cpu);
for (i = 0; i < NR_VM_EVENT_ITEMS; i++)
void all_vm_events(unsigned long *ret)
{
get_online_cpus();
- sum_vm_events(ret, &cpu_online_map);
+ sum_vm_events(ret, cpu_online_mask);
put_online_cpus();
}
EXPORT_SYMBOL_GPL(all_vm_events);
int cpu;
int threshold;
- for_each_zone(zone) {
-
- if (!zone->present_pages)
- continue;
-
+ for_each_populated_zone(zone) {
threshold = calculate_threshold(zone);
for_each_online_cpu(cpu)
- zone_pcp(zone, cpu)->stat_threshold = threshold;
+ per_cpu_ptr(zone->pageset, cpu)->stat_threshold
+ = threshold;
}
}
void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
int delta)
{
- struct per_cpu_pageset *pcp = zone_pcp(zone, smp_processor_id());
+ struct per_cpu_pageset *pcp = this_cpu_ptr(zone->pageset);
+
s8 *p = pcp->vm_stat_diff + item;
long x;
*/
void __inc_zone_state(struct zone *zone, enum zone_stat_item item)
{
- struct per_cpu_pageset *pcp = zone_pcp(zone, smp_processor_id());
+ struct per_cpu_pageset *pcp = this_cpu_ptr(zone->pageset);
s8 *p = pcp->vm_stat_diff + item;
(*p)++;
void __dec_zone_state(struct zone *zone, enum zone_stat_item item)
{
- struct per_cpu_pageset *pcp = zone_pcp(zone, smp_processor_id());
+ struct per_cpu_pageset *pcp = this_cpu_ptr(zone->pageset);
s8 *p = pcp->vm_stat_diff + item;
(*p)--;
int i;
int global_diff[NR_VM_ZONE_STAT_ITEMS] = { 0, };
- for_each_zone(zone) {
+ for_each_populated_zone(zone) {
struct per_cpu_pageset *p;
- if (!populated_zone(zone))
- continue;
-
- p = zone_pcp(zone, cpu);
+ p = per_cpu_ptr(zone->pageset, cpu);
for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
if (p->vm_stat_diff[i]) {
}
#endif
-#ifdef CONFIG_PROC_FS
+#ifdef CONFIG_COMPACTION
+struct contig_page_info {
+ unsigned long free_pages;
+ unsigned long free_blocks_total;
+ unsigned long free_blocks_suitable;
+};
+
+/*
+ * Calculate the number of free pages in a zone, how many contiguous
+ * pages are free and how many are large enough to satisfy an allocation of
+ * the target size. Note that this function makes no attempt to estimate
+ * how many suitable free blocks there *might* be if MOVABLE pages were
+ * migrated. Calculating that is possible, but expensive and can be
+ * figured out from userspace
+ */
+static void fill_contig_page_info(struct zone *zone,
+ unsigned int suitable_order,
+ struct contig_page_info *info)
+{
+ unsigned int order;
+
+ info->free_pages = 0;
+ info->free_blocks_total = 0;
+ info->free_blocks_suitable = 0;
+
+ for (order = 0; order < MAX_ORDER; order++) {
+ unsigned long blocks;
+
+ /* Count number of free blocks */
+ blocks = zone->free_area[order].nr_free;
+ info->free_blocks_total += blocks;
+
+ /* Count free base pages */
+ info->free_pages += blocks << order;
+
+ /* Count the suitable free blocks */
+ if (order >= suitable_order)
+ info->free_blocks_suitable += blocks <<
+ (order - suitable_order);
+ }
+}
+
+/*
+ * A fragmentation index only makes sense if an allocation of a requested
+ * size would fail. If that is true, the fragmentation index indicates
+ * whether external fragmentation or a lack of memory was the problem.
+ * The value can be used to determine if page reclaim or compaction
+ * should be used
+ */
+static int __fragmentation_index(unsigned int order, struct contig_page_info *info)
+{
+ unsigned long requested = 1UL << order;
+
+ if (!info->free_blocks_total)
+ return 0;
+
+ /* Fragmentation index only makes sense when a request would fail */
+ if (info->free_blocks_suitable)
+ return -1000;
+
+ /*
+ * Index is between 0 and 1 so return within 3 decimal places
+ *
+ * 0 => allocation would fail due to lack of memory
+ * 1 => allocation would fail due to fragmentation
+ */
+ return 1000 - div_u64( (1000+(div_u64(info->free_pages * 1000ULL, requested))), info->free_blocks_total);
+}
+
+/* Same as __fragmentation index but allocs contig_page_info on stack */
+int fragmentation_index(struct zone *zone, unsigned int order)
+{
+ struct contig_page_info info;
+
+ fill_contig_page_info(zone, order, &info);
+ return __fragmentation_index(order, &info);
+}
+#endif
+#if defined(CONFIG_PROC_FS) || defined(CONFIG_COMPACTION)
+#include <linux/proc_fs.h>
#include <linux/seq_file.h>
static char * const migratetype_names[MIGRATE_TYPES] = {
spin_unlock_irqrestore(&zone->lock, flags);
}
}
+#endif
+#ifdef CONFIG_PROC_FS
static void frag_show_print(struct seq_file *m, pg_data_t *pgdat,
struct zone *zone)
{
continue;
page = pfn_to_page(pfn);
-#ifdef CONFIG_ARCH_FLATMEM_HAS_HOLES
- /*
- * Ordinarily, memory holes in flatmem still have a valid
- * memmap for the PFN range. However, an architecture for
- * embedded systems (e.g. ARM) can free up the memmap backing
- * holes to save memory on the assumption the memmap is
- * never used. The page_zone linkages are then broken even
- * though pfn_valid() returns true. Skip the page if the
- * linkages are broken. Even if this test passed, the impact
- * is that the counters for the movable type are off but
- * fragmentation monitoring is likely meaningless on small
- * systems.
- */
- if (page_zone(page) != zone)
+
+ /* Watch for unexpected holes punched in the memmap */
+ if (!memmap_valid_within(pfn, page, zone))
continue;
-#endif
+
mtype = get_pageblock_migratetype(page);
if (mtype < MIGRATE_TYPES)
return 0;
}
-const struct seq_operations fragmentation_op = {
+static const struct seq_operations fragmentation_op = {
.start = frag_start,
.next = frag_next,
.stop = frag_stop,
.show = frag_show,
};
-const struct seq_operations pagetypeinfo_op = {
+static int fragmentation_open(struct inode *inode, struct file *file)
+{
+ return seq_open(file, &fragmentation_op);
+}
+
+static const struct file_operations fragmentation_file_operations = {
+ .open = fragmentation_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release,
+};
+
+static const struct seq_operations pagetypeinfo_op = {
.start = frag_start,
.next = frag_next,
.stop = frag_stop,
.show = pagetypeinfo_show,
};
+static int pagetypeinfo_open(struct inode *inode, struct file *file)
+{
+ return seq_open(file, &pagetypeinfo_op);
+}
+
+static const struct file_operations pagetypeinfo_file_ops = {
+ .open = pagetypeinfo_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release,
+};
+
#ifdef CONFIG_ZONE_DMA
#define TEXT_FOR_DMA(xx) xx "_dma",
#else
"nr_active_anon",
"nr_inactive_file",
"nr_active_file",
+ "nr_unevictable",
+ "nr_mlock",
"nr_anon_pages",
"nr_mapped",
"nr_file_pages",
"nr_slab_reclaimable",
"nr_slab_unreclaimable",
"nr_page_table_pages",
+ "nr_kernel_stack",
"nr_unstable",
"nr_bounce",
"nr_vmscan_write",
"nr_writeback_temp",
-
+ "nr_isolated_anon",
+ "nr_isolated_file",
+ "nr_shmem",
#ifdef CONFIG_NUMA
"numa_hit",
"numa_miss",
TEXTS_FOR_ZONES("pgscan_kswapd")
TEXTS_FOR_ZONES("pgscan_direct")
+#ifdef CONFIG_NUMA
+ "zone_reclaim_failed",
+#endif
"pginodesteal",
"slabs_scanned",
"kswapd_steal",
"kswapd_inodesteal",
+ "kswapd_low_wmark_hit_quickly",
+ "kswapd_high_wmark_hit_quickly",
+ "kswapd_skip_congestion_wait",
"pageoutrun",
"allocstall",
"pgrotated",
+
+#ifdef CONFIG_COMPACTION
+ "compact_blocks_moved",
+ "compact_pages_moved",
+ "compact_pagemigrate_failed",
+ "compact_stall",
+ "compact_fail",
+ "compact_success",
+#endif
+
#ifdef CONFIG_HUGETLB_PAGE
"htlb_buddy_alloc_success",
"htlb_buddy_alloc_fail",
#endif
+ "unevictable_pgs_culled",
+ "unevictable_pgs_scanned",
+ "unevictable_pgs_rescued",
+ "unevictable_pgs_mlocked",
+ "unevictable_pgs_munlocked",
+ "unevictable_pgs_cleared",
+ "unevictable_pgs_stranded",
+ "unevictable_pgs_mlockfreed",
#endif
};
"\n min %lu"
"\n low %lu"
"\n high %lu"
- "\n scanned %lu (aa: %lu ia: %lu af: %lu if: %lu)"
+ "\n scanned %lu"
"\n spanned %lu"
"\n present %lu",
zone_page_state(zone, NR_FREE_PAGES),
- zone->pages_min,
- zone->pages_low,
- zone->pages_high,
+ min_wmark_pages(zone),
+ low_wmark_pages(zone),
+ high_wmark_pages(zone),
zone->pages_scanned,
- zone->lru[LRU_ACTIVE_ANON].nr_scan,
- zone->lru[LRU_INACTIVE_ANON].nr_scan,
- zone->lru[LRU_ACTIVE_FILE].nr_scan,
- zone->lru[LRU_INACTIVE_FILE].nr_scan,
zone->spanned_pages,
zone->present_pages);
for_each_online_cpu(i) {
struct per_cpu_pageset *pageset;
- pageset = zone_pcp(zone, i);
+ pageset = per_cpu_ptr(zone->pageset, i);
seq_printf(m,
"\n cpu: %i"
"\n count: %i"
seq_printf(m,
"\n all_unreclaimable: %u"
"\n prev_priority: %i"
- "\n start_pfn: %lu",
- zone_is_all_unreclaimable(zone),
+ "\n start_pfn: %lu"
+ "\n inactive_ratio: %u",
+ zone->all_unreclaimable,
zone->prev_priority,
- zone->zone_start_pfn);
+ zone->zone_start_pfn,
+ zone->inactive_ratio);
seq_putc(m, '\n');
}
return 0;
}
-const struct seq_operations zoneinfo_op = {
+static const struct seq_operations zoneinfo_op = {
.start = frag_start, /* iterate over all zones. The same as in
* fragmentation. */
.next = frag_next,
.show = zoneinfo_show,
};
+static int zoneinfo_open(struct inode *inode, struct file *file)
+{
+ return seq_open(file, &zoneinfo_op);
+}
+
+static const struct file_operations proc_zoneinfo_file_operations = {
+ .open = zoneinfo_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release,
+};
+
static void *vmstat_start(struct seq_file *m, loff_t *pos)
{
unsigned long *v;
m->private = NULL;
}
-const struct seq_operations vmstat_op = {
+static const struct seq_operations vmstat_op = {
.start = vmstat_start,
.next = vmstat_next,
.stop = vmstat_stop,
.show = vmstat_show,
};
+static int vmstat_open(struct inode *inode, struct file *file)
+{
+ return seq_open(file, &vmstat_op);
+}
+
+static const struct file_operations proc_vmstat_file_operations = {
+ .open = vmstat_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release,
+};
#endif /* CONFIG_PROC_FS */
#ifdef CONFIG_SMP
{
refresh_cpu_vm_stats(smp_processor_id());
schedule_delayed_work(&__get_cpu_var(vmstat_work),
- sysctl_stat_interval);
+ round_jiffies_relative(sysctl_stat_interval));
}
static void __cpuinit start_cpu_timer(int cpu)
{
- struct delayed_work *vmstat_work = &per_cpu(vmstat_work, cpu);
+ struct delayed_work *work = &per_cpu(vmstat_work, cpu);
- INIT_DELAYED_WORK_DEFERRABLE(vmstat_work, vmstat_update);
- schedule_delayed_work_on(cpu, vmstat_work, HZ + cpu);
+ INIT_DELAYED_WORK_DEFERRABLE(work, vmstat_update);
+ schedule_delayed_work_on(cpu, work, __round_jiffies_relative(HZ, cpu));
}
/*
case CPU_ONLINE:
case CPU_ONLINE_FROZEN:
start_cpu_timer(cpu);
+ node_set_state(cpu_to_node(cpu), N_CPU);
break;
case CPU_DOWN_PREPARE:
case CPU_DOWN_PREPARE_FROZEN:
static struct notifier_block __cpuinitdata vmstat_notifier =
{ &vmstat_cpuup_callback, NULL, 0 };
+#endif
static int __init setup_vmstat(void)
{
+#ifdef CONFIG_SMP
int cpu;
refresh_zone_stat_thresholds();
for_each_online_cpu(cpu)
start_cpu_timer(cpu);
+#endif
+#ifdef CONFIG_PROC_FS
+ proc_create("buddyinfo", S_IRUGO, NULL, &fragmentation_file_operations);
+ proc_create("pagetypeinfo", S_IRUGO, NULL, &pagetypeinfo_file_ops);
+ proc_create("vmstat", S_IRUGO, NULL, &proc_vmstat_file_operations);
+ proc_create("zoneinfo", S_IRUGO, NULL, &proc_zoneinfo_file_operations);
+#endif
return 0;
}
module_init(setup_vmstat)
+
+#if defined(CONFIG_DEBUG_FS) && defined(CONFIG_COMPACTION)
+#include <linux/debugfs.h>
+
+static struct dentry *extfrag_debug_root;
+
+/*
+ * Return an index indicating how much of the available free memory is
+ * unusable for an allocation of the requested size.
+ */
+static int unusable_free_index(unsigned int order,
+ struct contig_page_info *info)
+{
+ /* No free memory is interpreted as all free memory is unusable */
+ if (info->free_pages == 0)
+ return 1000;
+
+ /*
+ * Index should be a value between 0 and 1. Return a value to 3
+ * decimal places.
+ *
+ * 0 => no fragmentation
+ * 1 => high fragmentation
+ */
+ return div_u64((info->free_pages - (info->free_blocks_suitable << order)) * 1000ULL, info->free_pages);
+
+}
+
+static void unusable_show_print(struct seq_file *m,
+ pg_data_t *pgdat, struct zone *zone)
+{
+ unsigned int order;
+ int index;
+ struct contig_page_info info;
+
+ seq_printf(m, "Node %d, zone %8s ",
+ pgdat->node_id,
+ zone->name);
+ for (order = 0; order < MAX_ORDER; ++order) {
+ fill_contig_page_info(zone, order, &info);
+ index = unusable_free_index(order, &info);
+ seq_printf(m, "%d.%03d ", index / 1000, index % 1000);
+ }
+
+ seq_putc(m, '\n');
+}
+
+/*
+ * Display unusable free space index
+ *
+ * The unusable free space index measures how much of the available free
+ * memory cannot be used to satisfy an allocation of a given size and is a
+ * value between 0 and 1. The higher the value, the more of free memory is
+ * unusable and by implication, the worse the external fragmentation is. This
+ * can be expressed as a percentage by multiplying by 100.
+ */
+static int unusable_show(struct seq_file *m, void *arg)
+{
+ pg_data_t *pgdat = (pg_data_t *)arg;
+
+ /* check memoryless node */
+ if (!node_state(pgdat->node_id, N_HIGH_MEMORY))
+ return 0;
+
+ walk_zones_in_node(m, pgdat, unusable_show_print);
+
+ return 0;
+}
+
+static const struct seq_operations unusable_op = {
+ .start = frag_start,
+ .next = frag_next,
+ .stop = frag_stop,
+ .show = unusable_show,
+};
+
+static int unusable_open(struct inode *inode, struct file *file)
+{
+ return seq_open(file, &unusable_op);
+}
+
+static const struct file_operations unusable_file_ops = {
+ .open = unusable_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release,
+};
+
+static void extfrag_show_print(struct seq_file *m,
+ pg_data_t *pgdat, struct zone *zone)
+{
+ unsigned int order;
+ int index;
+
+ /* Alloc on stack as interrupts are disabled for zone walk */
+ struct contig_page_info info;
+
+ seq_printf(m, "Node %d, zone %8s ",
+ pgdat->node_id,
+ zone->name);
+ for (order = 0; order < MAX_ORDER; ++order) {
+ fill_contig_page_info(zone, order, &info);
+ index = __fragmentation_index(order, &info);
+ seq_printf(m, "%d.%03d ", index / 1000, index % 1000);
+ }
+
+ seq_putc(m, '\n');
+}
+
+/*
+ * Display fragmentation index for orders that allocations would fail for
+ */
+static int extfrag_show(struct seq_file *m, void *arg)
+{
+ pg_data_t *pgdat = (pg_data_t *)arg;
+
+ walk_zones_in_node(m, pgdat, extfrag_show_print);
+
+ return 0;
+}
+
+static const struct seq_operations extfrag_op = {
+ .start = frag_start,
+ .next = frag_next,
+ .stop = frag_stop,
+ .show = extfrag_show,
+};
+
+static int extfrag_open(struct inode *inode, struct file *file)
+{
+ return seq_open(file, &extfrag_op);
+}
+
+static const struct file_operations extfrag_file_ops = {
+ .open = extfrag_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release,
+};
+
+static int __init extfrag_debug_init(void)
+{
+ extfrag_debug_root = debugfs_create_dir("extfrag", NULL);
+ if (!extfrag_debug_root)
+ return -ENOMEM;
+
+ if (!debugfs_create_file("unusable_index", 0444,
+ extfrag_debug_root, NULL, &unusable_file_ops))
+ return -ENOMEM;
+
+ if (!debugfs_create_file("extfrag_index", 0444,
+ extfrag_debug_root, NULL, &extfrag_file_ops))
+ return -ENOMEM;
+
+ return 0;
+}
+
+module_init(extfrag_debug_init);
#endif