X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=mm%2Fvmstat.c;h=6051fbab67ba26533594103c62790f779cd21c08;hb=e7b184f199fd3c80b618ec8244cbda70857d2779;hp=210f9bbbb04f4661bf1d2169c288a479488ab57c;hpb=2244b95a7bcf8d24196f8a3a44187ba5dfff754c;p=safe%2Fjmp%2Flinux-2.6 diff --git a/mm/vmstat.c b/mm/vmstat.c index 210f9bb..6051fba 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -8,145 +8,66 @@ * Copyright (C) 2006 Silicon Graphics, Inc., * Christoph Lameter */ - -#include +#include #include +#include #include +#include +#include +#include -/* - * Accumulate the page_state information across all CPUs. - * The result is unavoidably approximate - it can change - * during and after execution of this function. - */ -DEFINE_PER_CPU(struct page_state, page_states) = {0}; - -atomic_t nr_pagecache = ATOMIC_INIT(0); -EXPORT_SYMBOL(nr_pagecache); -#ifdef CONFIG_SMP -DEFINE_PER_CPU(long, nr_pagecache_local) = 0; -#endif +#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 __get_page_state(struct page_state *ret, int nr, cpumask_t *cpumask) +static void sum_vm_events(unsigned long *ret, const struct cpumask *cpumask) { - unsigned cpu; - - memset(ret, 0, nr * sizeof(unsigned long)); - cpus_and(*cpumask, *cpumask, cpu_online_map); - - for_each_cpu_mask(cpu, *cpumask) { - unsigned long *in; - unsigned long *out; - unsigned off; - unsigned next_cpu; - - in = (unsigned long *)&per_cpu(page_states, cpu); - - next_cpu = next_cpu(cpu, *cpumask); - if (likely(next_cpu < NR_CPUS)) - prefetch(&per_cpu(page_states, next_cpu)); - - out = (unsigned long *)ret; - for (off = 0; off < nr; off++) - *out++ += *in++; - } -} - -void get_page_state_node(struct page_state *ret, int node) -{ - int nr; - cpumask_t mask = node_to_cpumask(node); - - nr = offsetof(struct page_state, GET_PAGE_STATE_LAST); - nr /= sizeof(unsigned long); - - __get_page_state(ret, nr+1, &mask); -} - -void get_page_state(struct page_state *ret) -{ - int nr; - cpumask_t mask = CPU_MASK_ALL; - - nr = offsetof(struct page_state, GET_PAGE_STATE_LAST); - nr /= sizeof(unsigned long); - - __get_page_state(ret, nr + 1, &mask); -} - -void get_full_page_state(struct page_state *ret) -{ - cpumask_t mask = CPU_MASK_ALL; - - __get_page_state(ret, sizeof(*ret) / sizeof(unsigned long), &mask); -} - -unsigned long read_page_state_offset(unsigned long offset) -{ - unsigned long ret = 0; int cpu; + int i; - for_each_online_cpu(cpu) { - unsigned long in; + memset(ret, 0, NR_VM_EVENT_ITEMS * sizeof(unsigned long)); - in = (unsigned long)&per_cpu(page_states, cpu) + offset; - ret += *((unsigned long *)in); - } - return ret; -} - -void __mod_page_state_offset(unsigned long offset, unsigned long delta) -{ - void *ptr; + for_each_cpu(cpu, cpumask) { + struct vm_event_state *this = &per_cpu(vm_event_states, cpu); - ptr = &__get_cpu_var(page_states); - *(unsigned long *)(ptr + offset) += delta; + for (i = 0; i < NR_VM_EVENT_ITEMS; i++) + ret[i] += this->event[i]; + } } -EXPORT_SYMBOL(__mod_page_state_offset); -void mod_page_state_offset(unsigned long offset, unsigned long delta) +/* + * Accumulate the vm event counters across all CPUs. + * The result is unavoidably approximate - it can change + * during and after execution of this function. +*/ +void all_vm_events(unsigned long *ret) { - unsigned long flags; - void *ptr; - - local_irq_save(flags); - ptr = &__get_cpu_var(page_states); - *(unsigned long *)(ptr + offset) += delta; - local_irq_restore(flags); + get_online_cpus(); + sum_vm_events(ret, cpu_online_mask); + put_online_cpus(); } -EXPORT_SYMBOL(mod_page_state_offset); +EXPORT_SYMBOL_GPL(all_vm_events); -void __get_zone_counts(unsigned long *active, unsigned long *inactive, - unsigned long *free, struct pglist_data *pgdat) +#ifdef CONFIG_HOTPLUG +/* + * Fold the foreign cpu events into our own. + * + * This is adding to the events on one processor + * but keeps the global counts constant. + */ +void vm_events_fold_cpu(int cpu) { - struct zone *zones = pgdat->node_zones; + struct vm_event_state *fold_state = &per_cpu(vm_event_states, cpu); int i; - *active = 0; - *inactive = 0; - *free = 0; - for (i = 0; i < MAX_NR_ZONES; i++) { - *active += zones[i].nr_active; - *inactive += zones[i].nr_inactive; - *free += zones[i].free_pages; + for (i = 0; i < NR_VM_EVENT_ITEMS; i++) { + count_vm_events(i, fold_state->event[i]); + fold_state->event[i] = 0; } } +#endif /* CONFIG_HOTPLUG */ -void get_zone_counts(unsigned long *active, - unsigned long *inactive, unsigned long *free) -{ - struct pglist_data *pgdat; - - *active = 0; - *inactive = 0; - *free = 0; - for_each_online_pgdat(pgdat) { - unsigned long l, m, n; - __get_zone_counts(&l, &m, &n, pgdat); - *active += l; - *inactive += m; - *free += n; - } -} +#endif /* CONFIG_VM_EVENT_COUNTERS */ /* * Manage combined zone based / global counters @@ -158,17 +79,68 @@ EXPORT_SYMBOL(vm_stat); #ifdef CONFIG_SMP -#define STAT_THRESHOLD 32 +static int calculate_threshold(struct zone *zone) +{ + int threshold; + int mem; /* memory in 128 MB units */ + + /* + * The threshold scales with the number of processors and the amount + * of memory per zone. More memory means that we can defer updates for + * longer, more processors could lead to more contention. + * fls() is used to have a cheap way of logarithmic scaling. + * + * Some sample thresholds: + * + * Threshold Processors (fls) Zonesize fls(mem+1) + * ------------------------------------------------------------------ + * 8 1 1 0.9-1 GB 4 + * 16 2 2 0.9-1 GB 4 + * 20 2 2 1-2 GB 5 + * 24 2 2 2-4 GB 6 + * 28 2 2 4-8 GB 7 + * 32 2 2 8-16 GB 8 + * 4 2 2 <128M 1 + * 30 4 3 2-4 GB 5 + * 48 4 3 8-16 GB 8 + * 32 8 4 1-2 GB 4 + * 32 8 4 0.9-1GB 4 + * 10 16 5 <128M 1 + * 40 16 5 900M 4 + * 70 64 7 2-4 GB 5 + * 84 64 7 4-8 GB 6 + * 108 512 9 4-8 GB 6 + * 125 1024 10 8-16 GB 8 + * 125 1024 10 16-32 GB 9 + */ + + mem = zone->present_pages >> (27 - PAGE_SHIFT); + + threshold = 2 * fls(num_online_cpus()) * (1 + fls(mem)); + + /* + * Maximum threshold is 125 + */ + threshold = min(125, threshold); + + return threshold; +} /* - * Determine pointer to currently valid differential byte given a zone and - * the item number. - * - * Preemption must be off + * Refresh the thresholds for each zone. */ -static inline s8 *diff_pointer(struct zone *zone, enum zone_stat_item item) +static void refresh_zone_stat_thresholds(void) { - return &zone_pcp(zone, smp_processor_id())->vm_stat_diff[item]; + struct zone *zone; + int cpu; + int threshold; + + for_each_populated_zone(zone) { + threshold = calculate_threshold(zone); + + for_each_online_cpu(cpu) + zone_pcp(zone, cpu)->stat_threshold = threshold; + } } /* @@ -177,17 +149,16 @@ static inline s8 *diff_pointer(struct zone *zone, enum zone_stat_item item) void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item, int delta) { - s8 *p; + struct per_cpu_pageset *pcp = zone_pcp(zone, smp_processor_id()); + s8 *p = pcp->vm_stat_diff + item; long x; - p = diff_pointer(zone, item); x = delta + *p; - if (unlikely(x > STAT_THRESHOLD || x < -STAT_THRESHOLD)) { + if (unlikely(x > pcp->stat_threshold || x < -pcp->stat_threshold)) { zone_page_state_add(x, zone, item); x = 0; } - *p = x; } EXPORT_SYMBOL(__mod_zone_page_state); @@ -216,10 +187,12 @@ EXPORT_SYMBOL(mod_zone_page_state); * No overflow check is necessary and therefore the differential can be * incremented or decremented in place which may allow the compilers to * generate better code. - * * The increment or decrement is known and therefore one boundary check can * be omitted. * + * NOTE: These functions are very performance sensitive. Change only + * with care. + * * Some processors have inc/dec instructions that are atomic vs an interrupt. * However, the code must first determine the differential location in a zone * based on the processor number and then inc/dec the counter. There is no @@ -227,50 +200,65 @@ EXPORT_SYMBOL(mod_zone_page_state); * in between and therefore the atomicity vs. interrupt cannot be exploited * in a useful way here. */ -void __inc_zone_page_state(struct page *page, enum zone_stat_item item) +void __inc_zone_state(struct zone *zone, enum zone_stat_item item) { - struct zone *zone = page_zone(page); - s8 *p = diff_pointer(zone, item); + struct per_cpu_pageset *pcp = zone_pcp(zone, smp_processor_id()); + s8 *p = pcp->vm_stat_diff + item; (*p)++; - if (unlikely(*p > STAT_THRESHOLD)) { - zone_page_state_add(*p, zone, item); - *p = 0; + if (unlikely(*p > pcp->stat_threshold)) { + int overstep = pcp->stat_threshold / 2; + + zone_page_state_add(*p + overstep, zone, item); + *p = -overstep; } } + +void __inc_zone_page_state(struct page *page, enum zone_stat_item item) +{ + __inc_zone_state(page_zone(page), item); +} EXPORT_SYMBOL(__inc_zone_page_state); -void __dec_zone_page_state(struct page *page, enum zone_stat_item item) +void __dec_zone_state(struct zone *zone, enum zone_stat_item item) { - struct zone *zone = page_zone(page); - s8 *p = diff_pointer(zone, item); + struct per_cpu_pageset *pcp = zone_pcp(zone, smp_processor_id()); + s8 *p = pcp->vm_stat_diff + item; (*p)--; - if (unlikely(*p < -STAT_THRESHOLD)) { - zone_page_state_add(*p, zone, item); - *p = 0; + if (unlikely(*p < - pcp->stat_threshold)) { + int overstep = pcp->stat_threshold / 2; + + zone_page_state_add(*p - overstep, zone, item); + *p = overstep; } } + +void __dec_zone_page_state(struct page *page, enum zone_stat_item item) +{ + __dec_zone_state(page_zone(page), item); +} EXPORT_SYMBOL(__dec_zone_page_state); +void inc_zone_state(struct zone *zone, enum zone_stat_item item) +{ + unsigned long flags; + + local_irq_save(flags); + __inc_zone_state(zone, item); + local_irq_restore(flags); +} + void inc_zone_page_state(struct page *page, enum zone_stat_item item) { unsigned long flags; struct zone *zone; - s8 *p; zone = page_zone(page); local_irq_save(flags); - p = diff_pointer(zone, item); - - (*p)++; - - if (unlikely(*p > STAT_THRESHOLD)) { - zone_page_state_add(*p, zone, item); - *p = 0; - } + __inc_zone_state(zone, item); local_irq_restore(flags); } EXPORT_SYMBOL(inc_zone_page_state); @@ -278,71 +266,128 @@ EXPORT_SYMBOL(inc_zone_page_state); void dec_zone_page_state(struct page *page, enum zone_stat_item item) { unsigned long flags; - struct zone *zone; - s8 *p; - zone = page_zone(page); local_irq_save(flags); - p = diff_pointer(zone, item); - - (*p)--; - - if (unlikely(*p < -STAT_THRESHOLD)) { - zone_page_state_add(*p, zone, item); - *p = 0; - } + __dec_zone_page_state(page, item); local_irq_restore(flags); } EXPORT_SYMBOL(dec_zone_page_state); /* * Update the zone counters for one cpu. + * + * The cpu specified must be either the current cpu or a processor that + * is not online. If it is the current cpu then the execution thread must + * be pinned to the current cpu. + * + * Note that refresh_cpu_vm_stats strives to only access + * node local memory. The per cpu pagesets on remote zones are placed + * in the memory local to the processor using that pageset. So the + * loop over all zones will access a series of cachelines local to + * the processor. + * + * The call to zone_page_state_add updates the cachelines with the + * statistics in the remote zone struct as well as the global cachelines + * with the global counters. These could cause remote node cache line + * bouncing and will have to be only done when necessary. */ void refresh_cpu_vm_stats(int cpu) { struct zone *zone; int i; - unsigned long flags; + int global_diff[NR_VM_ZONE_STAT_ITEMS] = { 0, }; - for_each_zone(zone) { - struct per_cpu_pageset *pcp; + for_each_populated_zone(zone) { + struct per_cpu_pageset *p; - pcp = zone_pcp(zone, cpu); + p = zone_pcp(zone, cpu); for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) - if (pcp->vm_stat_diff[i]) { + if (p->vm_stat_diff[i]) { + unsigned long flags; + int v; + local_irq_save(flags); - zone_page_state_add(pcp->vm_stat_diff[i], - zone, i); - pcp->vm_stat_diff[i] = 0; + v = p->vm_stat_diff[i]; + p->vm_stat_diff[i] = 0; local_irq_restore(flags); + atomic_long_add(v, &zone->vm_stat[i]); + global_diff[i] += v; +#ifdef CONFIG_NUMA + /* 3 seconds idle till flush */ + p->expire = 3; +#endif } + cond_resched(); +#ifdef CONFIG_NUMA + /* + * Deal with draining the remote pageset of this + * processor + * + * Check if there are pages remaining in this pageset + * if not then there is nothing to expire. + */ + if (!p->expire || !p->pcp.count) + continue; + + /* + * We never drain zones local to this processor. + */ + if (zone_to_nid(zone) == numa_node_id()) { + p->expire = 0; + continue; + } + + p->expire--; + if (p->expire) + continue; + + if (p->pcp.count) + drain_zone_pages(zone, &p->pcp); +#endif } -} -static void __refresh_cpu_vm_stats(void *dummy) -{ - refresh_cpu_vm_stats(smp_processor_id()); + for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) + if (global_diff[i]) + atomic_long_add(global_diff[i], &vm_stat[i]); } +#endif + +#ifdef CONFIG_NUMA /* - * Consolidate all counters. + * zonelist = the list of zones passed to the allocator + * z = the zone from which the allocation occurred. * - * Note that the result is less inaccurate but still inaccurate - * if concurrent processes are allowed to run. + * Must be called with interrupts disabled. */ -void refresh_vm_stats(void) +void zone_statistics(struct zone *preferred_zone, struct zone *z) { - on_each_cpu(__refresh_cpu_vm_stats, NULL, 0, 1); + if (z->zone_pgdat == preferred_zone->zone_pgdat) { + __inc_zone_state(z, NUMA_HIT); + } else { + __inc_zone_state(z, NUMA_MISS); + __inc_zone_state(preferred_zone, NUMA_FOREIGN); + } + if (z->node == numa_node_id()) + __inc_zone_state(z, NUMA_LOCAL); + else + __inc_zone_state(z, NUMA_OTHER); } -EXPORT_SYMBOL(refresh_vm_stats); - #endif #ifdef CONFIG_PROC_FS - +#include #include +static char * const migratetype_names[MIGRATE_TYPES] = { + "Unmovable", + "Reclaimable", + "Movable", + "Reserve", + "Isolate", +}; + static void *frag_start(struct seq_file *m, loff_t *pos) { pg_data_t *pgdat; @@ -367,58 +412,257 @@ static void frag_stop(struct seq_file *m, void *arg) { } -/* - * This walks the free areas for each zone. - */ -static int frag_show(struct seq_file *m, void *arg) +/* Walk all the zones in a node and print using a callback */ +static void walk_zones_in_node(struct seq_file *m, pg_data_t *pgdat, + void (*print)(struct seq_file *m, pg_data_t *, struct zone *)) { - pg_data_t *pgdat = (pg_data_t *)arg; struct zone *zone; struct zone *node_zones = pgdat->node_zones; unsigned long flags; - int order; for (zone = node_zones; zone - node_zones < MAX_NR_ZONES; ++zone) { if (!populated_zone(zone)) continue; spin_lock_irqsave(&zone->lock, flags); - seq_printf(m, "Node %d, zone %8s ", pgdat->node_id, zone->name); - for (order = 0; order < MAX_ORDER; ++order) - seq_printf(m, "%6lu ", zone->free_area[order].nr_free); + print(m, pgdat, zone); spin_unlock_irqrestore(&zone->lock, flags); + } +} + +static void frag_show_print(struct seq_file *m, pg_data_t *pgdat, + struct zone *zone) +{ + int order; + + seq_printf(m, "Node %d, zone %8s ", pgdat->node_id, zone->name); + for (order = 0; order < MAX_ORDER; ++order) + seq_printf(m, "%6lu ", zone->free_area[order].nr_free); + seq_putc(m, '\n'); +} + +/* + * This walks the free areas for each zone. + */ +static int frag_show(struct seq_file *m, void *arg) +{ + pg_data_t *pgdat = (pg_data_t *)arg; + walk_zones_in_node(m, pgdat, frag_show_print); + return 0; +} + +static void pagetypeinfo_showfree_print(struct seq_file *m, + pg_data_t *pgdat, struct zone *zone) +{ + int order, mtype; + + for (mtype = 0; mtype < MIGRATE_TYPES; mtype++) { + seq_printf(m, "Node %4d, zone %8s, type %12s ", + pgdat->node_id, + zone->name, + migratetype_names[mtype]); + for (order = 0; order < MAX_ORDER; ++order) { + unsigned long freecount = 0; + struct free_area *area; + struct list_head *curr; + + area = &(zone->free_area[order]); + + list_for_each(curr, &area->free_list[mtype]) + freecount++; + seq_printf(m, "%6lu ", freecount); + } seq_putc(m, '\n'); } +} + +/* Print out the free pages at each order for each migatetype */ +static int pagetypeinfo_showfree(struct seq_file *m, void *arg) +{ + int order; + pg_data_t *pgdat = (pg_data_t *)arg; + + /* Print header */ + seq_printf(m, "%-43s ", "Free pages count per migrate type at order"); + for (order = 0; order < MAX_ORDER; ++order) + seq_printf(m, "%6d ", order); + seq_putc(m, '\n'); + + walk_zones_in_node(m, pgdat, pagetypeinfo_showfree_print); + return 0; } -struct seq_operations fragmentation_op = { +static void pagetypeinfo_showblockcount_print(struct seq_file *m, + pg_data_t *pgdat, struct zone *zone) +{ + int mtype; + unsigned long pfn; + unsigned long start_pfn = zone->zone_start_pfn; + unsigned long end_pfn = start_pfn + zone->spanned_pages; + unsigned long count[MIGRATE_TYPES] = { 0, }; + + for (pfn = start_pfn; pfn < end_pfn; pfn += pageblock_nr_pages) { + struct page *page; + + if (!pfn_valid(pfn)) + continue; + + page = pfn_to_page(pfn); + + /* Watch for unexpected holes punched in the memmap */ + if (!memmap_valid_within(pfn, page, zone)) + continue; + + mtype = get_pageblock_migratetype(page); + + if (mtype < MIGRATE_TYPES) + count[mtype]++; + } + + /* Print counts */ + seq_printf(m, "Node %d, zone %8s ", pgdat->node_id, zone->name); + for (mtype = 0; mtype < MIGRATE_TYPES; mtype++) + seq_printf(m, "%12lu ", count[mtype]); + seq_putc(m, '\n'); +} + +/* Print out the free pages at each order for each migratetype */ +static int pagetypeinfo_showblockcount(struct seq_file *m, void *arg) +{ + int mtype; + pg_data_t *pgdat = (pg_data_t *)arg; + + seq_printf(m, "\n%-23s", "Number of blocks type "); + for (mtype = 0; mtype < MIGRATE_TYPES; mtype++) + seq_printf(m, "%12s ", migratetype_names[mtype]); + seq_putc(m, '\n'); + walk_zones_in_node(m, pgdat, pagetypeinfo_showblockcount_print); + + return 0; +} + +/* + * This prints out statistics in relation to grouping pages by mobility. + * It is expensive to collect so do not constantly read the file. + */ +static int pagetypeinfo_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; + + seq_printf(m, "Page block order: %d\n", pageblock_order); + seq_printf(m, "Pages per block: %lu\n", pageblock_nr_pages); + seq_putc(m, '\n'); + pagetypeinfo_showfree(m, pgdat); + pagetypeinfo_showblockcount(m, pgdat); + + return 0; +} + +static const struct seq_operations fragmentation_op = { .start = frag_start, .next = frag_next, .stop = frag_stop, .show = frag_show, }; -static char *vmstat_text[] = { - /* Zoned VM counters */ +static int fragmentation_open(struct inode *inode, struct file *file) +{ + return seq_open(file, &fragmentation_op); +} - /* Page state */ +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 +#define TEXT_FOR_DMA(xx) +#endif + +#ifdef CONFIG_ZONE_DMA32 +#define TEXT_FOR_DMA32(xx) xx "_dma32", +#else +#define TEXT_FOR_DMA32(xx) +#endif + +#ifdef CONFIG_HIGHMEM +#define TEXT_FOR_HIGHMEM(xx) xx "_high", +#else +#define TEXT_FOR_HIGHMEM(xx) +#endif + +#define TEXTS_FOR_ZONES(xx) TEXT_FOR_DMA(xx) TEXT_FOR_DMA32(xx) xx "_normal", \ + TEXT_FOR_HIGHMEM(xx) xx "_movable", + +static const char * const vmstat_text[] = { + /* Zoned VM counters */ + "nr_free_pages", + "nr_inactive_anon", + "nr_active_anon", + "nr_inactive_file", + "nr_active_file", + "nr_unevictable", + "nr_mlock", + "nr_anon_pages", + "nr_mapped", + "nr_file_pages", "nr_dirty", "nr_writeback", - "nr_unstable", + "nr_slab_reclaimable", + "nr_slab_unreclaimable", "nr_page_table_pages", - "nr_mapped", - "nr_slab", + "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", + "numa_foreign", + "numa_interleave", + "numa_local", + "numa_other", +#endif +#ifdef CONFIG_VM_EVENT_COUNTERS "pgpgin", "pgpgout", "pswpin", "pswpout", - "pgalloc_high", - "pgalloc_normal", - "pgalloc_dma32", - "pgalloc_dma", + TEXTS_FOR_ZONES("pgalloc") "pgfree", "pgactivate", @@ -427,142 +671,114 @@ static char *vmstat_text[] = { "pgfault", "pgmajfault", - "pgrefill_high", - "pgrefill_normal", - "pgrefill_dma32", - "pgrefill_dma", - - "pgsteal_high", - "pgsteal_normal", - "pgsteal_dma32", - "pgsteal_dma", - - "pgscan_kswapd_high", - "pgscan_kswapd_normal", - "pgscan_kswapd_dma32", - "pgscan_kswapd_dma", - - "pgscan_direct_high", - "pgscan_direct_normal", - "pgscan_direct_dma32", - "pgscan_direct_dma", + TEXTS_FOR_ZONES("pgrefill") + TEXTS_FOR_ZONES("pgsteal") + 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", - "nr_bounce", +#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 }; -/* - * Output information about zones in @pgdat. - */ -static int zoneinfo_show(struct seq_file *m, void *arg) +static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat, + struct zone *zone) { - pg_data_t *pgdat = arg; - struct zone *zone; - struct zone *node_zones = pgdat->node_zones; - unsigned long flags; - - for (zone = node_zones; zone - node_zones < MAX_NR_ZONES; zone++) { - int i; - - if (!populated_zone(zone)) - continue; - - spin_lock_irqsave(&zone->lock, flags); - seq_printf(m, "Node %d, zone %8s", pgdat->node_id, zone->name); - seq_printf(m, - "\n pages free %lu" - "\n min %lu" - "\n low %lu" - "\n high %lu" - "\n active %lu" - "\n inactive %lu" - "\n scanned %lu (a: %lu i: %lu)" - "\n spanned %lu" - "\n present %lu", - zone->free_pages, - zone->pages_min, - zone->pages_low, - zone->pages_high, - zone->nr_active, - zone->nr_inactive, - zone->pages_scanned, - zone->nr_scan_active, zone->nr_scan_inactive, - zone->spanned_pages, - zone->present_pages); - - for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) - seq_printf(m, "\n %-12s %lu", vmstat_text[i], - zone_page_state(zone, i)); + int i; + seq_printf(m, "Node %d, zone %8s", pgdat->node_id, zone->name); + seq_printf(m, + "\n pages free %lu" + "\n min %lu" + "\n low %lu" + "\n high %lu" + "\n scanned %lu" + "\n spanned %lu" + "\n present %lu", + zone_page_state(zone, NR_FREE_PAGES), + min_wmark_pages(zone), + low_wmark_pages(zone), + high_wmark_pages(zone), + zone->pages_scanned, + zone->spanned_pages, + zone->present_pages); + for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) + seq_printf(m, "\n %-12s %lu", vmstat_text[i], + zone_page_state(zone, i)); + + seq_printf(m, + "\n protection: (%lu", + zone->lowmem_reserve[0]); + for (i = 1; i < ARRAY_SIZE(zone->lowmem_reserve); i++) + seq_printf(m, ", %lu", zone->lowmem_reserve[i]); + seq_printf(m, + ")" + "\n pagesets"); + for_each_online_cpu(i) { + struct per_cpu_pageset *pageset; + + pageset = zone_pcp(zone, i); seq_printf(m, - "\n protection: (%lu", - zone->lowmem_reserve[0]); - for (i = 1; i < ARRAY_SIZE(zone->lowmem_reserve); i++) - seq_printf(m, ", %lu", zone->lowmem_reserve[i]); - seq_printf(m, - ")" - "\n pagesets"); - for_each_online_cpu(i) { - struct per_cpu_pageset *pageset; - int j; - - pageset = zone_pcp(zone, i); - for (j = 0; j < ARRAY_SIZE(pageset->pcp); j++) { - if (pageset->pcp[j].count) - break; - } - if (j == ARRAY_SIZE(pageset->pcp)) - continue; - for (j = 0; j < ARRAY_SIZE(pageset->pcp); j++) { - seq_printf(m, - "\n cpu: %i pcp: %i" - "\n count: %i" - "\n high: %i" - "\n batch: %i", - i, j, - pageset->pcp[j].count, - pageset->pcp[j].high, - pageset->pcp[j].batch); - } -#ifdef CONFIG_NUMA - seq_printf(m, - "\n numa_hit: %lu" - "\n numa_miss: %lu" - "\n numa_foreign: %lu" - "\n interleave_hit: %lu" - "\n local_node: %lu" - "\n other_node: %lu", - pageset->numa_hit, - pageset->numa_miss, - pageset->numa_foreign, - pageset->interleave_hit, - pageset->local_node, - pageset->other_node); + "\n cpu: %i" + "\n count: %i" + "\n high: %i" + "\n batch: %i", + i, + pageset->pcp.count, + pageset->pcp.high, + pageset->pcp.batch); +#ifdef CONFIG_SMP + seq_printf(m, "\n vm stats threshold: %d", + pageset->stat_threshold); #endif - } - seq_printf(m, - "\n all_unreclaimable: %u" - "\n prev_priority: %i" - "\n temp_priority: %i" - "\n start_pfn: %lu", - zone->all_unreclaimable, - zone->prev_priority, - zone->temp_priority, - zone->zone_start_pfn); - spin_unlock_irqrestore(&zone->lock, flags); - seq_putc(m, '\n'); } + seq_printf(m, + "\n all_unreclaimable: %u" + "\n prev_priority: %i" + "\n start_pfn: %lu" + "\n inactive_ratio: %u", + zone_is_all_unreclaimable(zone), + zone->prev_priority, + zone->zone_start_pfn, + zone->inactive_ratio); + seq_putc(m, '\n'); +} + +/* + * Output information about zones in @pgdat. + */ +static int zoneinfo_show(struct seq_file *m, void *arg) +{ + pg_data_t *pgdat = (pg_data_t *)arg; + walk_zones_in_node(m, pgdat, zoneinfo_show_print); return 0; } -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, @@ -570,26 +786,47 @@ struct seq_operations zoneinfo_op = { .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; - struct page_state *ps; +#ifdef CONFIG_VM_EVENT_COUNTERS + unsigned long *e; +#endif int i; if (*pos >= ARRAY_SIZE(vmstat_text)) return NULL; +#ifdef CONFIG_VM_EVENT_COUNTERS v = kmalloc(NR_VM_ZONE_STAT_ITEMS * sizeof(unsigned long) - + sizeof(*ps), GFP_KERNEL); + + sizeof(struct vm_event_state), GFP_KERNEL); +#else + v = kmalloc(NR_VM_ZONE_STAT_ITEMS * sizeof(unsigned long), + GFP_KERNEL); +#endif m->private = v; if (!v) return ERR_PTR(-ENOMEM); for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) v[i] = global_page_state(i); - ps = (struct page_state *)(v + NR_VM_ZONE_STAT_ITEMS); - get_full_page_state(ps); - ps->pgpgin /= 2; /* sectors -> kbytes */ - ps->pgpgout /= 2; +#ifdef CONFIG_VM_EVENT_COUNTERS + e = v + NR_VM_ZONE_STAT_ITEMS; + all_vm_events(e); + e[PGPGIN] /= 2; /* sectors -> kbytes */ + e[PGPGOUT] /= 2; +#endif return v + *pos; } @@ -616,12 +853,100 @@ static void vmstat_stop(struct seq_file *m, void *arg) m->private = NULL; } -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 +static DEFINE_PER_CPU(struct delayed_work, vmstat_work); +int sysctl_stat_interval __read_mostly = HZ; + +static void vmstat_update(struct work_struct *w) +{ + refresh_cpu_vm_stats(smp_processor_id()); + schedule_delayed_work(&__get_cpu_var(vmstat_work), + round_jiffies_relative(sysctl_stat_interval)); +} + +static void __cpuinit start_cpu_timer(int cpu) +{ + struct delayed_work *work = &per_cpu(vmstat_work, cpu); + + INIT_DELAYED_WORK_DEFERRABLE(work, vmstat_update); + schedule_delayed_work_on(cpu, work, __round_jiffies_relative(HZ, cpu)); +} + +/* + * Use the cpu notifier to insure that the thresholds are recalculated + * when necessary. + */ +static int __cpuinit vmstat_cpuup_callback(struct notifier_block *nfb, + unsigned long action, + void *hcpu) +{ + long cpu = (long)hcpu; + + switch (action) { + case CPU_ONLINE: + case CPU_ONLINE_FROZEN: + start_cpu_timer(cpu); + break; + case CPU_DOWN_PREPARE: + case CPU_DOWN_PREPARE_FROZEN: + cancel_rearming_delayed_work(&per_cpu(vmstat_work, cpu)); + per_cpu(vmstat_work, cpu).work.func = NULL; + break; + case CPU_DOWN_FAILED: + case CPU_DOWN_FAILED_FROZEN: + start_cpu_timer(cpu); + break; + case CPU_DEAD: + case CPU_DEAD_FROZEN: + refresh_zone_stat_thresholds(); + break; + default: + break; + } + return NOTIFY_OK; +} + +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(); + register_cpu_notifier(&vmstat_notifier); + + 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)