X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=mm%2Fvmstat.c;h=dad2327e45804e16a8ff07564a80eb0cac79f482;hb=8d69aaee80c123b460918816cbfa2e83224c3646;hp=fadf791cd7e6828e3a778f7e636786a4dd6c2cbd;hpb=2a1e274acf0b1c192face19a4be7c12d4503eaaf;p=safe%2Fjmp%2Flinux-2.6 diff --git a/mm/vmstat.c b/mm/vmstat.c index fadf791..dad2327 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -8,33 +8,28 @@ * Copyright (C) 2006 Silicon Graphics, Inc., * Christoph Lameter */ - +#include #include +#include #include #include +#include #include #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 = 0; + int cpu; int i; memset(ret, 0, NR_VM_EVENT_ITEMS * sizeof(unsigned long)); - cpu = first_cpu(*cpumask); - while (cpu < NR_CPUS) { + for_each_cpu(cpu, cpumask) { struct vm_event_state *this = &per_cpu(vm_event_states, cpu); - cpu = next_cpu(cpu, *cpumask); - - if (cpu < NR_CPUS) - prefetch(&per_cpu(vm_event_states, cpu)); - - for (i = 0; i < NR_VM_EVENT_ITEMS; i++) ret[i] += this->event[i]; } @@ -47,7 +42,9 @@ static void sum_vm_events(unsigned long *ret, cpumask_t *cpumask) */ void all_vm_events(unsigned long *ret) { - sum_vm_events(ret, &cpu_online_map); + get_online_cpus(); + sum_vm_events(ret, cpu_online_mask); + put_online_cpus(); } EXPORT_SYMBOL_GPL(all_vm_events); @@ -138,11 +135,7 @@ static void refresh_zone_stat_thresholds(void) 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) @@ -283,6 +276,10 @@ 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 @@ -298,28 +295,30 @@ 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) { + for_each_populated_zone(zone) { struct per_cpu_pageset *p; - if (!populated_zone(zone)) - continue; - p = zone_pcp(zone, cpu); for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) if (p->vm_stat_diff[i]) { + unsigned long flags; + int v; + local_irq_save(flags); - zone_page_state_add(p->vm_stat_diff[i], - zone, i); + 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 - local_irq_restore(flags); } + cond_resched(); #ifdef CONFIG_NUMA /* * Deal with draining the remote pageset of this @@ -328,7 +327,7 @@ void refresh_cpu_vm_stats(int cpu) * Check if there are pages remaining in this pageset * if not then there is nothing to expire. */ - if (!p->expire || (!p->pcp[0].count && !p->pcp[1].count)) + if (!p->expire || !p->pcp.count) continue; /* @@ -343,31 +342,15 @@ void refresh_cpu_vm_stats(int cpu) if (p->expire) continue; - if (p->pcp[0].count) - drain_zone_pages(zone, p->pcp + 0); - - if (p->pcp[1].count) - drain_zone_pages(zone, p->pcp + 1); + 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()); -} -/* - * Consolidate all counters. - * - * Note that the result is less inaccurate but still inaccurate - * if concurrent processes are allowed to run. - */ -void refresh_vm_stats(void) -{ - on_each_cpu(__refresh_cpu_vm_stats, NULL, 0, 1); + for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) + if (global_diff[i]) + atomic_long_add(global_diff[i], &vm_stat[i]); } -EXPORT_SYMBOL(refresh_vm_stats); #endif @@ -378,13 +361,13 @@ EXPORT_SYMBOL(refresh_vm_stats); * * Must be called with interrupts disabled. */ -void zone_statistics(struct zonelist *zonelist, struct zone *z) +void zone_statistics(struct zone *preferred_zone, struct zone *z) { - if (z->zone_pgdat == zonelist->zones[0]->zone_pgdat) { + if (z->zone_pgdat == preferred_zone->zone_pgdat) { __inc_zone_state(z, NUMA_HIT); } else { __inc_zone_state(z, NUMA_MISS); - __inc_zone_state(zonelist->zones[0], NUMA_FOREIGN); + __inc_zone_state(preferred_zone, NUMA_FOREIGN); } if (z->node == numa_node_id()) __inc_zone_state(z, NUMA_LOCAL); @@ -394,9 +377,17 @@ void zone_statistics(struct zonelist *zonelist, struct zone *z) #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; @@ -421,38 +412,195 @@ 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; } -const 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 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 @@ -477,8 +625,12 @@ const struct seq_operations fragmentation_op = { static const char * const vmstat_text[] = { /* Zoned VM counters */ "nr_free_pages", - "nr_inactive", - "nr_active", + "nr_inactive_anon", + "nr_active_anon", + "nr_inactive_file", + "nr_active_file", + "nr_unevictable", + "nr_mlock", "nr_anon_pages", "nr_mapped", "nr_file_pages", @@ -487,10 +639,14 @@ static const char * const vmstat_text[] = { "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", @@ -520,6 +676,9 @@ static const char * const vmstat_text[] = { TEXTS_FOR_ZONES("pgscan_kswapd") TEXTS_FOR_ZONES("pgscan_direct") +#ifdef CONFIG_NUMA + "zone_reclaim_failed", +#endif "pginodesteal", "slabs_scanned", "kswapd_steal", @@ -528,91 +687,95 @@ static const char * const vmstat_text[] = { "allocstall", "pgrotated", +#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 scanned %lu (a: %lu i: %lu)" - "\n spanned %lu" - "\n present %lu", - zone_page_state(zone, NR_FREE_PAGES), - zone->pages_min, - zone->pages_low, - zone->pages_high, - 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++) { - 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); - } + "\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); + seq_printf(m, "\n vm stats threshold: %d", + pageset->stat_threshold); #endif - } - seq_printf(m, - "\n all_unreclaimable: %u" - "\n prev_priority: %i" - "\n start_pfn: %lu", - zone->all_unreclaimable, - zone->prev_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; } -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, @@ -620,6 +783,18 @@ const 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; @@ -675,13 +850,24 @@ static void vmstat_stop(struct seq_file *m, void *arg) 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 @@ -692,15 +878,15 @@ static void vmstat_update(struct work_struct *w) { 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 __devinit start_cpu_timer(int cpu) +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)); } /* @@ -739,9 +925,11 @@ static int __cpuinit vmstat_cpuup_callback(struct notifier_block *nfb, static struct notifier_block __cpuinitdata vmstat_notifier = { &vmstat_cpuup_callback, NULL, 0 }; +#endif -int __init setup_vmstat(void) +static int __init setup_vmstat(void) { +#ifdef CONFIG_SMP int cpu; refresh_zone_stat_thresholds(); @@ -749,7 +937,13 @@ int __init setup_vmstat(void) 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) -#endif