vmstat.c 15.2 KB
Newer Older
1 2 3 4 5
/*
 *  linux/mm/vmstat.c
 *
 *  Manages VM statistics
 *  Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
6 7 8 9
 *
 *  zoned VM statistics
 *  Copyright (C) 2006 Silicon Graphics, Inc.,
 *		Christoph Lameter <christoph@lameter.com>
10 11 12
 */

#include <linux/mm.h>
13
#include <linux/module.h>
14
#include <linux/cpu.h>
15 16 17 18

void __get_zone_counts(unsigned long *active, unsigned long *inactive,
			unsigned long *free, struct pglist_data *pgdat)
{
19 20
	*active = node_page_state(pgdat->node_id, NR_ACTIVE);
	*inactive = node_page_state(pgdat->node_id, NR_INACTIVE);
21
	*free = node_page_state(pgdat->node_id, NR_FREE_PAGES);
22 23 24 25 26
}

void get_zone_counts(unsigned long *active,
		unsigned long *inactive, unsigned long *free)
{
27 28
	*active = global_page_state(NR_ACTIVE);
	*inactive = global_page_state(NR_INACTIVE);
29
	*free = global_page_state(NR_FREE_PAGES);
30 31
}

32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66
#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)
{
	int cpu = 0;
	int i;

	memset(ret, 0, NR_VM_EVENT_ITEMS * sizeof(unsigned long));

	cpu = first_cpu(*cpumask);
	while (cpu < NR_CPUS) {
		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];
	}
}

/*
 * 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)
{
	sum_vm_events(ret, &cpu_online_map);
}
67
EXPORT_SYMBOL_GPL(all_vm_events);
68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89

#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 vm_event_state *fold_state = &per_cpu(vm_event_states, cpu);
	int i;

	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 */

#endif /* CONFIG_VM_EVENT_COUNTERS */

90 91 92 93 94 95 96 97 98 99
/*
 * Manage combined zone based / global counters
 *
 * vm_stat contains the global counters
 */
atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS];
EXPORT_SYMBOL(vm_stat);

#ifdef CONFIG_SMP

100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145
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;
}
146 147

/*
148
 * Refresh the thresholds for each zone.
149
 */
150
static void refresh_zone_stat_thresholds(void)
151
{
152 153 154 155 156 157 158 159 160 161 162 163 164 165
	struct zone *zone;
	int cpu;
	int threshold;

	for_each_zone(zone) {

		if (!zone->present_pages)
			continue;

		threshold = calculate_threshold(zone);

		for_each_online_cpu(cpu)
			zone_pcp(zone, cpu)->stat_threshold = threshold;
	}
166 167 168 169 170 171 172 173
}

/*
 * For use when we know that interrupts are disabled.
 */
void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
				int delta)
{
174 175
	struct per_cpu_pageset *pcp = zone_pcp(zone, smp_processor_id());
	s8 *p = pcp->vm_stat_diff + item;
176 177 178 179
	long x;

	x = delta + *p;

180
	if (unlikely(x > pcp->stat_threshold || x < -pcp->stat_threshold)) {
181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214
		zone_page_state_add(x, zone, item);
		x = 0;
	}
	*p = x;
}
EXPORT_SYMBOL(__mod_zone_page_state);

/*
 * For an unknown interrupt state
 */
void mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
					int delta)
{
	unsigned long flags;

	local_irq_save(flags);
	__mod_zone_page_state(zone, item, delta);
	local_irq_restore(flags);
}
EXPORT_SYMBOL(mod_zone_page_state);

/*
 * Optimized increment and decrement functions.
 *
 * These are only for a single page and therefore can take a struct page *
 * argument instead of struct zone *. This allows the inclusion of the code
 * generated for page_zone(page) into the optimized functions.
 *
 * 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.
 *
215 216 217
 * NOTE: These functions are very performance sensitive. Change only
 * with care.
 *
218 219 220 221 222 223 224
 * 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
 * guarantee without disabling preemption that the processor will not change
 * in between and therefore the atomicity vs. interrupt cannot be exploited
 * in a useful way here.
 */
225
void __inc_zone_state(struct zone *zone, enum zone_stat_item item)
226
{
227 228
	struct per_cpu_pageset *pcp = zone_pcp(zone, smp_processor_id());
	s8 *p = pcp->vm_stat_diff + item;
229 230 231

	(*p)++;

232 233 234 235 236
	if (unlikely(*p > pcp->stat_threshold)) {
		int overstep = pcp->stat_threshold / 2;

		zone_page_state_add(*p + overstep, zone, item);
		*p = -overstep;
237 238
	}
}
239 240 241 242 243

void __inc_zone_page_state(struct page *page, enum zone_stat_item item)
{
	__inc_zone_state(page_zone(page), item);
}
244 245
EXPORT_SYMBOL(__inc_zone_page_state);

246
void __dec_zone_state(struct zone *zone, enum zone_stat_item item)
247
{
248 249
	struct per_cpu_pageset *pcp = zone_pcp(zone, smp_processor_id());
	s8 *p = pcp->vm_stat_diff + item;
250 251 252

	(*p)--;

253 254 255 256 257
	if (unlikely(*p < - pcp->stat_threshold)) {
		int overstep = pcp->stat_threshold / 2;

		zone_page_state_add(*p - overstep, zone, item);
		*p = overstep;
258 259
	}
}
260 261 262 263 264

void __dec_zone_page_state(struct page *page, enum zone_stat_item item)
{
	__dec_zone_state(page_zone(page), item);
}
265 266
EXPORT_SYMBOL(__dec_zone_page_state);

267 268 269 270 271 272 273 274 275
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);
}

276 277 278 279 280 281 282
void inc_zone_page_state(struct page *page, enum zone_stat_item item)
{
	unsigned long flags;
	struct zone *zone;

	zone = page_zone(page);
	local_irq_save(flags);
283
	__inc_zone_state(zone, item);
284 285 286 287 288 289 290 291 292
	local_irq_restore(flags);
}
EXPORT_SYMBOL(inc_zone_page_state);

void dec_zone_page_state(struct page *page, enum zone_stat_item item)
{
	unsigned long flags;

	local_irq_save(flags);
293
	__dec_zone_page_state(page, item);
294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309
	local_irq_restore(flags);
}
EXPORT_SYMBOL(dec_zone_page_state);

/*
 * Update the zone counters for one cpu.
 */
void refresh_cpu_vm_stats(int cpu)
{
	struct zone *zone;
	int i;
	unsigned long flags;

	for_each_zone(zone) {
		struct per_cpu_pageset *pcp;

310 311 312
		if (!populated_zone(zone))
			continue;

313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344
		pcp = zone_pcp(zone, cpu);

		for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
			if (pcp->vm_stat_diff[i]) {
				local_irq_save(flags);
				zone_page_state_add(pcp->vm_stat_diff[i],
					zone, i);
				pcp->vm_stat_diff[i] = 0;
				local_irq_restore(flags);
			}
	}
}

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);
}
EXPORT_SYMBOL(refresh_vm_stats);

#endif

345 346 347 348 349 350 351 352 353 354 355 356 357 358 359
#ifdef CONFIG_NUMA
/*
 * zonelist = the list of zones passed to the allocator
 * z 	    = the zone from which the allocation occurred.
 *
 * Must be called with interrupts disabled.
 */
void zone_statistics(struct zonelist *zonelist, struct zone *z)
{
	if (z->zone_pgdat == zonelist->zones[0]->zone_pgdat) {
		__inc_zone_state(z, NUMA_HIT);
	} else {
		__inc_zone_state(z, NUMA_MISS);
		__inc_zone_state(zonelist->zones[0], NUMA_FOREIGN);
	}
360
	if (z->node == numa_node_id())
361 362 363 364 365 366
		__inc_zone_state(z, NUMA_LOCAL);
	else
		__inc_zone_state(z, NUMA_OTHER);
}
#endif

367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419
#ifdef CONFIG_PROC_FS

#include <linux/seq_file.h>

static void *frag_start(struct seq_file *m, loff_t *pos)
{
	pg_data_t *pgdat;
	loff_t node = *pos;
	for (pgdat = first_online_pgdat();
	     pgdat && node;
	     pgdat = next_online_pgdat(pgdat))
		--node;

	return pgdat;
}

static void *frag_next(struct seq_file *m, void *arg, loff_t *pos)
{
	pg_data_t *pgdat = (pg_data_t *)arg;

	(*pos)++;
	return next_online_pgdat(pgdat);
}

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)
{
	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);
		spin_unlock_irqrestore(&zone->lock, flags);
		seq_putc(m, '\n');
	}
	return 0;
}

420
const struct seq_operations fragmentation_op = {
421 422 423 424 425 426
	.start	= frag_start,
	.next	= frag_next,
	.stop	= frag_stop,
	.show	= frag_show,
};

427 428 429 430 431 432 433 434 435 436 437 438 439 440 441
#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) xx "_dma", TEXT_FOR_DMA32(xx) xx "_normal", \
					TEXT_FOR_HIGHMEM(xx)

442
static const char * const vmstat_text[] = {
443
	/* Zoned VM counters */
444
	"nr_free_pages",
445 446
	"nr_active",
	"nr_inactive",
447
	"nr_anon_pages",
448
	"nr_mapped",
449
	"nr_file_pages",
450 451
	"nr_slab_reclaimable",
	"nr_slab_unreclaimable",
452
	"nr_page_table_pages",
453
	"nr_dirty",
454
	"nr_writeback",
455
	"nr_unstable",
456
	"nr_bounce",
457
	"nr_vmscan_write",
458

459 460 461 462 463 464 465 466 467
#ifdef CONFIG_NUMA
	"numa_hit",
	"numa_miss",
	"numa_foreign",
	"numa_interleave",
	"numa_local",
	"numa_other",
#endif

468
#ifdef CONFIG_VM_EVENT_COUNTERS
469 470 471 472 473
	"pgpgin",
	"pgpgout",
	"pswpin",
	"pswpout",

474
	TEXTS_FOR_ZONES("pgalloc")
475 476 477 478 479 480 481 482

	"pgfree",
	"pgactivate",
	"pgdeactivate",

	"pgfault",
	"pgmajfault",

483 484 485 486
	TEXTS_FOR_ZONES("pgrefill")
	TEXTS_FOR_ZONES("pgsteal")
	TEXTS_FOR_ZONES("pgscan_kswapd")
	TEXTS_FOR_ZONES("pgscan_direct")
487 488 489 490 491 492 493 494 495

	"pginodesteal",
	"slabs_scanned",
	"kswapd_steal",
	"kswapd_inodesteal",
	"pageoutrun",
	"allocstall",

	"pgrotated",
496
#endif
497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524
};

/*
 * Output information about zones in @pgdat.
 */
static int zoneinfo_show(struct seq_file *m, void *arg)
{
	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",
525
			   zone_page_state(zone, NR_FREE_PAGES),
526 527 528 529 530 531 532
			   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);
533 534 535 536 537

		for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
			seq_printf(m, "\n    %-12s %lu", vmstat_text[i],
					zone_page_state(zone, i));

538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561
		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);
			}
562 563 564 565
#ifdef CONFIG_SMP
			seq_printf(m, "\n  vm stats threshold: %d",
					pageset->stat_threshold);
#endif
566 567 568 569 570 571 572 573 574 575 576 577 578 579
		}
		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');
	}
	return 0;
}

580
const struct seq_operations zoneinfo_op = {
581 582 583 584 585 586 587 588 589
	.start	= frag_start, /* iterate over all zones. The same as in
			       * fragmentation. */
	.next	= frag_next,
	.stop	= frag_stop,
	.show	= zoneinfo_show,
};

static void *vmstat_start(struct seq_file *m, loff_t *pos)
{
590
	unsigned long *v;
591 592 593
#ifdef CONFIG_VM_EVENT_COUNTERS
	unsigned long *e;
#endif
594
	int i;
595 596 597 598

	if (*pos >= ARRAY_SIZE(vmstat_text))
		return NULL;

599
#ifdef CONFIG_VM_EVENT_COUNTERS
600
	v = kmalloc(NR_VM_ZONE_STAT_ITEMS * sizeof(unsigned long)
601 602 603 604 605
			+ sizeof(struct vm_event_state), GFP_KERNEL);
#else
	v = kmalloc(NR_VM_ZONE_STAT_ITEMS * sizeof(unsigned long),
			GFP_KERNEL);
#endif
606 607
	m->private = v;
	if (!v)
608
		return ERR_PTR(-ENOMEM);
609 610
	for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
		v[i] = global_page_state(i);
611 612 613 614 615 616
#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
617
	return v + *pos;
618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642
}

static void *vmstat_next(struct seq_file *m, void *arg, loff_t *pos)
{
	(*pos)++;
	if (*pos >= ARRAY_SIZE(vmstat_text))
		return NULL;
	return (unsigned long *)m->private + *pos;
}

static int vmstat_show(struct seq_file *m, void *arg)
{
	unsigned long *l = arg;
	unsigned long off = l - (unsigned long *)m->private;

	seq_printf(m, "%s %lu\n", vmstat_text[off], *l);
	return 0;
}

static void vmstat_stop(struct seq_file *m, void *arg)
{
	kfree(m->private);
	m->private = NULL;
}

643
const struct seq_operations vmstat_op = {
644 645 646 647 648 649 650 651
	.start	= vmstat_start,
	.next	= vmstat_next,
	.stop	= vmstat_stop,
	.show	= vmstat_show,
};

#endif /* CONFIG_PROC_FS */

652 653 654 655 656 657 658 659 660 661
#ifdef CONFIG_SMP
/*
 * 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)
{
	switch (action) {
662 663 664 665 666 667 668
	case CPU_UP_PREPARE:
	case CPU_UP_CANCELED:
	case CPU_DEAD:
		refresh_zone_stat_thresholds();
		break;
	default:
		break;
669 670 671 672 673 674 675 676 677 678 679 680 681 682 683
	}
	return NOTIFY_OK;
}

static struct notifier_block __cpuinitdata vmstat_notifier =
	{ &vmstat_cpuup_callback, NULL, 0 };

int __init setup_vmstat(void)
{
	refresh_zone_stat_thresholds();
	register_cpu_notifier(&vmstat_notifier);
	return 0;
}
module_init(setup_vmstat)
#endif