Blame view
mm/vmstat.c
22.8 KB
f6ac2354d
|
1 2 3 4 5 |
/* * linux/mm/vmstat.c * * Manages VM statistics * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds |
2244b95a7
|
6 7 8 9 |
* * zoned VM statistics * Copyright (C) 2006 Silicon Graphics, Inc., * Christoph Lameter <christoph@lameter.com> |
f6ac2354d
|
10 |
*/ |
8f32f7e5a
|
11 |
#include <linux/fs.h> |
f6ac2354d
|
12 |
#include <linux/mm.h> |
4e950f6f0
|
13 |
#include <linux/err.h> |
2244b95a7
|
14 |
#include <linux/module.h> |
df9ecaba3
|
15 |
#include <linux/cpu.h> |
c748e1340
|
16 |
#include <linux/vmstat.h> |
e8edc6e03
|
17 |
#include <linux/sched.h> |
f6ac2354d
|
18 |
|
f8891e5e1
|
19 20 21 |
#ifdef CONFIG_VM_EVENT_COUNTERS DEFINE_PER_CPU(struct vm_event_state, vm_event_states) = {{0}}; EXPORT_PER_CPU_SYMBOL(vm_event_states); |
174596a0b
|
22 |
static void sum_vm_events(unsigned long *ret, const struct cpumask *cpumask) |
f8891e5e1
|
23 |
{ |
9eccf2a81
|
24 |
int cpu; |
f8891e5e1
|
25 26 27 |
int i; memset(ret, 0, NR_VM_EVENT_ITEMS * sizeof(unsigned long)); |
6d6a43608
|
28 |
for_each_cpu_mask_nr(cpu, *cpumask) { |
f8891e5e1
|
29 |
struct vm_event_state *this = &per_cpu(vm_event_states, cpu); |
f8891e5e1
|
30 31 32 33 34 35 36 37 38 39 40 41 |
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) { |
b5be11329
|
42 |
get_online_cpus(); |
174596a0b
|
43 |
sum_vm_events(ret, cpu_online_mask); |
b5be11329
|
44 |
put_online_cpus(); |
f8891e5e1
|
45 |
} |
32dd66fce
|
46 |
EXPORT_SYMBOL_GPL(all_vm_events); |
f8891e5e1
|
47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 |
#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 */ |
2244b95a7
|
68 69 70 71 72 73 74 75 76 |
/* * 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 |
df9ecaba3
|
77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 |
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; } |
2244b95a7
|
123 124 |
/* |
df9ecaba3
|
125 |
* Refresh the thresholds for each zone. |
2244b95a7
|
126 |
*/ |
df9ecaba3
|
127 |
static void refresh_zone_stat_thresholds(void) |
2244b95a7
|
128 |
{ |
df9ecaba3
|
129 130 131 132 133 134 135 136 137 138 139 140 141 142 |
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; } |
2244b95a7
|
143 144 145 146 147 148 149 150 |
} /* * For use when we know that interrupts are disabled. */ void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item, int delta) { |
df9ecaba3
|
151 152 |
struct per_cpu_pageset *pcp = zone_pcp(zone, smp_processor_id()); s8 *p = pcp->vm_stat_diff + item; |
2244b95a7
|
153 |
long x; |
2244b95a7
|
154 |
x = delta + *p; |
df9ecaba3
|
155 |
if (unlikely(x > pcp->stat_threshold || x < -pcp->stat_threshold)) { |
2244b95a7
|
156 157 158 |
zone_page_state_add(x, zone, item); x = 0; } |
2244b95a7
|
159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 |
*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. |
2244b95a7
|
187 188 189 |
* The increment or decrement is known and therefore one boundary check can * be omitted. * |
df9ecaba3
|
190 191 192 |
* NOTE: These functions are very performance sensitive. Change only * with care. * |
2244b95a7
|
193 194 195 196 197 198 199 |
* 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. */ |
c87853859
|
200 |
void __inc_zone_state(struct zone *zone, enum zone_stat_item item) |
2244b95a7
|
201 |
{ |
df9ecaba3
|
202 203 |
struct per_cpu_pageset *pcp = zone_pcp(zone, smp_processor_id()); s8 *p = pcp->vm_stat_diff + item; |
2244b95a7
|
204 205 |
(*p)++; |
df9ecaba3
|
206 207 208 209 210 |
if (unlikely(*p > pcp->stat_threshold)) { int overstep = pcp->stat_threshold / 2; zone_page_state_add(*p + overstep, zone, item); *p = -overstep; |
2244b95a7
|
211 212 |
} } |
ca889e6c4
|
213 214 215 216 217 |
void __inc_zone_page_state(struct page *page, enum zone_stat_item item) { __inc_zone_state(page_zone(page), item); } |
2244b95a7
|
218 |
EXPORT_SYMBOL(__inc_zone_page_state); |
c87853859
|
219 |
void __dec_zone_state(struct zone *zone, enum zone_stat_item item) |
2244b95a7
|
220 |
{ |
df9ecaba3
|
221 222 |
struct per_cpu_pageset *pcp = zone_pcp(zone, smp_processor_id()); s8 *p = pcp->vm_stat_diff + item; |
2244b95a7
|
223 224 |
(*p)--; |
df9ecaba3
|
225 226 227 228 229 |
if (unlikely(*p < - pcp->stat_threshold)) { int overstep = pcp->stat_threshold / 2; zone_page_state_add(*p - overstep, zone, item); *p = overstep; |
2244b95a7
|
230 231 |
} } |
c87853859
|
232 233 234 235 236 |
void __dec_zone_page_state(struct page *page, enum zone_stat_item item) { __dec_zone_state(page_zone(page), item); } |
2244b95a7
|
237 |
EXPORT_SYMBOL(__dec_zone_page_state); |
ca889e6c4
|
238 239 240 241 242 243 244 245 |
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); } |
2244b95a7
|
246 247 248 249 |
void inc_zone_page_state(struct page *page, enum zone_stat_item item) { unsigned long flags; struct zone *zone; |
2244b95a7
|
250 251 252 |
zone = page_zone(page); local_irq_save(flags); |
ca889e6c4
|
253 |
__inc_zone_state(zone, item); |
2244b95a7
|
254 255 256 257 258 259 260 |
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; |
2244b95a7
|
261 |
|
2244b95a7
|
262 |
local_irq_save(flags); |
a302eb4e4
|
263 |
__dec_zone_page_state(page, item); |
2244b95a7
|
264 265 266 267 268 269 |
local_irq_restore(flags); } EXPORT_SYMBOL(dec_zone_page_state); /* * Update the zone counters for one cpu. |
4037d4522
|
270 |
* |
a7f75e258
|
271 272 273 274 |
* 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. * |
4037d4522
|
275 276 277 278 279 280 281 282 283 284 |
* 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. |
2244b95a7
|
285 286 287 288 289 |
*/ void refresh_cpu_vm_stats(int cpu) { struct zone *zone; int i; |
a7f75e258
|
290 |
int global_diff[NR_VM_ZONE_STAT_ITEMS] = { 0, }; |
2244b95a7
|
291 292 |
for_each_zone(zone) { |
4037d4522
|
293 |
struct per_cpu_pageset *p; |
2244b95a7
|
294 |
|
39bbcb8f8
|
295 296 |
if (!populated_zone(zone)) continue; |
4037d4522
|
297 |
p = zone_pcp(zone, cpu); |
2244b95a7
|
298 299 |
for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) |
4037d4522
|
300 |
if (p->vm_stat_diff[i]) { |
a7f75e258
|
301 302 |
unsigned long flags; int v; |
2244b95a7
|
303 |
local_irq_save(flags); |
a7f75e258
|
304 |
v = p->vm_stat_diff[i]; |
4037d4522
|
305 |
p->vm_stat_diff[i] = 0; |
a7f75e258
|
306 307 308 |
local_irq_restore(flags); atomic_long_add(v, &zone->vm_stat[i]); global_diff[i] += v; |
4037d4522
|
309 310 311 312 |
#ifdef CONFIG_NUMA /* 3 seconds idle till flush */ p->expire = 3; #endif |
2244b95a7
|
313 |
} |
468fd62ed
|
314 |
cond_resched(); |
4037d4522
|
315 316 317 318 319 320 321 322 |
#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. */ |
3dfa5721f
|
323 |
if (!p->expire || !p->pcp.count) |
4037d4522
|
324 325 326 327 328 329 330 331 332 333 334 335 336 |
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; |
3dfa5721f
|
337 338 |
if (p->pcp.count) drain_zone_pages(zone, &p->pcp); |
4037d4522
|
339 |
#endif |
2244b95a7
|
340 |
} |
a7f75e258
|
341 342 343 344 |
for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) if (global_diff[i]) atomic_long_add(global_diff[i], &vm_stat[i]); |
2244b95a7
|
345 |
} |
2244b95a7
|
346 |
#endif |
ca889e6c4
|
347 348 349 350 351 352 353 |
#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. */ |
18ea7e710
|
354 |
void zone_statistics(struct zone *preferred_zone, struct zone *z) |
ca889e6c4
|
355 |
{ |
18ea7e710
|
356 |
if (z->zone_pgdat == preferred_zone->zone_pgdat) { |
ca889e6c4
|
357 358 359 |
__inc_zone_state(z, NUMA_HIT); } else { __inc_zone_state(z, NUMA_MISS); |
18ea7e710
|
360 |
__inc_zone_state(preferred_zone, NUMA_FOREIGN); |
ca889e6c4
|
361 |
} |
5d2923436
|
362 |
if (z->node == numa_node_id()) |
ca889e6c4
|
363 364 365 366 367 |
__inc_zone_state(z, NUMA_LOCAL); else __inc_zone_state(z, NUMA_OTHER); } #endif |
f6ac2354d
|
368 |
#ifdef CONFIG_PROC_FS |
8f32f7e5a
|
369 |
#include <linux/proc_fs.h> |
f6ac2354d
|
370 |
#include <linux/seq_file.h> |
467c996c1
|
371 372 373 374 375 |
static char * const migratetype_names[MIGRATE_TYPES] = { "Unmovable", "Reclaimable", "Movable", "Reserve", |
91446b064
|
376 |
"Isolate", |
467c996c1
|
377 |
}; |
f6ac2354d
|
378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 |
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) { } |
467c996c1
|
401 402 403 |
/* 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 *)) |
f6ac2354d
|
404 |
{ |
f6ac2354d
|
405 406 407 |
struct zone *zone; struct zone *node_zones = pgdat->node_zones; unsigned long flags; |
f6ac2354d
|
408 409 410 411 412 413 |
for (zone = node_zones; zone - node_zones < MAX_NR_ZONES; ++zone) { if (!populated_zone(zone)) continue; spin_lock_irqsave(&zone->lock, flags); |
467c996c1
|
414 |
print(m, pgdat, zone); |
f6ac2354d
|
415 |
spin_unlock_irqrestore(&zone->lock, flags); |
467c996c1
|
416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 |
} } 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, ' '); } /* * 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); } |
f6ac2354d
|
462 463 464 |
seq_putc(m, ' '); } |
467c996c1
|
465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 |
} /* 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, ' '); walk_zones_in_node(m, pgdat, pagetypeinfo_showfree_print); return 0; } 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); |
e80d6a248
|
501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 |
#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) continue; #endif |
467c996c1
|
517 |
mtype = get_pageblock_migratetype(page); |
e80d6a248
|
518 519 |
if (mtype < MIGRATE_TYPES) count[mtype]++; |
467c996c1
|
520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 |
} /* 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, ' '); } /* 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, " %-23s", "Number of blocks type "); for (mtype = 0; mtype < MIGRATE_TYPES; mtype++) seq_printf(m, "%12s ", migratetype_names[mtype]); seq_putc(m, ' '); 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; |
41b25a378
|
554 555 556 |
/* check memoryless node */ if (!node_state(pgdat->node_id, N_HIGH_MEMORY)) return 0; |
467c996c1
|
557 558 559 560 561 562 563 564 |
seq_printf(m, "Page block order: %d ", pageblock_order); seq_printf(m, "Pages per block: %lu ", pageblock_nr_pages); seq_putc(m, ' '); pagetypeinfo_showfree(m, pgdat); pagetypeinfo_showblockcount(m, pgdat); |
f6ac2354d
|
565 566 |
return 0; } |
8f32f7e5a
|
567 |
static const struct seq_operations fragmentation_op = { |
f6ac2354d
|
568 569 570 571 572 |
.start = frag_start, .next = frag_next, .stop = frag_stop, .show = frag_show, }; |
8f32f7e5a
|
573 574 575 576 577 578 579 580 581 582 583 |
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, }; |
74e2e8e8c
|
584 |
static const struct seq_operations pagetypeinfo_op = { |
467c996c1
|
585 586 587 588 589 |
.start = frag_start, .next = frag_next, .stop = frag_stop, .show = pagetypeinfo_show, }; |
74e2e8e8c
|
590 591 592 593 594 595 596 597 598 599 600 |
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, }; |
4b51d6698
|
601 602 603 604 605 |
#ifdef CONFIG_ZONE_DMA #define TEXT_FOR_DMA(xx) xx "_dma", #else #define TEXT_FOR_DMA(xx) #endif |
27bf71c2a
|
606 607 608 609 610 611 612 613 614 615 616 |
#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 |
4b51d6698
|
617 |
#define TEXTS_FOR_ZONES(xx) TEXT_FOR_DMA(xx) TEXT_FOR_DMA32(xx) xx "_normal", \ |
2a1e274ac
|
618 |
TEXT_FOR_HIGHMEM(xx) xx "_movable", |
27bf71c2a
|
619 |
|
15ad7cdcf
|
620 |
static const char * const vmstat_text[] = { |
2244b95a7
|
621 |
/* Zoned VM counters */ |
d23ad4232
|
622 |
"nr_free_pages", |
4f98a2fee
|
623 624 625 626 |
"nr_inactive_anon", "nr_active_anon", "nr_inactive_file", "nr_active_file", |
7b854121e
|
627 628 |
#ifdef CONFIG_UNEVICTABLE_LRU "nr_unevictable", |
5344b7e64
|
629 |
"nr_mlock", |
7b854121e
|
630 |
#endif |
f3dbd3446
|
631 |
"nr_anon_pages", |
65ba55f50
|
632 |
"nr_mapped", |
347ce434d
|
633 |
"nr_file_pages", |
51ed44912
|
634 635 |
"nr_dirty", "nr_writeback", |
972d1a7b1
|
636 637 |
"nr_slab_reclaimable", "nr_slab_unreclaimable", |
df849a152
|
638 |
"nr_page_table_pages", |
f6ac2354d
|
639 |
"nr_unstable", |
d2c5e30c9
|
640 |
"nr_bounce", |
e129b5c23
|
641 |
"nr_vmscan_write", |
fc3ba692a
|
642 |
"nr_writeback_temp", |
f6ac2354d
|
643 |
|
ca889e6c4
|
644 645 646 647 648 649 650 651 |
#ifdef CONFIG_NUMA "numa_hit", "numa_miss", "numa_foreign", "numa_interleave", "numa_local", "numa_other", #endif |
f8891e5e1
|
652 |
#ifdef CONFIG_VM_EVENT_COUNTERS |
f6ac2354d
|
653 654 655 656 |
"pgpgin", "pgpgout", "pswpin", "pswpout", |
27bf71c2a
|
657 |
TEXTS_FOR_ZONES("pgalloc") |
f6ac2354d
|
658 659 660 661 662 663 664 |
"pgfree", "pgactivate", "pgdeactivate", "pgfault", "pgmajfault", |
27bf71c2a
|
665 666 667 668 |
TEXTS_FOR_ZONES("pgrefill") TEXTS_FOR_ZONES("pgsteal") TEXTS_FOR_ZONES("pgscan_kswapd") TEXTS_FOR_ZONES("pgscan_direct") |
f6ac2354d
|
669 670 671 672 673 674 675 676 677 |
"pginodesteal", "slabs_scanned", "kswapd_steal", "kswapd_inodesteal", "pageoutrun", "allocstall", "pgrotated", |
3b1163006
|
678 679 680 681 |
#ifdef CONFIG_HUGETLB_PAGE "htlb_buddy_alloc_success", "htlb_buddy_alloc_fail", #endif |
bbfd28eee
|
682 683 684 685 |
#ifdef CONFIG_UNEVICTABLE_LRU "unevictable_pgs_culled", "unevictable_pgs_scanned", "unevictable_pgs_rescued", |
5344b7e64
|
686 687 688 689 |
"unevictable_pgs_mlocked", "unevictable_pgs_munlocked", "unevictable_pgs_cleared", "unevictable_pgs_stranded", |
985737cf2
|
690 |
"unevictable_pgs_mlockfreed", |
bbfd28eee
|
691 |
#endif |
f8891e5e1
|
692 |
#endif |
f6ac2354d
|
693 |
}; |
467c996c1
|
694 695 |
static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat, struct zone *zone) |
f6ac2354d
|
696 |
{ |
467c996c1
|
697 698 699 700 701 702 703 704 705 706 707 |
int i; seq_printf(m, "Node %d, zone %8s", pgdat->node_id, zone->name); seq_printf(m, " pages free %lu" " min %lu" " low %lu" " high %lu" |
4f98a2fee
|
708 709 |
" scanned %lu (aa: %lu ia: %lu af: %lu if: %lu)" |
467c996c1
|
710 711 712 713 714 715 716 717 718 |
" spanned %lu" " present %lu", zone_page_state(zone, NR_FREE_PAGES), zone->pages_min, zone->pages_low, zone->pages_high, zone->pages_scanned, |
4f98a2fee
|
719 720 721 722 |
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, |
467c996c1
|
723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 |
zone->spanned_pages, zone->present_pages); for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) seq_printf(m, " %-12s %lu", vmstat_text[i], zone_page_state(zone, i)); seq_printf(m, " 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, ")" " pagesets"); for_each_online_cpu(i) { struct per_cpu_pageset *pageset; |
467c996c1
|
743 744 |
pageset = zone_pcp(zone, i); |
3dfa5721f
|
745 746 747 748 749 750 751 752 753 754 755 756 757 |
seq_printf(m, " cpu: %i" " count: %i" " high: %i" " batch: %i", i, pageset->pcp.count, pageset->pcp.high, pageset->pcp.batch); |
df9ecaba3
|
758 |
#ifdef CONFIG_SMP |
467c996c1
|
759 760 761 |
seq_printf(m, " vm stats threshold: %d", pageset->stat_threshold); |
df9ecaba3
|
762 |
#endif |
f6ac2354d
|
763 |
} |
467c996c1
|
764 765 766 767 768 |
seq_printf(m, " all_unreclaimable: %u" " prev_priority: %i" |
556adecba
|
769 770 771 772 |
" start_pfn: %lu" " inactive_ratio: %u", |
e815af95f
|
773 |
zone_is_all_unreclaimable(zone), |
467c996c1
|
774 |
zone->prev_priority, |
556adecba
|
775 776 |
zone->zone_start_pfn, zone->inactive_ratio); |
467c996c1
|
777 778 779 780 781 782 783 784 785 786 787 |
seq_putc(m, ' '); } /* * 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); |
f6ac2354d
|
788 789 |
return 0; } |
5c9fe6281
|
790 |
static const struct seq_operations zoneinfo_op = { |
f6ac2354d
|
791 792 793 794 795 796 |
.start = frag_start, /* iterate over all zones. The same as in * fragmentation. */ .next = frag_next, .stop = frag_stop, .show = zoneinfo_show, }; |
5c9fe6281
|
797 798 799 800 801 802 803 804 805 806 807 |
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, }; |
f6ac2354d
|
808 809 |
static void *vmstat_start(struct seq_file *m, loff_t *pos) { |
2244b95a7
|
810 |
unsigned long *v; |
f8891e5e1
|
811 812 813 |
#ifdef CONFIG_VM_EVENT_COUNTERS unsigned long *e; #endif |
2244b95a7
|
814 |
int i; |
f6ac2354d
|
815 816 817 |
if (*pos >= ARRAY_SIZE(vmstat_text)) return NULL; |
f8891e5e1
|
818 |
#ifdef CONFIG_VM_EVENT_COUNTERS |
2244b95a7
|
819 |
v = kmalloc(NR_VM_ZONE_STAT_ITEMS * sizeof(unsigned long) |
f8891e5e1
|
820 821 822 823 824 |
+ sizeof(struct vm_event_state), GFP_KERNEL); #else v = kmalloc(NR_VM_ZONE_STAT_ITEMS * sizeof(unsigned long), GFP_KERNEL); #endif |
2244b95a7
|
825 826 |
m->private = v; if (!v) |
f6ac2354d
|
827 |
return ERR_PTR(-ENOMEM); |
2244b95a7
|
828 829 |
for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) v[i] = global_page_state(i); |
f8891e5e1
|
830 831 832 833 834 835 |
#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 |
2244b95a7
|
836 |
return v + *pos; |
f6ac2354d
|
837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 |
} 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 ", vmstat_text[off], *l); return 0; } static void vmstat_stop(struct seq_file *m, void *arg) { kfree(m->private); m->private = NULL; } |
b6aa44ab6
|
862 |
static const struct seq_operations vmstat_op = { |
f6ac2354d
|
863 864 865 866 867 |
.start = vmstat_start, .next = vmstat_next, .stop = vmstat_stop, .show = vmstat_show, }; |
b6aa44ab6
|
868 869 870 871 872 873 874 875 876 877 878 |
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, }; |
f6ac2354d
|
879 |
#endif /* CONFIG_PROC_FS */ |
df9ecaba3
|
880 |
#ifdef CONFIG_SMP |
d1187ed21
|
881 |
static DEFINE_PER_CPU(struct delayed_work, vmstat_work); |
77461ab33
|
882 |
int sysctl_stat_interval __read_mostly = HZ; |
d1187ed21
|
883 884 885 886 |
static void vmstat_update(struct work_struct *w) { refresh_cpu_vm_stats(smp_processor_id()); |
77461ab33
|
887 888 |
schedule_delayed_work(&__get_cpu_var(vmstat_work), sysctl_stat_interval); |
d1187ed21
|
889 |
} |
42614fcde
|
890 |
static void __cpuinit start_cpu_timer(int cpu) |
d1187ed21
|
891 892 |
{ struct delayed_work *vmstat_work = &per_cpu(vmstat_work, cpu); |
39bf6270f
|
893 |
INIT_DELAYED_WORK_DEFERRABLE(vmstat_work, vmstat_update); |
d1187ed21
|
894 895 |
schedule_delayed_work_on(cpu, vmstat_work, HZ + cpu); } |
df9ecaba3
|
896 897 898 899 900 901 902 903 |
/* * 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) { |
d1187ed21
|
904 |
long cpu = (long)hcpu; |
df9ecaba3
|
905 |
switch (action) { |
d1187ed21
|
906 907 908 909 910 911 912 913 914 915 916 917 918 |
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; |
ce421c799
|
919 |
case CPU_DEAD: |
8bb784428
|
920 |
case CPU_DEAD_FROZEN: |
ce421c799
|
921 922 923 924 |
refresh_zone_stat_thresholds(); break; default: break; |
df9ecaba3
|
925 926 927 928 929 930 |
} return NOTIFY_OK; } static struct notifier_block __cpuinitdata vmstat_notifier = { &vmstat_cpuup_callback, NULL, 0 }; |
8f32f7e5a
|
931 |
#endif |
df9ecaba3
|
932 |
|
e2fc88d06
|
933 |
static int __init setup_vmstat(void) |
df9ecaba3
|
934 |
{ |
8f32f7e5a
|
935 |
#ifdef CONFIG_SMP |
d1187ed21
|
936 |
int cpu; |
df9ecaba3
|
937 938 |
refresh_zone_stat_thresholds(); register_cpu_notifier(&vmstat_notifier); |
d1187ed21
|
939 940 941 |
for_each_online_cpu(cpu) start_cpu_timer(cpu); |
8f32f7e5a
|
942 943 944 |
#endif #ifdef CONFIG_PROC_FS proc_create("buddyinfo", S_IRUGO, NULL, &fragmentation_file_operations); |
74e2e8e8c
|
945 |
proc_create("pagetypeinfo", S_IRUGO, NULL, &pagetypeinfo_file_ops); |
b6aa44ab6
|
946 |
proc_create("vmstat", S_IRUGO, NULL, &proc_vmstat_file_operations); |
5c9fe6281
|
947 |
proc_create("zoneinfo", S_IRUGO, NULL, &proc_zoneinfo_file_operations); |
8f32f7e5a
|
948 |
#endif |
df9ecaba3
|
949 950 951 |
return 0; } module_init(setup_vmstat) |