1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 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 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575
|
/* -*- Mode: C; tab-width: 4; c-basic-offset: 4; indent-tabs-mode: nil -*- */
#include "memcached.h"
#include <sys/stat.h>
#include <sys/socket.h>
#include <sys/signal.h>
#include <sys/resource.h>
#include <fcntl.h>
#include <netinet/in.h>
#include <errno.h>
#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#include <time.h>
#include <assert.h>
/* Forward Declarations */
static void item_link_q(item *it);
static void item_unlink_q(item *it);
/*
* We only reposition items in the LRU queue if they haven't been repositioned
* in this many seconds. That saves us from churning on frequently-accessed
* items.
*/
#define ITEM_UPDATE_INTERVAL 60
#define LARGEST_ID POWER_LARGEST
typedef struct {
uint64_t evicted;
uint64_t evicted_nonzero;
rel_time_t evicted_time;
uint64_t reclaimed;
uint64_t outofmemory;
uint64_t tailrepairs;
uint64_t expired_unfetched;
uint64_t evicted_unfetched;
} itemstats_t;
static item *heads[LARGEST_ID];
static item *tails[LARGEST_ID];
static itemstats_t itemstats[LARGEST_ID];
static unsigned int sizes[LARGEST_ID];
void item_stats_reset(void) {
mutex_lock(&cache_lock);
memset(itemstats, 0, sizeof(itemstats));
pthread_mutex_unlock(&cache_lock);
}
/* Get the next CAS id for a new item. */
uint64_t get_cas_id(void) {
static uint64_t cas_id = 0;
return ++cas_id;
}
/* Enable this for reference-count debugging. */
#if 0
# define DEBUG_REFCNT(it,op) \
fprintf(stderr, "item %x refcnt(%c) %d %c%c%c\n", \
it, op, it->refcount, \
(it->it_flags & ITEM_LINKED) ? 'L' : ' ', \
(it->it_flags & ITEM_SLABBED) ? 'S' : ' ')
#else
# define DEBUG_REFCNT(it,op) while(0)
#endif
/**
* Generates the variable-sized part of the header for an object.
*
* key - The key
* nkey - The length of the key
* flags - key flags
* nbytes - Number of bytes to hold value and addition CRLF terminator
* suffix - Buffer for the "VALUE" line suffix (flags, size).
* nsuffix - The length of the suffix is stored here.
*
* Returns the total size of the header.
*/
static size_t item_make_header(const uint8_t nkey, const int flags, const int nbytes,
char *suffix, uint8_t *nsuffix) {
/* suffix is defined at 40 chars elsewhere.. */
*nsuffix = (uint8_t) snprintf(suffix, 40, " %d %d\r\n", flags, nbytes - 2);
return sizeof(item) + nkey + *nsuffix + nbytes;
}
/*@null@*/
item *do_item_alloc(char *key, const size_t nkey, const int flags, const rel_time_t exptime, const int nbytes) {
uint8_t nsuffix;
item *it = NULL;
char suffix[40];
size_t ntotal = item_make_header(nkey + 1, flags, nbytes, suffix, &nsuffix);
if (settings.use_cas) {
ntotal += sizeof(uint64_t);
}
unsigned int id = slabs_clsid(ntotal);
if (id == 0)
return 0;
mutex_lock(&cache_lock);
/* do a quick check if we have any expired items in the tail.. */
item *search;
rel_time_t oldest_live = settings.oldest_live;
search = tails[id];
if (search != NULL && (refcount_incr(&search->refcount) == 2)) {
if ((search->exptime != 0 && search->exptime < current_time)
|| (search->time <= oldest_live && oldest_live <= current_time)) { // dead by flush
STATS_LOCK();
stats.reclaimed++;
STATS_UNLOCK();
itemstats[id].reclaimed++;
if ((search->it_flags & ITEM_FETCHED) == 0) {
STATS_LOCK();
stats.expired_unfetched++;
STATS_UNLOCK();
itemstats[id].expired_unfetched++;
}
it = search;
slabs_adjust_mem_requested(it->slabs_clsid, ITEM_ntotal(it), ntotal);
do_item_unlink_nolock(it, hash(ITEM_key(it), it->nkey, 0));
/* Initialize the item block: */
it->slabs_clsid = 0;
} else if ((it = slabs_alloc(ntotal, id)) == NULL) {
if (settings.evict_to_free == 0) {
itemstats[id].outofmemory++;
pthread_mutex_unlock(&cache_lock);
return NULL;
}
itemstats[id].evicted++;
itemstats[id].evicted_time = current_time - search->time;
if (search->exptime != 0)
itemstats[id].evicted_nonzero++;
if ((search->it_flags & ITEM_FETCHED) == 0) {
STATS_LOCK();
stats.evicted_unfetched++;
STATS_UNLOCK();
itemstats[id].evicted_unfetched++;
}
STATS_LOCK();
stats.evictions++;
STATS_UNLOCK();
it = search;
slabs_adjust_mem_requested(it->slabs_clsid, ITEM_ntotal(it), ntotal);
do_item_unlink_nolock(it, hash(ITEM_key(it), it->nkey, 0));
/* Initialize the item block: */
it->slabs_clsid = 0;
} else {
refcount_decr(&search->refcount);
}
} else {
/* If the LRU is empty or locked, attempt to allocate memory */
it = slabs_alloc(ntotal, id);
if (search != NULL)
refcount_decr(&search->refcount);
}
if (it == NULL) {
itemstats[id].outofmemory++;
/* Last ditch effort. There was a very rare bug which caused
* refcount leaks. We leave this just in case they ever happen again.
* We can reasonably assume no item can stay locked for more than
* three hours, so if we find one in the tail which is that old,
* free it anyway.
*/
if (search != NULL &&
search->refcount != 2 &&
search->time + TAIL_REPAIR_TIME < current_time) {
itemstats[id].tailrepairs++;
search->refcount = 1;
do_item_unlink_nolock(search, hash(ITEM_key(search), search->nkey, 0));
}
pthread_mutex_unlock(&cache_lock);
return NULL;
}
assert(it->slabs_clsid == 0);
assert(it != heads[id]);
/* Item initialization can happen outside of the lock; the item's already
* been removed from the slab LRU.
*/
it->refcount = 1; /* the caller will have a reference */
pthread_mutex_unlock(&cache_lock);
it->next = it->prev = it->h_next = 0;
it->slabs_clsid = id;
DEBUG_REFCNT(it, '*');
it->it_flags = settings.use_cas ? ITEM_CAS : 0;
it->nkey = nkey;
it->nbytes = nbytes;
memcpy(ITEM_key(it), key, nkey);
it->exptime = exptime;
memcpy(ITEM_suffix(it), suffix, (size_t)nsuffix);
it->nsuffix = nsuffix;
return it;
}
void item_free(item *it) {
size_t ntotal = ITEM_ntotal(it);
unsigned int clsid;
assert((it->it_flags & ITEM_LINKED) == 0);
assert(it != heads[it->slabs_clsid]);
assert(it != tails[it->slabs_clsid]);
assert(it->refcount == 0);
/* so slab size changer can tell later if item is already free or not */
clsid = it->slabs_clsid;
it->slabs_clsid = 0;
DEBUG_REFCNT(it, 'F');
slabs_free(it, ntotal, clsid);
}
/**
* Returns true if an item will fit in the cache (its size does not exceed
* the maximum for a cache entry.)
*/
bool item_size_ok(const size_t nkey, const int flags, const int nbytes) {
char prefix[40];
uint8_t nsuffix;
size_t ntotal = item_make_header(nkey + 1, flags, nbytes,
prefix, &nsuffix);
if (settings.use_cas) {
ntotal += sizeof(uint64_t);
}
return slabs_clsid(ntotal) != 0;
}
static void item_link_q(item *it) { /* item is the new head */
item **head, **tail;
assert(it->slabs_clsid < LARGEST_ID);
assert((it->it_flags & ITEM_SLABBED) == 0);
head = &heads[it->slabs_clsid];
tail = &tails[it->slabs_clsid];
assert(it != *head);
assert((*head && *tail) || (*head == 0 && *tail == 0));
it->prev = 0;
it->next = *head;
if (it->next) it->next->prev = it;
*head = it;
if (*tail == 0) *tail = it;
sizes[it->slabs_clsid]++;
return;
}
static void item_unlink_q(item *it) {
item **head, **tail;
assert(it->slabs_clsid < LARGEST_ID);
head = &heads[it->slabs_clsid];
tail = &tails[it->slabs_clsid];
if (*head == it) {
assert(it->prev == 0);
*head = it->next;
}
if (*tail == it) {
assert(it->next == 0);
*tail = it->prev;
}
assert(it->next != it);
assert(it->prev != it);
if (it->next) it->next->prev = it->prev;
if (it->prev) it->prev->next = it->next;
sizes[it->slabs_clsid]--;
return;
}
int do_item_link(item *it, const uint32_t hv) {
MEMCACHED_ITEM_LINK(ITEM_key(it), it->nkey, it->nbytes);
assert((it->it_flags & (ITEM_LINKED|ITEM_SLABBED)) == 0);
mutex_lock(&cache_lock);
it->it_flags |= ITEM_LINKED;
it->time = current_time;
STATS_LOCK();
stats.curr_bytes += ITEM_ntotal(it);
stats.curr_items += 1;
stats.total_items += 1;
STATS_UNLOCK();
/* Allocate a new CAS ID on link. */
ITEM_set_cas(it, (settings.use_cas) ? get_cas_id() : 0);
assoc_insert(it, hv);
item_link_q(it);
refcount_incr(&it->refcount);
pthread_mutex_unlock(&cache_lock);
return 1;
}
void do_item_unlink(item *it, const uint32_t hv) {
MEMCACHED_ITEM_UNLINK(ITEM_key(it), it->nkey, it->nbytes);
mutex_lock(&cache_lock);
if ((it->it_flags & ITEM_LINKED) != 0) {
it->it_flags &= ~ITEM_LINKED;
STATS_LOCK();
stats.curr_bytes -= ITEM_ntotal(it);
stats.curr_items -= 1;
STATS_UNLOCK();
assoc_delete(ITEM_key(it), it->nkey, hv);
item_unlink_q(it);
do_item_remove(it);
}
pthread_mutex_unlock(&cache_lock);
}
/* FIXME: Is it necessary to keep this copy/pasted code? */
void do_item_unlink_nolock(item *it, const uint32_t hv) {
MEMCACHED_ITEM_UNLINK(ITEM_key(it), it->nkey, it->nbytes);
if ((it->it_flags & ITEM_LINKED) != 0) {
it->it_flags &= ~ITEM_LINKED;
STATS_LOCK();
stats.curr_bytes -= ITEM_ntotal(it);
stats.curr_items -= 1;
STATS_UNLOCK();
assoc_delete(ITEM_key(it), it->nkey, hv);
item_unlink_q(it);
do_item_remove(it);
}
}
void do_item_remove(item *it) {
MEMCACHED_ITEM_REMOVE(ITEM_key(it), it->nkey, it->nbytes);
assert((it->it_flags & ITEM_SLABBED) == 0);
if (refcount_decr(&it->refcount) == 0) {
item_free(it);
}
}
void do_item_update(item *it) {
MEMCACHED_ITEM_UPDATE(ITEM_key(it), it->nkey, it->nbytes);
if (it->time < current_time - ITEM_UPDATE_INTERVAL) {
assert((it->it_flags & ITEM_SLABBED) == 0);
mutex_lock(&cache_lock);
if ((it->it_flags & ITEM_LINKED) != 0) {
item_unlink_q(it);
it->time = current_time;
item_link_q(it);
}
pthread_mutex_unlock(&cache_lock);
}
}
int do_item_replace(item *it, item *new_it, const uint32_t hv) {
MEMCACHED_ITEM_REPLACE(ITEM_key(it), it->nkey, it->nbytes,
ITEM_key(new_it), new_it->nkey, new_it->nbytes);
assert((it->it_flags & ITEM_SLABBED) == 0);
do_item_unlink(it, hv);
return do_item_link(new_it, hv);
}
#ifndef __INTEL_COMPILER
#pragma GCC diagnostic ignored "-Wshadow"
#endif
/*@null@*/
char *do_item_cachedump(const unsigned int slabs_clsid, const unsigned int limit, unsigned int *bytes) {
unsigned int memlimit = 2 * 1024 * 1024; /* 2MB max response size */
char *buffer;
unsigned int bufcurr;
item *it;
unsigned int len;
unsigned int shown = 0;
char key_temp[KEY_MAX_LENGTH + 1];
char temp[512];
it = heads[slabs_clsid];
buffer = malloc((size_t)memlimit);
if (buffer == 0) return NULL;
bufcurr = 0;
while (it != NULL && (limit == 0 || shown < limit)) {
assert(it->nkey <= KEY_MAX_LENGTH);
/* Copy the key since it may not be null-terminated in the struct */
strncpy(key_temp, ITEM_key(it), it->nkey);
key_temp[it->nkey] = 0x00; /* terminate */
len = snprintf(temp, sizeof(temp), "ITEM %s [%d b; %lu s]\r\n",
key_temp, it->nbytes - 2,
(unsigned long)it->exptime + process_started);
if (bufcurr + len + 6 > memlimit) /* 6 is END\r\n\0 */
break;
memcpy(buffer + bufcurr, temp, len);
bufcurr += len;
shown++;
it = it->next;
}
memcpy(buffer + bufcurr, "END\r\n", 6);
bufcurr += 5;
*bytes = bufcurr;
return buffer;
}
void item_stats_evictions(uint64_t *evicted) {
int i;
mutex_lock(&cache_lock);
for (i = 0; i < LARGEST_ID; i++) {
evicted[i] = itemstats[i].evicted;
}
pthread_mutex_unlock(&cache_lock);
}
void do_item_stats(ADD_STAT add_stats, void *c) {
int i;
for (i = 0; i < LARGEST_ID; i++) {
if (tails[i] != NULL) {
const char *fmt = "items:%d:%s";
char key_str[STAT_KEY_LEN];
char val_str[STAT_VAL_LEN];
int klen = 0, vlen = 0;
if (tails[i] == NULL) {
/* We removed all of the items in this slab class */
continue;
}
APPEND_NUM_FMT_STAT(fmt, i, "number", "%u", sizes[i]);
APPEND_NUM_FMT_STAT(fmt, i, "age", "%u", current_time - tails[i]->time);
APPEND_NUM_FMT_STAT(fmt, i, "evicted",
"%llu", (unsigned long long)itemstats[i].evicted);
APPEND_NUM_FMT_STAT(fmt, i, "evicted_nonzero",
"%llu", (unsigned long long)itemstats[i].evicted_nonzero);
APPEND_NUM_FMT_STAT(fmt, i, "evicted_time",
"%u", itemstats[i].evicted_time);
APPEND_NUM_FMT_STAT(fmt, i, "outofmemory",
"%llu", (unsigned long long)itemstats[i].outofmemory);
APPEND_NUM_FMT_STAT(fmt, i, "tailrepairs",
"%llu", (unsigned long long)itemstats[i].tailrepairs);
APPEND_NUM_FMT_STAT(fmt, i, "reclaimed",
"%llu", (unsigned long long)itemstats[i].reclaimed);
APPEND_NUM_FMT_STAT(fmt, i, "expired_unfetched",
"%llu", (unsigned long long)itemstats[i].expired_unfetched);
APPEND_NUM_FMT_STAT(fmt, i, "evicted_unfetched",
"%llu", (unsigned long long)itemstats[i].evicted_unfetched);
}
}
/* getting here means both ascii and binary terminators fit */
add_stats(NULL, 0, NULL, 0, c);
}
/** dumps out a list of objects of each size, with granularity of 32 bytes */
/*@null@*/
void do_item_stats_sizes(ADD_STAT add_stats, void *c) {
/* max 1MB object, divided into 32 bytes size buckets */
const int num_buckets = 32768;
unsigned int *histogram = calloc(num_buckets, sizeof(int));
if (histogram != NULL) {
int i;
/* build the histogram */
for (i = 0; i < LARGEST_ID; i++) {
item *iter = heads[i];
while (iter) {
int ntotal = ITEM_ntotal(iter);
int bucket = ntotal / 32;
if ((ntotal % 32) != 0) bucket++;
if (bucket < num_buckets) histogram[bucket]++;
iter = iter->next;
}
}
/* write the buffer */
for (i = 0; i < num_buckets; i++) {
if (histogram[i] != 0) {
char key[8];
snprintf(key, sizeof(key), "%d", i * 32);
APPEND_STAT(key, "%u", histogram[i]);
}
}
free(histogram);
}
add_stats(NULL, 0, NULL, 0, c);
}
/** wrapper around assoc_find which does the lazy expiration logic */
item *do_item_get(const char *key, const size_t nkey, const uint32_t hv) {
mutex_lock(&cache_lock);
item *it = assoc_find(key, nkey, hv);
if (it != NULL) {
refcount_incr(&it->refcount);
/* Optimization for slab reassignment. prevents popular items from
* jamming in busy wait. Can only do this here to satisfy lock order
* of item_lock, cache_lock, slabs_lock. */
if (slab_rebalance_signal &&
((void *)it >= slab_rebal.slab_start && (void *)it < slab_rebal.slab_end)) {
do_item_unlink_nolock(it, hv);
do_item_remove(it);
it = NULL;
}
}
pthread_mutex_unlock(&cache_lock);
int was_found = 0;
if (settings.verbose > 2) {
if (it == NULL) {
fprintf(stderr, "> NOT FOUND %s", key);
} else {
fprintf(stderr, "> FOUND KEY %s", ITEM_key(it));
was_found++;
}
}
if (it != NULL) {
if (settings.oldest_live != 0 && settings.oldest_live <= current_time &&
it->time <= settings.oldest_live) {
do_item_unlink(it, hv);
do_item_remove(it);
it = NULL;
if (was_found) {
fprintf(stderr, " -nuked by flush");
}
} else if (it->exptime != 0 && it->exptime <= current_time) {
do_item_unlink(it, hv);
do_item_remove(it);
it = NULL;
if (was_found) {
fprintf(stderr, " -nuked by expire");
}
} else {
it->it_flags |= ITEM_FETCHED;
DEBUG_REFCNT(it, '+');
}
}
if (settings.verbose > 2)
fprintf(stderr, "\n");
return it;
}
item *do_item_touch(const char *key, size_t nkey, uint32_t exptime,
const uint32_t hv) {
item *it = do_item_get(key, nkey, hv);
if (it != NULL) {
it->exptime = exptime;
}
return it;
}
/* expires items that are more recent than the oldest_live setting. */
void do_item_flush_expired(void) {
int i;
item *iter, *next;
if (settings.oldest_live == 0)
return;
for (i = 0; i < LARGEST_ID; i++) {
/* The LRU is sorted in decreasing time order, and an item's timestamp
* is never newer than its last access time, so we only need to walk
* back until we hit an item older than the oldest_live time.
* The oldest_live checking will auto-expire the remaining items.
*/
for (iter = heads[i]; iter != NULL; iter = next) {
if (iter->time >= settings.oldest_live) {
next = iter->next;
if ((iter->it_flags & ITEM_SLABBED) == 0) {
do_item_unlink_nolock(iter, hash(ITEM_key(iter), iter->nkey, 0));
}
} else {
/* We've hit the first old item. Continue to the next queue. */
break;
}
}
}
}
|