db.c 14.8 KB
Newer Older
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
#include "redis.h"

#include <signal.h>

/*-----------------------------------------------------------------------------
 * C-level DB API
 *----------------------------------------------------------------------------*/

robj *lookupKey(redisDb *db, robj *key) {
    dictEntry *de = dictFind(db->dict,key->ptr);
    if (de) {
        robj *val = dictGetEntryVal(de);

        if (server.vm_enabled) {
            if (val->storage == REDIS_VM_MEMORY ||
                val->storage == REDIS_VM_SWAPPING)
            {
                /* If we were swapping the object out, cancel the operation */
                if (val->storage == REDIS_VM_SWAPPING)
                    vmCancelThreadedIOJob(val);
                /* Update the access time for the aging algorithm. */
                val->lru = server.lruclock;
            } else {
                int notify = (val->storage == REDIS_VM_LOADING);

                /* Our value was swapped on disk. Bring it at home. */
                redisAssert(val->type == REDIS_VMPOINTER);
                val = vmLoadObject(val);
                dictGetEntryVal(de) = val;

                /* Clients blocked by the VM subsystem may be waiting for
                 * this key... */
                if (notify) handleClientsBlockedOnSwappedKey(db,key);
            }
        }
        return val;
    } else {
        return NULL;
    }
}

robj *lookupKeyRead(redisDb *db, robj *key) {
    expireIfNeeded(db,key);
    return lookupKey(db,key);
}

robj *lookupKeyWrite(redisDb *db, robj *key) {
48
    expireIfNeeded(db,key);
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
    return lookupKey(db,key);
}

robj *lookupKeyReadOrReply(redisClient *c, robj *key, robj *reply) {
    robj *o = lookupKeyRead(c->db, key);
    if (!o) addReply(c,reply);
    return o;
}

robj *lookupKeyWriteOrReply(redisClient *c, robj *key, robj *reply) {
    robj *o = lookupKeyWrite(c->db, key);
    if (!o) addReply(c,reply);
    return o;
}

/* Add the key to the DB. If the key already exists REDIS_ERR is returned,
 * otherwise REDIS_OK is returned, and the caller should increment the
 * refcount of 'val'. */
int dbAdd(redisDb *db, robj *key, robj *val) {
    /* Perform a lookup before adding the key, as we need to copy the
     * key value. */
    if (dictFind(db->dict, key->ptr) != NULL) {
        return REDIS_ERR;
    } else {
        sds copy = sdsdup(key->ptr);
        dictAdd(db->dict, copy, val);
        return REDIS_OK;
    }
}

/* If the key does not exist, this is just like dbAdd(). Otherwise
 * the value associated to the key is replaced with the new one.
 *
 * On update (key already existed) 0 is returned. Otherwise 1. */
int dbReplace(redisDb *db, robj *key, robj *val) {
    if (dictFind(db->dict,key->ptr) == NULL) {
        sds copy = sdsdup(key->ptr);
        dictAdd(db->dict, copy, val);
        return 1;
    } else {
        dictReplace(db->dict, key->ptr, val);
        return 0;
    }
}

int dbExists(redisDb *db, robj *key) {
    return dictFind(db->dict,key->ptr) != NULL;
}

/* Return a random key, in form of a Redis object.
 * If there are no keys, NULL is returned.
 *
 * The function makes sure to return keys not already expired. */
robj *dbRandomKey(redisDb *db) {
    struct dictEntry *de;

    while(1) {
        sds key;
        robj *keyobj;

        de = dictGetRandomKey(db->dict);
        if (de == NULL) return NULL;

        key = dictGetEntryKey(de);
        keyobj = createStringObject(key,sdslen(key));
        if (dictFind(db->expires,key)) {
            if (expireIfNeeded(db,keyobj)) {
                decrRefCount(keyobj);
                continue; /* search for another key. This expired. */
            }
        }
        return keyobj;
    }
}

/* Delete a key, value, and associated expiration entry if any, from the DB */
int dbDelete(redisDb *db, robj *key) {
    /* Deleting an entry from the expires dict will not free the sds of
     * the key, because it is shared with the main dictionary. */
    if (dictSize(db->expires) > 0) dictDelete(db->expires,key->ptr);
    return dictDelete(db->dict,key->ptr) == DICT_OK;
}

/* Empty the whole database */
long long emptyDb() {
    int j;
    long long removed = 0;

    for (j = 0; j < server.dbnum; j++) {
        removed += dictSize(server.db[j].dict);
        dictEmpty(server.db[j].dict);
        dictEmpty(server.db[j].expires);
    }
    return removed;
}

int selectDb(redisClient *c, int id) {
    if (id < 0 || id >= server.dbnum)
        return REDIS_ERR;
    c->db = &server.db[id];
    return REDIS_OK;
}

/*-----------------------------------------------------------------------------
 * Type agnostic commands operating on the key space
 *----------------------------------------------------------------------------*/

void flushdbCommand(redisClient *c) {
    server.dirty += dictSize(c->db->dict);
    touchWatchedKeysOnFlush(c->db->id);
    dictEmpty(c->db->dict);
    dictEmpty(c->db->expires);
    addReply(c,shared.ok);
}

void flushallCommand(redisClient *c) {
    touchWatchedKeysOnFlush(-1);
    server.dirty += emptyDb();
    addReply(c,shared.ok);
    if (server.bgsavechildpid != -1) {
        kill(server.bgsavechildpid,SIGKILL);
        rdbRemoveTempFile(server.bgsavechildpid);
    }
    rdbSave(server.dbfilename);
    server.dirty++;
}

void delCommand(redisClient *c) {
    int deleted = 0, j;

    for (j = 1; j < c->argc; j++) {
        if (dbDelete(c->db,c->argv[j])) {
            touchWatchedKey(c->db,c->argv[j]);
            server.dirty++;
            deleted++;
        }
    }
    addReplyLongLong(c,deleted);
}

void existsCommand(redisClient *c) {
    expireIfNeeded(c->db,c->argv[1]);
    if (dbExists(c->db,c->argv[1])) {
        addReply(c, shared.cone);
    } else {
        addReply(c, shared.czero);
    }
}

void selectCommand(redisClient *c) {
    int id = atoi(c->argv[1]->ptr);

    if (selectDb(c,id) == REDIS_ERR) {
        addReplySds(c,sdsnew("-ERR invalid DB index\r\n"));
    } else {
        addReply(c,shared.ok);
    }
}

void randomkeyCommand(redisClient *c) {
    robj *key;

    if ((key = dbRandomKey(c->db)) == NULL) {
        addReply(c,shared.nullbulk);
        return;
    }

    addReplyBulk(c,key);
    decrRefCount(key);
}

void keysCommand(redisClient *c) {
    dictIterator *di;
    dictEntry *de;
    sds pattern = c->argv[1]->ptr;
    int plen = sdslen(pattern);
    unsigned long numkeys = 0;
    robj *lenobj = createObject(REDIS_STRING,NULL);

    di = dictGetIterator(c->db->dict);
    addReply(c,lenobj);
    decrRefCount(lenobj);
    while((de = dictNext(di)) != NULL) {
        sds key = dictGetEntryKey(de);
        robj *keyobj;

        if ((pattern[0] == '*' && pattern[1] == '\0') ||
            stringmatchlen(pattern,plen,key,sdslen(key),0)) {
            keyobj = createStringObject(key,sdslen(key));
            if (expireIfNeeded(c->db,keyobj) == 0) {
                addReplyBulk(c,keyobj);
                numkeys++;
            }
            decrRefCount(keyobj);
        }
    }
    dictReleaseIterator(di);
    lenobj->ptr = sdscatprintf(sdsempty(),"*%lu\r\n",numkeys);
}

void dbsizeCommand(redisClient *c) {
    addReplySds(c,
        sdscatprintf(sdsempty(),":%lu\r\n",dictSize(c->db->dict)));
}

void lastsaveCommand(redisClient *c) {
    addReplySds(c,
        sdscatprintf(sdsempty(),":%lu\r\n",server.lastsave));
}

void typeCommand(redisClient *c) {
    robj *o;
    char *type;

    o = lookupKeyRead(c->db,c->argv[1]);
    if (o == NULL) {
        type = "+none";
    } else {
        switch(o->type) {
        case REDIS_STRING: type = "+string"; break;
        case REDIS_LIST: type = "+list"; break;
        case REDIS_SET: type = "+set"; break;
        case REDIS_ZSET: type = "+zset"; break;
        case REDIS_HASH: type = "+hash"; break;
        default: type = "+unknown"; break;
        }
    }
    addReplySds(c,sdsnew(type));
    addReply(c,shared.crlf);
}

void saveCommand(redisClient *c) {
    if (server.bgsavechildpid != -1) {
        addReplySds(c,sdsnew("-ERR background save in progress\r\n"));
        return;
    }
    if (rdbSave(server.dbfilename) == REDIS_OK) {
        addReply(c,shared.ok);
    } else {
        addReply(c,shared.err);
    }
}

void bgsaveCommand(redisClient *c) {
    if (server.bgsavechildpid != -1) {
        addReplySds(c,sdsnew("-ERR background save already in progress\r\n"));
        return;
    }
    if (rdbSaveBackground(server.dbfilename) == REDIS_OK) {
        char *status = "+Background saving started\r\n";
        addReplySds(c,sdsnew(status));
    } else {
        addReply(c,shared.err);
    }
}

void shutdownCommand(redisClient *c) {
    if (prepareForShutdown() == REDIS_OK)
        exit(0);
    addReplySds(c, sdsnew("-ERR Errors trying to SHUTDOWN. Check logs.\r\n"));
}

void renameGenericCommand(redisClient *c, int nx) {
    robj *o;

    /* To use the same key as src and dst is probably an error */
    if (sdscmp(c->argv[1]->ptr,c->argv[2]->ptr) == 0) {
        addReply(c,shared.sameobjecterr);
        return;
    }

    if ((o = lookupKeyWriteOrReply(c,c->argv[1],shared.nokeyerr)) == NULL)
        return;

    incrRefCount(o);
    if (dbAdd(c->db,c->argv[2],o) == REDIS_ERR) {
        if (nx) {
            decrRefCount(o);
            addReply(c,shared.czero);
            return;
        }
        dbReplace(c->db,c->argv[2],o);
    }
    dbDelete(c->db,c->argv[1]);
333
    touchWatchedKey(c->db,c->argv[1]);
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
    touchWatchedKey(c->db,c->argv[2]);
    server.dirty++;
    addReply(c,nx ? shared.cone : shared.ok);
}

void renameCommand(redisClient *c) {
    renameGenericCommand(c,0);
}

void renamenxCommand(redisClient *c) {
    renameGenericCommand(c,1);
}

void moveCommand(redisClient *c) {
    robj *o;
    redisDb *src, *dst;
    int srcid;

    /* Obtain source and target DB pointers */
    src = c->db;
    srcid = c->db->id;
    if (selectDb(c,atoi(c->argv[2]->ptr)) == REDIS_ERR) {
        addReply(c,shared.outofrangeerr);
        return;
    }
    dst = c->db;
    selectDb(c,srcid); /* Back to the source DB */

    /* If the user is moving using as target the same
     * DB as the source DB it is probably an error. */
    if (src == dst) {
        addReply(c,shared.sameobjecterr);
        return;
    }

    /* Check if the element exists and get a reference */
    o = lookupKeyWrite(c->db,c->argv[1]);
    if (!o) {
        addReply(c,shared.czero);
        return;
    }

    /* Try to add the element to the target DB */
    if (dbAdd(dst,c->argv[1],o) == REDIS_ERR) {
        addReply(c,shared.czero);
        return;
    }
    incrRefCount(o);

    /* OK! key moved, free the entry in the source DB */
    dbDelete(src,c->argv[1]);
    server.dirty++;
    addReply(c,shared.cone);
}

/*-----------------------------------------------------------------------------
 * Expires API
 *----------------------------------------------------------------------------*/

int removeExpire(redisDb *db, robj *key) {
    /* An expire may only be removed if there is a corresponding entry in the
     * main dict. Otherwise, the key will never be freed. */
    redisAssert(dictFind(db->dict,key->ptr) != NULL);
    if (dictDelete(db->expires,key->ptr) == DICT_OK) {
        return 1;
    } else {
        return 0;
    }
}

int setExpire(redisDb *db, robj *key, time_t when) {
    dictEntry *de;

    /* Reuse the sds from the main dict in the expire dict */
    redisAssert((de = dictFind(db->dict,key->ptr)) != NULL);
    if (dictAdd(db->expires,dictGetEntryKey(de),(void*)when) == DICT_ERR) {
        return 0;
    } else {
        return 1;
    }
}

/* Return the expire time of the specified key, or -1 if no expire
 * is associated with this key (i.e. the key is non volatile) */
time_t getExpire(redisDb *db, robj *key) {
    dictEntry *de;

    /* No expire? return ASAP */
    if (dictSize(db->expires) == 0 ||
       (de = dictFind(db->expires,key->ptr)) == NULL) return -1;

    /* The entry was found in the expire dict, this means it should also
     * be present in the main dict (safety check). */
    redisAssert(dictFind(db->dict,key->ptr) != NULL);
    return (time_t) dictGetEntryVal(de);
}

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
/* Propagate expires into slaves and the AOF file.
 * When a key expires in the master, a DEL operation for this key is sent
 * to all the slaves and the AOF file if enabled.
 *
 * This way the key expiry is centralized in one place, and since both
 * AOF and the master->slave link guarantee operation ordering, everything
 * will be consistent even if we allow write operations against expiring
 * keys. */
void propagateExpire(redisDb *db, robj *key) {
    struct redisCommand *cmd;
    robj *argv[2];

    cmd = lookupCommand("del");
    argv[0] = createStringObject("DEL",3);
    argv[1] = key;
    incrRefCount(key);

    if (server.appendonly)
        feedAppendOnlyFile(cmd,db->id,argv,2);
    if (listLength(server.slaves))
        replicationFeedSlaves(server.slaves,db->id,argv,2);

    decrRefCount(key);
}

456 457
int expireIfNeeded(redisDb *db, robj *key) {
    time_t when = getExpire(db,key);
458 459 460 461 462 463 464 465 466 467 468 469

    /* If we are running in the context of a slave, return ASAP:
     * the slave key expiration is controlled by the master that will
     * send us synthesized DEL operations for expired keys.
     *
     * Still we try to return the right information to the caller, 
     * that is, 0 if we think the key should be still valid, 1 if
     * we think the key is expired at this time. */
    if (server.masterhost != NULL) {
        return time(NULL) > when;
    }

470 471 472 473 474 475 476 477
    if (when < 0) return 0;

    /* Return when this key has not expired */
    if (time(NULL) <= when) return 0;

    /* Delete the key */
    server.stat_expiredkeys++;
    server.dirty++;
478
    propagateExpire(db,key);
479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501
    return dbDelete(db,key);
}

/*-----------------------------------------------------------------------------
 * Expires Commands
 *----------------------------------------------------------------------------*/

void expireGenericCommand(redisClient *c, robj *key, robj *param, long offset) {
    dictEntry *de;
    time_t seconds;

    if (getLongFromObjectOrReply(c, param, &seconds, NULL) != REDIS_OK) return;

    seconds -= offset;

    de = dictFind(c->db->dict,key->ptr);
    if (de == NULL) {
        addReply(c,shared.czero);
        return;
    }
    if (seconds <= 0) {
        if (dbDelete(c->db,key)) server.dirty++;
        addReply(c, shared.cone);
502
        touchWatchedKey(c->db,key);
503 504 505 506 507
        return;
    } else {
        time_t when = time(NULL)+seconds;
        if (setExpire(c->db,key,when)) {
            addReply(c,shared.cone);
508
            touchWatchedKey(c->db,key);
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
            server.dirty++;
        } else {
            addReply(c,shared.czero);
        }
        return;
    }
}

void expireCommand(redisClient *c) {
    expireGenericCommand(c,c->argv[1],c->argv[2],0);
}

void expireatCommand(redisClient *c) {
    expireGenericCommand(c,c->argv[1],c->argv[2],time(NULL));
}

void ttlCommand(redisClient *c) {
    time_t expire;
    int ttl = -1;

    expire = getExpire(c->db,c->argv[1]);
    if (expire != -1) {
        ttl = (int) (expire-time(NULL));
        if (ttl < 0) ttl = -1;
    }
    addReplySds(c,sdscatprintf(sdsempty(),":%d\r\n",ttl));
}