/* * Copyright (c) 2009-2010, Salvatore Sanfilippo * All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: * * * Redistributions of source code must retain the above copyright notice, * this list of conditions and the following disclaimer. * * Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * * Neither the name of Redis nor the names of its contributors may be used * to endorse or promote products derived from this software without * specific prior written permission. * * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE * POSSIBILITY OF SUCH DAMAGE. */ #include "redis.h" #include "slowlog.h" #include "bio.h" #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include /* Our shared "common" objects */ struct sharedObjectsStruct shared; /* Global vars that are actually used as constants. The following double * values are used for double on-disk serialization, and are initialized * at runtime to avoid strange compiler optimizations. */ double R_Zero, R_PosInf, R_NegInf, R_Nan; /*================================= Globals ================================= */ /* Global vars */ struct redisServer server; /* server global state */ struct redisCommand *commandTable; /* Our command table. * * Every entry is composed of the following fields: * * name: a string representing the command name. * function: pointer to the C function implementing the command. * arity: number of arguments, it is possible to use -N to say >= N * sflags: command flags as string. See below for a table of flags. * flags: flags as bitmask. Computed by Redis using the 'sflags' field. * get_keys_proc: an optional function to get key arguments from a command. * This is only used when the following three fields are not * enough to specify what arguments are keys. * first_key_index: first argument that is a key * last_key_index: last argument that is a key * key_step: step to get all the keys from first to last argument. For instance * in MSET the step is two since arguments are key,val,key,val,... * microseconds: microseconds of total execution time for this command. * calls: total number of calls of this command. * * The flags, microseconds and calls fields are computed by Redis and should * always be set to zero. * * Command flags are expressed using strings where every character represents * a flag. Later the populateCommandTable() function will take care of * populating the real 'flags' field using this characters. * * This is the meaning of the flags: * * w: write command (may modify the key space). * r: read command (will never modify the key space). * m: may increase memory usage once called. Don't allow if out of memory. * a: admin command, like SAVE or SHUTDOWN. * p: Pub/Sub related command. * f: force replication of this command, regarless of server.dirty. * s: command not allowed in scripts. * R: random command. Command is not deterministic, that is, the same command * with the same arguments, with the same key space, may have different * results. For instance SPOP and RANDOMKEY are two random commands. * S: Sort command output array if called from script, so that the output * is deterministic. */ struct redisCommand redisCommandTable[] = { {"get",getCommand,2,"r",0,NULL,1,1,1,0,0}, {"set",setCommand,3,"wm",0,noPreloadGetKeys,1,1,1,0,0}, {"setnx",setnxCommand,3,"wm",0,noPreloadGetKeys,1,1,1,0,0}, {"setex",setexCommand,4,"wm",0,noPreloadGetKeys,1,1,1,0,0}, {"psetex",psetexCommand,4,"wm",0,noPreloadGetKeys,1,1,1,0,0}, {"append",appendCommand,3,"wm",0,NULL,1,1,1,0,0}, {"strlen",strlenCommand,2,"r",0,NULL,1,1,1,0,0}, {"del",delCommand,-2,"w",0,noPreloadGetKeys,1,-1,1,0,0}, {"exists",existsCommand,2,"r",0,NULL,1,1,1,0,0}, {"setbit",setbitCommand,4,"wm",0,NULL,1,1,1,0,0}, {"getbit",getbitCommand,3,"r",0,NULL,1,1,1,0,0}, {"setrange",setrangeCommand,4,"wm",0,NULL,1,1,1,0,0}, {"getrange",getrangeCommand,4,"r",0,NULL,1,1,1,0,0}, {"substr",getrangeCommand,4,"r",0,NULL,1,1,1,0,0}, {"incr",incrCommand,2,"wm",0,NULL,1,1,1,0,0}, {"decr",decrCommand,2,"wm",0,NULL,1,1,1,0,0}, {"mget",mgetCommand,-2,"r",0,NULL,1,-1,1,0,0}, {"rpush",rpushCommand,-3,"wm",0,NULL,1,1,1,0,0}, {"lpush",lpushCommand,-3,"wm",0,NULL,1,1,1,0,0}, {"rpushx",rpushxCommand,3,"wm",0,NULL,1,1,1,0,0}, {"lpushx",lpushxCommand,3,"wm",0,NULL,1,1,1,0,0}, {"linsert",linsertCommand,5,"wm",0,NULL,1,1,1,0,0}, {"rpop",rpopCommand,2,"w",0,NULL,1,1,1,0,0}, {"lpop",lpopCommand,2,"w",0,NULL,1,1,1,0,0}, {"brpop",brpopCommand,-3,"ws",0,NULL,1,1,1,0,0}, {"brpoplpush",brpoplpushCommand,4,"wms",0,NULL,1,2,1,0,0}, {"blpop",blpopCommand,-3,"ws",0,NULL,1,-2,1,0,0}, {"llen",llenCommand,2,"r",0,NULL,1,1,1,0,0}, {"lindex",lindexCommand,3,"r",0,NULL,1,1,1,0,0}, {"lset",lsetCommand,4,"wm",0,NULL,1,1,1,0,0}, {"lrange",lrangeCommand,4,"r",0,NULL,1,1,1,0,0}, {"ltrim",ltrimCommand,4,"w",0,NULL,1,1,1,0,0}, {"lrem",lremCommand,4,"w",0,NULL,1,1,1,0,0}, {"rpoplpush",rpoplpushCommand,3,"wm",0,NULL,1,2,1,0,0}, {"sadd",saddCommand,-3,"wm",0,NULL,1,1,1,0,0}, {"srem",sremCommand,-3,"w",0,NULL,1,1,1,0,0}, {"smove",smoveCommand,4,"w",0,NULL,1,2,1,0,0}, {"sismember",sismemberCommand,3,"r",0,NULL,1,1,1,0,0}, {"scard",scardCommand,2,"r",0,NULL,1,1,1,0,0}, {"spop",spopCommand,2,"wRs",0,NULL,1,1,1,0,0}, {"srandmember",srandmemberCommand,2,"rR",0,NULL,1,1,1,0,0}, {"sinter",sinterCommand,-2,"rS",0,NULL,1,-1,1,0,0}, {"sinterstore",sinterstoreCommand,-3,"wm",0,NULL,1,-1,1,0,0}, {"sunion",sunionCommand,-2,"rS",0,NULL,1,-1,1,0,0}, {"sunionstore",sunionstoreCommand,-3,"wm",0,NULL,1,-1,1,0,0}, {"sdiff",sdiffCommand,-2,"rS",0,NULL,1,-1,1,0,0}, {"sdiffstore",sdiffstoreCommand,-3,"wm",0,NULL,1,-1,1,0,0}, {"smembers",sinterCommand,2,"rS",0,NULL,1,1,1,0,0}, {"zadd",zaddCommand,-4,"wm",0,NULL,1,1,1,0,0}, {"zincrby",zincrbyCommand,4,"wm",0,NULL,1,1,1,0,0}, {"zrem",zremCommand,-3,"w",0,NULL,1,1,1,0,0}, {"zremrangebyscore",zremrangebyscoreCommand,4,"w",0,NULL,1,1,1,0,0}, {"zremrangebyrank",zremrangebyrankCommand,4,"w",0,NULL,1,1,1,0,0}, {"zunionstore",zunionstoreCommand,-4,"wm",0,zunionInterGetKeys,0,0,0,0,0}, {"zinterstore",zinterstoreCommand,-4,"wm",0,zunionInterGetKeys,0,0,0,0,0}, {"zrange",zrangeCommand,-4,"r",0,NULL,1,1,1,0,0}, {"zrangebyscore",zrangebyscoreCommand,-4,"r",0,NULL,1,1,1,0,0}, {"zrevrangebyscore",zrevrangebyscoreCommand,-4,"r",0,NULL,1,1,1,0,0}, {"zcount",zcountCommand,4,"r",0,NULL,1,1,1,0,0}, {"zrevrange",zrevrangeCommand,-4,"r",0,NULL,1,1,1,0,0}, {"zcard",zcardCommand,2,"r",0,NULL,1,1,1,0,0}, {"zscore",zscoreCommand,3,"r",0,NULL,1,1,1,0,0}, {"zrank",zrankCommand,3,"r",0,NULL,1,1,1,0,0}, {"zrevrank",zrevrankCommand,3,"r",0,NULL,1,1,1,0,0}, {"hset",hsetCommand,4,"wm",0,NULL,1,1,1,0,0}, {"hsetnx",hsetnxCommand,4,"wm",0,NULL,1,1,1,0,0}, {"hget",hgetCommand,3,"r",0,NULL,1,1,1,0,0}, {"hmset",hmsetCommand,-4,"wm",0,NULL,1,1,1,0,0}, {"hmget",hmgetCommand,-3,"r",0,NULL,1,1,1,0,0}, {"hincrby",hincrbyCommand,4,"wm",0,NULL,1,1,1,0,0}, {"hincrbyfloat",hincrbyfloatCommand,4,"wm",0,NULL,1,1,1,0,0}, {"hdel",hdelCommand,-3,"w",0,NULL,1,1,1,0,0}, {"hlen",hlenCommand,2,"r",0,NULL,1,1,1,0,0}, {"hkeys",hkeysCommand,2,"rS",0,NULL,1,1,1,0,0}, {"hvals",hvalsCommand,2,"rS",0,NULL,1,1,1,0,0}, {"hgetall",hgetallCommand,2,"r",0,NULL,1,1,1,0,0}, {"hexists",hexistsCommand,3,"r",0,NULL,1,1,1,0,0}, {"incrby",incrbyCommand,3,"wm",0,NULL,1,1,1,0,0}, {"decrby",decrbyCommand,3,"wm",0,NULL,1,1,1,0,0}, {"incrbyfloat",incrbyfloatCommand,3,"wm",0,NULL,1,1,1,0,0}, {"getset",getsetCommand,3,"wm",0,NULL,1,1,1,0,0}, {"mset",msetCommand,-3,"wm",0,NULL,1,-1,2,0,0}, {"msetnx",msetnxCommand,-3,"wm",0,NULL,1,-1,2,0,0}, {"randomkey",randomkeyCommand,1,"rR",0,NULL,0,0,0,0,0}, {"select",selectCommand,2,"r",0,NULL,0,0,0,0,0}, {"move",moveCommand,3,"w",0,NULL,1,1,1,0,0}, {"rename",renameCommand,3,"w",0,renameGetKeys,1,2,1,0,0}, {"renamenx",renamenxCommand,3,"w",0,renameGetKeys,1,2,1,0,0}, {"expire",expireCommand,3,"w",0,NULL,1,1,1,0,0}, {"expireat",expireatCommand,3,"w",0,NULL,1,1,1,0,0}, {"pexpire",pexpireCommand,3,"w",0,NULL,1,1,1,0,0}, {"pexpireat",pexpireatCommand,3,"w",0,NULL,1,1,1,0,0}, {"keys",keysCommand,2,"rS",0,NULL,0,0,0,0,0}, {"dbsize",dbsizeCommand,1,"r",0,NULL,0,0,0,0,0}, {"auth",authCommand,2,"rs",0,NULL,0,0,0,0,0}, {"ping",pingCommand,1,"r",0,NULL,0,0,0,0,0}, {"echo",echoCommand,2,"r",0,NULL,0,0,0,0,0}, {"save",saveCommand,1,"ars",0,NULL,0,0,0,0,0}, {"bgsave",bgsaveCommand,1,"ar",0,NULL,0,0,0,0,0}, {"bgrewriteaof",bgrewriteaofCommand,1,"ar",0,NULL,0,0,0,0,0}, {"shutdown",shutdownCommand,-1,"ar",0,NULL,0,0,0,0,0}, {"lastsave",lastsaveCommand,1,"r",0,NULL,0,0,0,0,0}, {"type",typeCommand,2,"r",0,NULL,1,1,1,0,0}, {"multi",multiCommand,1,"rs",0,NULL,0,0,0,0,0}, {"exec",execCommand,1,"wms",0,NULL,0,0,0,0,0}, {"discard",discardCommand,1,"rs",0,NULL,0,0,0,0,0}, {"sync",syncCommand,1,"ars",0,NULL,0,0,0,0,0}, {"flushdb",flushdbCommand,1,"w",0,NULL,0,0,0,0,0}, {"flushall",flushallCommand,1,"w",0,NULL,0,0,0,0,0}, {"sort",sortCommand,-2,"wmS",0,NULL,1,1,1,0,0}, {"info",infoCommand,-1,"r",0,NULL,0,0,0,0,0}, {"monitor",monitorCommand,1,"ars",0,NULL,0,0,0,0,0}, {"ttl",ttlCommand,2,"r",0,NULL,1,1,1,0,0}, {"pttl",pttlCommand,2,"r",0,NULL,1,1,1,0,0}, {"persist",persistCommand,2,"w",0,NULL,1,1,1,0,0}, {"slaveof",slaveofCommand,3,"aws",0,NULL,0,0,0,0,0}, {"debug",debugCommand,-2,"aws",0,NULL,0,0,0,0,0}, {"config",configCommand,-2,"ar",0,NULL,0,0,0,0,0}, {"subscribe",subscribeCommand,-2,"rps",0,NULL,0,0,0,0,0}, {"unsubscribe",unsubscribeCommand,-1,"rps",0,NULL,0,0,0,0,0}, {"psubscribe",psubscribeCommand,-2,"rps",0,NULL,0,0,0,0,0}, {"punsubscribe",punsubscribeCommand,-1,"rps",0,NULL,0,0,0,0,0}, {"publish",publishCommand,3,"rpf",0,NULL,0,0,0,0,0}, {"watch",watchCommand,-2,"rs",0,noPreloadGetKeys,1,-1,1,0,0}, {"unwatch",unwatchCommand,1,"rs",0,NULL,0,0,0,0,0}, {"cluster",clusterCommand,-2,"ar",0,NULL,0,0,0,0,0}, {"restore",restoreCommand,4,"awm",0,NULL,1,1,1,0,0}, {"migrate",migrateCommand,6,"aw",0,NULL,0,0,0,0,0}, {"asking",askingCommand,1,"r",0,NULL,0,0,0,0,0}, {"dump",dumpCommand,2,"ar",0,NULL,1,1,1,0,0}, {"object",objectCommand,-2,"r",0,NULL,2,2,2,0,0}, {"client",clientCommand,-2,"ar",0,NULL,0,0,0,0,0}, {"eval",evalCommand,-3,"wms",0,zunionInterGetKeys,0,0,0,0,0}, {"evalsha",evalShaCommand,-3,"wms",0,zunionInterGetKeys,0,0,0,0,0}, {"slowlog",slowlogCommand,-2,"r",0,NULL,0,0,0,0,0}, {"script",scriptCommand,-2,"ras",0,NULL,0,0,0,0,0}, {"time",timeCommand,1,"rR",0,NULL,0,0,0,0,0} }; /*============================ Utility functions ============================ */ /* Low level logging. To use only for very big messages, otherwise * redisLog() is to prefer. */ void redisLogRaw(int level, const char *msg) { const int syslogLevelMap[] = { LOG_DEBUG, LOG_INFO, LOG_NOTICE, LOG_WARNING }; const char *c = ".-*#"; time_t now = time(NULL); FILE *fp; char buf[64]; int rawmode = (level & REDIS_LOG_RAW); level &= 0xff; /* clear flags */ if (level < server.verbosity) return; fp = (server.logfile == NULL) ? stdout : fopen(server.logfile,"a"); if (!fp) return; if (rawmode) { fprintf(fp,"%s",msg); } else { strftime(buf,sizeof(buf),"%d %b %H:%M:%S",localtime(&now)); fprintf(fp,"[%d] %s %c %s\n",(int)getpid(),buf,c[level],msg); } fflush(fp); if (server.logfile) fclose(fp); if (server.syslog_enabled) syslog(syslogLevelMap[level], "%s", msg); } /* Like redisLogRaw() but with printf-alike support. This is the funciton that * is used across the code. The raw version is only used in order to dump * the INFO output on crash. */ void redisLog(int level, const char *fmt, ...) { va_list ap; char msg[REDIS_MAX_LOGMSG_LEN]; if ((level&0xff) < server.verbosity) return; va_start(ap, fmt); vsnprintf(msg, sizeof(msg), fmt, ap); va_end(ap); redisLogRaw(level,msg); } /* Redis generally does not try to recover from out of memory conditions * when allocating objects or strings, it is not clear if it will be possible * to report this condition to the client since the networking layer itself * is based on heap allocation for send buffers, so we simply abort. * At least the code will be simpler to read... */ void oom(const char *msg) { redisLog(REDIS_WARNING, "%s: Out of memory\n",msg); sleep(1); abort(); } /* Return the UNIX time in microseconds */ long long ustime(void) { struct timeval tv; long long ust; gettimeofday(&tv, NULL); ust = ((long long)tv.tv_sec)*1000000; ust += tv.tv_usec; return ust; } /* Return the UNIX time in milliseconds */ long long mstime(void) { return ustime()/1000; } /*====================== Hash table type implementation ==================== */ /* This is an hash table type that uses the SDS dynamic strings libary as * keys and radis objects as values (objects can hold SDS strings, * lists, sets). */ void dictVanillaFree(void *privdata, void *val) { DICT_NOTUSED(privdata); zfree(val); } void dictListDestructor(void *privdata, void *val) { DICT_NOTUSED(privdata); listRelease((list*)val); } int dictSdsKeyCompare(void *privdata, const void *key1, const void *key2) { int l1,l2; DICT_NOTUSED(privdata); l1 = sdslen((sds)key1); l2 = sdslen((sds)key2); if (l1 != l2) return 0; return memcmp(key1, key2, l1) == 0; } /* A case insensitive version used for the command lookup table. */ int dictSdsKeyCaseCompare(void *privdata, const void *key1, const void *key2) { DICT_NOTUSED(privdata); return strcasecmp(key1, key2) == 0; } void dictRedisObjectDestructor(void *privdata, void *val) { DICT_NOTUSED(privdata); if (val == NULL) return; /* Values of swapped out keys as set to NULL */ decrRefCount(val); } void dictSdsDestructor(void *privdata, void *val) { DICT_NOTUSED(privdata); sdsfree(val); } int dictObjKeyCompare(void *privdata, const void *key1, const void *key2) { const robj *o1 = key1, *o2 = key2; return dictSdsKeyCompare(privdata,o1->ptr,o2->ptr); } unsigned int dictObjHash(const void *key) { const robj *o = key; return dictGenHashFunction(o->ptr, sdslen((sds)o->ptr)); } unsigned int dictSdsHash(const void *key) { return dictGenHashFunction((unsigned char*)key, sdslen((char*)key)); } unsigned int dictSdsCaseHash(const void *key) { return dictGenCaseHashFunction((unsigned char*)key, sdslen((char*)key)); } int dictEncObjKeyCompare(void *privdata, const void *key1, const void *key2) { robj *o1 = (robj*) key1, *o2 = (robj*) key2; int cmp; if (o1->encoding == REDIS_ENCODING_INT && o2->encoding == REDIS_ENCODING_INT) return o1->ptr == o2->ptr; o1 = getDecodedObject(o1); o2 = getDecodedObject(o2); cmp = dictSdsKeyCompare(privdata,o1->ptr,o2->ptr); decrRefCount(o1); decrRefCount(o2); return cmp; } unsigned int dictEncObjHash(const void *key) { robj *o = (robj*) key; if (o->encoding == REDIS_ENCODING_RAW) { return dictGenHashFunction(o->ptr, sdslen((sds)o->ptr)); } else { if (o->encoding == REDIS_ENCODING_INT) { char buf[32]; int len; len = ll2string(buf,32,(long)o->ptr); return dictGenHashFunction((unsigned char*)buf, len); } else { unsigned int hash; o = getDecodedObject(o); hash = dictGenHashFunction(o->ptr, sdslen((sds)o->ptr)); decrRefCount(o); return hash; } } } /* Sets type hash table */ dictType setDictType = { dictEncObjHash, /* hash function */ NULL, /* key dup */ NULL, /* val dup */ dictEncObjKeyCompare, /* key compare */ dictRedisObjectDestructor, /* key destructor */ NULL /* val destructor */ }; /* Sorted sets hash (note: a skiplist is used in addition to the hash table) */ dictType zsetDictType = { dictEncObjHash, /* hash function */ NULL, /* key dup */ NULL, /* val dup */ dictEncObjKeyCompare, /* key compare */ dictRedisObjectDestructor, /* key destructor */ NULL /* val destructor */ }; /* Db->dict, keys are sds strings, vals are Redis objects. */ dictType dbDictType = { dictSdsHash, /* hash function */ NULL, /* key dup */ NULL, /* val dup */ dictSdsKeyCompare, /* key compare */ dictSdsDestructor, /* key destructor */ dictRedisObjectDestructor /* val destructor */ }; /* Db->expires */ dictType keyptrDictType = { dictSdsHash, /* hash function */ NULL, /* key dup */ NULL, /* val dup */ dictSdsKeyCompare, /* key compare */ NULL, /* key destructor */ NULL /* val destructor */ }; /* Command table. sds string -> command struct pointer. */ dictType commandTableDictType = { dictSdsCaseHash, /* hash function */ NULL, /* key dup */ NULL, /* val dup */ dictSdsKeyCaseCompare, /* key compare */ dictSdsDestructor, /* key destructor */ NULL /* val destructor */ }; /* Hash type hash table (note that small hashes are represented with zimpaps) */ dictType hashDictType = { dictEncObjHash, /* hash function */ NULL, /* key dup */ NULL, /* val dup */ dictEncObjKeyCompare, /* key compare */ dictRedisObjectDestructor, /* key destructor */ dictRedisObjectDestructor /* val destructor */ }; /* Keylist hash table type has unencoded redis objects as keys and * lists as values. It's used for blocking operations (BLPOP) and to * map swapped keys to a list of clients waiting for this keys to be loaded. */ dictType keylistDictType = { dictObjHash, /* hash function */ NULL, /* key dup */ NULL, /* val dup */ dictObjKeyCompare, /* key compare */ dictRedisObjectDestructor, /* key destructor */ dictListDestructor /* val destructor */ }; /* Cluster nodes hash table, mapping nodes addresses 1.2.3.4:6379 to * clusterNode structures. */ dictType clusterNodesDictType = { dictSdsHash, /* hash function */ NULL, /* key dup */ NULL, /* val dup */ dictSdsKeyCompare, /* key compare */ dictSdsDestructor, /* key destructor */ NULL /* val destructor */ }; int htNeedsResize(dict *dict) { long long size, used; size = dictSlots(dict); used = dictSize(dict); return (size && used && size > DICT_HT_INITIAL_SIZE && (used*100/size < REDIS_HT_MINFILL)); } /* If the percentage of used slots in the HT reaches REDIS_HT_MINFILL * we resize the hash table to save memory */ void tryResizeHashTables(void) { int j; for (j = 0; j < server.dbnum; j++) { if (htNeedsResize(server.db[j].dict)) dictResize(server.db[j].dict); if (htNeedsResize(server.db[j].expires)) dictResize(server.db[j].expires); } } /* Our hash table implementation performs rehashing incrementally while * we write/read from the hash table. Still if the server is idle, the hash * table will use two tables for a long time. So we try to use 1 millisecond * of CPU time at every serverCron() loop in order to rehash some key. */ void incrementallyRehash(void) { int j; for (j = 0; j < server.dbnum; j++) { if (dictIsRehashing(server.db[j].dict)) { dictRehashMilliseconds(server.db[j].dict,1); break; /* already used our millisecond for this loop... */ } } } /* This function is called once a background process of some kind terminates, * as we want to avoid resizing the hash tables when there is a child in order * to play well with copy-on-write (otherwise when a resize happens lots of * memory pages are copied). The goal of this function is to update the ability * for dict.c to resize the hash tables accordingly to the fact we have o not * running childs. */ void updateDictResizePolicy(void) { if (server.rdb_child_pid == -1 && server.aof_child_pid == -1) dictEnableResize(); else dictDisableResize(); } /* ======================= Cron: called every 100 ms ======================== */ /* Try to expire a few timed out keys. The algorithm used is adaptive and * will use few CPU cycles if there are few expiring keys, otherwise * it will get more aggressive to avoid that too much memory is used by * keys that can be removed from the keyspace. */ void activeExpireCycle(void) { int j; for (j = 0; j < server.dbnum; j++) { int expired; redisDb *db = server.db+j; /* Continue to expire if at the end of the cycle more than 25% * of the keys were expired. */ do { long num = dictSize(db->expires); long long now = mstime(); expired = 0; if (num > REDIS_EXPIRELOOKUPS_PER_CRON) num = REDIS_EXPIRELOOKUPS_PER_CRON; while (num--) { dictEntry *de; long long t; if ((de = dictGetRandomKey(db->expires)) == NULL) break; t = dictGetSignedIntegerVal(de); if (now > t) { sds key = dictGetKey(de); robj *keyobj = createStringObject(key,sdslen(key)); propagateExpire(db,keyobj); dbDelete(db,keyobj); decrRefCount(keyobj); expired++; server.stat_expiredkeys++; } } } while (expired > REDIS_EXPIRELOOKUPS_PER_CRON/4); } } void updateLRUClock(void) { server.lruclock = (time(NULL)/REDIS_LRU_CLOCK_RESOLUTION) & REDIS_LRU_CLOCK_MAX; } /* Add a sample to the operations per second array of samples. */ void trackOperationsPerSecond(void) { long long t = mstime() - server.ops_sec_last_sample_time; long long ops = server.stat_numcommands - server.ops_sec_last_sample_ops; long long ops_sec; ops_sec = t > 0 ? (ops*1000/t) : 0; server.ops_sec_samples[server.ops_sec_idx] = ops_sec; server.ops_sec_idx = (server.ops_sec_idx+1) % REDIS_OPS_SEC_SAMPLES; server.ops_sec_last_sample_time = mstime(); server.ops_sec_last_sample_ops = server.stat_numcommands; } /* Return the mean of all the samples. */ long long getOperationsPerSecond(void) { int j; long long sum = 0; for (j = 0; j < REDIS_OPS_SEC_SAMPLES; j++) sum += server.ops_sec_samples[j]; return sum / REDIS_OPS_SEC_SAMPLES; } /* Check for timeouts. Returns non-zero if the client was terminated */ int clientsCronHandleTimeout(redisClient *c) { time_t now = server.unixtime; if (server.maxidletime && !(c->flags & REDIS_SLAVE) && /* no timeout for slaves */ !(c->flags & REDIS_MASTER) && /* no timeout for masters */ !(c->flags & REDIS_BLOCKED) && /* no timeout for BLPOP */ dictSize(c->pubsub_channels) == 0 && /* no timeout for pubsub */ listLength(c->pubsub_patterns) == 0 && (now - c->lastinteraction > server.maxidletime)) { redisLog(REDIS_VERBOSE,"Closing idle client"); freeClient(c); return 1; } else if (c->flags & REDIS_BLOCKED) { if (c->bpop.timeout != 0 && c->bpop.timeout < now) { addReply(c,shared.nullmultibulk); unblockClientWaitingData(c); } } return 0; } /* The client query buffer is an sds.c string that can end with a lot of * free space not used, this function reclaims space if needed. * * The funciton always returns 0 as it never terminates the client. */ int clientsCronResizeQueryBuffer(redisClient *c) { size_t querybuf_size = sdsAllocSize(c->querybuf); time_t idletime = server.unixtime - c->lastinteraction; /* There are two conditions to resize the query buffer: * 1) Query buffer is > BIG_ARG and too big for latest peak. * 2) Client is inactive and the buffer is bigger than 1k. */ if (((querybuf_size > REDIS_MBULK_BIG_ARG) && (querybuf_size/(c->querybuf_peak+1)) > 2) || (querybuf_size > 1024 && idletime > 2)) { /* Only resize the query buffer if it is actually wasting space. */ if (sdsavail(c->querybuf) > 1024) { c->querybuf = sdsRemoveFreeSpace(c->querybuf); } } /* Reset the peak again to capture the peak memory usage in the next * cycle. */ c->querybuf_peak = 0; return 0; } void clientsCron(void) { /* Make sure to process at least 1/100 of clients per call. * Since this function is called 10 times per second we are sure that * in the worst case we process all the clients in 10 seconds. * In normal conditions (a reasonable number of clients) we process * all the clients in a shorter time. */ int numclients = listLength(server.clients); int iterations = numclients/100; if (iterations < 50) iterations = (numclients < 50) ? numclients : 50; while(listLength(server.clients) && iterations--) { redisClient *c; listNode *head; /* Rotate the list, take the current head, process. * This way if the client must be removed from the list it's the * first element and we don't incur into O(N) computation. */ listRotate(server.clients); head = listFirst(server.clients); c = listNodeValue(head); /* The following functions do different service checks on the client. * The protocol is that they return non-zero if the client was * terminated. */ if (clientsCronHandleTimeout(c)) continue; if (clientsCronResizeQueryBuffer(c)) continue; } } int serverCron(struct aeEventLoop *eventLoop, long long id, void *clientData) { int j, loops = server.cronloops; REDIS_NOTUSED(eventLoop); REDIS_NOTUSED(id); REDIS_NOTUSED(clientData); /* We take a cached value of the unix time in the global state because * with virtual memory and aging there is to store the current time * in objects at every object access, and accuracy is not needed. * To access a global var is faster than calling time(NULL) */ server.unixtime = time(NULL); trackOperationsPerSecond(); /* We have just 22 bits per object for LRU information. * So we use an (eventually wrapping) LRU clock with 10 seconds resolution. * 2^22 bits with 10 seconds resoluton is more or less 1.5 years. * * Note that even if this will wrap after 1.5 years it's not a problem, * everything will still work but just some object will appear younger * to Redis. But for this to happen a given object should never be touched * for 1.5 years. * * Note that you can change the resolution altering the * REDIS_LRU_CLOCK_RESOLUTION define. */ updateLRUClock(); /* Record the max memory used since the server was started. */ if (zmalloc_used_memory() > server.stat_peak_memory) server.stat_peak_memory = zmalloc_used_memory(); /* We received a SIGTERM, shutting down here in a safe way, as it is * not ok doing so inside the signal handler. */ if (server.shutdown_asap) { if (prepareForShutdown(0) == REDIS_OK) exit(0); redisLog(REDIS_WARNING,"SIGTERM received but errors trying to shut down the server, check the logs for more information"); } /* Show some info about non-empty databases */ for (j = 0; j < server.dbnum; j++) { long long size, used, vkeys; size = dictSlots(server.db[j].dict); used = dictSize(server.db[j].dict); vkeys = dictSize(server.db[j].expires); if (!(loops % 50) && (used || vkeys)) { redisLog(REDIS_VERBOSE,"DB %d: %lld keys (%lld volatile) in %lld slots HT.",j,used,vkeys,size); /* dictPrintStats(server.dict); */ } } /* We don't want to resize the hash tables while a bacground saving * is in progress: the saving child is created using fork() that is * implemented with a copy-on-write semantic in most modern systems, so * if we resize the HT while there is the saving child at work actually * a lot of memory movements in the parent will cause a lot of pages * copied. */ if (server.rdb_child_pid == -1 && server.aof_child_pid == -1) { if (!(loops % 10)) tryResizeHashTables(); if (server.activerehashing) incrementallyRehash(); } /* Show information about connected clients */ if (!(loops % 50)) { redisLog(REDIS_VERBOSE,"%d clients connected (%d slaves), %zu bytes in use", listLength(server.clients)-listLength(server.slaves), listLength(server.slaves), zmalloc_used_memory()); } /* We need to do a few operations on clients asynchronously. */ clientsCron(); /* Start a scheduled AOF rewrite if this was requested by the user while * a BGSAVE was in progress. */ if (server.rdb_child_pid == -1 && server.aof_child_pid == -1 && server.aof_rewrite_scheduled) { rewriteAppendOnlyFileBackground(); } /* Check if a background saving or AOF rewrite in progress terminated. */ if (server.rdb_child_pid != -1 || server.aof_child_pid != -1) { int statloc; pid_t pid; if ((pid = wait3(&statloc,WNOHANG,NULL)) != 0) { int exitcode = WEXITSTATUS(statloc); int bysignal = 0; if (WIFSIGNALED(statloc)) bysignal = WTERMSIG(statloc); if (pid == server.rdb_child_pid) { backgroundSaveDoneHandler(exitcode,bysignal); } else { backgroundRewriteDoneHandler(exitcode,bysignal); } updateDictResizePolicy(); } } else { time_t now = time(NULL); /* If there is not a background saving/rewrite in progress check if * we have to save/rewrite now */ for (j = 0; j < server.saveparamslen; j++) { struct saveparam *sp = server.saveparams+j; if (server.dirty >= sp->changes && now-server.lastsave > sp->seconds) { redisLog(REDIS_NOTICE,"%d changes in %d seconds. Saving...", sp->changes, sp->seconds); rdbSaveBackground(server.rdb_filename); break; } } /* Trigger an AOF rewrite if needed */ if (server.rdb_child_pid == -1 && server.aof_child_pid == -1 && server.aof_rewrite_perc && server.aof_current_size > server.aof_rewrite_min_size) { long long base = server.aof_rewrite_base_size ? server.aof_rewrite_base_size : 1; long long growth = (server.aof_current_size*100/base) - 100; if (growth >= server.aof_rewrite_perc) { redisLog(REDIS_NOTICE,"Starting automatic rewriting of AOF on %lld%% growth",growth); rewriteAppendOnlyFileBackground(); } } } /* If we postponed an AOF buffer flush, let's try to do it every time the * cron function is called. */ if (server.aof_flush_postponed_start) flushAppendOnlyFile(0); /* Expire a few keys per cycle, only if this is a master. * On slaves we wait for DEL operations synthesized by the master * in order to guarantee a strict consistency. */ if (server.masterhost == NULL) activeExpireCycle(); /* Close clients that need to be closed asynchronous */ freeClientsInAsyncFreeQueue(); /* Replication cron function -- used to reconnect to master and * to detect transfer failures. */ if (!(loops % 10)) replicationCron(); /* Run other sub-systems specific cron jobs */ if (server.cluster_enabled && !(loops % 10)) clusterCron(); server.cronloops++; return 100; } /* This function gets called every time Redis is entering the * main loop of the event driven library, that is, before to sleep * for ready file descriptors. */ void beforeSleep(struct aeEventLoop *eventLoop) { REDIS_NOTUSED(eventLoop); listNode *ln; redisClient *c; /* Try to process pending commands for clients that were just unblocked. */ while (listLength(server.unblocked_clients)) { ln = listFirst(server.unblocked_clients); redisAssert(ln != NULL); c = ln->value; listDelNode(server.unblocked_clients,ln); c->flags &= ~REDIS_UNBLOCKED; /* Process remaining data in the input buffer. */ if (c->querybuf && sdslen(c->querybuf) > 0) { server.current_client = c; processInputBuffer(c); server.current_client = NULL; } } /* Write the AOF buffer on disk */ flushAppendOnlyFile(0); } /* =========================== Server initialization ======================== */ void createSharedObjects(void) { int j; shared.crlf = createObject(REDIS_STRING,sdsnew("\r\n")); shared.ok = createObject(REDIS_STRING,sdsnew("+OK\r\n")); shared.err = createObject(REDIS_STRING,sdsnew("-ERR\r\n")); shared.emptybulk = createObject(REDIS_STRING,sdsnew("$0\r\n\r\n")); shared.czero = createObject(REDIS_STRING,sdsnew(":0\r\n")); shared.cone = createObject(REDIS_STRING,sdsnew(":1\r\n")); shared.cnegone = createObject(REDIS_STRING,sdsnew(":-1\r\n")); shared.nullbulk = createObject(REDIS_STRING,sdsnew("$-1\r\n")); shared.nullmultibulk = createObject(REDIS_STRING,sdsnew("*-1\r\n")); shared.emptymultibulk = createObject(REDIS_STRING,sdsnew("*0\r\n")); shared.pong = createObject(REDIS_STRING,sdsnew("+PONG\r\n")); shared.queued = createObject(REDIS_STRING,sdsnew("+QUEUED\r\n")); shared.wrongtypeerr = createObject(REDIS_STRING,sdsnew( "-ERR Operation against a key holding the wrong kind of value\r\n")); shared.nokeyerr = createObject(REDIS_STRING,sdsnew( "-ERR no such key\r\n")); shared.syntaxerr = createObject(REDIS_STRING,sdsnew( "-ERR syntax error\r\n")); shared.sameobjecterr = createObject(REDIS_STRING,sdsnew( "-ERR source and destination objects are the same\r\n")); shared.outofrangeerr = createObject(REDIS_STRING,sdsnew( "-ERR index out of range\r\n")); shared.noscripterr = createObject(REDIS_STRING,sdsnew( "-NOSCRIPT No matching script. Please use EVAL.\r\n")); shared.loadingerr = createObject(REDIS_STRING,sdsnew( "-LOADING Redis is loading the dataset in memory\r\n")); shared.slowscripterr = createObject(REDIS_STRING,sdsnew( "-BUSY Redis is busy running a script. You can only call SCRIPT KILL or SHUTDOWN NOSAVE.\r\n")); shared.bgsaveerr = createObject(REDIS_STRING,sdsnew( "-MISCONF Redis is configured to save RDB snapshots, but is currently not able to persist on disk. Write commands are disabled. Please check Redis logs for details about the error.\r\n")); shared.space = createObject(REDIS_STRING,sdsnew(" ")); shared.colon = createObject(REDIS_STRING,sdsnew(":")); shared.plus = createObject(REDIS_STRING,sdsnew("+")); shared.select0 = createStringObject("select 0\r\n",10); shared.select1 = createStringObject("select 1\r\n",10); shared.select2 = createStringObject("select 2\r\n",10); shared.select3 = createStringObject("select 3\r\n",10); shared.select4 = createStringObject("select 4\r\n",10); shared.select5 = createStringObject("select 5\r\n",10); shared.select6 = createStringObject("select 6\r\n",10); shared.select7 = createStringObject("select 7\r\n",10); shared.select8 = createStringObject("select 8\r\n",10); shared.select9 = createStringObject("select 9\r\n",10); shared.messagebulk = createStringObject("$7\r\nmessage\r\n",13); shared.pmessagebulk = createStringObject("$8\r\npmessage\r\n",14); shared.subscribebulk = createStringObject("$9\r\nsubscribe\r\n",15); shared.unsubscribebulk = createStringObject("$11\r\nunsubscribe\r\n",18); shared.psubscribebulk = createStringObject("$10\r\npsubscribe\r\n",17); shared.punsubscribebulk = createStringObject("$12\r\npunsubscribe\r\n",19); shared.del = createStringObject("DEL",3); shared.rpop = createStringObject("RPOP",4); shared.lpop = createStringObject("LPOP",4); for (j = 0; j < REDIS_SHARED_INTEGERS; j++) { shared.integers[j] = createObject(REDIS_STRING,(void*)(long)j); shared.integers[j]->encoding = REDIS_ENCODING_INT; } for (j = 0; j < REDIS_SHARED_BULKHDR_LEN; j++) { shared.mbulkhdr[j] = createObject(REDIS_STRING, sdscatprintf(sdsempty(),"*%d\r\n",j)); shared.bulkhdr[j] = createObject(REDIS_STRING, sdscatprintf(sdsempty(),"$%d\r\n",j)); } } void initServerConfig() { getRandomHexChars(server.runid,REDIS_RUN_ID_SIZE); server.runid[REDIS_RUN_ID_SIZE] = '\0'; server.arch_bits = (sizeof(long) == 8) ? 64 : 32; server.port = REDIS_SERVERPORT; server.bindaddr = NULL; server.unixsocket = NULL; server.unixsocketperm = 0; server.ipfd = -1; server.sofd = -1; server.dbnum = REDIS_DEFAULT_DBNUM; server.verbosity = REDIS_NOTICE; server.maxidletime = REDIS_MAXIDLETIME; server.client_max_querybuf_len = REDIS_MAX_QUERYBUF_LEN; server.saveparams = NULL; server.loading = 0; server.logfile = NULL; /* NULL = log on standard output */ server.syslog_enabled = 0; server.syslog_ident = zstrdup("redis"); server.syslog_facility = LOG_LOCAL0; server.daemonize = 0; server.aof_state = REDIS_AOF_OFF; server.aof_fsync = AOF_FSYNC_EVERYSEC; server.aof_no_fsync_on_rewrite = 0; server.aof_rewrite_perc = REDIS_AOF_REWRITE_PERC; server.aof_rewrite_min_size = REDIS_AOF_REWRITE_MIN_SIZE; server.aof_rewrite_base_size = 0; server.aof_rewrite_scheduled = 0; server.aof_last_fsync = time(NULL); server.aof_fd = -1; server.aof_selected_db = -1; /* Make sure the first time will not match */ server.aof_flush_postponed_start = 0; server.pidfile = zstrdup("/var/run/redis.pid"); server.rdb_filename = zstrdup("dump.rdb"); server.aof_filename = zstrdup("appendonly.aof"); server.requirepass = NULL; server.rdb_compression = 1; server.activerehashing = 1; server.maxclients = REDIS_MAX_CLIENTS; server.bpop_blocked_clients = 0; server.maxmemory = 0; server.maxmemory_policy = REDIS_MAXMEMORY_VOLATILE_LRU; server.maxmemory_samples = 3; server.hash_max_ziplist_entries = REDIS_HASH_MAX_ZIPLIST_ENTRIES; server.hash_max_ziplist_value = REDIS_HASH_MAX_ZIPLIST_VALUE; server.list_max_ziplist_entries = REDIS_LIST_MAX_ZIPLIST_ENTRIES; server.list_max_ziplist_value = REDIS_LIST_MAX_ZIPLIST_VALUE; server.set_max_intset_entries = REDIS_SET_MAX_INTSET_ENTRIES; server.zset_max_ziplist_entries = REDIS_ZSET_MAX_ZIPLIST_ENTRIES; server.zset_max_ziplist_value = REDIS_ZSET_MAX_ZIPLIST_VALUE; server.shutdown_asap = 0; server.repl_ping_slave_period = REDIS_REPL_PING_SLAVE_PERIOD; server.repl_timeout = REDIS_REPL_TIMEOUT; server.cluster_enabled = 0; server.cluster.configfile = zstrdup("nodes.conf"); server.lua_caller = NULL; server.lua_time_limit = REDIS_LUA_TIME_LIMIT; server.lua_client = NULL; server.lua_timedout = 0; updateLRUClock(); resetServerSaveParams(); appendServerSaveParams(60*60,1); /* save after 1 hour and 1 change */ appendServerSaveParams(300,100); /* save after 5 minutes and 100 changes */ appendServerSaveParams(60,10000); /* save after 1 minute and 10000 changes */ /* Replication related */ server.masterauth = NULL; server.masterhost = NULL; server.masterport = 6379; server.master = NULL; server.repl_state = REDIS_REPL_NONE; server.repl_syncio_timeout = REDIS_REPL_SYNCIO_TIMEOUT; server.repl_serve_stale_data = 1; server.repl_down_since = -1; /* Client output buffer limits */ server.client_obuf_limits[REDIS_CLIENT_LIMIT_CLASS_NORMAL].hard_limit_bytes = 0; server.client_obuf_limits[REDIS_CLIENT_LIMIT_CLASS_NORMAL].soft_limit_bytes = 0; server.client_obuf_limits[REDIS_CLIENT_LIMIT_CLASS_NORMAL].soft_limit_seconds = 0; server.client_obuf_limits[REDIS_CLIENT_LIMIT_CLASS_SLAVE].hard_limit_bytes = 1024*1024*256; server.client_obuf_limits[REDIS_CLIENT_LIMIT_CLASS_SLAVE].soft_limit_bytes = 1024*1024*64; server.client_obuf_limits[REDIS_CLIENT_LIMIT_CLASS_SLAVE].soft_limit_seconds = 60; server.client_obuf_limits[REDIS_CLIENT_LIMIT_CLASS_PUBSUB].hard_limit_bytes = 1024*1024*32; server.client_obuf_limits[REDIS_CLIENT_LIMIT_CLASS_PUBSUB].soft_limit_bytes = 1024*1024*8; server.client_obuf_limits[REDIS_CLIENT_LIMIT_CLASS_PUBSUB].soft_limit_seconds = 60; /* Double constants initialization */ R_Zero = 0.0; R_PosInf = 1.0/R_Zero; R_NegInf = -1.0/R_Zero; R_Nan = R_Zero/R_Zero; /* Command table -- we intiialize it here as it is part of the * initial configuration, since command names may be changed via * redis.conf using the rename-command directive. */ server.commands = dictCreate(&commandTableDictType,NULL); populateCommandTable(); server.delCommand = lookupCommandByCString("del"); server.multiCommand = lookupCommandByCString("multi"); server.lpushCommand = lookupCommandByCString("lpush"); /* Slow log */ server.slowlog_log_slower_than = REDIS_SLOWLOG_LOG_SLOWER_THAN; server.slowlog_max_len = REDIS_SLOWLOG_MAX_LEN; /* Assert */ server.assert_failed = ""; server.assert_file = ""; server.assert_line = 0; server.bug_report_start = 0; } /* This function will try to raise the max number of open files accordingly to * the configured max number of clients. It will also account for 32 additional * file descriptors as we need a few more for persistence, listening * sockets, log files and so forth. * * If it will not be possible to set the limit accordingly to the configured * max number of clients, the function will do the reverse setting * server.maxclients to the value that we can actually handle. */ void adjustOpenFilesLimit(void) { rlim_t maxfiles = server.maxclients+32; struct rlimit limit; if (maxfiles < 1024) maxfiles = 1024; if (getrlimit(RLIMIT_NOFILE,&limit) == -1) { redisLog(REDIS_WARNING,"Unable to obtain the current NOFILE limit (%s), assuming 1024 and setting the max clients configuration accordingly.", strerror(errno)); server.maxclients = 1024-32; } else { rlim_t oldlimit = limit.rlim_cur; /* Set the max number of files if the current limit is not enough * for our needs. */ if (oldlimit < maxfiles) { limit.rlim_cur = maxfiles; limit.rlim_max = maxfiles; if (setrlimit(RLIMIT_NOFILE,&limit) == -1) { server.maxclients = oldlimit-32; redisLog(REDIS_WARNING,"Unable to set the max number of files limit to %d (%s), setting the max clients configuration to %d.", (int) maxfiles, strerror(errno), (int) server.maxclients); } else { redisLog(REDIS_NOTICE,"Max number of open files set to %d", (int) maxfiles); } } } } void initServer() { int j; signal(SIGHUP, SIG_IGN); signal(SIGPIPE, SIG_IGN); setupSignalHandlers(); if (server.syslog_enabled) { openlog(server.syslog_ident, LOG_PID | LOG_NDELAY | LOG_NOWAIT, server.syslog_facility); } server.current_client = NULL; server.clients = listCreate(); server.clients_to_close = listCreate(); server.slaves = listCreate(); server.monitors = listCreate(); server.unblocked_clients = listCreate(); createSharedObjects(); adjustOpenFilesLimit(); server.el = aeCreateEventLoop(server.maxclients+1024); server.db = zmalloc(sizeof(redisDb)*server.dbnum); if (server.port != 0) { server.ipfd = anetTcpServer(server.neterr,server.port,server.bindaddr); if (server.ipfd == ANET_ERR) { redisLog(REDIS_WARNING, "Opening port %d: %s", server.port, server.neterr); exit(1); } } if (server.unixsocket != NULL) { unlink(server.unixsocket); /* don't care if this fails */ server.sofd = anetUnixServer(server.neterr,server.unixsocket,server.unixsocketperm); if (server.sofd == ANET_ERR) { redisLog(REDIS_WARNING, "Opening socket: %s", server.neterr); exit(1); } } if (server.ipfd < 0 && server.sofd < 0) { redisLog(REDIS_WARNING, "Configured to not listen anywhere, exiting."); exit(1); } for (j = 0; j < server.dbnum; j++) { server.db[j].dict = dictCreate(&dbDictType,NULL); server.db[j].expires = dictCreate(&keyptrDictType,NULL); server.db[j].blocking_keys = dictCreate(&keylistDictType,NULL); server.db[j].watched_keys = dictCreate(&keylistDictType,NULL); server.db[j].id = j; } server.pubsub_channels = dictCreate(&keylistDictType,NULL); server.pubsub_patterns = listCreate(); listSetFreeMethod(server.pubsub_patterns,freePubsubPattern); listSetMatchMethod(server.pubsub_patterns,listMatchPubsubPattern); server.cronloops = 0; server.rdb_child_pid = -1; server.aof_child_pid = -1; server.aof_rewrite_buf = sdsempty(); server.aof_buf = sdsempty(); server.lastsave = time(NULL); server.dirty = 0; server.stat_numcommands = 0; server.stat_numconnections = 0; server.stat_expiredkeys = 0; server.stat_evictedkeys = 0; server.stat_starttime = time(NULL); server.stat_keyspace_misses = 0; server.stat_keyspace_hits = 0; server.stat_peak_memory = 0; server.stat_fork_time = 0; server.stat_rejected_conn = 0; memset(server.ops_sec_samples,0,sizeof(server.ops_sec_samples)); server.ops_sec_idx = 0; server.ops_sec_last_sample_time = mstime(); server.ops_sec_last_sample_ops = 0; server.unixtime = time(NULL); server.lastbgsave_status = REDIS_OK; server.stop_writes_on_bgsave_err = 1; aeCreateTimeEvent(server.el, 1, serverCron, NULL, NULL); if (server.ipfd > 0 && aeCreateFileEvent(server.el,server.ipfd,AE_READABLE, acceptTcpHandler,NULL) == AE_ERR) oom("creating file event"); if (server.sofd > 0 && aeCreateFileEvent(server.el,server.sofd,AE_READABLE, acceptUnixHandler,NULL) == AE_ERR) oom("creating file event"); if (server.aof_state == REDIS_AOF_ON) { server.aof_fd = open(server.aof_filename, O_WRONLY|O_APPEND|O_CREAT,0644); if (server.aof_fd == -1) { redisLog(REDIS_WARNING, "Can't open the append-only file: %s", strerror(errno)); exit(1); } } /* 32 bit instances are limited to 4GB of address space, so if there is * no explicit limit in the user provided configuration we set a limit * at 3.5GB using maxmemory with 'noeviction' policy'. This saves * useless crashes of the Redis instance. */ if (server.arch_bits == 32 && server.maxmemory == 0) { redisLog(REDIS_WARNING,"Warning: 32 bit instance detected but no memory limit set. Setting 3.5 GB maxmemory limit with 'noeviction' policy now."); server.maxmemory = 3584LL*(1024*1024); /* 3584 MB = 3.5 GB */ server.maxmemory_policy = REDIS_MAXMEMORY_NO_EVICTION; } if (server.cluster_enabled) clusterInit(); scriptingInit(); slowlogInit(); bioInit(); } /* Populates the Redis Command Table starting from the hard coded list * we have on top of redis.c file. */ void populateCommandTable(void) { int j; int numcommands = sizeof(redisCommandTable)/sizeof(struct redisCommand); for (j = 0; j < numcommands; j++) { struct redisCommand *c = redisCommandTable+j; char *f = c->sflags; int retval; while(*f != '\0') { switch(*f) { case 'w': c->flags |= REDIS_CMD_WRITE; break; case 'r': c->flags |= REDIS_CMD_READONLY; break; case 'm': c->flags |= REDIS_CMD_DENYOOM; break; case 'a': c->flags |= REDIS_CMD_ADMIN; break; case 'p': c->flags |= REDIS_CMD_PUBSUB; break; case 'f': c->flags |= REDIS_CMD_FORCE_REPLICATION; break; case 's': c->flags |= REDIS_CMD_NOSCRIPT; break; case 'R': c->flags |= REDIS_CMD_RANDOM; break; case 'S': c->flags |= REDIS_CMD_SORT_FOR_SCRIPT; break; default: redisPanic("Unsupported command flag"); break; } f++; } retval = dictAdd(server.commands, sdsnew(c->name), c); assert(retval == DICT_OK); } } void resetCommandTableStats(void) { int numcommands = sizeof(redisCommandTable)/sizeof(struct redisCommand); int j; for (j = 0; j < numcommands; j++) { struct redisCommand *c = redisCommandTable+j; c->microseconds = 0; c->calls = 0; } } /* ========================== Redis OP Array API ============================ */ void redisOpArrayInit(redisOpArray *oa) { oa->ops = NULL; oa->numops = 0; } int redisOpArrayAppend(redisOpArray *oa, struct redisCommand *cmd, int dbid, robj **argv, int argc, int target) { redisOp *op; oa->ops = zrealloc(oa->ops,sizeof(redisOp)*(oa->numops+1)); op = oa->ops+oa->numops; op->cmd = cmd; op->dbid = dbid; op->argv = argv; op->argc = argc; op->target = target; oa->numops++; return oa->numops; } void redisOpArrayFree(redisOpArray *oa) { while(oa->numops) { int j; redisOp *op; oa->numops--; op = oa->ops+oa->numops; for (j = 0; j < op->argc; j++) decrRefCount(op->argv[j]); zfree(op->argv); } zfree(oa->ops); } /* ====================== Commands lookup and execution ===================== */ struct redisCommand *lookupCommand(sds name) { return dictFetchValue(server.commands, name); } struct redisCommand *lookupCommandByCString(char *s) { struct redisCommand *cmd; sds name = sdsnew(s); cmd = dictFetchValue(server.commands, name); sdsfree(name); return cmd; } /* Propagate the specified command (in the context of the specified database id) * to AOF, Slaves and Monitors. * * flags are an xor between: * + REDIS_PROPAGATE_NONE (no propagation of command at all) * + REDIS_PROPAGATE_AOF (propagate into the AOF file if is enabled) * + REDIS_PROPAGATE_REPL (propagate into the replication link) */ void propagate(struct redisCommand *cmd, int dbid, robj **argv, int argc, int flags) { if (server.aof_state != REDIS_AOF_OFF && flags & REDIS_PROPAGATE_AOF) feedAppendOnlyFile(cmd,dbid,argv,argc); if (flags & REDIS_PROPAGATE_REPL && listLength(server.slaves)) replicationFeedSlaves(server.slaves,dbid,argv,argc); } /* Used inside commands to schedule the propagation of additional commands * after the current command is propagated to AOF / Replication. */ void alsoPropagate(struct redisCommand *cmd, int dbid, robj **argv, int argc, int target) { redisOpArrayAppend(&server.also_propagate,cmd,dbid,argv,argc,target); } /* Call() is the core of Redis execution of a command */ void call(redisClient *c, int flags) { long long dirty, start = ustime(), duration; /* Sent the command to clients in MONITOR mode, only if the commands are * not geneated from reading an AOF. */ if (listLength(server.monitors) && !server.loading) replicationFeedMonitors(c,server.monitors,c->db->id,c->argv,c->argc); /* Call the command. */ redisOpArrayInit(&server.also_propagate); dirty = server.dirty; c->cmd->proc(c); dirty = server.dirty-dirty; duration = ustime()-start; /* When EVAL is called loading the AOF we don't want commands called * from Lua to go into the slowlog or to populate statistics. */ if (server.loading && c->flags & REDIS_LUA_CLIENT) flags &= ~(REDIS_CALL_SLOWLOG | REDIS_CALL_STATS); /* Log the command into the Slow log if needed, and populate the * per-command statistics that we show in INFO commandstats. */ if (flags & REDIS_CALL_SLOWLOG) slowlogPushEntryIfNeeded(c->argv,c->argc,duration); if (flags & REDIS_CALL_STATS) { c->cmd->microseconds += duration; c->cmd->calls++; } /* Propagate the command into the AOF and replication link */ if (flags & REDIS_CALL_PROPAGATE) { int flags = REDIS_PROPAGATE_NONE; if (c->cmd->flags & REDIS_CMD_FORCE_REPLICATION) flags |= REDIS_PROPAGATE_REPL; if (dirty) flags |= (REDIS_PROPAGATE_REPL | REDIS_PROPAGATE_AOF); if (flags != REDIS_PROPAGATE_NONE) propagate(c->cmd,c->db->id,c->argv,c->argc,flags); } /* Commands such as LPUSH or BRPOPLPUSH may propagate an additional * PUSH command. */ if (server.also_propagate.numops) { int j; redisOp *rop; for (j = 0; j < server.also_propagate.numops; j++) { rop = &server.also_propagate.ops[j]; propagate(rop->cmd, rop->dbid, rop->argv, rop->argc, rop->target); } redisOpArrayFree(&server.also_propagate); } server.stat_numcommands++; } /* If this function gets called we already read a whole * command, argments are in the client argv/argc fields. * processCommand() execute the command or prepare the * server for a bulk read from the client. * * If 1 is returned the client is still alive and valid and * and other operations can be performed by the caller. Otherwise * if 0 is returned the client was destroied (i.e. after QUIT). */ int processCommand(redisClient *c) { /* The QUIT command is handled separately. Normal command procs will * go through checking for replication and QUIT will cause trouble * when FORCE_REPLICATION is enabled and would be implemented in * a regular command proc. */ if (!strcasecmp(c->argv[0]->ptr,"quit")) { addReply(c,shared.ok); c->flags |= REDIS_CLOSE_AFTER_REPLY; return REDIS_ERR; } /* Now lookup the command and check ASAP about trivial error conditions * such as wrong arity, bad command name and so forth. */ c->cmd = c->lastcmd = lookupCommand(c->argv[0]->ptr); if (!c->cmd) { addReplyErrorFormat(c,"unknown command '%s'", (char*)c->argv[0]->ptr); return REDIS_OK; } else if ((c->cmd->arity > 0 && c->cmd->arity != c->argc) || (c->argc < -c->cmd->arity)) { addReplyErrorFormat(c,"wrong number of arguments for '%s' command", c->cmd->name); return REDIS_OK; } /* Check if the user is authenticated */ if (server.requirepass && !c->authenticated && c->cmd->proc != authCommand) { addReplyError(c,"operation not permitted"); return REDIS_OK; } /* If cluster is enabled, redirect here */ if (server.cluster_enabled && !(c->cmd->getkeys_proc == NULL && c->cmd->firstkey == 0)) { int hashslot; if (server.cluster.state != REDIS_CLUSTER_OK) { addReplyError(c,"The cluster is down. Check with CLUSTER INFO for more information"); return REDIS_OK; } else { int ask; clusterNode *n = getNodeByQuery(c,c->cmd,c->argv,c->argc,&hashslot,&ask); if (n == NULL) { addReplyError(c,"Multi keys request invalid in cluster"); return REDIS_OK; } else if (n != server.cluster.myself) { addReplySds(c,sdscatprintf(sdsempty(), "-%s %d %s:%d\r\n", ask ? "ASK" : "MOVED", hashslot,n->ip,n->port)); return REDIS_OK; } } } /* Handle the maxmemory directive. * * First we try to free some memory if possible (if there are volatile * keys in the dataset). If there are not the only thing we can do * is returning an error. */ if (server.maxmemory) { int retval = freeMemoryIfNeeded(); if ((c->cmd->flags & REDIS_CMD_DENYOOM) && retval == REDIS_ERR) { addReplyError(c, "command not allowed when used memory > 'maxmemory'"); return REDIS_OK; } } /* Don't accept write commands if there are problems persisting on disk. */ if (server.stop_writes_on_bgsave_err && server.saveparamslen > 0 && server.lastbgsave_status == REDIS_ERR && c->cmd->flags & REDIS_CMD_WRITE) { addReply(c, shared.bgsaveerr); return REDIS_OK; } /* Only allow SUBSCRIBE and UNSUBSCRIBE in the context of Pub/Sub */ if ((dictSize(c->pubsub_channels) > 0 || listLength(c->pubsub_patterns) > 0) && c->cmd->proc != subscribeCommand && c->cmd->proc != unsubscribeCommand && c->cmd->proc != psubscribeCommand && c->cmd->proc != punsubscribeCommand) { addReplyError(c,"only (P)SUBSCRIBE / (P)UNSUBSCRIBE / QUIT allowed in this context"); return REDIS_OK; } /* Only allow INFO and SLAVEOF when slave-serve-stale-data is no and * we are a slave with a broken link with master. */ if (server.masterhost && server.repl_state != REDIS_REPL_CONNECTED && server.repl_serve_stale_data == 0 && c->cmd->proc != infoCommand && c->cmd->proc != slaveofCommand) { addReplyError(c, "link with MASTER is down and slave-serve-stale-data is set to no"); return REDIS_OK; } /* Loading DB? Return an error if the command is not INFO */ if (server.loading && c->cmd->proc != infoCommand) { addReply(c, shared.loadingerr); return REDIS_OK; } /* Lua script too slow? Only allow SHUTDOWN NOSAVE and SCRIPT KILL. */ if (server.lua_timedout && !(c->cmd->proc != shutdownCommand && c->argc == 2 && tolower(((char*)c->argv[1]->ptr)[0]) == 'n') && !(c->cmd->proc == scriptCommand && c->argc == 2 && tolower(((char*)c->argv[1]->ptr)[0]) == 'k')) { addReply(c, shared.slowscripterr); return REDIS_OK; } /* Exec the command */ if (c->flags & REDIS_MULTI && c->cmd->proc != execCommand && c->cmd->proc != discardCommand && c->cmd->proc != multiCommand && c->cmd->proc != watchCommand) { queueMultiCommand(c); addReply(c,shared.queued); } else { call(c,REDIS_CALL_FULL); } return REDIS_OK; } /*================================== Shutdown =============================== */ int prepareForShutdown(int flags) { int save = flags & REDIS_SHUTDOWN_SAVE; int nosave = flags & REDIS_SHUTDOWN_NOSAVE; redisLog(REDIS_WARNING,"User requested shutdown..."); /* Kill the saving child if there is a background saving in progress. We want to avoid race conditions, for instance our saving child may overwrite the synchronous saving did by SHUTDOWN. */ if (server.rdb_child_pid != -1) { redisLog(REDIS_WARNING,"There is a child saving an .rdb. Killing it!"); kill(server.rdb_child_pid,SIGKILL); rdbRemoveTempFile(server.rdb_child_pid); } if (server.aof_state != REDIS_AOF_OFF) { /* Kill the AOF saving child as the AOF we already have may be longer * but contains the full dataset anyway. */ if (server.aof_child_pid != -1) { redisLog(REDIS_WARNING, "There is a child rewriting the AOF. Killing it!"); kill(server.aof_child_pid,SIGKILL); } /* Append only file: fsync() the AOF and exit */ redisLog(REDIS_NOTICE,"Calling fsync() on the AOF file."); aof_fsync(server.aof_fd); } if ((server.saveparamslen > 0 && !nosave) || save) { redisLog(REDIS_NOTICE,"Saving the final RDB snapshot before exiting."); /* Snapshotting. Perform a SYNC SAVE and exit */ if (rdbSave(server.rdb_filename) != REDIS_OK) { /* Ooops.. error saving! The best we can do is to continue * operating. Note that if there was a background saving process, * in the next cron() Redis will be notified that the background * saving aborted, handling special stuff like slaves pending for * synchronization... */ redisLog(REDIS_WARNING,"Error trying to save the DB, can't exit."); return REDIS_ERR; } } if (server.daemonize) { redisLog(REDIS_NOTICE,"Removing the pid file."); unlink(server.pidfile); } /* Close the listening sockets. Apparently this allows faster restarts. */ if (server.ipfd != -1) close(server.ipfd); if (server.sofd != -1) close(server.sofd); if (server.unixsocket) { redisLog(REDIS_NOTICE,"Removing the unix socket file."); unlink(server.unixsocket); /* don't care if this fails */ } redisLog(REDIS_WARNING,"Redis is now ready to exit, bye bye..."); return REDIS_OK; } /*================================== Commands =============================== */ void authCommand(redisClient *c) { if (!server.requirepass) { addReplyError(c,"Client sent AUTH, but no password is set"); } else if (!strcmp(c->argv[1]->ptr, server.requirepass)) { c->authenticated = 1; addReply(c,shared.ok); } else { c->authenticated = 0; addReplyError(c,"invalid password"); } } void pingCommand(redisClient *c) { addReply(c,shared.pong); } void echoCommand(redisClient *c) { addReplyBulk(c,c->argv[1]); } void timeCommand(redisClient *c) { struct timeval tv; /* gettimeofday() can only fail if &tv is a bad addresss so we * don't check for errors. */ gettimeofday(&tv,NULL); addReplyMultiBulkLen(c,2); addReplyBulkLongLong(c,tv.tv_sec); addReplyBulkLongLong(c,tv.tv_usec); } /* Convert an amount of bytes into a human readable string in the form * of 100B, 2G, 100M, 4K, and so forth. */ void bytesToHuman(char *s, unsigned long long n) { double d; if (n < 1024) { /* Bytes */ sprintf(s,"%lluB",n); return; } else if (n < (1024*1024)) { d = (double)n/(1024); sprintf(s,"%.2fK",d); } else if (n < (1024LL*1024*1024)) { d = (double)n/(1024*1024); sprintf(s,"%.2fM",d); } else if (n < (1024LL*1024*1024*1024)) { d = (double)n/(1024LL*1024*1024); sprintf(s,"%.2fG",d); } } /* Create the string returned by the INFO command. This is decoupled * by the INFO command itself as we need to report the same information * on memory corruption problems. */ sds genRedisInfoString(char *section) { sds info = sdsempty(); time_t uptime = time(NULL)-server.stat_starttime; int j, numcommands; struct rusage self_ru, c_ru; unsigned long lol, bib; int allsections = 0, defsections = 0; int sections = 0; if (section) { allsections = strcasecmp(section,"all") == 0; defsections = strcasecmp(section,"default") == 0; } getrusage(RUSAGE_SELF, &self_ru); getrusage(RUSAGE_CHILDREN, &c_ru); getClientsMaxBuffers(&lol,&bib); /* Server */ if (allsections || defsections || !strcasecmp(section,"server")) { if (sections++) info = sdscat(info,"\r\n"); info = sdscatprintf(info, "# Server\r\n" "redis_version:%s\r\n" "redis_git_sha1:%s\r\n" "redis_git_dirty:%d\r\n" "arch_bits:%d\r\n" "multiplexing_api:%s\r\n" "gcc_version:%d.%d.%d\r\n" "process_id:%ld\r\n" "run_id:%s\r\n" "tcp_port:%d\r\n" "uptime_in_seconds:%ld\r\n" "uptime_in_days:%ld\r\n" "lru_clock:%ld\r\n", REDIS_VERSION, redisGitSHA1(), strtol(redisGitDirty(),NULL,10) > 0, server.arch_bits, aeGetApiName(), #ifdef __GNUC__ __GNUC__,__GNUC_MINOR__,__GNUC_PATCHLEVEL__, #else 0,0,0, #endif (long) getpid(), server.runid, server.port, uptime, uptime/(3600*24), (unsigned long) server.lruclock); } /* Clients */ if (allsections || defsections || !strcasecmp(section,"clients")) { if (sections++) info = sdscat(info,"\r\n"); info = sdscatprintf(info, "# Clients\r\n" "connected_clients:%lu\r\n" "client_longest_output_list:%lu\r\n" "client_biggest_input_buf:%lu\r\n" "blocked_clients:%d\r\n", listLength(server.clients)-listLength(server.slaves), lol, bib, server.bpop_blocked_clients); } /* Memory */ if (allsections || defsections || !strcasecmp(section,"memory")) { char hmem[64]; char peak_hmem[64]; bytesToHuman(hmem,zmalloc_used_memory()); bytesToHuman(peak_hmem,server.stat_peak_memory); if (sections++) info = sdscat(info,"\r\n"); info = sdscatprintf(info, "# Memory\r\n" "used_memory:%zu\r\n" "used_memory_human:%s\r\n" "used_memory_rss:%zu\r\n" "used_memory_peak:%zu\r\n" "used_memory_peak_human:%s\r\n" "used_memory_lua:%lld\r\n" "mem_fragmentation_ratio:%.2f\r\n" "mem_allocator:%s\r\n", zmalloc_used_memory(), hmem, zmalloc_get_rss(), server.stat_peak_memory, peak_hmem, ((long long)lua_gc(server.lua,LUA_GCCOUNT,0))*1024LL, zmalloc_get_fragmentation_ratio(), ZMALLOC_LIB ); } /* Persistence */ if (allsections || defsections || !strcasecmp(section,"persistence")) { if (sections++) info = sdscat(info,"\r\n"); info = sdscatprintf(info, "# Persistence\r\n" "loading:%d\r\n" "aof_enabled:%d\r\n" "changes_since_last_save:%lld\r\n" "bgsave_in_progress:%d\r\n" "last_save_time:%ld\r\n" "last_bgsave_status:%s\r\n" "bgrewriteaof_in_progress:%d\r\n", server.loading, server.aof_state != REDIS_AOF_OFF, server.dirty, server.rdb_child_pid != -1, server.lastsave, server.lastbgsave_status == REDIS_OK ? "ok" : "err", server.aof_child_pid != -1); if (server.aof_state != REDIS_AOF_OFF) { info = sdscatprintf(info, "aof_current_size:%lld\r\n" "aof_base_size:%lld\r\n" "aof_pending_rewrite:%d\r\n" "aof_buffer_length:%zu\r\n" "aof_pending_bio_fsync:%llu\r\n", (long long) server.aof_current_size, (long long) server.aof_rewrite_base_size, server.aof_rewrite_scheduled, sdslen(server.aof_buf), bioPendingJobsOfType(REDIS_BIO_AOF_FSYNC)); } if (server.loading) { double perc; time_t eta, elapsed; off_t remaining_bytes = server.loading_total_bytes- server.loading_loaded_bytes; perc = ((double)server.loading_loaded_bytes / server.loading_total_bytes) * 100; elapsed = time(NULL)-server.loading_start_time; if (elapsed == 0) { eta = 1; /* A fake 1 second figure if we don't have enough info */ } else { eta = (elapsed*remaining_bytes)/server.loading_loaded_bytes; } info = sdscatprintf(info, "loading_start_time:%ld\r\n" "loading_total_bytes:%llu\r\n" "loading_loaded_bytes:%llu\r\n" "loading_loaded_perc:%.2f\r\n" "loading_eta_seconds:%ld\r\n" ,(unsigned long) server.loading_start_time, (unsigned long long) server.loading_total_bytes, (unsigned long long) server.loading_loaded_bytes, perc, eta ); } } /* Stats */ if (allsections || defsections || !strcasecmp(section,"stats")) { if (sections++) info = sdscat(info,"\r\n"); info = sdscatprintf(info, "# Stats\r\n" "total_connections_received:%lld\r\n" "total_commands_processed:%lld\r\n" "instantaneous_ops_per_sec:%lld\r\n" "rejected_connections:%lld\r\n" "expired_keys:%lld\r\n" "evicted_keys:%lld\r\n" "keyspace_hits:%lld\r\n" "keyspace_misses:%lld\r\n" "pubsub_channels:%ld\r\n" "pubsub_patterns:%lu\r\n" "latest_fork_usec:%lld\r\n", server.stat_numconnections, server.stat_numcommands, getOperationsPerSecond(), server.stat_rejected_conn, server.stat_expiredkeys, server.stat_evictedkeys, server.stat_keyspace_hits, server.stat_keyspace_misses, dictSize(server.pubsub_channels), listLength(server.pubsub_patterns), server.stat_fork_time); } /* Replication */ if (allsections || defsections || !strcasecmp(section,"replication")) { if (sections++) info = sdscat(info,"\r\n"); info = sdscatprintf(info, "# Replication\r\n" "role:%s\r\n", server.masterhost == NULL ? "master" : "slave"); if (server.masterhost) { info = sdscatprintf(info, "master_host:%s\r\n" "master_port:%d\r\n" "master_link_status:%s\r\n" "master_last_io_seconds_ago:%d\r\n" "master_sync_in_progress:%d\r\n" ,server.masterhost, server.masterport, (server.repl_state == REDIS_REPL_CONNECTED) ? "up" : "down", server.master ? ((int)(time(NULL)-server.master->lastinteraction)) : -1, server.repl_state == REDIS_REPL_TRANSFER ); if (server.repl_state == REDIS_REPL_TRANSFER) { info = sdscatprintf(info, "master_sync_left_bytes:%ld\r\n" "master_sync_last_io_seconds_ago:%d\r\n" ,(long)server.repl_transfer_left, (int)(time(NULL)-server.repl_transfer_lastio) ); } if (server.repl_state != REDIS_REPL_CONNECTED) { info = sdscatprintf(info, "master_link_down_since_seconds:%ld\r\n", (long)time(NULL)-server.repl_down_since); } } info = sdscatprintf(info, "connected_slaves:%lu\r\n", listLength(server.slaves)); if (listLength(server.slaves)) { int slaveid = 0; listNode *ln; listIter li; listRewind(server.slaves,&li); while((ln = listNext(&li))) { redisClient *slave = listNodeValue(ln); char *state = NULL; char ip[32]; int port; if (anetPeerToString(slave->fd,ip,&port) == -1) continue; switch(slave->replstate) { case REDIS_REPL_WAIT_BGSAVE_START: case REDIS_REPL_WAIT_BGSAVE_END: state = "wait_bgsave"; break; case REDIS_REPL_SEND_BULK: state = "send_bulk"; break; case REDIS_REPL_ONLINE: state = "online"; break; } if (state == NULL) continue; info = sdscatprintf(info,"slave%d:%s,%d,%s\r\n", slaveid,ip,port,state); slaveid++; } } } /* CPU */ if (allsections || defsections || !strcasecmp(section,"cpu")) { if (sections++) info = sdscat(info,"\r\n"); info = sdscatprintf(info, "# CPU\r\n" "used_cpu_sys:%.2f\r\n" "used_cpu_user:%.2f\r\n" "used_cpu_sys_children:%.2f\r\n" "used_cpu_user_children:%.2f\r\n", (float)self_ru.ru_stime.tv_sec+(float)self_ru.ru_stime.tv_usec/1000000, (float)self_ru.ru_utime.tv_sec+(float)self_ru.ru_utime.tv_usec/1000000, (float)c_ru.ru_stime.tv_sec+(float)c_ru.ru_stime.tv_usec/1000000, (float)c_ru.ru_utime.tv_sec+(float)c_ru.ru_utime.tv_usec/1000000); } /* cmdtime */ if (allsections || !strcasecmp(section,"commandstats")) { if (sections++) info = sdscat(info,"\r\n"); info = sdscatprintf(info, "# Commandstats\r\n"); numcommands = sizeof(redisCommandTable)/sizeof(struct redisCommand); for (j = 0; j < numcommands; j++) { struct redisCommand *c = redisCommandTable+j; if (!c->calls) continue; info = sdscatprintf(info, "cmdstat_%s:calls=%lld,usec=%lld,usec_per_call=%.2f\r\n", c->name, c->calls, c->microseconds, (c->calls == 0) ? 0 : ((float)c->microseconds/c->calls)); } } /* Clusetr */ if (allsections || defsections || !strcasecmp(section,"cluster")) { if (sections++) info = sdscat(info,"\r\n"); info = sdscatprintf(info, "# Cluster\r\n" "cluster_enabled:%d\r\n", server.cluster_enabled); } /* Key space */ if (allsections || defsections || !strcasecmp(section,"keyspace")) { if (sections++) info = sdscat(info,"\r\n"); info = sdscatprintf(info, "# Keyspace\r\n"); for (j = 0; j < server.dbnum; j++) { long long keys, vkeys; keys = dictSize(server.db[j].dict); vkeys = dictSize(server.db[j].expires); if (keys || vkeys) { info = sdscatprintf(info, "db%d:keys=%lld,expires=%lld\r\n", j, keys, vkeys); } } } return info; } void infoCommand(redisClient *c) { char *section = c->argc == 2 ? c->argv[1]->ptr : "default"; if (c->argc > 2) { addReply(c,shared.syntaxerr); return; } sds info = genRedisInfoString(section); addReplySds(c,sdscatprintf(sdsempty(),"$%lu\r\n", (unsigned long)sdslen(info))); addReplySds(c,info); addReply(c,shared.crlf); } void monitorCommand(redisClient *c) { /* ignore MONITOR if aleady slave or in monitor mode */ if (c->flags & REDIS_SLAVE) return; c->flags |= (REDIS_SLAVE|REDIS_MONITOR); c->slaveseldb = 0; listAddNodeTail(server.monitors,c); addReply(c,shared.ok); } /* ============================ Maxmemory directive ======================== */ /* This function gets called when 'maxmemory' is set on the config file to limit * the max memory used by the server, before processing a command. * * The goal of the function is to free enough memory to keep Redis under the * configured memory limit. * * The function starts calculating how many bytes should be freed to keep * Redis under the limit, and enters a loop selecting the best keys to * evict accordingly to the configured policy. * * If all the bytes needed to return back under the limit were freed the * function returns REDIS_OK, otherwise REDIS_ERR is returned, and the caller * should block the execution of commands that will result in more memory * used by the server. */ int freeMemoryIfNeeded(void) { size_t mem_used, mem_tofree, mem_freed; int slaves = listLength(server.slaves); /* Remove the size of slaves output buffers and AOF buffer from the * count of used memory. */ mem_used = zmalloc_used_memory(); if (slaves) { listIter li; listNode *ln; listRewind(server.slaves,&li); while((ln = listNext(&li))) { redisClient *slave = listNodeValue(ln); unsigned long obuf_bytes = getClientOutputBufferMemoryUsage(slave); if (obuf_bytes > mem_used) mem_used = 0; else mem_used -= obuf_bytes; } } if (server.aof_state != REDIS_AOF_OFF) { mem_used -= sdslen(server.aof_buf); mem_used -= sdslen(server.aof_rewrite_buf); } /* Check if we are over the memory limit. */ if (mem_used <= server.maxmemory) return REDIS_OK; if (server.maxmemory_policy == REDIS_MAXMEMORY_NO_EVICTION) return REDIS_ERR; /* We need to free memory, but policy forbids. */ /* Compute how much memory we need to free. */ mem_tofree = mem_used - server.maxmemory; mem_freed = 0; while (mem_freed < mem_tofree) { int j, k, keys_freed = 0; for (j = 0; j < server.dbnum; j++) { long bestval = 0; /* just to prevent warning */ sds bestkey = NULL; struct dictEntry *de; redisDb *db = server.db+j; dict *dict; if (server.maxmemory_policy == REDIS_MAXMEMORY_ALLKEYS_LRU || server.maxmemory_policy == REDIS_MAXMEMORY_ALLKEYS_RANDOM) { dict = server.db[j].dict; } else { dict = server.db[j].expires; } if (dictSize(dict) == 0) continue; /* volatile-random and allkeys-random policy */ if (server.maxmemory_policy == REDIS_MAXMEMORY_ALLKEYS_RANDOM || server.maxmemory_policy == REDIS_MAXMEMORY_VOLATILE_RANDOM) { de = dictGetRandomKey(dict); bestkey = dictGetKey(de); } /* volatile-lru and allkeys-lru policy */ else if (server.maxmemory_policy == REDIS_MAXMEMORY_ALLKEYS_LRU || server.maxmemory_policy == REDIS_MAXMEMORY_VOLATILE_LRU) { for (k = 0; k < server.maxmemory_samples; k++) { sds thiskey; long thisval; robj *o; de = dictGetRandomKey(dict); thiskey = dictGetKey(de); /* When policy is volatile-lru we need an additonal lookup * to locate the real key, as dict is set to db->expires. */ if (server.maxmemory_policy == REDIS_MAXMEMORY_VOLATILE_LRU) de = dictFind(db->dict, thiskey); o = dictGetVal(de); thisval = estimateObjectIdleTime(o); /* Higher idle time is better candidate for deletion */ if (bestkey == NULL || thisval > bestval) { bestkey = thiskey; bestval = thisval; } } } /* volatile-ttl */ else if (server.maxmemory_policy == REDIS_MAXMEMORY_VOLATILE_TTL) { for (k = 0; k < server.maxmemory_samples; k++) { sds thiskey; long thisval; de = dictGetRandomKey(dict); thiskey = dictGetKey(de); thisval = (long) dictGetVal(de); /* Expire sooner (minor expire unix timestamp) is better * candidate for deletion */ if (bestkey == NULL || thisval < bestval) { bestkey = thiskey; bestval = thisval; } } } /* Finally remove the selected key. */ if (bestkey) { long long delta; robj *keyobj = createStringObject(bestkey,sdslen(bestkey)); propagateExpire(db,keyobj); /* We compute the amount of memory freed by dbDelete() alone. * It is possible that actually the memory needed to propagate * the DEL in AOF and replication link is greater than the one * we are freeing removing the key, but we can't account for * that otherwise we would never exit the loop. * * AOF and Output buffer memory will be freed eventually so * we only care about memory used by the key space. */ delta = (long long) zmalloc_used_memory(); dbDelete(db,keyobj); delta -= (long long) zmalloc_used_memory(); mem_freed += delta; server.stat_evictedkeys++; decrRefCount(keyobj); keys_freed++; /* When the memory to free starts to be big enough, we may * start spending so much time here that is impossible to * deliver data to the slaves fast enough, so we force the * transmission here inside the loop. */ if (slaves) flushSlavesOutputBuffers(); } } if (!keys_freed) return REDIS_ERR; /* nothing to free... */ } return REDIS_OK; } /* =================================== Main! ================================ */ #ifdef __linux__ int linuxOvercommitMemoryValue(void) { FILE *fp = fopen("/proc/sys/vm/overcommit_memory","r"); char buf[64]; if (!fp) return -1; if (fgets(buf,64,fp) == NULL) { fclose(fp); return -1; } fclose(fp); return atoi(buf); } void linuxOvercommitMemoryWarning(void) { if (linuxOvercommitMemoryValue() == 0) { redisLog(REDIS_WARNING,"WARNING overcommit_memory is set to 0! Background save may fail under low memory condition. To fix this issue add 'vm.overcommit_memory = 1' to /etc/sysctl.conf and then reboot or run the command 'sysctl vm.overcommit_memory=1' for this to take effect."); } } #endif /* __linux__ */ void createPidFile(void) { /* Try to write the pid file in a best-effort way. */ FILE *fp = fopen(server.pidfile,"w"); if (fp) { fprintf(fp,"%d\n",(int)getpid()); fclose(fp); } } void daemonize(void) { int fd; if (fork() != 0) exit(0); /* parent exits */ setsid(); /* create a new session */ /* Every output goes to /dev/null. If Redis is daemonized but * the 'logfile' is set to 'stdout' in the configuration file * it will not log at all. */ if ((fd = open("/dev/null", O_RDWR, 0)) != -1) { dup2(fd, STDIN_FILENO); dup2(fd, STDOUT_FILENO); dup2(fd, STDERR_FILENO); if (fd > STDERR_FILENO) close(fd); } } void version() { printf("Redis server version %s (%s:%d)\n", REDIS_VERSION, redisGitSHA1(), atoi(redisGitDirty()) > 0); exit(0); } void usage() { fprintf(stderr,"Usage: ./redis-server [/path/to/redis.conf] [options]\n"); fprintf(stderr," ./redis-server - (read config from stdin)\n"); fprintf(stderr," ./redis-server -v or --version\n"); fprintf(stderr," ./redis-server -h or --help\n"); fprintf(stderr," ./redis-server --test-memory \n\n"); fprintf(stderr,"Examples:\n"); fprintf(stderr," ./redis-server (run the server with default conf)\n"); fprintf(stderr," ./redis-server /etc/redis/6379.conf\n"); fprintf(stderr," ./redis-server --port 7777\n"); fprintf(stderr," ./redis-server --port 7777 --slaveof 127.0.0.1 8888\n"); fprintf(stderr," ./redis-server /etc/myredis.conf --loglevel verbose\n"); exit(1); } void redisAsciiArt(void) { #include "asciilogo.h" char *buf = zmalloc(1024*16); snprintf(buf,1024*16,ascii_logo, REDIS_VERSION, redisGitSHA1(), strtol(redisGitDirty(),NULL,10) > 0, (sizeof(long) == 8) ? "64" : "32", server.cluster_enabled ? "cluster" : "stand alone", server.port, (long) getpid() ); redisLogRaw(REDIS_NOTICE|REDIS_LOG_RAW,buf); zfree(buf); } static void sigtermHandler(int sig) { REDIS_NOTUSED(sig); redisLog(REDIS_WARNING,"Received SIGTERM, scheduling shutdown..."); server.shutdown_asap = 1; } void setupSignalHandlers(void) { struct sigaction act; /* When the SA_SIGINFO flag is set in sa_flags then sa_sigaction is used. * Otherwise, sa_handler is used. */ sigemptyset(&act.sa_mask); act.sa_flags = SA_NODEFER | SA_ONSTACK | SA_RESETHAND; act.sa_handler = sigtermHandler; sigaction(SIGTERM, &act, NULL); #ifdef HAVE_BACKTRACE sigemptyset(&act.sa_mask); act.sa_flags = SA_NODEFER | SA_ONSTACK | SA_RESETHAND | SA_SIGINFO; act.sa_sigaction = sigsegvHandler; sigaction(SIGSEGV, &act, NULL); sigaction(SIGBUS, &act, NULL); sigaction(SIGFPE, &act, NULL); sigaction(SIGILL, &act, NULL); #endif return; } void memtest(size_t megabytes, int passes); int main(int argc, char **argv) { long long start; struct timeval tv; /* We need to initialize our libraries, and the server configuration. */ zmalloc_enable_thread_safeness(); srand(time(NULL)^getpid()); gettimeofday(&tv,NULL); dictSetHashFunctionSeed(tv.tv_sec^tv.tv_usec^getpid()); initServerConfig(); if (argc >= 2) { int j = 1; /* First option to parse in argv[] */ sds options = sdsempty(); char *configfile = NULL; /* Handle special options --help and --version */ if (strcmp(argv[1], "-v") == 0 || strcmp(argv[1], "--version") == 0) version(); if (strcmp(argv[1], "--help") == 0 || strcmp(argv[1], "-h") == 0) usage(); if (strcmp(argv[1], "--test-memory") == 0) { if (argc == 3) { memtest(atoi(argv[2]),50); exit(0); } else { fprintf(stderr,"Please specify the amount of memory to test in megabytes.\n"); fprintf(stderr,"Example: ./redis-server --test-memory 4096\n\n"); exit(1); } } /* First argument is the config file name? */ if (argv[j][0] != '-' || argv[j][1] != '-') configfile = argv[j++]; /* All the other options are parsed and conceptually appended to the * configuration file. For instance --port 6380 will generate the * string "port 6380\n" to be parsed after the actual file name * is parsed, if any. */ while(j != argc) { if (argv[j][0] == '-' && argv[j][1] == '-') { /* Option name */ if (sdslen(options)) options = sdscat(options,"\n"); options = sdscat(options,argv[j]+2); options = sdscat(options," "); } else { /* Option argument */ options = sdscatrepr(options,argv[j],strlen(argv[j])); options = sdscat(options," "); } j++; } resetServerSaveParams(); loadServerConfig(configfile,options); sdsfree(options); } else { redisLog(REDIS_WARNING,"Warning: no config file specified, using the default config. In order to specify a config file use 'redis-server /path/to/redis.conf'"); } if (server.daemonize) daemonize(); initServer(); if (server.daemonize) createPidFile(); redisAsciiArt(); redisLog(REDIS_WARNING,"Server started, Redis version " REDIS_VERSION); #ifdef __linux__ linuxOvercommitMemoryWarning(); #endif start = ustime(); if (server.aof_state == REDIS_AOF_ON) { if (loadAppendOnlyFile(server.aof_filename) == REDIS_OK) redisLog(REDIS_NOTICE,"DB loaded from append only file: %.3f seconds",(float)(ustime()-start)/1000000); } else { if (rdbLoad(server.rdb_filename) == REDIS_OK) { redisLog(REDIS_NOTICE,"DB loaded from disk: %.3f seconds", (float)(ustime()-start)/1000000); } else if (errno != ENOENT) { redisLog(REDIS_WARNING,"Fatal error loading the DB. Exiting."); exit(1); } } if (server.ipfd > 0) redisLog(REDIS_NOTICE,"The server is now ready to accept connections on port %d", server.port); if (server.sofd > 0) redisLog(REDIS_NOTICE,"The server is now ready to accept connections at %s", server.unixsocket); aeSetBeforeSleepProc(server.el,beforeSleep); aeMain(server.el); aeDeleteEventLoop(server.el); return 0; } /* The End */