X-Git-Url: https://git.saurik.com/redis.git/blobdiff_plain/ae22bf1ef6dbfa07a485f61c119eb2e275a7916f..5513397de7526f0e5e01c1d29a37813008703d6d:/src/redis.c diff --git a/src/redis.c b/src/redis.c index 5388f5b7..1e90edef 100644 --- a/src/redis.c +++ b/src/redis.c @@ -1,5 +1,5 @@ /* - * Copyright (c) 2009-2010, Salvatore Sanfilippo + * Copyright (c) 2009-2012, Salvatore Sanfilippo * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -48,6 +48,7 @@ #include #include #include +#include /* Our shared "common" objects */ @@ -105,6 +106,11 @@ struct redisCommand *commandTable; * 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. + * l: Allow command while loading the database. + * t: Allow command while a slave has stale data but is not allowed to + * server this data. Normally no command is accepted in this condition + * but just a few. + * M: Do not automatically propagate the command on MONITOR. */ struct redisCommand redisCommandTable[] = { {"get",getCommand,2,"r",0,NULL,1,1,1,0,0}, @@ -147,7 +153,7 @@ struct redisCommand redisCommandTable[] = { {"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}, + {"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}, @@ -211,39 +217,42 @@ struct redisCommand redisCommandTable[] = { {"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}, + {"exec",execCommand,1,"sM",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}, + {"replconf",replconfCommand,-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}, + {"sort",sortCommand,-2,"wm",0,NULL,1,1,1,0,0}, + {"info",infoCommand,-1,"rlt",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}, + {"slaveof",slaveofCommand,3,"ast",0,NULL,0,0,0,0,0}, + {"debug",debugCommand,-2,"as",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}, + {"subscribe",subscribeCommand,-2,"rpslt",0,NULL,0,0,0,0,0}, + {"unsubscribe",unsubscribeCommand,-1,"rpslt",0,NULL,0,0,0,0,0}, + {"psubscribe",psubscribeCommand,-2,"rpslt",0,NULL,0,0,0,0,0}, + {"punsubscribe",punsubscribeCommand,-1,"rpslt",0,NULL,0,0,0,0,0}, + {"publish",publishCommand,3,"pflt",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}, + {"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}, + {"eval",evalCommand,-3,"s",0,zunionInterGetKeys,0,0,0,0,0}, + {"evalsha",evalShaCommand,-3,"s",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} + {"time",timeCommand,1,"rR",0,NULL,0,0,0,0,0}, + {"bitop",bitopCommand,-4,"wm",0,NULL,2,-1,1,0,0}, + {"bitcount",bitcountCommand,-2,"r",0,NULL,1,1,1,0,0} }; /*============================ Utility functions ============================ */ @@ -253,7 +262,6 @@ struct redisCommand redisCommandTable[] = { 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); @@ -267,7 +275,12 @@ void redisLogRaw(int level, const char *msg) { if (rawmode) { fprintf(fp,"%s",msg); } else { - strftime(buf,sizeof(buf),"%d %b %H:%M:%S",localtime(&now)); + int off; + struct timeval tv; + + gettimeofday(&tv,NULL); + off = strftime(buf,sizeof(buf),"%d %b %H:%M:%S.",localtime(&tv.tv_sec)); + snprintf(buf+off,sizeof(buf)-off,"%03d",(int)tv.tv_usec/1000); fprintf(fp,"[%d] %s %c %s\n",(int)getpid(),buf,c[level],msg); } fflush(fp); @@ -293,15 +306,33 @@ void redisLog(int level, const char *fmt, ...) { 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(); +/* Log a fixed message without printf-alike capabilities, in a way that is + * safe to call from a signal handler. + * + * We actually use this only for signals that are not fatal from the point + * of view of Redis. Signals that are going to kill the server anyway and + * where we need printf-alike features are served by redisLog(). */ +void redisLogFromHandler(int level, const char *msg) { + int fd; + char buf[64]; + + if ((level&0xff) < server.verbosity || + (server.logfile == NULL && server.daemonize)) return; + fd = server.logfile ? + open(server.logfile, O_APPEND|O_CREAT|O_WRONLY, 0644) : + STDOUT_FILENO; + if (fd == -1) return; + ll2string(buf,sizeof(buf),getpid()); + if (write(fd,"[",1) == -1) goto err; + if (write(fd,buf,strlen(buf)) == -1) goto err; + if (write(fd," | signal handler] (",20) == -1) goto err; + ll2string(buf,sizeof(buf),time(NULL)); + if (write(fd,buf,strlen(buf)) == -1) goto err; + if (write(fd,") ",2) == -1) goto err; + if (write(fd,msg,strlen(msg)) == -1) goto err; + if (write(fd,"\n",1) == -1) goto err; +err: + if (server.logfile) close(fd); } /* Return the UNIX time in microseconds */ @@ -320,6 +351,18 @@ long long mstime(void) { return ustime()/1000; } +/* After an RDB dump or AOF rewrite we exit from children using _exit() instead of + * exit(), because the latter may interact with the same file objects used by + * the parent process. However if we are testing the coverage normal exit() is + * used in order to obtain the right coverage information. */ +void exitFromChild(int retcode) { +#ifdef COVERAGE_TEST + exit(retcode); +#else + _exit(retcode); +#endif +} + /*====================== Hash table type implementation ==================== */ /* This is an hash table type that uses the SDS dynamic strings libary as @@ -548,10 +591,16 @@ void incrementallyRehash(void) { int j; for (j = 0; j < server.dbnum; j++) { + /* Keys dictionary */ if (dictIsRehashing(server.db[j].dict)) { dictRehashMilliseconds(server.db[j].dict,1); break; /* already used our millisecond for this loop... */ } + /* Expires */ + if (dictIsRehashing(server.db[j].expires)) { + dictRehashMilliseconds(server.db[j].expires,1); + break; /* already used our millisecond for this loop... */ + } } } @@ -575,7 +624,15 @@ void updateDictResizePolicy(void) { * 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; + int j, iteration = 0; + long long start = ustime(), timelimit; + + /* We can use at max REDIS_EXPIRELOOKUPS_TIME_PERC percentage of CPU time + * per iteration. Since this function gets called with a frequency of + * REDIS_HZ times per second, the following is the max amount of + * microseconds we can spend in this function. */ + timelimit = 1000000*REDIS_EXPIRELOOKUPS_TIME_PERC/REDIS_HZ/100; + if (timelimit <= 0) timelimit = 1; for (j = 0; j < server.dbnum; j++) { int expired; @@ -584,9 +641,18 @@ void activeExpireCycle(void) { /* Continue to expire if at the end of the cycle more than 25% * of the keys were expired. */ do { - long num = dictSize(db->expires); + unsigned long num = dictSize(db->expires); + unsigned long slots = dictSlots(db->expires); long long now = mstime(); + /* When there are less than 1% filled slots getting random + * keys is expensive, so stop here waiting for better times... + * The dictionary will be resized asap. */ + if (num && slots > DICT_HT_INITIAL_SIZE && + (num*100/slots < 1)) break; + + /* The main collection cycle. Sample random keys among keys + * with an expire set, checking for expired ones. */ expired = 0; if (num > REDIS_EXPIRELOOKUPS_PER_CRON) num = REDIS_EXPIRELOOKUPS_PER_CRON; @@ -607,12 +673,18 @@ void activeExpireCycle(void) { server.stat_expiredkeys++; } } + /* We can't block forever here even if there are many keys to + * expire. So after a given amount of milliseconds return to the + * caller waiting for the other active expire cycle. */ + iteration++; + if ((iteration & 0xf) == 0 && /* check once every 16 cycles. */ + (ustime()-start) > timelimit) return; } while (expired > REDIS_EXPIRELOOKUPS_PER_CRON/4); } } void updateLRUClock(void) { - server.lruclock = (time(NULL)/REDIS_LRU_CLOCK_RESOLUTION) & + server.lruclock = (server.unixtime/REDIS_LRU_CLOCK_RESOLUTION) & REDIS_LRU_CLOCK_MAX; } @@ -641,7 +713,8 @@ long long getOperationsPerSecond(void) { return sum / REDIS_OPS_SEC_SAMPLES; } -void clientsCronHandleTimeout(redisClient *c) { +/* Check for timeouts. Returns non-zero if the client was terminated */ +int clientsCronHandleTimeout(redisClient *c) { time_t now = server.unixtime; if (server.maxidletime && @@ -654,17 +727,21 @@ void clientsCronHandleTimeout(redisClient *c) { { 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. */ -void clientsCronResizeQueryBuffer(redisClient *c) { + * 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; @@ -683,16 +760,17 @@ void clientsCronResizeQueryBuffer(redisClient *c) { /* 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 + /* Make sure to process at least 1/(REDIS_HZ*10) of clients per call. + * Since this function is called REDIS_HZ 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; + int iterations = numclients/(REDIS_HZ*10); if (iterations < 50) iterations = (numclients < 50) ? numclients : 50; @@ -706,24 +784,50 @@ void clientsCron(void) { listRotate(server.clients); head = listFirst(server.clients); c = listNodeValue(head); - clientsCronHandleTimeout(c); - clientsCronResizeQueryBuffer(c); + /* 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; } } +/* This is our timer interrupt, called REDIS_HZ times per second. + * Here is where we do a number of things that need to be done asynchronously. + * For instance: + * + * - Active expired keys collection (it is also performed in a lazy way on + * lookup). + * - Software watchdong. + * - Update some statistic. + * - Incremental rehashing of the DBs hash tables. + * - Triggering BGSAVE / AOF rewrite, and handling of terminated children. + * - Clients timeout of differnet kinds. + * - Replication reconnection. + * - Many more... + * + * Everything directly called here will be called REDIS_HZ times per second, + * so in order to throttle execution of things we want to do less frequently + * a macro is used: run_with_period(milliseconds) { .... } + */ + int serverCron(struct aeEventLoop *eventLoop, long long id, void *clientData) { - int j, loops = server.cronloops; + int j; REDIS_NOTUSED(eventLoop); REDIS_NOTUSED(id); REDIS_NOTUSED(clientData); + /* Software watchdog: deliver the SIGALRM that will reach the signal + * handler if we don't return here fast enough. */ + if (server.watchdog_period) watchdogScheduleSignal(server.watchdog_period); + /* 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(); + run_with_period(100) trackOperationsPerSecond(); /* We have just 22 bits per object for LRU information. * So we use an (eventually wrapping) LRU clock with 10 seconds resolution. @@ -751,15 +855,17 @@ int serverCron(struct aeEventLoop *eventLoop, long long id, void *clientData) { } /* 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); */ + run_with_period(5000) { + 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 (used || vkeys) { + redisLog(REDIS_VERBOSE,"DB %d: %lld keys (%lld volatile) in %lld slots HT.",j,used,vkeys,size); + /* dictPrintStats(server.dict); */ + } } } @@ -770,16 +876,19 @@ int serverCron(struct aeEventLoop *eventLoop, long long id, void *clientData) { * 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(); + 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()); + if (!server.sentinel_mode) { + run_with_period(5000) { + 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. */ @@ -806,21 +915,23 @@ int serverCron(struct aeEventLoop *eventLoop, long long id, void *clientData) { if (pid == server.rdb_child_pid) { backgroundSaveDoneHandler(exitcode,bysignal); - } else { + } else if (pid == server.aof_child_pid) { backgroundRewriteDoneHandler(exitcode,bysignal); + } else { + redisLog(REDIS_WARNING, + "Warning, detected child with unmatched pid: %ld", + (long)pid); } 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) { + server.unixtime-server.lastsave > sp->seconds) { redisLog(REDIS_NOTICE,"%d changes in %d seconds. Saving...", sp->changes, sp->seconds); rdbSaveBackground(server.rdb_filename); @@ -859,13 +970,20 @@ int serverCron(struct aeEventLoop *eventLoop, long long id, void *clientData) { /* Replication cron function -- used to reconnect to master and * to detect transfer failures. */ - if (!(loops % 10)) replicationCron(); + run_with_period(1000) replicationCron(); /* Run other sub-systems specific cron jobs */ - if (server.cluster_enabled && !(loops % 10)) clusterCron(); + run_with_period(1000) { + if (server.cluster_enabled) clusterCron(); + } + + /* Run the sentinel timer if we are in sentinel mode. */ + run_with_period(100) { + if (server.sentinel_mode) sentinelTimer(); + } server.cronloops++; - return 100; + return 1000/REDIS_HZ; } /* This function gets called every time Redis is entering the @@ -914,7 +1032,7 @@ void createSharedObjects(void) { 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")); + "-WRONGTYPE 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( @@ -929,21 +1047,22 @@ void createSharedObjects(void) { "-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.masterdownerr = createObject(REDIS_STRING,sdsnew( + "-MASTERDOWN Link with MASTER is down and slave-serve-stale-data is set to 'no'.\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")); + "-MISCONF Redis is configured to save RDB snapshots, but is currently not able to persist on disk. Commands that may modify the data set are disabled. Please check Redis logs for details about the error.\r\n")); + shared.roslaveerr = createObject(REDIS_STRING,sdsnew( + "-READONLY You can't write against a read only slave.\r\n")); + shared.oomerr = createObject(REDIS_STRING,sdsnew( + "-OOM command not allowed when used memory > 'maxmemory'.\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); + + for (j = 0; j < REDIS_SHARED_SELECT_CMDS; j++) { + shared.select[j] = createObject(REDIS_STRING, + sdscatprintf(sdsempty(),"select %d\r\n", j)); + } 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); @@ -953,6 +1072,7 @@ void createSharedObjects(void) { shared.del = createStringObject("DEL",3); shared.rpop = createStringObject("RPOP",4); shared.lpop = createStringObject("LPOP",4); + shared.lpush = createStringObject("LPUSH",5); for (j = 0; j < REDIS_SHARED_INTEGERS; j++) { shared.integers[j] = createObject(REDIS_STRING,(void*)(long)j); shared.integers[j]->encoding = REDIS_ENCODING_INT; @@ -994,6 +1114,10 @@ void initServerConfig() { server.aof_rewrite_base_size = 0; server.aof_rewrite_scheduled = 0; server.aof_last_fsync = time(NULL); + server.aof_rewrite_time_last = -1; + server.aof_rewrite_time_start = -1; + server.aof_lastbgrewrite_status = REDIS_OK; + server.aof_delayed_fsync = 0; server.aof_fd = -1; server.aof_selected_db = -1; /* Make sure the first time will not match */ server.aof_flush_postponed_start = 0; @@ -1002,6 +1126,7 @@ void initServerConfig() { server.aof_filename = zstrdup("appendonly.aof"); server.requirepass = NULL; server.rdb_compression = 1; + server.rdb_checksum = 1; server.activerehashing = 1; server.maxclients = REDIS_MAX_CLIENTS; server.bpop_blocked_clients = 0; @@ -1039,7 +1164,9 @@ void initServerConfig() { 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; + server.repl_slave_ro = 1; + server.repl_down_since = time(NULL); + server.slave_priority = REDIS_DEFAULT_SLAVE_PRIORITY; /* Client output buffer limits */ server.client_obuf_limits[REDIS_CLIENT_LIMIT_CLASS_NORMAL].hard_limit_bytes = 0; @@ -1066,16 +1193,19 @@ void initServerConfig() { server.delCommand = lookupCommandByCString("del"); server.multiCommand = lookupCommandByCString("multi"); server.lpushCommand = lookupCommandByCString("lpush"); + server.lpopCommand = lookupCommandByCString("lpop"); + server.rpopCommand = lookupCommandByCString("rpop"); /* Slow log */ server.slowlog_log_slower_than = REDIS_SLOWLOG_LOG_SLOWER_THAN; server.slowlog_max_len = REDIS_SLOWLOG_MAX_LEN; - /* Assert */ + /* Debugging */ server.assert_failed = ""; server.assert_file = ""; server.assert_line = 0; server.bug_report_start = 0; + server.watchdog_period = 0; } /* This function will try to raise the max number of open files accordingly to @@ -1090,7 +1220,6 @@ 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)); @@ -1101,10 +1230,18 @@ void adjustOpenFilesLimit(void) { /* 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; + rlim_t f; + + f = maxfiles; + while(f > oldlimit) { + limit.rlim_cur = f; + limit.rlim_max = f; + if (setrlimit(RLIMIT_NOFILE,&limit) != -1) break; + f -= 128; + } + if (f < oldlimit) f = oldlimit; + if (f != maxfiles) { + server.maxclients = f-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 { @@ -1133,6 +1270,7 @@ void initServer() { server.slaves = listCreate(); server.monitors = listCreate(); server.unblocked_clients = listCreate(); + server.ready_keys = listCreate(); createSharedObjects(); adjustOpenFilesLimit(); @@ -1163,6 +1301,7 @@ void initServer() { 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].ready_keys = dictCreate(&setDictType,NULL); server.db[j].watched_keys = dictCreate(&keylistDictType,NULL); server.db[j].id = j; } @@ -1173,9 +1312,11 @@ void initServer() { server.cronloops = 0; server.rdb_child_pid = -1; server.aof_child_pid = -1; - server.aof_rewrite_buf = sdsempty(); + aofRewriteBufferReset(); server.aof_buf = sdsempty(); server.lastsave = time(NULL); + server.rdb_save_time_last = -1; + server.rdb_save_time_start = -1; server.dirty = 0; server.stat_numcommands = 0; server.stat_numconnections = 0; @@ -1196,9 +1337,9 @@ void initServer() { 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"); + acceptTcpHandler,NULL) == AE_ERR) redisPanic("Unrecoverable error creating server.ipfd file event."); if (server.sofd > 0 && aeCreateFileEvent(server.el,server.sofd,AE_READABLE, - acceptUnixHandler,NULL) == AE_ERR) oom("creating file event"); + acceptUnixHandler,NULL) == AE_ERR) redisPanic("Unrecoverable error creating server.sofd file event."); if (server.aof_state == REDIS_AOF_ON) { server.aof_fd = open(server.aof_filename, @@ -1212,11 +1353,11 @@ void initServer() { /* 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. */ + * at 3 GB using maxmemory with 'noeviction' policy'. This avoids + * useless crashes of the Redis instance for out of memory. */ 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 */ + redisLog(REDIS_WARNING,"Warning: 32 bit instance detected but no memory limit set. Setting 3 GB maxmemory limit with 'noeviction' policy now."); + server.maxmemory = 3072LL*(1024*1024); /* 3 GB */ server.maxmemory_policy = REDIS_MAXMEMORY_NO_EVICTION; } @@ -1248,6 +1389,9 @@ void populateCommandTable(void) { 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; + case 'l': c->flags |= REDIS_CMD_LOADING; break; + case 't': c->flags |= REDIS_CMD_STALE; break; + case 'M': c->flags |= REDIS_CMD_SKIP_MONITOR; break; default: redisPanic("Unsupported command flag"); break; } f++; @@ -1323,7 +1467,7 @@ struct redisCommand *lookupCommandByCString(char *s) { } /* Propagate the specified command (in the context of the specified database id) - * to AOF, Slaves and Monitors. + * to AOF and Slaves. * * flags are an xor between: * + REDIS_PROPAGATE_NONE (no propagation of command at all) @@ -1353,8 +1497,12 @@ void call(redisClient *c, int flags) { /* 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) + if (listLength(server.monitors) && + !server.loading && + !(c->cmd->flags & REDIS_CMD_SKIP_MONITOR)) + { replicationFeedMonitors(c,server.monitors,c->db->id,c->argv,c->argc); + } /* Call the command. */ redisOpArrayInit(&server.also_propagate); @@ -1404,7 +1552,7 @@ void call(redisClient *c, int flags) { } /* If this function gets called we already read a whole - * command, argments are in the client argv/argc fields. + * command, arguments are in the client argv/argc fields. * processCommand() execute the command or prepare the * server for a bulk read from the client. * @@ -1474,8 +1622,7 @@ int processCommand(redisClient *c) { 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'"); + addReply(c, shared.oomerr); return REDIS_OK; } } @@ -1490,6 +1637,16 @@ int processCommand(redisClient *c) { return REDIS_OK; } + /* Don't accept write commands if this is a read only slave. But + * accept write commands if this is our master. */ + if (server.masterhost && server.repl_slave_ro && + !(c->flags & REDIS_MASTER) && + c->cmd->flags & REDIS_CMD_WRITE) + { + addReply(c, shared.roslaveerr); + 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) && @@ -1505,22 +1662,23 @@ int processCommand(redisClient *c) { * 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) + !(c->cmd->flags & REDIS_CMD_STALE)) { - addReplyError(c, - "link with MASTER is down and slave-serve-stale-data is set to no"); + addReply(c, shared.masterdownerr); return REDIS_OK; } - /* Loading DB? Return an error if the command is not INFO */ - if (server.loading && c->cmd->proc != infoCommand) { + /* Loading DB? Return an error if the command has not the + * REDIS_CMD_LOADING flag. */ + if (server.loading && !(c->cmd->flags & REDIS_CMD_LOADING)) { addReply(c, shared.loadingerr); return REDIS_OK; } - /* Lua script too slow? Only allow SHUTDOWN NOSAVE and SCRIPT KILL. */ + /* Lua script too slow? Only allow commands with REDIS_CMD_STALE flag. */ if (server.lua_timedout && - !(c->cmd->proc != shutdownCommand && + c->cmd->proc != authCommand && + !(c->cmd->proc == shutdownCommand && c->argc == 2 && tolower(((char*)c->argv[1]->ptr)[0]) == 'n') && !(c->cmd->proc == scriptCommand && @@ -1540,6 +1698,8 @@ int processCommand(redisClient *c) { addReply(c,shared.queued); } else { call(c,REDIS_CALL_FULL); + if (listLength(server.ready_keys)) + handleClientsBlockedOnLists(); } return REDIS_OK; } @@ -1602,10 +1762,52 @@ int prepareForShutdown(int flags) { /*================================== Commands =============================== */ +/* Return zero if strings are the same, non-zero if they are not. + * The comparison is performed in a way that prevents an attacker to obtain + * information about the nature of the strings just monitoring the execution + * time of the function. + * + * Note that limiting the comparison length to strings up to 512 bytes we + * can avoid leaking any information about the password length and any + * possible branch misprediction related leak. + */ +int time_independent_strcmp(char *a, char *b) { + char bufa[REDIS_AUTHPASS_MAX_LEN], bufb[REDIS_AUTHPASS_MAX_LEN]; + /* The above two strlen perform len(a) + len(b) operations where either + * a or b are fixed (our password) length, and the difference is only + * relative to the length of the user provided string, so no information + * leak is possible in the following two lines of code. */ + int alen = strlen(a); + int blen = strlen(b); + int j; + int diff = 0; + + /* We can't compare strings longer than our static buffers. + * Note that this will never pass the first test in practical circumstances + * so there is no info leak. */ + if (alen > sizeof(bufa) || blen > sizeof(bufb)) return 1; + + memset(bufa,0,sizeof(bufa)); /* Constant time. */ + memset(bufb,0,sizeof(bufb)); /* Constant time. */ + /* Again the time of the following two copies is proportional to + * len(a) + len(b) so no info is leaked. */ + memcpy(bufa,a,alen); + memcpy(bufb,b,blen); + + /* Always compare all the chars in the two buffers without + * conditional expressions. */ + for (j = 0; j < sizeof(bufa); j++) { + diff |= (bufa[j] ^ bufb[j]); + } + /* Length must be equal as well. */ + diff |= alen ^ blen; + return diff; /* If zero strings are the same. */ +} + 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)) { + } else if (!time_independent_strcmp(c->argv[1]->ptr, server.requirepass)) { c->authenticated = 1; addReply(c,shared.ok); } else { @@ -1659,13 +1861,13 @@ void bytesToHuman(char *s, unsigned long long n) { * on memory corruption problems. */ sds genRedisInfoString(char *section) { sds info = sdsempty(); - time_t uptime = time(NULL)-server.stat_starttime; + time_t uptime = server.unixtime-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; @@ -1677,12 +1879,22 @@ sds genRedisInfoString(char *section) { /* Server */ if (allsections || defsections || !strcasecmp(section,"server")) { + struct utsname name; + char *mode; + + if (server.cluster_enabled) mode = "cluster"; + else if (server.sentinel_mode) mode = "sentinel"; + else mode = "standalone"; + if (sections++) info = sdscat(info,"\r\n"); + uname(&name); info = sdscatprintf(info, "# Server\r\n" "redis_version:%s\r\n" "redis_git_sha1:%s\r\n" "redis_git_dirty:%d\r\n" + "redis_mode:%s\r\n" + "os:%s %s %s\r\n" "arch_bits:%d\r\n" "multiplexing_api:%s\r\n" "gcc_version:%d.%d.%d\r\n" @@ -1695,6 +1907,8 @@ sds genRedisInfoString(char *section) { REDIS_VERSION, redisGitSHA1(), strtol(redisGitDirty(),NULL,10) > 0, + mode, + name.sysname, name.release, name.machine, server.arch_bits, aeGetApiName(), #ifdef __GNUC__ @@ -1759,19 +1973,33 @@ sds genRedisInfoString(char *section) { info = sdscatprintf(info, "# Persistence\r\n" "loading:%d\r\n" + "rdb_changes_since_last_save:%lld\r\n" + "rdb_bgsave_in_progress:%d\r\n" + "rdb_last_save_time:%ld\r\n" + "rdb_last_bgsave_status:%s\r\n" + "rdb_last_bgsave_time_sec:%ld\r\n" + "rdb_current_bgsave_time_sec:%ld\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", + "aof_rewrite_in_progress:%d\r\n" + "aof_rewrite_scheduled:%d\r\n" + "aof_last_rewrite_time_sec:%ld\r\n" + "aof_current_rewrite_time_sec:%ld\r\n" + "aof_last_bgrewrite_status:%s\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); + (server.lastbgsave_status == REDIS_OK) ? "ok" : "err", + server.rdb_save_time_last, + (server.rdb_child_pid == -1) ? + -1 : time(NULL)-server.rdb_save_time_start, + server.aof_state != REDIS_AOF_OFF, + server.aof_child_pid != -1, + server.aof_rewrite_scheduled, + server.aof_rewrite_time_last, + (server.aof_child_pid == -1) ? + -1 : time(NULL)-server.aof_rewrite_time_start, + (server.aof_lastbgrewrite_status == REDIS_OK) ? "ok" : "err"); if (server.aof_state != REDIS_AOF_OFF) { info = sdscatprintf(info, @@ -1779,12 +2007,16 @@ sds genRedisInfoString(char *section) { "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", + "aof_rewrite_buffer_length:%lu\r\n" + "aof_pending_bio_fsync:%llu\r\n" + "aof_delayed_fsync:%lu\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)); + aofRewriteBufferSize(), + bioPendingJobsOfType(REDIS_BIO_AOF_FSYNC), + server.aof_delayed_fsync); } if (server.loading) { @@ -1796,7 +2028,7 @@ sds genRedisInfoString(char *section) { perc = ((double)server.loading_loaded_bytes / server.loading_total_bytes) * 100; - elapsed = time(NULL)-server.loading_start_time; + elapsed = server.unixtime-server.loading_start_time; if (elapsed == 0) { eta = 1; /* A fake 1 second figure if we don't have enough info */ @@ -1867,24 +2099,30 @@ sds genRedisInfoString(char *section) { (server.repl_state == REDIS_REPL_CONNECTED) ? "up" : "down", server.master ? - ((int)(time(NULL)-server.master->lastinteraction)) : -1, + ((int)(server.unixtime-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_left_bytes:%lld\r\n" "master_sync_last_io_seconds_ago:%d\r\n" - ,(long)server.repl_transfer_left, - (int)(time(NULL)-server.repl_transfer_lastio) + , (long long) + (server.repl_transfer_size - server.repl_transfer_read), + (int)(server.unixtime-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); + (long)server.unixtime-server.repl_down_since); } + info = sdscatprintf(info, + "slave_priority:%d\r\n" + "slave_read_only:%d\r\n", + server.slave_priority, + server.repl_slave_ro); } info = sdscatprintf(info, "connected_slaves:%lu\r\n", @@ -1916,7 +2154,7 @@ sds genRedisInfoString(char *section) { } if (state == NULL) continue; info = sdscatprintf(info,"slave%d:%s,%d,%s\r\n", - slaveid,ip,port,state); + slaveid,ip,slave->slave_listening_port,state); slaveid++; } } @@ -1953,7 +2191,7 @@ sds genRedisInfoString(char *section) { } } - /* Clusetr */ + /* Cluster */ if (allsections || defsections || !strcasecmp(section,"cluster")) { if (sections++) info = sdscat(info,"\r\n"); info = sdscatprintf(info, @@ -1995,7 +2233,7 @@ void infoCommand(redisClient *c) { } void monitorCommand(redisClient *c) { - /* ignore MONITOR if aleady slave or in monitor mode */ + /* ignore MONITOR if already slave or in monitor mode */ if (c->flags & REDIS_SLAVE) return; c->flags |= (REDIS_SLAVE|REDIS_MONITOR); @@ -2044,7 +2282,7 @@ int freeMemoryIfNeeded(void) { } if (server.aof_state != REDIS_AOF_OFF) { mem_used -= sdslen(server.aof_buf); - mem_used -= sdslen(server.aof_rewrite_buf); + mem_used -= aofRewriteBufferSize(); } /* Check if we are over the memory limit. */ @@ -2094,7 +2332,7 @@ int freeMemoryIfNeeded(void) { de = dictGetRandomKey(dict); thiskey = dictGetKey(de); - /* When policy is volatile-lru we need an additonal lookup + /* When policy is volatile-lru we need an additional 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); @@ -2213,8 +2451,12 @@ void daemonize(void) { } void version() { - printf("Redis server version %s (%s:%d)\n", REDIS_VERSION, - redisGitSHA1(), atoi(redisGitDirty()) > 0); + printf("Redis server v=%s sha=%s:%d malloc=%s bits=%d\n", + REDIS_VERSION, + redisGitSHA1(), + atoi(redisGitDirty()) > 0, + ZMALLOC_LIB, + sizeof(long) == 4 ? 32 : 64); exit(0); } @@ -2222,27 +2464,33 @@ 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\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"); + fprintf(stderr," ./redis-server /etc/myredis.conf --loglevel verbose\n\n"); + fprintf(stderr,"Sentinel mode:\n"); + fprintf(stderr," ./redis-server /etc/sentinel.conf --sentinel\n"); exit(1); } void redisAsciiArt(void) { #include "asciilogo.h" char *buf = zmalloc(1024*16); + char *mode = "stand alone"; + + if (server.cluster_enabled) mode = "cluster"; + else if (server.sentinel_mode) mode = "sentinel"; 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, + mode, server.port, (long) getpid() ); redisLogRaw(REDIS_NOTICE|REDIS_LOG_RAW,buf); @@ -2252,7 +2500,7 @@ void redisAsciiArt(void) { static void sigtermHandler(int sig) { REDIS_NOTUSED(sig); - redisLog(REDIS_WARNING,"Received SIGTERM, scheduling shutdown..."); + redisLogFromHandler(REDIS_WARNING,"Received SIGTERM, scheduling shutdown..."); server.shutdown_asap = 1; } @@ -2262,13 +2510,13 @@ void setupSignalHandlers(void) { /* 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_flags = 0; 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_flags = SA_NODEFER | SA_RESETHAND | SA_SIGINFO; act.sa_sigaction = sigsegvHandler; sigaction(SIGSEGV, &act, NULL); sigaction(SIGBUS, &act, NULL); @@ -2278,17 +2526,62 @@ void setupSignalHandlers(void) { return; } +void memtest(size_t megabytes, int passes); + +/* Returns 1 if there is --sentinel among the arguments or if + * argv[0] is exactly "redis-sentinel". */ +int checkForSentinelMode(int argc, char **argv) { + int j; + + if (strstr(argv[0],"redis-sentinel") != NULL) return 1; + for (j = 1; j < argc; j++) + if (!strcmp(argv[j],"--sentinel")) return 1; + return 0; +} + +/* Function called at startup to load RDB or AOF file in memory. */ +void loadDataFromDisk(void) { + long long 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); + } + } +} + +void redisOutOfMemoryHandler(size_t allocation_size) { + redisLog(REDIS_WARNING,"Out Of Memory allocating %zu bytes!", + allocation_size); + redisPanic("OOM"); +} + 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(); + zmalloc_set_oom_handler(redisOutOfMemoryHandler); srand(time(NULL)^getpid()); gettimeofday(&tv,NULL); dictSetHashFunctionSeed(tv.tv_sec^tv.tv_usec^getpid()); + server.sentinel_mode = checkForSentinelMode(argc,argv); initServerConfig(); + /* We need to init sentinel right now as parsing the configuration file + * in sentinel mode will have the effect of populating the sentinel + * data structures with master nodes to monitor. */ + if (server.sentinel_mode) { + initSentinelConfig(); + initSentinel(); + } + if (argc >= 2) { int j = 1; /* First option to parse in argv[] */ sds options = sdsempty(); @@ -2299,6 +2592,17 @@ int main(int argc, char **argv) { 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++]; @@ -2323,33 +2627,31 @@ int main(int argc, char **argv) { 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'"); + redisLog(REDIS_WARNING, "Warning: no config file specified, using the default config. In order to specify a config file use %s /path/to/%s.conf", argv[0], server.sentinel_mode ? "sentinel" : "redis"); } 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.sentinel_mode) { + /* Things only needed when not running in Sentinel mode. */ + redisLog(REDIS_WARNING,"Server started, Redis version " REDIS_VERSION); + #ifdef __linux__ + linuxOvercommitMemoryWarning(); + #endif + loadDataFromDisk(); + 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); } - 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); + + /* Warning the user about suspicious maxmemory setting. */ + if (server.maxmemory > 0 && server.maxmemory < 1024*1024) { + redisLog(REDIS_WARNING,"WARNING: You specified a maxmemory value that is less than 1MB (current value is %llu bytes). Are you sure this is what you really want?", server.maxmemory); + } + aeSetBeforeSleepProc(server.el,beforeSleep); aeMain(server.el); aeDeleteEventLoop(server.el);