Redis(5.0.0)持久化AOF和 RDB 结合源码分析

主要是挖个坑。候补（代码还没看完。。）

https://github.com/antirez/redis/tree/5.0

一、Redis保存持久化文件

二、Redis启动加载持久化文件

src/server.c loadDataFromDisk函数 AOF 和 RDB 通过不同的方式加载

/* Function called at startup to load RDB or AOF file in memory. */
void loadDataFromDisk(void) {
    long long start = ustime();
    if (server.aof_state == AOF_ON) {
        if (loadAppendOnlyFile(server.aof_filename) == C_OK)
            serverLog(LL_NOTICE,"DB loaded from append only file: %.3f seconds",(float)(ustime()-start)/1000000);
    } else {
        rdbSaveInfo rsi = RDB_SAVE_INFO_INIT;
        if (rdbLoad(server.rdb_filename,&rsi) == C_OK) {
            serverLog(LL_NOTICE,"DB loaded from disk: %.3f seconds",
                (float)(ustime()-start)/1000000);

            /* Restore the replication ID / offset from the RDB file. */
            if (server.masterhost &&
                rsi.repl_id_is_set &&
                rsi.repl_offset != -1 &&
                /* Note that older implementations may save a repl_stream_db
                 * of -1 inside the RDB file in a wrong way, see more information
                 * in function rdbPopulateSaveInfo. */
                rsi.repl_stream_db != -1)
            {
                memcpy(server.replid,rsi.repl_id,sizeof(server.replid));
                server.master_repl_offset = rsi.repl_offset;
                /* If we are a slave, create a cached master from this
                 * information, in order to allow partial resynchronizations
                 * with masters. */
                replicationCacheMasterUsingMyself();
                selectDb(server.cached_master,rsi.repl_stream_db);
            }
        } else if (errno != ENOENT) {
            serverLog(LL_WARNING,"Fatal error loading the DB: %s. Exiting.",strerror(errno));
            exit(1);
        }
    }
}

AOF路线

src/aof.c loadAppendOnlyFile 主要通过检查是否含有RDB前缀文件，如果有则加载，创建一个FakeClient一条条的执行AOF文件中的指令 。

特别地，事务会单独加载。

int loadAppendOnlyFile(char *filename) {
    struct client *fakeClient;
    FILE *fp = fopen(filename,"r");
    struct redis_stat sb;
    int old_aof_state = server.aof_state;
    long loops = 0;
    off_t valid_up_to = 0; /* Offset of latest well-formed command loaded. */
    off_t valid_before_multi = 0; /* Offset before MULTI command loaded. */

    if (fp == NULL) {
        serverLog(LL_WARNING,"Fatal error: can't open the append log file for reading: %s",strerror(errno));
        exit(1);
    }

    /* Handle a zero-length AOF file as a special case. An empty AOF file
     * is a valid AOF because an empty server with AOF enabled will create
     * a zero length file at startup, that will remain like that if no write
     * operation is received. */
    if (fp && redis_fstat(fileno(fp),&sb) != -1 && sb.st_size == 0) {
        server.aof_current_size = 0;
        fclose(fp);
        return C_ERR;
    }

    /* Temporarily disable AOF, to prevent EXEC from feeding a MULTI
     * to the same file we're about to read. */
    server.aof_state = AOF_OFF;

    fakeClient = createFakeClient();
    startLoading(fp);

    /* Check if this AOF file has an RDB preamble. In that case we need to
     * load the RDB file and later continue loading the AOF tail. */
    char sig[5]; /* "REDIS" */
    if (fread(sig,1,5,fp) != 5 || memcmp(sig,"REDIS",5) != 0) {
        /* No RDB preamble, seek back at 0 offset. */
        if (fseek(fp,0,SEEK_SET) == -1) goto readerr;
    } else {
        /* RDB preamble. Pass loading the RDB functions. */
        rio rdb;

        serverLog(LL_NOTICE,"Reading RDB preamble from AOF file...");
        if (fseek(fp,0,SEEK_SET) == -1) goto readerr;
        rioInitWithFile(&rdb,fp);
        if (rdbLoadRio(&rdb,NULL,1) != C_OK) {
            serverLog(LL_WARNING,"Error reading the RDB preamble of the AOF file, AOF loading aborted");
            goto readerr;
        } else {
            serverLog(LL_NOTICE,"Reading the remaining AOF tail...");
        }
    }

    /* Read the actual AOF file, in REPL format, command by command. */
    while(1) {
        int argc, j;
        unsigned long len;
        robj **argv;
        char buf[128];
        sds argsds;
        struct redisCommand *cmd;

        /* Serve the clients from time to time */
        if (!(loops++ % 1000)) {
            loadingProgress(ftello(fp));
            processEventsWhileBlocked();
        }

        if (fgets(buf,sizeof(buf),fp) == NULL) {
            if (feof(fp))
                break;
            else
                goto readerr;
        }
        if (buf[0] != '*') goto fmterr;
        if (buf[1] == '') goto readerr;
        argc = atoi(buf+1);
        if (argc < 1) goto fmterr;

        argv = zmalloc(sizeof(robj*)*argc);
        fakeClient->argc = argc;
        fakeClient->argv = argv;

        for (j = 0; j < argc; j++) {
            if (fgets(buf,sizeof(buf),fp) == NULL) {
                fakeClient->argc = j; /* Free up to j-1. */
                freeFakeClientArgv(fakeClient);
                goto readerr;
            }
            if (buf[0] != '$') goto fmterr;
            len = strtol(buf+1,NULL,10);
            argsds = sdsnewlen(SDS_NOINIT,len);
            if (len && fread(argsds,len,1,fp) == 0) {
                sdsfree(argsds);
                fakeClient->argc = j; /* Free up to j-1. */
                freeFakeClientArgv(fakeClient);
                goto readerr;
            }
            argv[j] = createObject(OBJ_STRING,argsds);
            if (fread(buf,2,1,fp) == 0) {
                fakeClient->argc = j+1; /* Free up to j. */
                freeFakeClientArgv(fakeClient);
                goto readerr; /* discard CRLF */
            }
        }

        /* Command lookup */
        cmd = lookupCommand(argv[0]->ptr);
        if (!cmd) {
            serverLog(LL_WARNING,
                "Unknown command '%s' reading the append only file",
                (char*)argv[0]->ptr);
            exit(1);
        }

        if (cmd == server.multiCommand) valid_before_multi = valid_up_to;

        /* Run the command in the context of a fake client */
        fakeClient->cmd = cmd;
        if (fakeClient->flags & CLIENT_MULTI &&
            fakeClient->cmd->proc != execCommand)
        {
            queueMultiCommand(fakeClient);
        } else {
            cmd->proc(fakeClient);
        }

        /* The fake client should not have a reply */
        serverAssert(fakeClient->bufpos == 0 &&
                     listLength(fakeClient->reply) == 0);

        /* The fake client should never get blocked */
        serverAssert((fakeClient->flags & CLIENT_BLOCKED) == 0);

        /* Clean up. Command code may have changed argv/argc so we use the
         * argv/argc of the client instead of the local variables. */
        freeFakeClientArgv(fakeClient);
        fakeClient->cmd = NULL;
        if (server.aof_load_truncated) valid_up_to = ftello(fp);
    }

    /* This point can only be reached when EOF is reached without errors.
     * If the client is in the middle of a MULTI/EXEC, handle it as it was
     * a short read, even if technically the protocol is correct: we want
     * to remove the unprocessed tail and continue. */
    if (fakeClient->flags & CLIENT_MULTI) {
        serverLog(LL_WARNING,
            "Revert incomplete MULTI/EXEC transaction in AOF file");
        valid_up_to = valid_before_multi;
        goto uxeof;
    }

loaded_ok: /* DB loaded, cleanup and return C_OK to the caller. */
    fclose(fp);
    freeFakeClient(fakeClient);
    server.aof_state = old_aof_state;
    stopLoading();
    aofUpdateCurrentSize();
    server.aof_rewrite_base_size = server.aof_current_size;
    return C_OK;

readerr: /* Read error. If feof(fp) is true, fall through to unexpected EOF. */
    if (!feof(fp)) {
        if (fakeClient) freeFakeClient(fakeClient); /* avoid valgrind warning */
        serverLog(LL_WARNING,"Unrecoverable error reading the append only file: %s", strerror(errno));
        exit(1);
    }

uxeof: /* Unexpected AOF end of file. */
    if (server.aof_load_truncated) {
        serverLog(LL_WARNING,"!!! Warning: short read while loading the AOF file !!!");
        serverLog(LL_WARNING,"!!! Truncating the AOF at offset %llu !!!",
            (unsigned long long) valid_up_to);
        if (valid_up_to == -1 || truncate(filename,valid_up_to) == -1) {
            if (valid_up_to == -1) {
                serverLog(LL_WARNING,"Last valid command offset is invalid");
            } else {
                serverLog(LL_WARNING,"Error truncating the AOF file: %s",
                    strerror(errno));
            }
        } else {
            /* Make sure the AOF file descriptor points to the end of the
             * file after the truncate call. */
            if (server.aof_fd != -1 && lseek(server.aof_fd,0,SEEK_END) == -1) {
                serverLog(LL_WARNING,"Can't seek the end of the AOF file: %s",
                    strerror(errno));
            } else {
                serverLog(LL_WARNING,
                    "AOF loaded anyway because aof-load-truncated is enabled");
                goto loaded_ok;
            }
        }
    }
    if (fakeClient) freeFakeClient(fakeClient); /* avoid valgrind warning */
    serverLog(LL_WARNING,"Unexpected end of file reading the append only file. You can: 1) Make a backup of your AOF file, then use ./redis-check-aof --fix <filename>. 2) Alternatively you can set the 'aof-load-truncated' configuration option to yes and restart the server.");
    exit(1);

fmterr: /* Format error. */
    if (fakeClient) freeFakeClient(fakeClient); /* avoid valgrind warning */
    serverLog(LL_WARNING,"Bad file format reading the append only file: make a backup of your AOF file, then use ./redis-check-aof --fix <filename>");
    exit(1);
}

RDB路线

RDB就像是一个redis快照

src/rdb.c  redis抽象出一个rio层，负责处理IO操作的，通过rio进行rdb文件恢复redis（快照保存的逆操作）。

/* Like rdbLoadRio() but takes a filename instead of a rio stream. The
 * filename is open for reading and a rio stream object created in order
 * to do the actual loading. Moreover the ETA displayed in the INFO
 * output is initialized and finalized.
 *
 * If you pass an 'rsi' structure initialied with RDB_SAVE_OPTION_INIT, the
 * loading code will fiil the information fields in the structure. */
int rdbLoad(char *filename, rdbSaveInfo *rsi) {
    FILE *fp;
    rio rdb;
    int retval;

    if ((fp = fopen(filename,"r")) == NULL) return C_ERR;
    startLoading(fp);
    rioInitWithFile(&rdb,fp);
    retval = rdbLoadRio(&rdb,rsi,0);
    fclose(fp);
    stopLoading();
    return retval;
}

/* Load an RDB file from the rio stream 'rdb'. On success C_OK is returned,
 * otherwise C_ERR is returned and 'errno' is set accordingly. */
int rdbLoadRio(rio *rdb, rdbSaveInfo *rsi, int loading_aof) {
    uint64_t dbid;
    int type, rdbver;
    redisDb *db = server.db+0;
    char buf[1024];

    rdb->update_cksum = rdbLoadProgressCallback;
    rdb->max_processing_chunk = server.loading_process_events_interval_bytes;
    if (rioRead(rdb,buf,9) == 0) goto eoferr;
    buf[9] = '';
    if (memcmp(buf,"REDIS",5) != 0) {
        serverLog(LL_WARNING,"Wrong signature trying to load DB from file");
        errno = EINVAL;
        return C_ERR;
    }
    rdbver = atoi(buf+5);
    if (rdbver < 1 || rdbver > RDB_VERSION) {
        serverLog(LL_WARNING,"Can't handle RDB format version %d",rdbver);
        errno = EINVAL;
        return C_ERR;
    }

    /* Key-specific attributes, set by opcodes before the key type. */
    long long lru_idle = -1, lfu_freq = -1, expiretime = -1, now = mstime();
    long long lru_clock = LRU_CLOCK();
    
    while(1) {
        robj *key, *val;

        /* Read type. */
        if ((type = rdbLoadType(rdb)) == -1) goto eoferr;

        /* Handle special types. */
        if (type == RDB_OPCODE_EXPIRETIME) {
            /* EXPIRETIME: load an expire associated with the next key
             * to load. Note that after loading an expire we need to
             * load the actual type, and continue. */
            expiretime = rdbLoadTime(rdb);
            expiretime *= 1000;
            continue; /* Read next opcode. */
        } else if (type == RDB_OPCODE_EXPIRETIME_MS) {
            /* EXPIRETIME_MS: milliseconds precision expire times introduced
             * with RDB v3. Like EXPIRETIME but no with more precision. */
            expiretime = rdbLoadMillisecondTime(rdb,rdbver);
            continue; /* Read next opcode. */
        } else if (type == RDB_OPCODE_FREQ) {
            /* FREQ: LFU frequency. */
            uint8_t byte;
            if (rioRead(rdb,&byte,1) == 0) goto eoferr;
            lfu_freq = byte;
            continue; /* Read next opcode. */
        } else if (type == RDB_OPCODE_IDLE) {
            /* IDLE: LRU idle time. */
            uint64_t qword;
            if ((qword = rdbLoadLen(rdb,NULL)) == RDB_LENERR) goto eoferr;
            lru_idle = qword;
            continue; /* Read next opcode. */
        } else if (type == RDB_OPCODE_EOF) {
            /* EOF: End of file, exit the main loop. */
            break;
        } else if (type == RDB_OPCODE_SELECTDB) {
            /* SELECTDB: Select the specified database. */
            if ((dbid = rdbLoadLen(rdb,NULL)) == RDB_LENERR) goto eoferr;
            if (dbid >= (unsigned)server.dbnum) {
                serverLog(LL_WARNING,
                    "FATAL: Data file was created with a Redis "
                    "server configured to handle more than %d "
                    "databases. Exiting
", server.dbnum);
                exit(1);
            }
            db = server.db+dbid;
            continue; /* Read next opcode. */
        } else if (type == RDB_OPCODE_RESIZEDB) {
            /* RESIZEDB: Hint about the size of the keys in the currently
             * selected data base, in order to avoid useless rehashing. */
            uint64_t db_size, expires_size;
            if ((db_size = rdbLoadLen(rdb,NULL)) == RDB_LENERR)
                goto eoferr;
            if ((expires_size = rdbLoadLen(rdb,NULL)) == RDB_LENERR)
                goto eoferr;
            dictExpand(db->dict,db_size);
            dictExpand(db->expires,expires_size);
            continue; /* Read next opcode. */
        } else if (type == RDB_OPCODE_AUX) {
            /* AUX: generic string-string fields. Use to add state to RDB
             * which is backward compatible. Implementations of RDB loading
             * are requierd to skip AUX fields they don't understand.
             *
             * An AUX field is composed of two strings: key and value. */
            robj *auxkey, *auxval;
            if ((auxkey = rdbLoadStringObject(rdb)) == NULL) goto eoferr;
            if ((auxval = rdbLoadStringObject(rdb)) == NULL) goto eoferr;

            if (((char*)auxkey->ptr)[0] == '%') {
                /* All the fields with a name staring with '%' are considered
                 * information fields and are logged at startup with a log
                 * level of NOTICE. */
                serverLog(LL_NOTICE,"RDB '%s': %s",
                    (char*)auxkey->ptr,
                    (char*)auxval->ptr);
            } else if (!strcasecmp(auxkey->ptr,"repl-stream-db")) {
                if (rsi) rsi->repl_stream_db = atoi(auxval->ptr);
            } else if (!strcasecmp(auxkey->ptr,"repl-id")) {
                if (rsi && sdslen(auxval->ptr) == CONFIG_RUN_ID_SIZE) {
                    memcpy(rsi->repl_id,auxval->ptr,CONFIG_RUN_ID_SIZE+1);
                    rsi->repl_id_is_set = 1;
                }
            } else if (!strcasecmp(auxkey->ptr,"repl-offset")) {
                if (rsi) rsi->repl_offset = strtoll(auxval->ptr,NULL,10);
            } else if (!strcasecmp(auxkey->ptr,"lua")) {
                /* Load the script back in memory. */
                if (luaCreateFunction(NULL,server.lua,auxval) == NULL) {
                    rdbExitReportCorruptRDB(
                        "Can't load Lua script from RDB file! "
                        "BODY: %s", auxval->ptr);
                }
            } else {
                /* We ignore fields we don't understand, as by AUX field
                 * contract. */
                serverLog(LL_DEBUG,"Unrecognized RDB AUX field: '%s'",
                    (char*)auxkey->ptr);
            }

            decrRefCount(auxkey);
            decrRefCount(auxval);
            continue; /* Read type again. */
        } else if (type == RDB_OPCODE_MODULE_AUX) {
            /* This is just for compatibility with the future: we have plans
             * to add the ability for modules to store anything in the RDB
             * file, like data that is not related to the Redis key space.
             * Such data will potentially be stored both before and after the
             * RDB keys-values section. For this reason since RDB version 9,
             * we have the ability to read a MODULE_AUX opcode followed by an
             * identifier of the module, and a serialized value in "MODULE V2"
             * format. */
            uint64_t moduleid = rdbLoadLen(rdb,NULL);
            moduleType *mt = moduleTypeLookupModuleByID(moduleid);
            char name[10];
            moduleTypeNameByID(name,moduleid);

            if (!rdbCheckMode && mt == NULL) {
                /* Unknown module. */
                serverLog(LL_WARNING,"The RDB file contains AUX module data I can't load: no matching module '%s'", name);
                exit(1);
            } else if (!rdbCheckMode && mt != NULL) {
                /* This version of Redis actually does not know what to do
                 * with modules AUX data... */
                serverLog(LL_WARNING,"The RDB file contains AUX module data I can't load for the module '%s'. Probably you want to use a newer version of Redis which implements aux data callbacks", name);
                exit(1);
            } else {
                /* RDB check mode. */
                robj *aux = rdbLoadCheckModuleValue(rdb,name);
                decrRefCount(aux);
            }
        }

        /* Read key */
        if ((key = rdbLoadStringObject(rdb)) == NULL) goto eoferr;
        /* Read value */
        if ((val = rdbLoadObject(type,rdb)) == NULL) goto eoferr;
        /* Check if the key already expired. This function is used when loading
         * an RDB file from disk, either at startup, or when an RDB was
         * received from the master. In the latter case, the master is
         * responsible for key expiry. If we would expire keys here, the
         * snapshot taken by the master may not be reflected on the slave. */
        if (server.masterhost == NULL && !loading_aof && expiretime != -1 && expiretime < now) {
            decrRefCount(key);
            decrRefCount(val);
        } else {
            /* Add the new object in the hash table */
            dbAdd(db,key,val);

            /* Set the expire time if needed */
            if (expiretime != -1) setExpire(NULL,db,key,expiretime);
            
            /* Set usage information (for eviction). */
            objectSetLRUOrLFU(val,lfu_freq,lru_idle,lru_clock);

            /* Decrement the key refcount since dbAdd() will take its
             * own reference. */
            decrRefCount(key);
        }

        /* Reset the state that is key-specified and is populated by
         * opcodes before the key, so that we start from scratch again. */
        expiretime = -1;
        lfu_freq = -1;
        lru_idle = -1;
    }
    /* Verify the checksum if RDB version is >= 5 */
    if (rdbver >= 5) {
        uint64_t cksum, expected = rdb->cksum;

        if (rioRead(rdb,&cksum,8) == 0) goto eoferr;
        if (server.rdb_checksum) {
            memrev64ifbe(&cksum);
            if (cksum == 0) {
                serverLog(LL_WARNING,"RDB file was saved with checksum disabled: no check performed.");
            } else if (cksum != expected) {
                serverLog(LL_WARNING,"Wrong RDB checksum. Aborting now.");
                rdbExitReportCorruptRDB("RDB CRC error");
            }
        }
    }
    return C_OK;

eoferr: /* unexpected end of file is handled here with a fatal exit */
    serverLog(LL_WARNING,"Short read or OOM loading DB. Unrecoverable error, aborting now.");
    rdbExitReportCorruptRDB("Unexpected EOF reading RDB file");
    return C_ERR; /* Just to avoid warning */
}