【redis源码学习】持久化机制（1）：RDB

/* This is our timer interrupt, called server.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 watchdog.
 * - Update some statistic.
 * - Incremental rehashing of the DBs hash tables.
 * - Triggering BGSAVE / AOF rewrite, and handling of terminated children.
 * - Clients timeout of different kinds.
 * - Replication reconnection.
 * - Many more...
 *
 * Everything directly called here will be called server.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;
    UNUSED(eventLoop);
    UNUSED(id);
    UNUSED(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);

    /* Update the time cache. */
    updateCachedTime(1);

    server.hz = server.config_hz;
    /* Adapt the server.hz value to the number of configured clients. If we have
     * many clients, we want to call serverCron() with an higher frequency. */
    if (server.dynamic_hz) {
        while (listLength(server.clients) / server.hz >
               MAX_CLIENTS_PER_CLOCK_TICK)
        {
            server.hz *= 2;
            if (server.hz > CONFIG_MAX_HZ) {
                server.hz = CONFIG_MAX_HZ;
                break;
            }
        }
    }

    run_with_period(100) {
        trackInstantaneousMetric(STATS_METRIC_COMMAND,server.stat_numcommands);
        trackInstantaneousMetric(STATS_METRIC_NET_INPUT,
                server.stat_net_input_bytes);
        trackInstantaneousMetric(STATS_METRIC_NET_OUTPUT,
                server.stat_net_output_bytes);
    }

    /* We have just LRU_BITS bits per object for LRU information.
     * So we use an (eventually wrapping) LRU clock.
     *
     * Note that even if the counter wraps it's not a big problem,
     * everything will still work but some object will appear younger
     * to Redis. However for this to happen a given object should never be
     * touched for all the time needed to the counter to wrap, which is
     * not likely.
     *
     * Note that you can change the resolution altering the
     * LRU_CLOCK_RESOLUTION define. */
    server.lruclock = getLRUClock();

    /* 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();

    run_with_period(100) {
        /* Sample the RSS and other metrics here since this is a relatively slow call.
         * We must sample the zmalloc_used at the same time we take the rss, otherwise
         * the frag ratio calculate may be off (ratio of two samples at different times) */
        server.cron_malloc_stats.process_rss = zmalloc_get_rss();
        server.cron_malloc_stats.zmalloc_used = zmalloc_used_memory();
        /* Sampling the allcator info can be slow too.
         * The fragmentation ratio it'll show is potentically more accurate
         * it excludes other RSS pages such as: shared libraries, LUA and other non-zmalloc
         * allocations, and allocator reserved pages that can be pursed (all not actual frag) */
        zmalloc_get_allocator_info(&server.cron_malloc_stats.allocator_allocated,
                                   &server.cron_malloc_stats.allocator_active,
                                   &server.cron_malloc_stats.allocator_resident);
        /* in case the allocator isn't providing these stats, fake them so that
         * fragmention info still shows some (inaccurate metrics) */
        if (!server.cron_malloc_stats.allocator_resident) {
            /* LUA memory isn't part of zmalloc_used, but it is part of the process RSS,
             * so we must desuct it in order to be able to calculate correct
             * "allocator fragmentation" ratio */
            size_t lua_memory = lua_gc(server.lua,LUA_GCCOUNT,0)*1024LL;
            server.cron_malloc_stats.allocator_resident = server.cron_malloc_stats.process_rss - lua_memory;
        }
        if (!server.cron_malloc_stats.allocator_active)
            server.cron_malloc_stats.allocator_active = server.cron_malloc_stats.allocator_resident;
        if (!server.cron_malloc_stats.allocator_allocated)
            server.cron_malloc_stats.allocator_allocated = server.cron_malloc_stats.zmalloc_used;
    }

    /* 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(SHUTDOWN_NOFLAGS) == C_OK) exit(0);
        serverLog(LL_WARNING,"SIGTERM received but errors trying to shut down the server, check the logs for more information");
        server.shutdown_asap = 0;
    }

    /* Show some info about non-empty databases */
    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) {
                serverLog(LL_VERBOSE,"DB %d: %lld keys (%lld volatile) in %lld slots HT.",j,used,vkeys,size);
                /* dictPrintStats(server.dict); */
            }
        }
    }

    /* Show information about connected clients */
    if (!server.sentinel_mode) {
        run_with_period(5000) {
            serverLog(LL_DEBUG,
                "%lu clients connected (%lu replicas), %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();

    /* Handle background operations on Redis databases. */
    databasesCron();

    /* Start a scheduled AOF rewrite if this was requested by the user while
     * a BGSAVE was in progress. */
    if (!hasActiveChildProcess() &&
        server.aof_rewrite_scheduled)
    {
        rewriteAppendOnlyFileBackground();
    }

    /* Check if a background saving or AOF rewrite in progress terminated. */
    if (hasActiveChildProcess() || ldbPendingChildren())
    {
        checkChildrenDone();
    } else {
        /* 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;

            /* Save if we reached the given amount of changes,
             * the given amount of seconds, and if the latest bgsave was
             * successful or if, in case of an error, at least
             * CONFIG_BGSAVE_RETRY_DELAY seconds already elapsed. */
            if (server.dirty >= sp->changes &&
                server.unixtime-server.lastsave > sp->seconds &&
                (server.unixtime-server.lastbgsave_try >
                 CONFIG_BGSAVE_RETRY_DELAY ||
                 server.lastbgsave_status == C_OK))
            {
                serverLog(LL_NOTICE,"%d changes in %d seconds. Saving...",
                    sp->changes, (int)sp->seconds);
                rdbSaveInfo rsi, *rsiptr;
                rsiptr = rdbPopulateSaveInfo(&rsi);
                rdbSaveBackground(server.rdb_filename,rsiptr);
                break;
            }
        }

        /* Trigger an AOF rewrite if needed. */
        if (server.aof_state == AOF_ON &&
            !hasActiveChildProcess() &&
            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) {
                serverLog(LL_NOTICE,"Starting automatic rewriting of AOF on %lld%% growth",growth);
                rewriteAppendOnlyFileBackground();
            }
        }
    }


    /* AOF postponed flush: Try at every cron cycle if the slow fsync
     * completed. */
    if (server.aof_flush_postponed_start) flushAppendOnlyFile(0);

    /* AOF write errors: in this case we have a buffer to flush as well and
     * clear the AOF error in case of success to make the DB writable again,
     * however to try every second is enough in case of 'hz' is set to
     * an higher frequency. */
    run_with_period(1000) {
        if (server.aof_last_write_status == C_ERR)
            flushAppendOnlyFile(0);
    }

    /* Clear the paused clients flag if needed. */
    clientsArePaused(); /* Don't check return value, just use the side effect.*/

    /* Replication cron function -- used to reconnect to master,
     * detect transfer failures, start background RDB transfers and so forth. */
    run_with_period(1000) replicationCron();

    /* Run the Redis Cluster cron. */
    run_with_period(100) {
        if (server.cluster_enabled) clusterCron();
    }

    /* Run the Sentinel timer if we are in sentinel mode. */
    if (server.sentinel_mode) sentinelTimer();

    /* Cleanup expired MIGRATE cached sockets. */
    run_with_period(1000) {
        migrateCloseTimedoutSockets();
    }

    /* Stop the I/O threads if we don't have enough pending work. */
    stopThreadedIOIfNeeded();

    /* Resize tracking keys table if needed. This is also done at every
     * command execution, but we want to be sure that if the last command
     * executed changes the value via CONFIG SET, the server will perform
     * the operation even if completely idle. */
    if (server.tracking_clients) trackingLimitUsedSlots();

    /* Start a scheduled BGSAVE if the corresponding flag is set. This is
     * useful when we are forced to postpone a BGSAVE because an AOF
     * rewrite is in progress.
     *
     * Note: this code must be after the replicationCron() call above so
     * make sure when refactoring this file to keep this order. This is useful
     * because we want to give priority to RDB savings for replication. */
    if (!hasActiveChildProcess() &&
        server.rdb_bgsave_scheduled &&
        (server.unixtime-server.lastbgsave_try > CONFIG_BGSAVE_RETRY_DELAY ||
         server.lastbgsave_status == C_OK))
    {
        rdbSaveInfo rsi, *rsiptr;
        rsiptr = rdbPopulateSaveInfo(&rsi);
        if (rdbSaveBackground(server.rdb_filename,rsiptr) == C_OK)
            server.rdb_bgsave_scheduled = 0;
    }

    /* Fire the cron loop modules event. */
    RedisModuleCronLoopV1 ei = {REDISMODULE_CRON_LOOP_VERSION,server.hz};
    moduleFireServerEvent(REDISMODULE_EVENT_CRON_LOOP,
                          0,
                          &ei);

    server.cronloops++;
    return 1000/server.hz;
}

int rdbSaveBackground(char *filename, rdbSaveInfo *rsi) {
    pid_t childpid;

    if (hasActiveChildProcess()) return C_ERR;

    server.dirty_before_bgsave = server.dirty;
    server.lastbgsave_try = time(NULL);
    openChildInfoPipe();

    if ((childpid = redisFork()) == 0) {
        int retval;

        /* Child */
        redisSetProcTitle("redis-rdb-bgsave");
        redisSetCpuAffinity(server.bgsave_cpulist);
        retval = rdbSave(filename,rsi);
        if (retval == C_OK) {
            sendChildCOWInfo(CHILD_INFO_TYPE_RDB, "RDB");
        }
        exitFromChild((retval == C_OK) ? 0 : 1);
    } else {
        /* Parent */
        if (childpid == -1) {
            closeChildInfoPipe();
            server.lastbgsave_status = C_ERR;
            serverLog(LL_WARNING,"Can't save in background: fork: %s",
                strerror(errno));
            return C_ERR;
        }
        serverLog(LL_NOTICE,"Background saving started by pid %d",childpid);
        server.rdb_save_time_start = time(NULL);
        server.rdb_child_pid = childpid;
        server.rdb_child_type = RDB_CHILD_TYPE_DISK;
        return C_OK;
    }
    return C_OK; /* unreached */
}

/* Save the DB on disk. Return C_ERR on error, C_OK on success. */
int rdbSave(char *filename, rdbSaveInfo *rsi) {
    char tmpfile[256];
    char cwd[MAXPATHLEN]; /* Current working dir path for error messages. */
    FILE *fp;
    rio rdb;
    int error = 0;

    snprintf(tmpfile,256,"temp-%d.rdb", (int) getpid());
    fp = fopen(tmpfile,"w");
    if (!fp) {
        char *cwdp = getcwd(cwd,MAXPATHLEN);
        serverLog(LL_WARNING,
            "Failed opening the RDB file %s (in server root dir %s) "
            "for saving: %s",
            filename,
            cwdp ? cwdp : "unknown",
            strerror(errno));
        return C_ERR;
    }

    rioInitWithFile(&rdb,fp);
    startSaving(RDBFLAGS_NONE);

    if (server.rdb_save_incremental_fsync)
        rioSetAutoSync(&rdb,REDIS_AUTOSYNC_BYTES);

    if (rdbSaveRio(&rdb,&error,RDBFLAGS_NONE,rsi) == C_ERR) {
        errno = error;
        goto werr;
    }

    /* Make sure data will not remain on the OS's output buffers */
    if (fflush(fp) == EOF) goto werr;
    if (fsync(fileno(fp)) == -1) goto werr;
    if (fclose(fp) == EOF) goto werr;

    /* Use RENAME to make sure the DB file is changed atomically only
     * if the generate DB file is ok. */
    if (rename(tmpfile,filename) == -1) {
        char *cwdp = getcwd(cwd,MAXPATHLEN);
        serverLog(LL_WARNING,
            "Error moving temp DB file %s on the final "
            "destination %s (in server root dir %s): %s",
            tmpfile,
            filename,
            cwdp ? cwdp : "unknown",
            strerror(errno));
        unlink(tmpfile);
        stopSaving(0);
        return C_ERR;
    }

    serverLog(LL_NOTICE,"DB saved on disk");
    server.dirty = 0;
    server.lastsave = time(NULL);
    server.lastbgsave_status = C_OK;
    stopSaving(1);
    return C_OK;

werr:
    serverLog(LL_WARNING,"Write error saving DB on disk: %s", strerror(errno));
    fclose(fp);
    unlink(tmpfile);
    stopSaving(0);
    return C_ERR;
}

/* Produces a dump of the database in RDB format sending it to the specified
 * Redis I/O channel. On success C_OK is returned, otherwise C_ERR
 * is returned and part of the output, or all the output, can be
 * missing because of I/O errors.
 *
 * When the function returns C_ERR and if 'error' is not NULL, the
 * integer pointed by 'error' is set to the value of errno just after the I/O
 * error. */
int rdbSaveRio(rio *rdb, int *error, int rdbflags, rdbSaveInfo *rsi) {
    dictIterator *di = NULL;
    dictEntry *de;
    char magic[10];
    int j;
    uint64_t cksum;
    size_t processed = 0;

    if (server.rdb_checksum)
        rdb->update_cksum = rioGenericUpdateChecksum;
    snprintf(magic,sizeof(magic),"REDIS%04d",RDB_VERSION);
    if (rdbWriteRaw(rdb,magic,9) == -1) goto werr;
    if (rdbSaveInfoAuxFields(rdb,rdbflags,rsi) == -1) goto werr;
    if (rdbSaveModulesAux(rdb, REDISMODULE_AUX_BEFORE_RDB) == -1) goto werr;

    for (j = 0; j < server.dbnum; j++) {
        redisDb *db = server.db+j;
        dict *d = db->dict;
        if (dictSize(d) == 0) continue;
        di = dictGetSafeIterator(d);

        /* Write the SELECT DB opcode */
        if (rdbSaveType(rdb,RDB_OPCODE_SELECTDB) == -1) goto werr;
        if (rdbSaveLen(rdb,j) == -1) goto werr;

        /* Write the RESIZE DB opcode. */
        uint64_t db_size, expires_size;
        db_size = dictSize(db->dict);
        expires_size = dictSize(db->expires);
        if (rdbSaveType(rdb,RDB_OPCODE_RESIZEDB) == -1) goto werr;
        if (rdbSaveLen(rdb,db_size) == -1) goto werr;
        if (rdbSaveLen(rdb,expires_size) == -1) goto werr;

        /* Iterate this DB writing every entry */
        while((de = dictNext(di)) != NULL) {
            sds keystr = dictGetKey(de);
            robj key, *o = dictGetVal(de);
            long long expire;

            initStaticStringObject(key,keystr);
            expire = getExpire(db,&key);
            if (rdbSaveKeyValuePair(rdb,&key,o,expire) == -1) goto werr;

            /* When this RDB is produced as part of an AOF rewrite, move
             * accumulated diff from parent to child while rewriting in
             * order to have a smaller final write. */
            if (rdbflags & RDBFLAGS_AOF_PREAMBLE &&
                rdb->processed_bytes > processed+AOF_READ_DIFF_INTERVAL_BYTES)
            {
                processed = rdb->processed_bytes;
                aofReadDiffFromParent();
            }
        }
        dictReleaseIterator(di);
        di = NULL; /* So that we don't release it again on error. */
    }

    /* If we are storing the replication information on disk, persist
     * the script cache as well: on successful PSYNC after a restart, we need
     * to be able to process any EVALSHA inside the replication backlog the
     * master will send us. */
    if (rsi && dictSize(server.lua_scripts)) {
        di = dictGetIterator(server.lua_scripts);
        while((de = dictNext(di)) != NULL) {
            robj *body = dictGetVal(de);
            if (rdbSaveAuxField(rdb,"lua",3,body->ptr,sdslen(body->ptr)) == -1)
                goto werr;
        }
        dictReleaseIterator(di);
        di = NULL; /* So that we don't release it again on error. */
    }

    if (rdbSaveModulesAux(rdb, REDISMODULE_AUX_AFTER_RDB) == -1) goto werr;

    /* EOF opcode */
    if (rdbSaveType(rdb,RDB_OPCODE_EOF) == -1) goto werr;

    /* CRC64 checksum. It will be zero if checksum computation is disabled, the
     * loading code skips the check in this case. */
    cksum = rdb->cksum;
    memrev64ifbe(&cksum);
    if (rioWrite(rdb,&cksum,8) == 0) goto werr;
    return C_OK;

werr:
    if (error) *error = errno;
    if (di) dictReleaseIterator(di);
    return C_ERR;
}

/* Save a key-value pair, with expire time, type, key, value.
 * On error -1 is returned.
 * On success if the key was actually saved 1 is returned, otherwise 0
 * is returned (the key was already expired). */
int rdbSaveKeyValuePair(rio *rdb, robj *key, robj *val, long long expiretime) {
    int savelru = server.maxmemory_policy & MAXMEMORY_FLAG_LRU;
    int savelfu = server.maxmemory_policy & MAXMEMORY_FLAG_LFU;

    /* Save the expire time */
    if (expiretime != -1) {
        if (rdbSaveType(rdb,RDB_OPCODE_EXPIRETIME_MS) == -1) return -1;
        if (rdbSaveMillisecondTime(rdb,expiretime) == -1) return -1;
    }

    /* Save the LRU info. */
    if (savelru) {
        uint64_t idletime = estimateObjectIdleTime(val);
        idletime /= 1000; /* Using seconds is enough and requires less space.*/
        if (rdbSaveType(rdb,RDB_OPCODE_IDLE) == -1) return -1;
        if (rdbSaveLen(rdb,idletime) == -1) return -1;
    }

    /* Save the LFU info. */
    if (savelfu) {
        uint8_t buf[1];
        buf[0] = LFUDecrAndReturn(val);
        /* We can encode this in exactly two bytes: the opcode and an 8
         * bit counter, since the frequency is logarithmic with a 0-255 range.
         * Note that we do not store the halving time because to reset it
         * a single time when loading does not affect the frequency much. */
        if (rdbSaveType(rdb,RDB_OPCODE_FREQ) == -1) return -1;
        if (rdbWriteRaw(rdb,buf,1) == -1) return -1;
    }

    /* Save type, key, value */
    if (rdbSaveObjectType(rdb,val) == -1) return -1;
    if (rdbSaveStringObject(rdb,key) == -1) return -1;
    if (rdbSaveObject(rdb,val,key) == -1) return -1;

    /* Delay return if required (for testing) */
    if (server.rdb_key_save_delay)
        usleep(server.rdb_key_save_delay);

    return 1;
}