[redis] rdb持久化

[redis] rdb持久化

rdb应用场景

redis有两种持久化方式：rdb和aof，rdb默认开启。

rdb持久化是异步执行的

bgsave命令 => rdbSaveBackground(breakpoint)

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

    if (hasActiveChildProcess()) return C_ERR;
    server.stat_rdb_saves++;

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

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

        /* Child */
        redisSetProcTitle("redis-rdb-bgsave");
        redisSetCpuAffinity(server.bgsave_cpulist);
        retval = rdbSave(req, filename,rsi);
        if (retval == C_OK) {
            sendChildCowInfo(CHILD_INFO_TYPE_RDB_COW_SIZE, "RDB");
        }
        exitFromChild((retval == C_OK) ? 0 : 1);
    } else {
        /* Parent */
        if (childpid == -1) {
            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 %ld",(long) childpid);
        server.rdb_save_time_start = time(NULL);
        server.rdb_child_type = RDB_CHILD_TYPE_DISK;
        return C_OK;
    }
    return C_OK; /* unreached */
}

rdb是如何将数据保存到磁盘的

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

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

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

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

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

    /* Make sure data will not remain on the OS's output buffers */
    if (fflush(fp)) { err_op = "fflush"; goto werr; }
    if (fsync(fileno(fp))) { err_op = "fsync"; goto werr; }
    if (fclose(fp)) { fp = NULL; err_op = "fclose"; goto werr; }
    fp = NULL;
    
    /* 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 *str_err = strerror(errno);
        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",
            str_err);
        unlink(tmpfile);
        stopSaving(0);
        return C_ERR;
    }
    if (fsyncFileDir(filename) == -1) { err_op = "fsyncFileDir"; goto werr; }

    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): %s", err_op, strerror(errno));
    if (fp) fclose(fp);
    unlink(tmpfile);
    stopSaving(0);
    return C_ERR;
}

实际将dict数据写入到磁盘的调用顺序为:
rdbSaveRio
=> rdbSaveDb

rdbSaveDb

ssize_t rdbSaveDb(rio *rdb, int dbid, int rdbflags, long *key_counter) {
    dictIterator *di;
    dictEntry *de;
    ssize_t written = 0;
    ssize_t res;
    static long long info_updated_time = 0;
    char *pname = (rdbflags & RDBFLAGS_AOF_PREAMBLE) ? "AOF rewrite" :  "RDB";

    redisDb *db = server.db + dbid;
    dict *d = db->dict;
    if (dictSize(d) == 0) return 0;
    di = dictGetSafeIterator(d);

    /* Write the SELECT DB opcode */
    if ((res = rdbSaveType(rdb,RDB_OPCODE_SELECTDB)) < 0) goto werr;
    written += res;
    if ((res = rdbSaveLen(rdb, dbid)) < 0) goto werr;
    written += res;

    /* Write the RESIZE DB opcode. */
    uint64_t db_size, expires_size;
    db_size = dictSize(db->dict);
    expires_size = dictSize(db->expires);
    if ((res = rdbSaveType(rdb,RDB_OPCODE_RESIZEDB)) < 0) goto werr;
    written += res;
    if ((res = rdbSaveLen(rdb,db_size)) < 0) goto werr;
    written += res;
    if ((res = rdbSaveLen(rdb,expires_size)) < 0) goto werr;
    written += res;

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

        initStaticStringObject(key,keystr);
        expire = getExpire(db,&key);
        if ((res = rdbSaveKeyValuePair(rdb, &key, o, expire, dbid)) < 0) goto werr;
        written += res;

        /* In fork child process, we can try to release memory back to the
         * OS and possibly avoid or decrease COW. We give the dismiss
         * mechanism a hint about an estimated size of the object we stored. */
        size_t dump_size = rdb->processed_bytes - rdb_bytes_before_key;
        if (server.in_fork_child) dismissObject(o, dump_size);

        /* Update child info every 1 second (approximately).
         * in order to avoid calling mstime() on each iteration, we will
         * check the diff every 1024 keys */
        if (((*key_counter)++ & 1023) == 0) {
            long long now = mstime();
            if (now - info_updated_time >= 1000) {
                sendChildInfo(CHILD_INFO_TYPE_CURRENT_INFO, *key_counter, pname);
                info_updated_time = now;
            }
        }
    }

    dictReleaseIterator(di);
    return written;

werr:
    dictReleaseIterator(di);
    return -1;
}

遍历dict中的所有kv对，然后写入文件。
最后利用rename的原子性，将tmp文件更换为最新的rdb即可。

redis启动时加载rdb

server.c loadDataFromDisk

/* 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) {
        int ret = loadAppendOnlyFiles(server.aof_manifest);
        if (ret == AOF_FAILED || ret == AOF_OPEN_ERR)
            exit(1);
        if (ret != AOF_NOT_EXIST)
            serverLog(LL_NOTICE, "DB loaded from append only file: %.3f seconds", (float)(ustime()-start)/1000000);
    } else {
        rdbSaveInfo rsi = RDB_SAVE_INFO_INIT;
        errno = 0; /* Prevent a stale value from affecting error checking */
        int rdb_flags = RDBFLAGS_NONE;
        if (iAmMaster()) {
            /* Master may delete expired keys when loading, we should
             * propagate expire to replication backlog. */
            createReplicationBacklog();
            rdb_flags |= RDBFLAGS_FEED_REPL;
        }
        if (rdbLoad(server.rdb_filename,&rsi,rdb_flags) == 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 (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)
            {
                if (!iAmMaster()) {
                    memcpy(server.replid,rsi.repl_id,sizeof(server.replid));
                    server.master_repl_offset = rsi.repl_offset;
                    /* If this is a replica, 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 this is a master, we can save the replication info
                     * as secondary ID and offset, in order to allow replicas
                     * to partial resynchronizations with masters. */
                    memcpy(server.replid2,rsi.repl_id,sizeof(server.replid));
                    server.second_replid_offset = rsi.repl_offset+1;
                    /* Rebase master_repl_offset from rsi.repl_offset. */
                    server.master_repl_offset += rsi.repl_offset;
                    serverAssert(server.repl_backlog);
                    server.repl_backlog->offset = server.master_repl_offset -
                              server.repl_backlog->histlen + 1;
                    rebaseReplicationBuffer(rsi.repl_offset);
                    server.repl_no_slaves_since = time(NULL);
                }
            }
        } else if (errno != ENOENT) {
            serverLog(LL_WARNING,"Fatal error loading the DB: %s. Exiting.",strerror(errno));
            exit(1);
        }

        /* We always create replication backlog if server is a master, we need
         * it because we put DELs in it when loading expired keys in RDB, but
         * if RDB doesn't have replication info or there is no rdb, it is not
         * possible to support partial resynchronization, to avoid extra memory
         * of replication backlog, we drop it. */
        if (server.master_repl_offset == 0 && server.repl_backlog)
            freeReplicationBacklog();
    }
}