本文所引用的源码全部来自Redis2.8.2版本。

Redis AOF数据持久化机制的实现相关代码是redis.c, redis.h, aof.c, bio.c, rio.c, config.c

在阅读本文之前请先阅读Redis数据持久化机制AOF原理分析之配置详解文章，了解AOF相关参数的解析，文章链接

转载请注明，文章出自

下面将介绍AOF数据持久化机制的实现

 

Server启动加载AOF文件数据

 

Server启动加载AOF文件数据的执行步骤为:main() -> initServerConfig() -> loadServerConfig() -> initServer() -> loadDataFromDisk()。initServerConfig()主要为初始化默认的AOF参数配置；loadServerConfig()加载配置文件redis.conf中AOF的参数配置，覆盖Server的默认AOF参数配置，如果配置appendonly on，那么AOF数据持久化功能将被激活，server.aof_state参数被设置为REDIS_AOF_ON；loadDataFromDisk()判断server.aof_state == REDIS_AOF_ON，结果为True就调用loadAppendOnlyFile函数加载AOF文件中的数据，加载的方法就是读取AOF文件中数据，由于AOF文件中存储的数据与客户端发送的请求格式相同完全符合Redis的通信协议，因此Server创建伪客户端fakeClient，将解析后的AOF文件数据像客户端请求一样调用各种指令，cmd->proc(fakeClient)，将AOF文件中的数据重现到Redis Server数据库中。

 

/* 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: %s. Exiting.",strerror(errno));
            exit(1);
        }
    }
}

Server首先判断加载AOF文件是因为AOF文件中的数据要比RDB文件中的数据要新。

 

 

int loadAppendOnlyFile(char *filename) {
    struct redisClient *fakeClient;
    FILE *fp = fopen(filename,"r");
    struct redis_stat sb;
    int old_aof_state = server.aof_state;
    long loops = 0;

    //redis_fstat就是fstat64函数，通过fileno(fp)得到文件描述符，获取文件的状态存储于sb中，
    //具体可以参考stat函数，st_size就是文件的字节数
    if (fp && redis_fstat(fileno(fp),&sb) != -1 && sb.st_size == 0) {
        server.aof_current_size = 0;
        fclose(fp);
        return REDIS_ERR;
    }

    if (fp == NULL) {       //打开文件失败
        redisLog(REDIS_WARNING,"Fatal error: can't open the append log file for reading: %s",strerror(errno));
        exit(1);
    }

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

    fakeClient = createFakeClient(); //建立伪终端
    startLoading(fp); // 定义于 rdb.c ，更新服务器的载入状态

    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 */
        // 有间隔地处理外部请求，ftello()函数得到文件的当前位置，返回值为long
        if (!(loops++ % 1000)) {
            loadingProgress(ftello(fp));//保存aof文件读取的位置，ftellno(fp)获取文件当前位置
            aeProcessEvents(server.el, AE_FILE_EVENTS|AE_DONT_WAIT);//处理事件
        }
        //按行读取AOF数据
        if (fgets(buf,sizeof(buf),fp) == NULL) {
            if (feof(fp))//达到文件尾EOF
                break;
            else
                goto readerr;
        }
        //读取AOF文件中的命令，依照Redis的协议处理
        if (buf[0] != '*') goto fmterr;
        argc = atoi(buf+1);//参数个数
        if (argc < 1) goto fmterr;

        argv = zmalloc(sizeof(robj*)*argc);//参数值
        for (j = 0; j < argc; j++) {
            if (fgets(buf,sizeof(buf),fp) == NULL) goto readerr;
            if (buf[0] != '$') goto fmterr;
            len = strtol(buf+1,NULL,10);//每个bulk的长度
            argsds = sdsnewlen(NULL,len);//新建一个空sds
            //按照bulk的长度读取
            if (len && fread(argsds,len,1,fp) == 0) goto fmterr;
            argv[j] = createObject(REDIS_STRING,argsds);
            if (fread(buf,2,1,fp) == 0) goto fmterr; /* discard CRLF 跳过\r\n*/
        }

        /* Command lookup */
        cmd = lookupCommand(argv[0]->ptr);
        if (!cmd) {
            redisLog(REDIS_WARNING,"Unknown command '%s' reading the append only file", (char*)argv[0]->ptr);
            exit(1);
        }
        /* Run the command in the context of a fake client */
        fakeClient->argc = argc;
        fakeClient->argv = argv;
        cmd->proc(fakeClient);//执行命令

        /* The fake client should not have a reply */
        redisAssert(fakeClient->bufpos == 0 && listLength(fakeClient->reply) == 0);
        /* The fake client should never get blocked */
        redisAssert((fakeClient->flags & REDIS_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. */
        for (j = 0; j < fakeClient->argc; j++)
            decrRefCount(fakeClient->argv[j]);
        zfree(fakeClient->argv);
    }

    /* This point can only be reached when EOF is reached without errors.
     * If the client is in the middle of a MULTI/EXEC, log error and quit. */
    if (fakeClient->flags & REDIS_MULTI) goto readerr;

    fclose(fp);
    freeFakeClient(fakeClient);
    server.aof_state = old_aof_state;
    stopLoading();
    aofUpdateCurrentSize(); //更新server.aof_current_size，AOF文件大小
    server.aof_rewrite_base_size = server.aof_current_size;
    return REDIS_OK;
    …………
}

在前面一篇关于AOF参数配置的博客遗留了一个问题，server.aof_current_size参数的初始化，下面解决这个疑问。

 

 

void aofUpdateCurrentSize(void) {
    struct redis_stat sb;

    if (redis_fstat(server.aof_fd,&sb) == -1) {
        redisLog(REDIS_WARNING,"Unable to obtain the AOF file length. stat: %s",
            strerror(errno));
    } else {
        server.aof_current_size = sb.st_size;
    }
}

redis_fstat是作者对Linux中fstat64函数的重命名，该还是就是获取文件相关的参数信息，具体可以Google之，sb.st_size就是当前AOF文件的大小。这里需要知道server.aof_fd即AOF文件描述符，该参数的初始化在initServer()函数中

 

 

/* Open the AOF file if needed. */
    if (server.aof_state == REDIS_AOF_ON) {
        server.aof_fd = open(server.aof_filename,O_WRONLY|O_APPEND|O_CREAT,0644);
        if (server.aof_fd == -1) {
            redisLog(REDIS_WARNING, "Can't open the append-only file: %s",strerror(errno));
            exit(1);
        }
    }

 

 

至此，Redis Server启动加载硬盘中AOF文件数据的操作就成功结束了。

 

 

Server数据库产生新数据如何持久化到硬盘

当客户端执行Set等修改数据库中字段的指令时就会造成Server数据库中数据被修改，这些修改的数据应该被实时更新到AOF文件中，并且也要按照一定的fsync机制刷新到硬盘中，保证数据不会丢失。

 

在上一篇博客中，提到了三种fsync方式:appendfsync always, appendfsync everysec, appendfsync no. 具体体现在server.aof_fsync参数中。

首先看当客户端请求的指令造成数据被修改，Redis是如何将修改数据的指令添加到server.aof_buf中的。

call() -> propagate() -> feedAppendOnlyFile()，call()函数判断执行指令后是否造成数据被修改。

feedAppendOnlyFile函数首先会判断Server是否开启了AOF，如果开启AOF，那么根据Redis通讯协议将修改数据的指令重现成请求的字符串，注意在超时设置的处理方式，接着将字符串append到server.aof_buf中即可。该函数最后两行代码需要注意，这才是重点，如果server.aof_child_pid != -1那么表明此时Server正在重写rewrite AOF文件，需要将被修改的数据追加到server.aof_rewrite_buf_blocks链表中，等待rewrite结束后，追加到AOF文件中。具体见下面代码的注释。

 

/* Propagate the specified command (in the context of the specified database id)
 * to AOF and Slaves.
 *
 * flags are an xor between:
 * + REDIS_PROPAGATE_NONE (no propagation of command at all)
 * + REDIS_PROPAGATE_AOF (propagate into the AOF file if is enabled)
 * + REDIS_PROPAGATE_REPL (propagate into the replication link)
 */
void propagate(struct redisCommand *cmd, int dbid, robj **argv, int argc,
               int flags)
{
    //将cmd指令变动的数据追加到AOF文件中
    if (server.aof_state != REDIS_AOF_OFF && flags & REDIS_PROPAGATE_AOF)
        feedAppendOnlyFile(cmd,dbid,argv,argc);
    if (flags & REDIS_PROPAGATE_REPL)
        replicationFeedSlaves(server.slaves,dbid,argv,argc);
}

//cmd指令修改了数据，先将更新的数据写到server.aof_buf中
void feedAppendOnlyFile(struct redisCommand *cmd, int dictid, robj **argv, int argc) {
    sds buf = sdsempty();
    robj *tmpargv[3];

    /* The DB this command was targeting is not the same as the last command
     * we appendend. To issue a SELECT command is needed. */
    // 当前 db 不是指定的 aof db，通过创建 SELECT 命令来切换数据库
    if (dictid != server.aof_selected_db) {
        char seldb[64];

        snprintf(seldb,sizeof(seldb),"%d",dictid);
        buf = sdscatprintf(buf,"*2\r\n$6\r\nSELECT\r\n$%lu\r\n%s\r\n",
            (unsigned long)strlen(seldb),seldb);
        server.aof_selected_db = dictid;
    }

    // 将 EXPIRE / PEXPIRE / EXPIREAT 命令翻译为 PEXPIREAT 命令
    if (cmd->proc == expireCommand || cmd->proc == pexpireCommand ||
        cmd->proc == expireatCommand) {
        /* Translate EXPIRE/PEXPIRE/EXPIREAT into PEXPIREAT */
        buf = catAppendOnlyExpireAtCommand(buf,cmd,argv[1],argv[2]);
    }// 将 SETEX / PSETEX 命令翻译为 SET 和 PEXPIREAT 组合命令
    else if (cmd->proc == setexCommand || cmd->proc == psetexCommand) {
        /* Translate SETEX/PSETEX to SET and PEXPIREAT */
        tmpargv[0] = createStringObject("SET",3);
        tmpargv[1] = argv[1];
        tmpargv[2] = argv[3];
        buf = catAppendOnlyGenericCommand(buf,3,tmpargv);
        decrRefCount(tmpargv[0]);
        buf = catAppendOnlyExpireAtCommand(buf,cmd,argv[1],argv[2]);
    } else {       //其他的指令直接追加
        /* All the other commands don't need translation or need the
         * same translation already operated in the command vector
         * for the replication itself. */
        buf = catAppendOnlyGenericCommand(buf,argc,argv);
    }

    /* Append to the AOF buffer. This will be flushed on disk just before
     * of re-entering the event loop, so before the client will get a
     * positive reply about the operation performed. */
    // 将 buf 追加到服务器的 aof_buf 末尾，在beforeSleep中写到AOF文件中，并且根据情况fsync刷新到硬盘
    if (server.aof_state == REDIS_AOF_ON)
        server.aof_buf = sdscatlen(server.aof_buf,buf,sdslen(buf));

    /* If a background append only file rewriting is in progress we want to
     * accumulate the differences between the child DB and the current one
     * in a buffer, so that when the child process will do its work we
     * can append the differences to the new append only file. */
    //如果server.aof_child_pid不为1，那就说明有快照进程正在写数据到临时文件(已经开始rewrite)，
    //那么必须先将这段时间接收到的指令更新的数据先暂时存储起来，等到快照进程完成任务后，
    //将这部分数据写入到AOF文件末尾，保证数据不丢失
    //解释为什么需要aof_rewrite_buf_blocks，当server在进行rewrite时即读取所有数据库中的数据，
    //有些数据已经写到新的AOF文件，但是此时客户端执行指令又将该值修改了，因此造成了差异
    if (server.aof_child_pid != -1)
        aofRewriteBufferAppend((unsigned char*)buf,sdslen(buf));
    /*这里说一下server.aof_buf和server.aof_rewrite_buf_blocks的区别
      aof_buf是正常情况下aof文件打开的时候，会不断将这份数据写入到AOF文件中。
      aof_rewrite_buf_blocks 是如果用户主动触发了写AOF文件的命令时，比如 config set appendonly yes命令
      那么redis会fork创建一个后台进程,也就是当时的数据快照，然后将数据写入到一个临时文件中去。
      在此期间发送的命令，我们需要把它们记录起来，等后台进程完成AOF临时文件写后，serverCron定时任务
      感知到这个退出动作，然后就会调用backgroundRewriteDoneHandler进而调用aofRewriteBufferWrite函数，
      将aof_rewrite_buf_blocks上面的数据，也就是diff数据写入到临时AOF文件中，然后再unlink替换正常的AOF文件。
      因此可以知道，aof_buf一般情况下比aof_rewrite_buf_blocks要少，
      但开始的时候可能aof_buf包含一些后者不包含的前面部分数据。*/

    sdsfree(buf);
}

 

 

Server在每次事件循环之前会调用一次beforeSleep函数，下面看看这个函数做了什么工作？

 

/* This function gets called every time Redis is entering the
 * main loop of the event driven library, that is, before to sleep
 * for ready file descriptors. */
void beforeSleep(struct aeEventLoop *eventLoop) {
    REDIS_NOTUSED(eventLoop);
    listNode *ln;
    redisClient *c;

    /* Run a fast expire cycle (the called function will return
     * ASAP if a fast cycle is not needed). */
    if (server.active_expire_enabled && server.masterhost == NULL)
        activeExpireCycle(ACTIVE_EXPIRE_CYCLE_FAST);

    /* Try to process pending commands for clients that were just unblocked. */
    while (listLength(server.unblocked_clients)) {
        ln = listFirst(server.unblocked_clients);
        redisAssert(ln != NULL);
        c = ln->value;
        listDelNode(server.unblocked_clients,ln);
        c->flags &= ~REDIS_UNBLOCKED;

        /* Process remaining data in the input buffer. */
        //处理客户端在阻塞期间接收到的客户端发送的请求
        if (c->querybuf && sdslen(c->querybuf) > 0) {
            server.current_client = c;
            processInputBuffer(c);
            server.current_client = NULL;
        }
    }

    /* Write the AOF buffer on disk */
    //将server.aof_buf中的数据追加到AOF文件中并fsync到硬盘上
    flushAppendOnlyFile(0);
}

通过上面的代码及注释可以发现，beforeSleep函数做了三件事：1、处理过期键，2、处理阻塞期间的客户端请求，3、将server.aof_buf中的数据追加到AOF文件中并fsync刷新到硬盘上，flushAppendOnlyFile函数给定了一个参数force，表示是否强制写入AOF文件，0表示非强制即支持延迟写，1表示强制写入。

 

 

void flushAppendOnlyFile(int force) {
    ssize_t nwritten;
    int sync_in_progress = 0;
    if (sdslen(server.aof_buf) == 0) return;
    // 返回后台正在等待执行的 fsync 数量
    if (server.aof_fsync == AOF_FSYNC_EVERYSEC)
        sync_in_progress = bioPendingJobsOfType(REDIS_BIO_AOF_FSYNC) != 0;

    // AOF 模式为每秒 fsync ，并且 force 不为 1 如果可以的话，推延冲洗
    if (server.aof_fsync == AOF_FSYNC_EVERYSEC && !force) {
        /* With this append fsync policy we do background fsyncing.
         * If the fsync is still in progress we can try to delay
         * the write for a couple of seconds. */
        // 如果 aof_fsync 队列里已经有正在等待的任务
        if (sync_in_progress) {
            // 上一次没有推迟冲洗过，记录推延的当前时间，然后返回
            if (server.aof_flush_postponed_start == 0) {
                /* No previous write postponinig, remember that we are
                 * postponing the flush and return. */
                server.aof_flush_postponed_start = server.unixtime;
                return;
            } else if (server.unixtime - server.aof_flush_postponed_start < 2) {
                // 允许在两秒之内的推延冲洗
                /* We were already waiting for fsync to finish, but for less
                 * than two seconds this is still ok. Postpone again. */
                return;
            }
            /* Otherwise fall trough, and go write since we can't wait
             * over two seconds. */
            server.aof_delayed_fsync++;
            redisLog(REDIS_NOTICE,"Asynchronous AOF fsync is taking too long (disk is busy?). Writing the AOF buffer without waiting for fsync to complete, this may slow down Redis.");
        }
    }
    /* If you are following this code path, then we are going to write so
     * set reset the postponed flush sentinel to zero. */
    server.aof_flush_postponed_start = 0;

    /* We want to perform a single write. This should be guaranteed atomic
     * at least if the filesystem we are writing is a real physical one.
     * While this will save us against the server being killed I don't think
     * there is much to do about the whole server stopping for power problems
     * or alike */
    // 将 AOF 缓存写入到文件，如果一切幸运的话，写入会原子性地完成
    nwritten = write(server.aof_fd,server.aof_buf,sdslen(server.aof_buf));
    if (nwritten != (signed)sdslen(server.aof_buf)) {       //出错
        /* Ooops, we are in troubles. The best thing to do for now is
         * aborting instead of giving the illusion that everything is
         * working as expected. */
        if (nwritten == -1) {
            redisLog(REDIS_WARNING,"Exiting on error writing to the append-only file: %s",strerror(errno));
        } else {
            redisLog(REDIS_WARNING,"Exiting on short write while writing to "
                                   "the append-only file: %s (nwritten=%ld, "
                                   "expected=%ld)",
                                   strerror(errno),
                                   (long)nwritten,
                                   (long)sdslen(server.aof_buf));

            if (ftruncate(server.aof_fd, server.aof_current_size) == -1) {
                redisLog(REDIS_WARNING, "Could not remove short write "
                         "from the append-only file.  Redis may refuse "
                         "to load the AOF the next time it starts.  "
                         "ftruncate: %s", strerror(errno));
            }
        }
        exit(1);
    }
    server.aof_current_size += nwritten;

    /* Re-use AOF buffer when it is small enough. The maximum comes from the
     * arena size of 4k minus some overhead (but is otherwise arbitrary). */
    // 如果 aof 缓存不是太大，那么重用它，否则，清空 aof 缓存
    if ((sdslen(server.aof_buf)+sdsavail(server.aof_buf)) < 4000) {
        sdsclear(server.aof_buf);
    } else {
        sdsfree(server.aof_buf);
        server.aof_buf = sdsempty();
    }

    /* Don't fsync if no-appendfsync-on-rewrite is set to yes and there are
     * children doing I/O in the background. */
    //aof rdb子进程运行中不支持fsync并且aof rdb子进程正在运行，那么直接返回，
    //但是数据已经写到aof文件中，只是没有刷新到硬盘
    if (server.aof_no_fsync_on_rewrite &&
        (server.aof_child_pid != -1 || server.rdb_child_pid != -1))
            return;

    /* Perform the fsync if needed. */
    if (server.aof_fsync == AOF_FSYNC_ALWAYS) {       //总是fsync，那么直接进行fsync
        /* aof_fsync is defined as fdatasync() for Linux in order to avoid
         * flushing metadata. */
        aof_fsync(server.aof_fd); /* Let's try to get this data on the disk */
        server.aof_last_fsync = server.unixtime;
    } else if ((server.aof_fsync == AOF_FSYNC_EVERYSEC &&
                server.unixtime > server.aof_last_fsync)) {
        if (!sync_in_progress) aof_background_fsync(server.aof_fd);//放到后台线程进行fsync
        server.aof_last_fsync = server.unixtime;
    }
}

上述代码中请关注server.aof_fsync参数，即设置Redis fsync AOF文件到硬盘的策略，如果设置为AOF_FSYNC_ALWAYS，那么直接在主进程中fsync，如果设置为AOF_FSYNC_EVERYSEC，那么放入后台线程中fsync，后台线程的代码在bio.c中。

 

 

小结

文章写到这，已经解决的了Redis Server启动加载AOF文件和如何将客户端请求产生的新的数据追加到AOF文件中，对于追加数据到AOF文件中，根据fsync的配置策略如何将写入到AOF文件中的新数据刷新到硬盘中，直接在主进程中fsync或是在后台线程fsync。

至此，AOF数据持久化还剩下如何rewrite AOF，接受客户端发送的BGREWRITEAOF请求，此部分内容待下篇博客中解析。

感谢此篇博客给我在理解Redis AOF数据持久化方面的巨大帮助，

本人Redis-2.8.2的源码注释已经放到Github中，有需要的读者可以下载，我也会在后续的时间中更新，

本人不怎么会使用Git，望有人能教我一下。

 

--------------------------------------------------------------------------------------------------------------------------------------------------------------

本文所引用的源码全部来自Redis2.8.2版本。

Redis AOF数据持久化机制的实现相关代码是redis.c, redis.h, aof.c, bio.c, rio.c, config.c

在阅读本文之前请先阅读Redis数据持久化机制AOF原理分析之配置详解文章，了解AOF相关参数的解析，文章链接

接着上一篇文章，本文将介绍Redis是如何实现AOF rewrite的。

转载请注明，文章出自

 

AOF rewrite的触发机制

 

如果Redis只是将客户端修改数据库的指令重现存储在AOF文件中，那么AOF文件的大小会不断的增加，因为AOF文件只是简单的重现存储了客户端的指令，而并没有进行合并。对于该问题最简单的处理方式，即当AOF文件满足一定条件时就对AOF进行rewrite，rewrite是根据当前内存数据库中的数据进行遍历写到一个临时的AOF文件，待写完后替换掉原来的AOF文件即可。

 

Redis触发AOF rewrite机制有三种：

1、Redis Server接收到客户端发送的BGREWRITEAOF指令请求，如果当前AOF/RDB数据持久化没有在执行，那么执行，反之，等当前AOF/RDB数据持久化结束后执行AOF rewrite

2、在Redis配置文件redis.conf中，用户设置了auto-aof-rewrite-percentage和auto-aof-rewrite-min-size参数，并且当前AOF文件大小server.aof_current_size大于auto-aof-rewrite-min-size(server.aof_rewrite_min_size)，同时AOF文件大小的增长率大于auto-aof-rewrite-percentage(server.aof_rewrite_perc)时，会自动触发AOF rewrite

3、用户设置“config set appendonly yes”开启AOF的时，调用startAppendOnly函数会触发rewrite

下面分别介绍上述三种机制的处理.

 

接收到BGREWRITEAOF指令

 

<span style="font-size:12px;">void bgrewriteaofCommand(redisClient *c) {
    //AOF rewrite正在执行，那么直接返回
    if (server.aof_child_pid != -1) {
        addReplyError(c,"Background append only file rewriting already in progress");
    } else if (server.rdb_child_pid != -1) {
        //AOF rewrite未执行，但RDB数据持久化正在执行，那么设置AOF rewrite状态为scheduled
        //待RDB结束后执行AOF rewrite
        server.aof_rewrite_scheduled = 1;
        addReplyStatus(c,"Background append only file rewriting scheduled");
    } else if (rewriteAppendOnlyFileBackground() == REDIS_OK) {
        //直接执行AOF rewrite
        addReplyStatus(c,"Background append only file rewriting started");
    } else {
        addReply(c,shared.err);
    }
}</span>

当AOF rewrite请求被挂起时，在serverCron函数中，会处理。

/* Start a scheduled AOF rewrite if this was requested by the user while
     * a BGSAVE was in progress. */
    // 如果用户执行 BGREWRITEAOF 命令的话，在后台开始 AOF 重写
    //当用户执行BGREWRITEAOF命令时，如果RDB文件正在写，那么将server.aof_rewrite_scheduled标记为1
    //当RDB文件写完后开启AOF rewrite
    if (server.rdb_child_pid == -1 && server.aof_child_pid == -1 &&
        server.aof_rewrite_scheduled)
    {
        rewriteAppendOnlyFileBackground();
    }

Server自动对AOF进行rewrite

在serverCron函数中会周期性判断

/* Trigger an AOF rewrite if needed */
         //满足一定条件rewrite AOF文件
         if (server.rdb_child_pid == -1 &&
             server.aof_child_pid == -1 &&
             server.aof_rewrite_perc &&
             server.aof_current_size > server.aof_rewrite_min_size)
         {
            long long base = server.aof_rewrite_base_size ?
                            server.aof_rewrite_base_size : 1;
            long long growth = (server.aof_current_size*100/base) - 100;
            if (growth >= server.aof_rewrite_perc) {
                redisLog(REDIS_NOTICE,"Starting automatic rewriting of AOF on %lld%% growth",growth);
                rewriteAppendOnlyFileBackground();
            }
         }

config set appendonly yes

当客户端发送该指令时，config.c中的configSetCommand函数会做出响应，startAppendOnly函数会执行AOF rewrite

if (!strcasecmp(c->argv[2]->ptr,"appendonly")) {
    int enable = yesnotoi(o->ptr);

    if (enable == -1) goto badfmt;
    if (enable == 0 && server.aof_state != REDIS_AOF_OFF) {        //appendonly no 关闭AOF
        stopAppendOnly();
    } else if (enable && server.aof_state == REDIS_AOF_OFF) {        //appendonly yes rewrite AOF
        if (startAppendOnly() == REDIS_ERR) {
            addReplyError(c,
                "Unable to turn on AOF. Check server logs.");
            return;
        }
    }
}

int startAppendOnly(void) {
    server.aof_last_fsync = server.unixtime;
    server.aof_fd = open(server.aof_filename,O_WRONLY|O_APPEND|O_CREAT,0644);
    redisAssert(server.aof_state == REDIS_AOF_OFF);
    if (server.aof_fd == -1) {
        redisLog(REDIS_WARNING,"Redis needs to enable the AOF but can't open the append only file: %s",strerror(errno));
        return REDIS_ERR;
    }
    if (rewriteAppendOnlyFileBackground() == REDIS_ERR) {        //rewrite
        close(server.aof_fd);
        redisLog(REDIS_WARNING,"Redis needs to enable the AOF but can't trigger a background AOF rewrite operation. Check the above logs for more info about the error.");
        return REDIS_ERR;
    }
    /* We correctly switched on AOF, now wait for the rerwite to be complete
     * in order to append data on disk. */
    server.aof_state = REDIS_AOF_WAIT_REWRITE;
    return REDIS_OK;
}

Redis AOF rewrite机制的实现

从上述分析可以看出rewrite的实现全部依靠rewriteAppendOnlyFileBackground函数，下面分析该函数，通过下面的代码可以看出，Redis是fork出一个子进程来操作AOF rewrite，然后子进程调用rewriteAppendOnlyFile函数，将数据写到一个临时文件temp-rewriteaof-bg-%d.aof中。如果子进程完成会通过exit(0)函数通知父进程rewrite结束，在serverCron函数中使用wait3函数接收子进程退出状态，然后执行后续的AOF rewrite的收尾工作，后面将会分析。

父进程的工作主要包括清楚server.aof_rewrite_scheduled标志，记录子进程IDserver.aof_child_pid = childpid，记录rewrite的开始时间server.aof_rewrite_time_start = time(NULL)等。

int rewriteAppendOnlyFileBackground(void) {
    pid_t childpid;
    long long start;

    // 后台重写正在执行
    if (server.aof_child_pid != -1) return REDIS_ERR;
    start = ustime();
    if ((childpid = fork()) == 0) {
        char tmpfile[256];

        /* Child */
        closeListeningSockets(0);//
        redisSetProcTitle("redis-aof-rewrite");
        snprintf(tmpfile,256,"temp-rewriteaof-bg-%d.aof", (int) getpid());
        if (rewriteAppendOnlyFile(tmpfile) == REDIS_OK) {
            size_t private_dirty = zmalloc_get_private_dirty();

            if (private_dirty) {
                redisLog(REDIS_NOTICE,
                    "AOF rewrite: %zu MB of memory used by copy-on-write",
                    private_dirty/(1024*1024));
            }
            exitFromChild(0);
        } else {
            exitFromChild(1);
        }
    } else {
        /* Parent */
        server.stat_fork_time = ustime()-start;
        if (childpid == -1) {
            redisLog(REDIS_WARNING,
                "Can't rewrite append only file in background: fork: %s",
                strerror(errno));
            return REDIS_ERR;
        }
        redisLog(REDIS_NOTICE,
            "Background append only file rewriting started by pid %d",childpid);
        server.aof_rewrite_scheduled = 0;
        server.aof_rewrite_time_start = time(NULL);
        server.aof_child_pid = childpid;
        updateDictResizePolicy();
        /* We set appendseldb to -1 in order to force the next call to the
         * feedAppendOnlyFile() to issue a SELECT command, so the differences
         * accumulated by the parent into server.aof_rewrite_buf will start
         * with a SELECT statement and it will be safe to merge. */
        server.aof_selected_db = -1;
        replicationScriptCacheFlush();
        return REDIS_OK;
    }
    return REDIS_OK; /* unreached */
}

接下来介绍rewriteAppendOnlyFile函数，该函数的主要工作为：遍历所有数据库中的数据，将其写入到临时文件temp-rewriteaof-%d.aof中，写入函数定义在rio.c中，比较简单，然后将数据刷新到硬盘中，然后将文件名rename为其调用者给定的临时文件名，注意仔细看代码，这里并没有修改为正式的AOF文件名。

在写入文件时如果设置server.aof_rewrite_incremental_fsync参数，那么在rioWrite函数中fwrite部分数据就会将数据fsync到硬盘中，来保证数据的正确性。

int rewriteAppendOnlyFile(char *filename) {
    dictIterator *di = NULL;
    dictEntry *de;
    rio aof;
    FILE *fp;
    char tmpfile[256];
    int j;
    long long now = mstime();

    /* Note that we have to use a different temp name here compared to the
     * one used by rewriteAppendOnlyFileBackground() function. */
    snprintf(tmpfile,256,"temp-rewriteaof-%d.aof", (int) getpid());
    fp = fopen(tmpfile,"w");
    if (!fp) {
        redisLog(REDIS_WARNING, "Opening the temp file for AOF rewrite in rewriteAppendOnlyFile(): %s", strerror(errno));
        return REDIS_ERR;
    }

    rioInitWithFile(&aof,fp); //初始化读写函数，rio.c
    //设置r->io.file.autosync = bytes;每32M刷新一次
    if (server.aof_rewrite_incremental_fsync)
        rioSetAutoSync(&aof,REDIS_AOF_AUTOSYNC_BYTES);
    for (j = 0; j < server.dbnum; j++) {        //遍历每个数据库
        char selectcmd[] = "*2\r\n$6\r\nSELECT\r\n";
        redisDb *db = server.db+j;
        dict *d = db->dict;
        if (dictSize(d) == 0) continue;
        di = dictGetSafeIterator(d);
        if (!di) {
            fclose(fp);
            return REDIS_ERR;
        }

        /* SELECT the new DB */
        if (rioWrite(&aof,selectcmd,sizeof(selectcmd)-1) == 0) goto werr;
        if (rioWriteBulkLongLong(&aof,j) == 0) goto werr;

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

            keystr = dictGetKey(de);
            o = dictGetVal(de);
            initStaticStringObject(key,keystr);

            expiretime = getExpire(db,&key);

            /* If this key is already expired skip it */
            if (expiretime != -1 && expiretime < now) continue;

            /* Save the key and associated value */
            if (o->type == REDIS_STRING) {
                /* Emit a SET command */
                char cmd[]="*3\r\n$3\r\nSET\r\n";
                if (rioWrite(&aof,cmd,sizeof(cmd)-1) == 0) goto werr;
                /* Key and value */
                if (rioWriteBulkObject(&aof,&key) == 0) goto werr;
                if (rioWriteBulkObject(&aof,o) == 0) goto werr;
            } else if (o->type == REDIS_LIST) {
                if (rewriteListObject(&aof,&key,o) == 0) goto werr;
            } else if (o->type == REDIS_SET) {
                if (rewriteSetObject(&aof,&key,o) == 0) goto werr;
            } else if (o->type == REDIS_ZSET) {
                if (rewriteSortedSetObject(&aof,&key,o) == 0) goto werr;
            } else if (o->type == REDIS_HASH) {
                if (rewriteHashObject(&aof,&key,o) == 0) goto werr;
            } else {
                redisPanic("Unknown object type");
            }
            /* Save the expire time */
            if (expiretime != -1) {
                char cmd[]="*3\r\n$9\r\nPEXPIREAT\r\n";
                if (rioWrite(&aof,cmd,sizeof(cmd)-1) == 0) goto werr;
                if (rioWriteBulkObject(&aof,&key) == 0) goto werr;
                if (rioWriteBulkLongLong(&aof,expiretime) == 0) goto werr;
            }
        }
        dictReleaseIterator(di);
    }

    /* Make sure data will not remain on the OS's output buffers */
    fflush(fp);
    aof_fsync(fileno(fp));//将tempfile文件刷新到硬盘
    fclose(fp);

    /* Use RENAME to make sure the DB file is changed atomically only
     * if the generate DB file is ok. */
    if (rename(tmpfile,filename) == -1) {        //重命名文件名，注意rename后的文件也是一个临时文件
        redisLog(REDIS_WARNING,"Error moving temp append only file on the final destination: %s", strerror(errno));
        unlink(tmpfile);
        return REDIS_ERR;
    }
    redisLog(REDIS_NOTICE,"SYNC append only file rewrite performed");
    return REDIS_OK;

werr:
    fclose(fp);
    unlink(tmpfile);
    redisLog(REDIS_WARNING,"Write error writing append only file on disk: %s", strerror(errno));
    if (di) dictReleaseIterator(di);
    return REDIS_ERR;
}

AOF rewrite工作到这里已经结束一半，上一篇文章提到如果server.aof_state != REDIS_AOF_OFF，那么就会将客户端请求指令修改的数据通过feedAppendOnlyFile函数追加到AOF文件中，那么此时AOF已经rewrite了，必须要处理此时出现的差异数据，记得在feedAppendOnlyFile函数中有这么一段代码

if (server.aof_child_pid != -1)
        aofRewriteBufferAppend((unsigned char*)buf,sdslen(buf));

如果AOF rewrite正在进行，那么就将修改数据的指令字符串存储到server.aof_rewrite_buf_blocks链表中，等待AOF rewrite子进程结束后处理，处理此部分数据的代码在serverCron函数中。需要指出的是wait3函数我不了解，可能下面注释会有点问题。

/* Check if a background saving or AOF rewrite in progress terminated. */
//如果RDB bgsave或AOF rewrite子进程已经执行,通过获取子进程的退出状态，对后续的工作进行处理
if (server.rdb_child_pid != -1 || server.aof_child_pid != -1) {        //
    int statloc;
    pid_t pid;

    if ((pid = wait3(&statloc,WNOHANG,NULL)) != 0) {
        int exitcode = WEXITSTATUS(statloc);//获取退出的状态
        int bysignal = 0;

        if (WIFSIGNALED(statloc)) bysignal = WTERMSIG(statloc);

        if (pid == server.rdb_child_pid) {
            backgroundSaveDoneHandler(exitcode,bysignal);
        } else if (pid == server.aof_child_pid) {
            backgroundRewriteDoneHandler(exitcode,bysignal);
        } else {
            redisLog(REDIS_WARNING,
                "Warning, detected child with unmatched pid: %ld",
                (long)pid);
        }
        // 如果 BGSAVE 和 BGREWRITEAOF 都已经完成，那么重新开始 REHASH
        updateDictResizePolicy();
    }
}

对于AOF rewrite期间出现的差异数据，Server通过backgroundSaveDoneHandler函数将 server.aof_rewrite_buf_blocks链表中数据追加到新的AOF文件中。

backgroundSaveDoneHandler函数执行步骤：

1、通过判断子进程的退出状态，正确的退出状态为exit(0)，即exitcode为0，bysignal我不清楚具体意义，如果退出状态正确，backgroundSaveDoneHandler函数才会开始处理

2、通过对rewriteAppendOnlyFileBackground函数的分析，可以知道rewrite后的AOF临时文件名为temp-rewriteaof-bg-%d.aof(%d=server.aof_child_pid)中，接着需要打开此临时文件

3、调用aofRewriteBufferWrite函数将server.aof_rewrite_buf_blocks中差异数据写到该临时文件中

4、如果旧的AOF文件未打开，那么打开旧的AOF文件，将文件描述符赋值给临时变量oldfd

5、将临时的AOF文件名rename为正常的AOF文件名

6、如果旧的AOF文件未打开，那么此时只需要关闭新的AOF文件，此时的server.aof_rewrite_buf_blocks数据应该为空；如果旧的AOF是打开的，那么将server.aof_fd指向newfd,然后根据相应的fsync策略将数据刷新到硬盘上

7、调用aofUpdateCurrentSize函数统计AOF文件的大小，更新server.aof_rewrite_base_size，为serverCron中自动AOF rewrite做相应判断

8、如果之前是REDIS_AOF_WAIT_REWRITE状态，则设置server.aof_state为REDIS_AOF_ON，因为只有“config set appendonly yes”指令才会设置这个状态，也就是需要写完快照后，立即打开AOF；而BGREWRITEAOF不需要打开AOF

9、调用后台线程去关闭旧的AOF文件

下面是backgroundSaveDoneHandler函数的注释代码

 

/* A background append only file rewriting (BGREWRITEAOF) terminated its work.
 * Handle this. */
void backgroundRewriteDoneHandler(int exitcode, int bysignal) {
    if (!bysignal && exitcode == 0) {        //子进程退出状态正确
        int newfd, oldfd;
        char tmpfile[256];
        long long now = ustime();

        redisLog(REDIS_NOTICE,
            "Background AOF rewrite terminated with success");

        /* Flush the differences accumulated by the parent to the
         * rewritten AOF. */
        snprintf(tmpfile,256,"temp-rewriteaof-bg-%d.aof",
            (int)server.aof_child_pid);
        newfd = open(tmpfile,O_WRONLY|O_APPEND);
        if (newfd == -1) {
            redisLog(REDIS_WARNING,
                "Unable to open the temporary AOF produced by the child: %s", strerror(errno));
            goto cleanup;
        }
        //处理server.aof_rewrite_buf_blocks中DIFF数据
        if (aofRewriteBufferWrite(newfd) == -1) {
            redisLog(REDIS_WARNING,
                "Error trying to flush the parent diff to the rewritten AOF: %s", strerror(errno));
            close(newfd);
            goto cleanup;
        }

        redisLog(REDIS_NOTICE,
            "Parent diff successfully flushed to the rewritten AOF (%lu bytes)", aofRewriteBufferSize());

        /* The only remaining thing to do is to rename the temporary file to
         * the configured file and switch the file descriptor used to do AOF
         * writes. We don't want close(2) or rename(2) calls to block the
         * server on old file deletion.
         *
         * There are two possible scenarios:
         *
         * 1) AOF is DISABLED and this was a one time rewrite. The temporary
         * file will be renamed to the configured file. When this file already
         * exists, it will be unlinked, which may block the server.
         *
         * 2) AOF is ENABLED and the rewritten AOF will immediately start
         * receiving writes. After the temporary file is renamed to the
         * configured file, the original AOF file descriptor will be closed.
         * Since this will be the last reference to that file, closing it
         * causes the underlying file to be unlinked, which may block the
         * server.
         *
         * To mitigate the blocking effect of the unlink operation (either
         * caused by rename(2) in scenario 1, or by close(2) in scenario 2), we
         * use a background thread to take care of this. First, we
         * make scenario 1 identical to scenario 2 by opening the target file
         * when it exists. The unlink operation after the rename(2) will then
         * be executed upon calling close(2) for its descriptor. Everything to
         * guarantee atomicity for this switch has already happened by then, so
         * we don't care what the outcome or duration of that close operation
         * is, as long as the file descriptor is released again. */
        if (server.aof_fd == -1) {
            /* AOF disabled */

             /* Don't care if this fails: oldfd will be -1 and we handle that.
              * One notable case of -1 return is if the old file does
              * not exist. */
             oldfd = open(server.aof_filename,O_RDONLY|O_NONBLOCK);
        } else {
            /* AOF enabled */
            oldfd = -1; /* We'll set this to the current AOF filedes later. */
        }

        /* Rename the temporary file. This will not unlink the target file if
         * it exists, because we reference it with "oldfd". */
        //把临时文件改名为正常的AOF文件名。由于当前oldfd已经指向这个之前的正常文件名的文件，
        //所以当前不会造成unlink操作，得等那个oldfd被close的时候，内核判断该文件没有指向了，就删除之。
        if (rename(tmpfile,server.aof_filename) == -1) {
            redisLog(REDIS_WARNING,
                "Error trying to rename the temporary AOF file: %s", strerror(errno));
            close(newfd);
            if (oldfd != -1) close(oldfd);
            goto cleanup;
        }
        //如果AOF关闭了，那只要处理新文件，直接关闭这个新的文件即可
        //但是这里会不会导致服务器卡呢?这个newfd应该是临时文件的最后一个fd了，不会的，
        //因为这个文件在本函数不会写入数据，因为stopAppendOnly函数会清空aof_rewrite_buf_blocks列表。
        if (server.aof_fd == -1) {
            /* AOF disabled, we don't need to set the AOF file descriptor
             * to this new file, so we can close it. */
            close(newfd);
        } else {
            /* AOF enabled, replace the old fd with the new one. */
            oldfd = server.aof_fd;
            //指向新的fd，此时这个fd由于上面的rename语句存在，已经为正常aof文件名
            server.aof_fd = newfd;
            //fsync到硬盘
            if (server.aof_fsync == AOF_FSYNC_ALWAYS)
                aof_fsync(newfd);
            else if (server.aof_fsync == AOF_FSYNC_EVERYSEC)
                aof_background_fsync(newfd);
            server.aof_selected_db = -1; /* Make sure SELECT is re-issued */
            aofUpdateCurrentSize();
            server.aof_rewrite_base_size = server.aof_current_size;

            /* Clear regular AOF buffer since its contents was just written to
             * the new AOF from the background rewrite buffer. */
            //rewrite得到的肯定是最新的数据，所以aof_buf中的数据没有意义，直接清空
            sdsfree(server.aof_buf);
            server.aof_buf = sdsempty();
        }

        server.aof_lastbgrewrite_status = REDIS_OK;

        redisLog(REDIS_NOTICE, "Background AOF rewrite finished successfully");
        /* Change state from WAIT_REWRITE to ON if needed */
        //下面判断是否需要打开AOF，比如bgrewriteaofCommand就不需要打开AOF。
        if (server.aof_state == REDIS_AOF_WAIT_REWRITE)
            server.aof_state = REDIS_AOF_ON;

        /* Asynchronously close the overwritten AOF. */
        //让后台线程去关闭这个旧的AOF文件FD，只要CLOSE就行，会自动unlink的，因为上面已经有rename
        if (oldfd != -1) bioCreateBackgroundJob(REDIS_BIO_CLOSE_FILE,(void*)(long)oldfd,NULL,NULL);

        redisLog(REDIS_VERBOSE,
            "Background AOF rewrite signal handler took %lldus", ustime()-now);
    } else if (!bysignal && exitcode != 0) {
        server.aof_lastbgrewrite_status = REDIS_ERR;

        redisLog(REDIS_WARNING,
            "Background AOF rewrite terminated with error");
    } else {
        server.aof_lastbgrewrite_status = REDIS_ERR;

        redisLog(REDIS_WARNING,
            "Background AOF rewrite terminated by signal %d", bysignal);
    }

cleanup:
    aofRewriteBufferReset();
    aofRemoveTempFile(server.aof_child_pid);
    server.aof_child_pid = -1;
    server.aof_rewrite_time_last = time(NULL)-server.aof_rewrite_time_start;
    server.aof_rewrite_time_start = -1;
    /* Schedule a new rewrite if we are waiting for it to switch the AOF ON. */
    if (server.aof_state == REDIS_AOF_WAIT_REWRITE)
        server.aof_rewrite_scheduled = 1;
}

 

至此，AOF数据持久化已经全部结束了，剩下的就是一些细节的处理，以及一些Linux库函数的理解，对于rename、unlink、wait3等库 函数的深入认识就去问Google吧。

 

小结

 

Redis AOF数据持久化的实现机制通过三篇文章基本上比较详细的分析了， 但这只是从代码层面去看AOF，对于AOF持久化的优缺点网上有很多分析，Redis的官方网站也有英文介绍，Redis的数据持久化还有一种方法叫RDB，更多RDB的内容等下次再分析。

感谢此篇博客给我在理解Redis AOF数据持久化方面的巨大帮助， ，此篇博客对AOF的分析十分的详细。