Redis源码学习-AOF

前言

网络上也有许多介绍redis的AOF机制的文章，但是从宏观上介绍aof的流程，没有具体分析在AOF过程中涉及到的数据结构和控制机制。昨晚特别看了2.8源码，感觉源码中的许多细节是值得细细深究的。特别是list *aof_rewrite_buf_blocks结构。仔细看源码，会发现原来看网络文章多的到的领会是片面的，最好的学习还是得自己动手...

原文链接： http://blog.csdn.net/ordeder/article/details/39271543

作者提及的AOF简化的流程为：
 * 1) The user calls BGREWRITEAOF
 * 2) Redis calls this function, that forks():
 *    2a) the child rewrite the append only file in a temp file.
 *    2b) the parent accumulates differences in server.aof_rewrite_buf.
 * 3) When the child finished '2a' exists.
 * 4) The parent will trap the exit code, if it's OK, will append the
 *    data accumulated into server.aof_rewrite_buf into the temp file, and
 *    finally will rename(2) the temp file in the actual file name.
 *    The the new file is reopened as the new append only file. Profit!

AOF流程

依据源码，AOF总体有一下操作：

主要函数：
//函数1：将command写入aof_buff
void feedAppendOnlyFile(struct redisCommand *cmd, int dictid, robj **argv, int argc);
//函数2：启动子进程，子进程用于刷一遍redis中的数据
int rewriteAppendOnlyFileBackground(void);
//函数3：刷一遍server.db[16],依次将对象写入磁盘临时文件tmpfile
int rewriteAppendOnlyFile(char *filename);
//函数4：将aof_buff内容持久化
void flushAppendOnlyFile(int force);
//函数5：将server.aof_rewrite_buf_blocks中的内容写入tmpfile，并替换aof文件

void backgroundRewriteDoneHandler(exitcode,bysignal);

1 AOF日常命令append：
1.1. Redis执行文件事件：执行用户命令，并将该命令缓存于Server.aof_buf中{函数1}
1.2. Redis执行时间时间的ServerCron：依据参数server.aof_flush_postponed_start，{函数4}
    1.2.1. 将redisServer.aof_buf写入文件Server.aof_fd。
    1.2.2. 该文件何时fsync到磁盘有三种机制：
        AOF_FSYNC_EVERYSEC    每秒调用fsync
        AOF_FSYNC_ALWAYS    写文件后立即调用fsync
        其他                听系统的

2 AOF日志简化操作：
2.1. Redis执行时间时间的ServerCron：{函数2-3}
   2.1.1. 开启后台AOF进程，依据redis内存数据（redis.db[16]），生成可重建数据库的命令集，并写入tmpfile临时文件
2.2. Redis执行文件事件：
   执行用户命令时，{函数1}
   2.2.1. 将该命令缓存于redisServer.aof_buf;
   2.2.2. 同时将该命令缓存于server.aof_rewrite_buf_blocks
2.3. Redis执行时间时间的ServerCron：
   2.3.1 {函数4}在aof子进程还未结束期间，步骤 1.2 照常执行，将aof_buf写入aof_fd（该干嘛干嘛）
   2.3.2 wait3发现aof子进程结束，那么：{函数5}
        2.3.2.1 将server.aof_rewrite_buf_blocks中的内容写入tmpfile中
        2.3.2.2 用tmpfile替换原有aof文件，并重置Server.aof_fd
        
函数和数据间关系如下图所示：

源码

struct redisServer{
	...
    /* AOF persistence */
    int aof_state;                  /* REDIS_AOF_(ON|OFF|WAIT_REWRITE) */
    int aof_fsync;                  /* Kind of fsync() policy （每个操作|每秒|缓冲区满）*/
    char *aof_filename;             /* Name of the AOF file */
    int aof_no_fsync_on_rewrite;    /* Don't fsync if a rewrite is in prog. */
    int aof_rewrite_perc;           /* Rewrite AOF if % growth is > M and... */
    off_t aof_rewrite_min_size;     /* the AOF file is at least N bytes. */
    off_t aof_rewrite_base_size;    /* AOF size on latest startup or rewrite. */
    off_t aof_current_size;         /* AOF current size. */
    int aof_rewrite_scheduled;      /* Rewrite once BGSAVE terminates. 是否需要开启后台aof子进程*/
    pid_t aof_child_pid;            /* PID if rewriting process */
    list *aof_rewrite_buf_blocks;   /* Hold changes during an AOF rewrite. 在aof bgsave期间redis执行的命令将存储到aof_rewrite_buf_blocks，当然aof_buf还是要照常使用的，二者不冲突*/
    sds aof_buf;      /* AOF buffer, written before entering the event loop */
    int aof_fd;       /* File descriptor of currently selected AOF file */
    int aof_selected_db; /* Currently selected DB in AOF */
    time_t aof_flush_postponed_start; /* UNIX time of postponed AOF flush */
    time_t aof_last_fsync;            /* UNIX time of last fsync() */
    time_t aof_rewrite_time_last;   /* Time used by last AOF rewrite run. */
    time_t aof_rewrite_time_start;  /* Current AOF rewrite start time. */
    int aof_lastbgrewrite_status;   /* REDIS_OK or REDIS_ERR */
    unsigned long aof_delayed_fsync;  /* delayed AOF fsync() counter */
    int aof_rewrite_incremental_fsync;/* fsync incrementally while rewriting? */
	...
}


/
/* Call() is the core of Redis execution of a command */
void call(redisClient *c, int flags) {
    long long dirty, start = ustime(), duration;
    int client_old_flags = c->flags;
	
	...
	
	 /* 执行用户命令 */
    c->flags &= ~(REDIS_FORCE_AOF|REDIS_FORCE_REPL);
    redisOpArrayInit(&server.also_propagate);
    dirty = server.dirty;
    c->cmd->proc(c);
    dirty = server.dirty-dirty;
    duration = ustime()-start;
	
	...
	
	/* 将用户命令进行AOF备份 */
    if (flags & REDIS_CALL_PROPAGATE) {
        int flags = REDIS_PROPAGATE_NONE;

        if (c->flags & REDIS_FORCE_REPL) flags |= REDIS_PROPAGATE_REPL;
        if (c->flags & REDIS_FORCE_AOF) flags |= REDIS_PROPAGATE_AOF;
        if (dirty)
            flags |= (REDIS_PROPAGATE_REPL | REDIS_PROPAGATE_AOF);
        if (flags != REDIS_PROPAGATE_NONE)
            propagate(c->cmd,c->db->id,c->argv,c->argc,flags);
    }
}

void propagate(struct redisCommand *cmd, int dbid, robj **argv, int argc,
               int flags)
{
    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);
}

void feedAppendOnlyFile(struct redisCommand *cmd, int dictid, robj **argv, int argc) {
    sds buf = sdsempty();
    robj *tmpargv[3];

    /* 如果当前操作的dict和前一次操作的dict不同，
	那么redis要在aof中添加一条：select命令，选择当前dict */
    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;
    }
	//依据不同的命令，进行字符画处理，并将结果写入临时的buff中
    if (cmd->proc == expireCommand || cmd->proc == pexpireCommand ||
        cmd->proc == expireatCommand) {
        /* Translate EXPIRE/PEXPIRE/EXPIREAT into PEXPIREAT */
        buf = catAppendOnlyExpireAtCommand(buf,cmd,argv[1],argv[2]);
    } 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 {
        /* 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. */
	//如果用户开启的AOF，那么将当前命令的buff Append到server.aof_buf缓冲的尾部
    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. */
	 //如果当前有子进程正在进行AOF日志的重构（即扫描redis数据库，依据数据构建日志）
	 //那么将当前命令的buff添加到server.aof_rewrite_buf_blocks内存中（该部分内存
	 //专门记录在重构AOF期间redis处理的操作）
    if (server.aof_child_pid != -1)
        aofRewriteBufferAppend((unsigned char*)buf,sdslen(buf));

    sdsfree(buf);
}



int serverCron(struct aeEventLoop *eventLoop, long long id, void *clientData) {
    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) */
	 //缓存系统时间...
    server.unixtime = time(NULL);
    server.mstime = mstime();

    ...

    /* Start a scheduled AOF rewrite if this was requested by the user while
     * a BGSAVE was in progress. */
	 //开启AOF日志重建的子进程（简化日志）
	 //后台AOF子进程通过扫描redis.db[16]数据，生成可重建当前数据库的命令，
	 //并写入临时文件tmpfile
    if (server.rdb_child_pid == -1 && server.aof_child_pid == -1 &&
        server.aof_rewrite_scheduled)
    {
    	//AOF
        rewriteAppendOnlyFileBackground();
    }

    /* Check if a background saving or AOF rewrite in progress terminated. */
	//后台AOF进程结束：将在后台AOF子进程构建AOF日志期间redis执行的新命令
	//（记录于server.aof_rewrite_buf_blocks）append 到后台子进程构建的tmpfile中
	//最后将tmpfile重名为server.aof_filename 替换原有AOF
    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);
            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);
            }
            updateDictResizePolicy();
        }
    } else {
        /* If there is not a background saving/rewrite in progress check if
         * we have to save/rewrite now */
         //没有后台子进程在跑，那么检查是否要开启一个AOF或者RDB的子进程。。。
		 ...
    }


    /* If we postponed an AOF buffer flush, let's try to do it every time the
     * cron function is called. */
	 //将server.aof_buf（缓存redis最近执行过的命名）flush到磁盘AOF文件中
	 //flush的策略有如下：
	 //每个操作，调用fync将命令持久化
	 //间隔1秒，调用fync将aof_buf持久化
	 //从不调用fync，由系统自行安排时机
    if (server.aof_flush_postponed_start) flushAppendOnlyFile(0);

    ...

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


/* This is how rewriting of the append only file in background works:
 *
 * 1) The user calls BGREWRITEAOF
 * 2) Redis calls this function, that forks():
 *    2a) the child rewrite the append only file in a temp file.
 *    2b) the parent accumulates differences in server.aof_rewrite_buf.
 * 3) When the child finished '2a' exists.
 * 4) The parent will trap the exit code, if it's OK, will append the
 *    data accumulated into server.aof_rewrite_buf into the temp file, and
 *    finally will rename(2) the temp file in the actual file name.
 *    The the new file is reopened as the new append only file. Profit!
 */
int rewriteAppendOnlyFileBackground(void) {
    pid_t childpid;
    long long start;

    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 */
}


/* Write a sequence of commands able to fully rebuild the dataset into
 * "filename". Used both by REWRITEAOF and BGREWRITEAOF.
 *
 * In order to minimize the number of commands needed in the rewritten
 * log Redis uses variadic commands when possible, such as RPUSH, SADD
 * and ZADD. However at max REDIS_AOF_REWRITE_ITEMS_PER_CMD items per time
 * are inserted using a single command. */
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);
    if (server.aof_rewrite_incremental_fsync)
        rioSetAutoSync(&aof,REDIS_AOF_AUTOSYNC_BYTES);
    for (j = 0; j < server.dbnum; j++) {
		//添加一条定位dict的命令
        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));
    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) {
        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;
}


/* Write the append only file buffer on disk.
 *
 * Since we are required to write the AOF before replying to the client,
 * and the only way the client socket can get a write is entering when the
 * the event loop, we accumulate all the AOF writes in a memory
 * buffer and write it on disk using this function just before entering
 * the event loop again.
 *
 * About the 'force' argument:
 *
 * When the fsync policy is set to 'everysec' we may delay the flush if there
 * is still an fsync() going on in the background thread, since for instance
 * on Linux write(2) will be blocked by the background fsync anyway.
 * When this happens we remember that there is some aof buffer to be
 * flushed ASAP, and will try to do that in the serverCron() function.
 *
 * However if force is set to 1 we'll write regardless of the background
 * fsync. */
void flushAppendOnlyFile(int force) {
    ssize_t nwritten;
    int sync_in_progress = 0;

    if (sdslen(server.aof_buf) == 0) return;

    if (server.aof_fsync == AOF_FSYNC_EVERYSEC)
        sync_in_progress = bioPendingJobsOfType(REDIS_BIO_AOF_FSYNC) != 0;

	//判定是否该开始将server.aof_buff中缓存的命令flush到server.aof_fd文件的写缓冲中
    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. */
        if (sync_in_progress) {
            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) {
                /* 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redis最近执行的一些命令（存于server.aof_buf）写入文件（server.aof_fd）
	 //注意，写入文件并不能保证马上写入磁盘，因为这是带缓冲的写。关于何时将
	 //文件写缓冲中的命令fync到磁盘，这就要看用户的设置：（见下文）
    nwritten = write(server.aof_fd,server.aof_buf,sdslen(server.aof_buf));
    if (nwritten != (signed)sdslen(server.aof_buf)) {
        /* 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. */
        ...
        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). */
    if ((sdslen(server.aof_buf)+sdsavail(server.aof_buf)) < 4000) {
        sdsclear(server.aof_buf);
    } else {
        sdsfree(server.aof_buf);
        server.aof_buf = sdsempty();
    }

	 //aof_no_fsync_on_rewrite ： 该标志位表示当有aof或rdb子进程时，不进行fsync操作
    if (server.aof_no_fsync_on_rewrite &&
        (server.aof_child_pid != -1 || server.rdb_child_pid != -1))
            return;

	//fsync...
	//每个操作，调用fync将命令持久化 [1]
	//间隔1秒，调用fync将aof_buf持久化 [2]
	//从不调用fync，由系统自行安排时机（fd的写缓冲区满了）[3]
	
	//【1】
	//每个操作都需要将文件缓冲区的写 buff sync到磁盘。从而保证每个redis操作在
	//被redis执行后，都能马上持久化，安全性很高，就是磁盘写的系统开销有点大大
    if (server.aof_fsync == AOF_FSYNC_ALWAYS) {
        /* 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;
    } 
	//【2】
	//每隔1s将文件缓冲区的写缓冲区sync到磁盘
	else if ((server.aof_fsync == AOF_FSYNC_EVERYSEC &&
                server.unixtime > server.aof_last_fsync)) {
        if (!sync_in_progress) aof_background_fsync(server.aof_fd);
        server.aof_last_fsync = server.unixtime;
    }
	
	//【3】
	//else fd的写缓冲满后会由系统安排执行（听天由命）
}