redis aof重写

除了手动条件下，有两种条件会自动触发redis的aof重写。

if (server.rdb_child_pid == -1 && server.aof_child_pid == -1 &&
        server.aof_rewrite_scheduled)
    {
        rewriteAppendOnlyFileBackground();
    }

在redis服务器上每秒执行一次的ServerCron()中，如果当前没有rdb进程或者aof进程在工作，那么就会进行aof重写操作。

  if (server.aof_state == AOF_ON &&
            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) {
                serverLog(LL_NOTICE,"Starting automatic rewriting of AOF on %lld%% growth",growth);
                rewriteAppendOnlyFileBackground();
            }
        }

在此处，如果当前aof文件大于最小重写触发大小，并且距离上一次重写增长率超过了默认的百分之一百，那么也会通过调用rewiriteAppendOnlyFileBackground()函数开始进行aof重写。

 pid_t childpid;
    long long start;

    if (server.aof_child_pid != -1 || server.rdb_child_pid != -1) return C_ERR;
    if (aofCreatePipes() != C_OK) return C_ERR;
    openChildInfoPipe();
    start = ustime();

在rewiriteAppendOnlyFileBackground()函数一开始，会确认没有aof和rdb子进程正在工作，如果存在就会马上退出，否则记录开始时间，并通过fork()方法建立子进程来进行aof的重写。

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) == C_OK) {
            size_t private_dirty = zmalloc_get_private_dirty(-1);

            if (private_dirty) {
                serverLog(LL_NOTICE,
                    "AOF rewrite: %zu MB of memory used by copy-on-write",
                    private_dirty/(1024*1024));
            }

            server.child_info_data.cow_size = private_dirty;
            sendChildInfo(CHILD_INFO_TYPE_AOF);
            exitFromChild(0);
        } else {
            exitFromChild(1);
        }

在fork()方法进入子进程之后，将会在开头一开始关闭对于socket的监听，并且调用rewriteAppendOnlyFile()函数生成临时aof文件名开始对db中的数据进行重写。

在rewriteAppendOnlyFile()函数中，具体执行重写的代码在rewriteAppendOnlyFileRio()函数中。

for (j = 0; j < server.dbnum; j++) {
        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);

        /* 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);

            /* Save the key and associated value */
            if (o->type == OBJ_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 == OBJ_LIST) {
                if (rewriteListObject(aof,&key,o) == 0) goto werr;
            } else if (o->type == OBJ_SET) {
                if (rewriteSetObject(aof,&key,o) == 0) goto werr;
            } else if (o->type == OBJ_ZSET) {
                if (rewriteSortedSetObject(aof,&key,o) == 0) goto werr;
            } else if (o->type == OBJ_HASH) {
                if (rewriteHashObject(aof,&key,o) == 0) goto werr;
            } else if (o->type == OBJ_STREAM) {
                if (rewriteStreamObject(aof,&key,o) == 0) goto werr;
            } else if (o->type == OBJ_MODULE) {
                if (rewriteModuleObject(aof,&key,o) == 0) goto werr;
            } else {
                serverPanic("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;
            }
            /* Read some diff from the parent process from time to time. */
            if (aof->processed_bytes > processed+AOF_READ_DIFF_INTERVAL_BYTES) {
                processed = aof->processed_bytes;
                aofReadDiffFromParent();
            }
        }
        dictReleaseIterator(di);
        di = NULL;
    }

首先，aof遍历需要遍历当前redis中的所有db中的数据，在确定某个db之后，会在处理某db中的数据的一开始，首先生成切换db命令，并写道aof临时文件中，并之后遍历该db中的所有数据，生成set命令，同时对于含有过期时间的字段同时根据生成expire命令，以保证过期时间能够在重写后的文件中表现。

在上述函数中完成初步重写之后，回到rewriteAppendOnlyFile()函数中。

int nodata = 0;
    mstime_t start = mstime();
    while(mstime()-start < 1000 && nodata < 20) {
        if (aeWait(server.aof_pipe_read_data_from_parent, AE_READABLE, 1) <= 0)
        {
            nodata++;
            continue;
        }
        nodata = 0; /* Start counting from zero, we stop on N *contiguous*
                       timeouts. */
        aofReadDiffFromParent();
    }

    /* Ask the master to stop sending diffs. */
    if (write(server.aof_pipe_write_ack_to_parent,"!",1) != 1) goto werr;
    if (anetNonBlock(NULL,server.aof_pipe_read_ack_from_parent) != ANET_OK)
        goto werr;
    /* We read the ACK from the server using a 10 seconds timeout. Normally
     * it should reply ASAP, but just in case we lose its reply, we are sure
     * the child will eventually get terminated. */
    if (syncRead(server.aof_pipe_read_ack_from_parent,&byte,1,5000) != 1 ||
        byte != '!') goto werr;
    serverLog(LL_NOTICE,"Parent agreed to stop sending diffs. Finalizing AOF...");

    /* Read the final diff if any. */
    aofReadDiffFromParent();

    /* Write the received diff to the file. */
    serverLog(LL_NOTICE,
        "Concatenating %.2f MB of AOF diff received from parent.",
        (double) sdslen(server.aof_child_diff) / (1024*1024));
    if (rioWrite(&aof,server.aof_child_diff,sdslen(server.aof_child_diff)) == 0)
        goto werr;

此后，在正式刷新aof数据到磁盘前，还会不断通过aof_child_diff接受父进程对于db中数据的改变，直到时间大于一秒或者新增加的数据超过20次，则会告知父进程停止发送区别，并将新的数据写入到aof文件中。

 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) {
        serverLog(LL_WARNING,"Error moving temp append only file on the final destination: %s", strerror(errno));
        unlink(tmpfile);
        return C_ERR;
    }
    serverLog(LL_NOTICE,"SYNC append only file rewrite performed");
    return C_OK;

最后刷新文件缓冲区数据到磁盘，并重命名临时文件为aof重写文件，子进程的主要工作结束。这里所有的异常都会引向werr代码块。

werr:
    serverLog(LL_WARNING,"Write error writing append only file on disk: %s", strerror(errno));
    fclose(fp);
    unlink(tmpfile);
    return C_ERR;
}

这里会记录日志删除临时文件。

server.stat_fork_time = ustime()-start;
        server.stat_fork_rate = (double) zmalloc_used_memory() * 1000000 / server.stat_fork_time / (1024*1024*1024); /* GB per second. */
        latencyAddSampleIfNeeded("fork",server.stat_fork_time/1000);
        if (childpid == -1) {
            closeChildInfoPipe();
            serverLog(LL_WARNING,
                "Can't rewrite append only file in background: fork: %s",
                strerror(errno));
            aofClosePipes();
            return C_ERR;
        }
        serverLog(LL_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 C_OK;

回到父进程，会记录子进程开始重写时间，并重置一系列aof参数，通过updateDictResizePolicy()函数禁止redis中的resize。更新aof_selected_db为-1，是为了下一次aof记录必定将记录aof中的db选择命令，确保aof的命令准确性。

 

在父进程回到ServerCron()函数中，通过wait3()函数监听子进程的返回，并通过backgroundSaveDoneHandler()函数处理。

 /* AOF enabled, replace the old fd with the new one. */
            oldfd = server.aof_fd;
            server.aof_fd = newfd;
            if (server.aof_fsync == AOF_FSYNC_ALWAYS)
                redis_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. */
            sdsfree(server.aof_buf);
            server.aof_buf = sdsempty();

在此处，如果aof重写正常结束并退出，将会把当前aof文件替换为重写之后的文件，并更新重写文件大小和当前aof文件大小，清空aof缓存。