【redis源码学习】持久化机制（2）：AOF

...
/* 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 {
	......
		//执行AOF的条件：
		/*
			1、服务器开启了AOF功能
			2、当前AOF文件大小大于aof_rewrite_min_size
			3、对于上次重写后的AOF文件大小，当前AOF文件增加的空间大小所占比例已经超过了aof_rewrite_perc 配置
		*/
        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();
    }
...

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 appended. To issue a SELECT command is needed. */
    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;
    }

    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 if (cmd->proc == setCommand && argc > 3) {
        int i;
        robj *exarg = NULL, *pxarg = NULL;
        for (i = 3; i < argc; i ++) {
            if (!strcasecmp(argv[i]->ptr, "ex")) exarg = argv[i+1];
            if (!strcasecmp(argv[i]->ptr, "px")) pxarg = argv[i+1];
        }
        serverAssert(!(exarg && pxarg));

        if (exarg || pxarg) {
            /* Translate SET [EX seconds][PX milliseconds] to SET and PEXPIREAT */
            buf = catAppendOnlyGenericCommand(buf,3,argv);
            if (exarg)
                buf = catAppendOnlyExpireAtCommand(buf,server.expireCommand,argv[1],
                                                   exarg);
            if (pxarg)
                buf = catAppendOnlyExpireAtCommand(buf,server.pexpireCommand,argv[1],
                                                   pxarg);
        } else {
            buf = catAppendOnlyGenericCommand(buf,argc,argv);
        }
    } 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. */
    if (server.aof_state == 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. */
    if (server.aof_child_pid != -1)
        aofRewriteBufferAppend((unsigned char*)buf,sdslen(buf));

    sdsfree(buf);
}

void flushAppendOnlyFile(int force) {
    ssize_t nwritten;
    int sync_in_progress = 0;
    mstime_t latency;

    if (sdslen(server.aof_buf) == 0) {
        /* Check if we need to do fsync even the aof buffer is empty,
         * because previously in AOF_FSYNC_EVERYSEC mode, fsync is
         * called only when aof buffer is not empty, so if users
         * stop write commands before fsync called in one second,
         * the data in page cache cannot be flushed in time. */
        if (server.aof_fsync == AOF_FSYNC_EVERYSEC &&
            server.aof_fsync_offset != server.aof_current_size &&
            server.unixtime > server.aof_last_fsync &&
            !(sync_in_progress = aofFsyncInProgress())) {
            goto try_fsync;
        } else {
            return;
        }
    }

	//检查当前是否存在后台线程正在同步磁盘
    if (server.aof_fsync == AOF_FSYNC_EVERYSEC)
        sync_in_progress = aofFsyncInProgress();
	//如果存在，如果磁盘同步策略为每秒同步，则延迟该AOF缓冲区刷新操作，退出函数；
	//如果已延迟时间超过2s，则强制刷新AOF缓冲区，函数继续向下执行。
    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 postponing, 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++;
            serverLog(LL_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.");
        }
    }
    /* 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 */

    if (server.aof_flush_sleep && sdslen(server.aof_buf)) {
        usleep(server.aof_flush_sleep);
    }

    latencyStartMonitor(latency);
    nwritten = aofWrite(server.aof_fd,server.aof_buf,sdslen(server.aof_buf));
    latencyEndMonitor(latency);
    /* We want to capture different events for delayed writes:
     * when the delay happens with a pending fsync, or with a saving child
     * active, and when the above two conditions are missing.
     * We also use an additional event name to save all samples which is
     * useful for graphing / monitoring purposes. */
    if (sync_in_progress) {
        latencyAddSampleIfNeeded("aof-write-pending-fsync",latency);
    } else if (hasActiveChildProcess()) {
        latencyAddSampleIfNeeded("aof-write-active-child",latency);
    } else {
        latencyAddSampleIfNeeded("aof-write-alone",latency);
    }
    latencyAddSampleIfNeeded("aof-write",latency);

    /* We performed the write so reset the postponed flush sentinel to zero. */
    server.aof_flush_postponed_start = 0;

    if (nwritten != (ssize_t)sdslen(server.aof_buf)) {
        static time_t last_write_error_log = 0;
        int can_log = 0;

        /* Limit logging rate to 1 line per AOF_WRITE_LOG_ERROR_RATE seconds. */
        if ((server.unixtime - last_write_error_log) > AOF_WRITE_LOG_ERROR_RATE) {
            can_log = 1;
            last_write_error_log = server.unixtime;
        }

        /* Log the AOF write error and record the error code. */
        if (nwritten == -1) {
            if (can_log) {
                serverLog(LL_WARNING,"Error writing to the AOF file: %s",
                    strerror(errno));
                server.aof_last_write_errno = errno;
            }
        } else {
            if (can_log) {
                serverLog(LL_WARNING,"Short write while writing to "
                                       "the AOF file: (nwritten=%lld, "
                                       "expected=%lld)",
                                       (long long)nwritten,
                                       (long long)sdslen(server.aof_buf));
            }

            if (ftruncate(server.aof_fd, server.aof_current_size) == -1) {
                if (can_log) {
                    serverLog(LL_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));
                }
            } else {
                /* If the ftruncate() succeeded we can set nwritten to
                 * -1 since there is no longer partial data into the AOF. */
                nwritten = -1;
            }
            server.aof_last_write_errno = ENOSPC;
        }

        /* Handle the AOF write error. */
        if (server.aof_fsync == AOF_FSYNC_ALWAYS) {
            /* We can't recover when the fsync policy is ALWAYS since the
             * reply for the client is already in the output buffers, and we
             * have the contract with the user that on acknowledged write data
             * is synced on disk. */
            serverLog(LL_WARNING,"Can't recover from AOF write error when the AOF fsync policy is 'always'. Exiting...");
            exit(1);
        } else {
            /* Recover from failed write leaving data into the buffer. However
             * set an error to stop accepting writes as long as the error
             * condition is not cleared. */
            server.aof_last_write_status = C_ERR;

            /* Trim the sds buffer if there was a partial write, and there
             * was no way to undo it with ftruncate(2). */
            if (nwritten > 0) {
                server.aof_current_size += nwritten;
                sdsrange(server.aof_buf,nwritten,-1);
            }
            return; /* We'll try again on the next call... */
        }
    } else {
        /* Successful write(2). If AOF was in error state, restore the
         * OK state and log the event. */
        if (server.aof_last_write_status == C_ERR) {
            serverLog(LL_WARNING,
                "AOF write error looks solved, Redis can write again.");
            server.aof_last_write_status = C_OK;
        }
    }
    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();
    }

//下面属于同步磁盘范畴
try_fsync:
    /* Don't fsync if no-appendfsync-on-rewrite is set to yes and there are
     * children doing I/O in the background. */
    if (server.aof_no_fsync_on_rewrite && hasActiveChildProcess())
        return;

    /* Perform the fsync if needed. */
    if (server.aof_fsync == AOF_FSYNC_ALWAYS) {
        /* redis_fsync is defined as fdatasync() for Linux in order to avoid
         * flushing metadata. */
        latencyStartMonitor(latency);
        redis_fsync(server.aof_fd); /* Let's try to get this data on the disk */
        latencyEndMonitor(latency);
        latencyAddSampleIfNeeded("aof-fsync-always",latency);
        server.aof_fsync_offset = server.aof_current_size;
        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);
            server.aof_fsync_offset = server.aof_current_size;
        }
        server.aof_last_fsync = server.unixtime;
    }
}