Redis 3.0.4 AOF持久化

//命令追加
void feedAppendOnlyFile(struct redisCommand *cmd, int dictid, robj **argv, int argc) {
    sds buf = sdsempty();
    robj *tmpargv[3];
    //判断这次写入操作的数据库索引和上次的 是否一致
    /* 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;
    }
    //判断是否有过期时间
    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. */
    if (server.aof_state == REDIS_AOF_ON)
        server.aof_buf = sdscatlen(server.aof_buf,buf,sdslen(buf));
    //如果实例正在重写，则还要将数据写入到aof重写缓冲区中
    /* 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);
}   

/* 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. */
#define AOF_WRITE_LOG_ERROR_RATE 30 /* Seconds between errors logging. */
void flushAppendOnlyFile(int force) {
    ssize_t nwritten;
    int sync_in_progress = 0;
    mstime_t latency;

    if (sdslen(server.aof_buf) == 0) return;
    //查看是否有其他fsync正在进行
    if (server.aof_fsync == AOF_FSYNC_EVERYSEC)
        sync_in_progress = bioPendingJobsOfType(REDIS_BIO_AOF_FSYNC) != 0;
    //当同步策略是everysec时，并且force=0
    //如果有fsync正在同步，那么：
    //1.如果aof_flush_postponed_start = 0 表示是首次推迟写  那么将写入文件推迟  并且aof_flush_postponed_start记录为当前时间 返回
    //2.如果不是首次推迟，那么判断首次推迟的时间和当前时间是否大于2s 如果否，则返回
    //3.不满足1、2 则进行写入并将aof_delayed_fsync++

    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++;
            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.");
        }
    }
    /* 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 */

    latencyStartMonitor(latency);
    //将aof_buf写入到aof_fd 
    nwritten = write(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 (server.aof_child_pid != -1 || server.rdb_child_pid != -1) {
        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;
    //如果写入的数据不等于aof_buf的长度
    if (nwritten != (signed)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. */
    //如果写入错误 则记录在log中
        if (nwritten == -1) {
            if (can_log) {
                redisLog(REDIS_WARNING,"Error writing to the AOF file: %s",
                    strerror(errno));
                server.aof_last_write_errno = errno;
            }
        } else {
        //如果写入了一部分发生错误  
            if (can_log) {
                redisLog(REDIS_WARNING,"Short write while writing to "
                                       "the AOF file: (nwritten=%lld, "
                                       "expected=%lld)",
                                       (long long)nwritten,
                                       (long long)sdslen(server.aof_buf));
            }
        //将追加的内容截断 删除掉追加的内容 恢复成写入文件之前
            if (ftruncate(server.aof_fd, server.aof_current_size) == -1) {
                if (can_log) {
                    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));
                }
            } 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. */
    //如果同步策略是每次写入就同步 无法恢复这种策略的写，因为我们已经告知客户，已经将写的数据同步到磁盘，所以直接退出。
        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. */
            redisLog(REDIS_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. */
        //设置执行write操作的状态
            server.aof_last_write_status = REDIS_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 == REDIS_ERR) {
            redisLog(REDIS_WARNING,
                "AOF write error looks solved, Redis can write again.");
            server.aof_last_write_status = REDIS_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). */
    //如果当前aof_buf大小小于4k 则将缓存内容清空 重用缓存 否则重新申请
    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. */
    //如果no-appendfsync-on-rewrite设置为yes 并且正在重写或者save  则不执行fsync
    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) {
        /* aof_fsync is defined as fdatasync() for Linux in order to avoid
         * flushing metadata. */
        latencyStartMonitor(latency);
        aof_fsync(server.aof_fd); /* Let‘s try to get this data on the disk */
        latencyEndMonitor(latency);
        latencyAddSampleIfNeeded("aof-fsync-always",latency);
        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_last_fsync = server.unixtime;
    }
}

/* Replay the append log file. On success REDIS_OK is returned. On non fatal
 * error (the append only file is zero-length) REDIS_ERR is returned. On
 * fatal error an error message is logged and the program exists. */
//aof的载入
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;
    off_t valid_up_to = 0; /* Offset of the latest well-formed command loaded. */

    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) {
        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;
    //生成一个伪客户端
    fakeClient = createFakeClient();
    // 设置载入的状态信息
    startLoading(fp);

    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 */
        if (!(loops++ % 1000)) {
        // ftello(fp)返回当前文件载入的偏移量
            // 设置载入时server的状态信息，更新当前载入的进度
            loadingProgress(ftello(fp));
        // 在服务器被阻塞的状态下，仍然能处理请求
            // 因为当前处于载入状态，当client的请求到来时，总是返回loading的状态错误
            processEventsWhileBlocked();
        }
    // 将一行文件内容读到buf中，遇到"\r\n"停止
        if (fgets(buf,sizeof(buf),fp) == NULL) {
            if (feof(fp))
                break;
            else
                goto readerr;
        }
        if (buf[0] != ‘*‘) goto fmterr;
        if (buf[1] == ‘\0‘) goto readerr;
        argc = atoi(buf+1);
        if (argc < 1) goto fmterr;

        argv = zmalloc(sizeof(robj*)*argc);
        fakeClient->argc = argc;
        fakeClient->argv = argv;

        for (j = 0; j < argc; j++) {
            if (fgets(buf,sizeof(buf),fp) == NULL) {
                fakeClient->argc = j; /* Free up to j-1. */
                freeFakeClientArgv(fakeClient);
                goto readerr;
            }
            if (buf[0] != ‘$‘) goto fmterr;
            len = strtol(buf+1,NULL,10);
            argsds = sdsnewlen(NULL,len);
            if (len && fread(argsds,len,1,fp) == 0) {
                sdsfree(argsds);
                fakeClient->argc = j; /* Free up to j-1. */
                freeFakeClientArgv(fakeClient);
                goto readerr;
            }
            argv[j] = createObject(REDIS_STRING,argsds);
            if (fread(buf,2,1,fp) == 0) {
                fakeClient->argc = j+1; /* Free up to j. */
                freeFakeClientArgv(fakeClient);
                goto readerr; /* discard CRLF */
            }
        }

        /* Command lookup */
     // 查找命令
        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 */
        cmd->proc(fakeClient);

        /* 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. */
        freeFakeClientArgv(fakeClient);
        if (server.aof_load_truncated) valid_up_to = ftello(fp);
    }

    /* 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 uxeof;

loaded_ok: /* DB loaded, cleanup and return REDIS_OK to the caller. */
    fclose(fp);
    freeFakeClient(fakeClient);
    server.aof_state = old_aof_state;
    stopLoading();
    aofUpdateCurrentSize();
    server.aof_rewrite_base_size = server.aof_current_size;
    return REDIS_OK;

readerr: /* Read error. If feof(fp) is true, fall through to unexpected EOF. */
    if (!feof(fp)) {
        redisLog(REDIS_WARNING,"Unrecoverable error reading the append only file: %s", strerror(errno));
        exit(1);
    }

uxeof: /* Unexpected AOF end of file. */
    if (server.aof_load_truncated) {
        redisLog(REDIS_WARNING,"!!! Warning: short read while loading the AOF file !!!");
        redisLog(REDIS_WARNING,"!!! Truncating the AOF at offset %llu !!!",
            (unsigned long long) valid_up_to);
        if (valid_up_to == -1 || truncate(filename,valid_up_to) == -1) {
            if (valid_up_to == -1) {
                redisLog(REDIS_WARNING,"Last valid command offset is invalid");
            } else {
                redisLog(REDIS_WARNING,"Error truncating the AOF file: %s",
                    strerror(errno));
            }
        } else {
            /* Make sure the AOF file descriptor points to the end of the
             * file after the truncate call. */
            if (server.aof_fd != -1 && lseek(server.aof_fd,0,SEEK_END) == -1) {
                redisLog(REDIS_WARNING,"Can‘t seek the end of the AOF file: %s",
                    strerror(errno));
            } else {
                redisLog(REDIS_WARNING,
                    "AOF loaded anyway because aof-load-truncated is enabled");
                goto loaded_ok;
            }
        }
    }
    redisLog(REDIS_WARNING,"Unexpected end of file reading the append only file. You can: 1) Make a backup of your AOF file, then use ./redis-check-aof --fix <filename>. 2) Alternatively you can set the ‘aof-load-truncated‘ configuration option to yes and restart the server.");
    exit(1);

fmterr: /* Format error. */
    redisLog(REDIS_WARNING,"Bad file format reading the append only file: make a backup of your AOF file, then use ./redis-check-aof --fix <filename>");
    exit(1);
}