Redis源码解析（十五）---aof-appendonlyfile解析

/* AOF的下面的一些代码都用到了一个简单buffer缓存块来进行存储，存储了数据的一些改变操作记录，等到
	缓冲中的达到一定的数据规模时，在持久化地写入到一个文件中，redis采用的方式是append追加的形式，这意味
	每次追加都要调整存储的块的大小，但是不可能会有无限大小的块空间，所以redis在这里引入了块列表的概念，
	设定死一个块的大小，超过单位块大小，存入另一个块中,这里定义每个块的大小为10M. */
#define AOF_RW_BUF_BLOCK_SIZE (1024*1024*10)    /* 10 MB per block */

/* 标准的aof文件读写块 */
typedef struct aofrwblock {
	//当前文件块被使用了多少，空闲的大小
    unsigned long used, free;
    //具体存储内容，大小10M
    char buf[AOF_RW_BUF_BLOCK_SIZE];
} aofrwblock;

/* Append data to the AOF rewrite buffer, allocating new blocks if needed. */
/* 在缓冲区中追加数据，如果超出空间，会新申请一个缓冲块 */
void aofRewriteBufferAppend(unsigned char *s, unsigned long len) {
    listNode *ln = listLast(server.aof_rewrite_buf_blocks);
    //定位到缓冲区的最后一块，在最后一块的位置上进行追加写操作
    aofrwblock *block = ln ? ln->value : NULL;

    while(len) {
        /* If we already got at least an allocated block, try appending
         * at least some piece into it. */
        if (block) {
        	//如果当前的缓冲块的剩余空闲能支持len长度的内容时，直接写入
            unsigned long thislen = (block->free < len) ? block->free : len;
            if (thislen) {  /* The current block is not already full. */
                memcpy(block->buf+block->used, s, thislen);
                block->used += thislen;
                block->free -= thislen;
                s += thislen;
                len -= thislen;
            }
        }

        if (len) { /* First block to allocate, or need another block. */
            int numblocks;
			//如果不够的话，需要新创建，进行写操作
            block = zmalloc(sizeof(*block));
            block->free = AOF_RW_BUF_BLOCK_SIZE;
            block->used = 0;
            //还要把缓冲块追加到服务端的buffer列表中
            listAddNodeTail(server.aof_rewrite_buf_blocks,block);

            /* Log every time we cross more 10 or 100 blocks, respectively
             * as a notice or warning. */
            numblocks = listLength(server.aof_rewrite_buf_blocks);
            if (((numblocks+1) % 10) == 0) {
                int level = ((numblocks+1) % 100) == 0 ? REDIS_WARNING :
                                                         REDIS_NOTICE;
                redisLog(level,"Background AOF buffer size: %lu MB",
                    aofRewriteBufferSize()/(1024*1024));
            }
        }
    }
}

/* 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. */
/* 刷新缓存区的内容到磁盘中 */
void flushAppendOnlyFile(int force) {
    ssize_t nwritten;
    int sync_in_progress = 0;
    mstime_t latency;

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

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

    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.");
        }
    }
    /* 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 */

	//在进行写入操作的时候，还监听了延迟
    latencyStartMonitor(latency);
    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;

    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;
        }

        /* Lof the AOF write error and record the error code. */
        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 {
            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));
            }

            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 ftrunacate() 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 synched 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. */
            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). */
    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. */
    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;
    }
}

/* 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. */
/* 将数据库的内容按照键值，再次完全重写入文件中 */
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++) {
        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 */
        //遍历数据库中的每条记录，进行日志记录
        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 */
    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) {
        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;
}

/* 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!
 */
/* 后台进行AOF数据文件写入操作 */
int rewriteAppendOnlyFileBackground(void)

/* aof.c 中的API */
void aofRewriteBufferReset(void) /* 释放server中旧的buffer，并创建一份新的buffer */
unsigned long aofRewriteBufferSize(void) /* 返回当前AOF的buffer的总大小 */
void aofRewriteBufferAppend(unsigned char *s, unsigned long len) /* 在缓冲区中追加数据，如果超出空间，会新申请一个缓冲块 */
ssize_t aofRewriteBufferWrite(int fd) /* 将保存内存中的buffer内容写入到文件中，也是分块分块的写入 */
void aof_background_fsync(int fd) /* 开启后台线程进行文件同步操作 */
void stopAppendOnly(void) /* 停止追加数据操作,这里用的是一个命令模式 */
int startAppendOnly(void) /* 开启追加模式 */
void flushAppendOnlyFile(int force) /* 刷新缓存区的内容到磁盘中 */
sds catAppendOnlyGenericCommand(sds dst, int argc, robj **argv) /* 根据输入的字符串，进行参数包装，再次输出 */
sds catAppendOnlyExpireAtCommand(sds buf, struct redisCommand *cmd, robj *key, robj *seconds) /* 将过期等的命令都转化为PEXPIREAT命令，把时间转化为了绝对时间 */
void feedAppendOnlyFile(struct redisCommand *cmd, int dictid, robj **argv, int argc) /* 根据cmd的不同操作，进行命令的不同转化 */
struct redisClient *createFakeClient(void) /* 命令总是被客户端所执行的，因此要引入客户端的方法 */
void freeFakeClientArgv(struct redisClient *c) /* 释放客户端参数操作 */
void freeFakeClient(struct redisClient *c) /* 释放客户端参数操作 */
int loadAppendOnlyFile(char *filename) /* 加载AOF文件内容 */
int rioWriteBulkObject(rio *r, robj *obj) /* 写入bulk对象，分为LongLong对象，和普通的String对象 */
int rewriteListObject(rio *r, robj *key, robj *o) /* 写入List列表对象，分为ZIPLIST压缩列表和LINEDLIST普通链表操作 */
int rewriteSetObject(rio *r, robj *key, robj *o) /* 写入set对象数据 */
int rewriteSortedSetObject(rio *r, robj *key, robj *o) /* 写入排序好的set对象 */
static int rioWriteHashIteratorCursor(rio *r, hashTypeIterator *hi, int what) /* 写入哈希迭代器当前指向的对象 */
int rewriteHashObject(rio *r, robj *key, robj *o) /* 写入哈希字典对象 */
int rewriteAppendOnlyFile(char *filename) /* 将数据库的内容按照键值，再次完全重写入文件中 */
int rewriteAppendOnlyFileBackground(void) /* 后台进行AOF数据文件写入操作 */
void bgrewriteaofCommand(redisClient *c) /* 后台写AOF文件操作命令模式 */
void aofRemoveTempFile(pid_t childpid) /* 移除某次子线程ID为childpid所生产的aof文件 */
void aofUpdateCurrentSize(void) /* 更新当前aof文件的大小 */
void backgroundRewriteDoneHandler(int exitcode, int bysignal) /* 后台子线程写操作完成后的回调方法 */