3、AOF持久化
关键字:AOF持久化:文件写入与同步,AOF文件重写,数据一致性
与RDB持久化通过保存数据库中的键值对来记录数据库状态不同,AOF持久化是通过保存redis服务器所执行的写命令来记录数据库状态的
被写入AOF文件的所有命令都是以redis的命令请求协议格式保存的,因为redis的命令请求协议是纯文本格式,所以可以直接打开一个AOF文件,观察里面的内容
AOF文件初始会自动添加一个用于指定数据库的select命令。
服务器在启动时,可以通过载入和执行AOF文件中保存的命令来还原服务器关闭之前的数据库状态
AOF持久化的实现
AOF持久化功能的实现分为命令追加(append)、文件写入、文件同步(sync)三个步骤。
struct redisServer{
// ...
/* AOF persistence */
// AOF 状态(开启/关闭/可写)
int aof_state; /* REDIS_AOF_(ON|OFF|WAIT_REWRITE) */
// 所使用的 fsync 策略(每个写入/每秒/从不)
int aof_fsync; /* Kind of fsync() policy */
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. */
// 最后一次执行 BGREWRITEAOF 时, AOF 文件的大小
off_t aof_rewrite_base_size; /* AOF size on latest startup or rewrite. */
// AOF 文件的当前字节大小
off_t aof_current_size; /* AOF current size. */
//记录服务器是否延迟了bgrewriteaof即AOF重写命令,如果值为1 ,表示有AOF重写命令被延迟了
int aof_rewrite_scheduled; /* Rewrite once BGSAVE terminates. */
// 负责进行 AOF 重写的子进程 ID,如果没有执行,属性值为-1
pid_t aof_child_pid; /* PID if rewriting process */
// AOF 重写缓存链表,链接着多个缓存块
list *aof_rewrite_buf_blocks; /* Hold changes during an AOF rewrite. */
// AOF 缓冲区
sds aof_buf; /* AOF buffer, written before entering the event loop */
// AOF 文件的描述符
int aof_fd; /* File descriptor of currently selected AOF file */
// AOF 的当前目标数据库
int aof_selected_db; /* Currently selected DB in AOF */
// 推迟 write 操作的时间
time_t aof_flush_postponed_start; /* UNIX time of postponed AOF flush */
// 最后一直执行 fsync 的时间
time_t aof_last_fsync; /* UNIX time of last fsync() */
time_t aof_rewrite_time_last; /* Time used by last AOF rewrite run. */
// AOF 重写的开始时间
time_t aof_rewrite_time_start; /* Current AOF rewrite start time. */
// 最后一次执行 BGREWRITEAOF 的结果
int aof_lastbgrewrite_status; /* REDIS_OK or REDIS_ERR */
// 记录 AOF 的 write 操作被推迟了多少次
unsigned long aof_delayed_fsync; /* delayed AOF fsync() counter */
// 指示是否需要每写入一定量的数据,就主动执行一次 fsync()
int aof_rewrite_incremental_fsync;/* fsync incrementally while rewriting? */
int aof_last_write_status; /* REDIS_OK or REDIS_ERR */
int aof_last_write_errno; /* Valid if aof_last_write_status is ERR */
// ...
};
当AOF持久化功能处于打开状态(aof_state为REDIS_AOF_ON)时,服务器在执行完一个写命令之后,会以协议格式将被执行的写命令追加到服务器的aof_buf缓冲区的末尾
Redis的服务器进程就是一个事件循环(loop),这个循环中的文件事件负责接收客户端的命令请求,以及向客户端发送命令回复,而时间事件则负责执行像serverCron函数这样需要定时运行的函数
因为服务器在处理文件事件时可能会执行写命令,使得一些内容被追加到aof_buf缓冲区里面,所以在服务器每次结束一个事件循环之前,它都会调用flushAppendOnlyFile函数,考虑是否需要将aof_buf缓冲区中的内容写入和保存到AOF文件里面:
/* Write the append only file buffer on disk.
*
* 将 AOF 缓存写入到文件中。
*
* 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.
*
* 因为程序需要在回复客户端之前对 AOF 执行写操作。
* 而客户端能执行写操作的唯一机会就是在事件 loop 中,
* 因此,程序将所有 AOF 写累积到缓存中,
* 并在重新进入事件 loop 之前,将缓存写入到文件中。
*
* About the 'force' argument:
*
* 关于 force 参数:
*
* 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.
*
* 当 fsync 策略为每秒钟保存一次时,如果后台线程仍然有 fsync 在执行,
* 那么我们可能会延迟执行冲洗(flush)操作,
* 因为 Linux 上的 write(2) 会被后台的 fsync 阻塞。
*
* 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.
*
* 当这种情况发生时,说明需要尽快冲洗 aof 缓存,
* 程序会尝试在 serverCron() 函数中对缓存进行冲洗。
*
* However if force is set to 1 we'll write regardless of the background
* fsync.
*
* 不过,如果 force 为 1 的话,那么不管后台是否正在 fsync ,
* 程序都直接进行写入。
*/
#define AOF_WRITE_LOG_ERROR_RATE 30 /* Seconds between errors logging. */
void flushAppendOnlyFile(int force) {
ssize_t nwritten;
int sync_in_progress = 0;
// 缓冲区中没有任何内容,直接返回
if (sdslen(server.aof_buf) == 0) return;
// 策略为每秒 FSYNC
if (server.aof_fsync == AOF_FSYNC_EVERYSEC)
// 是否有 SYNC 正在后台进行?
sync_in_progress = bioPendingJobsOfType(REDIS_BIO_AOF_FSYNC) != 0;
// 每秒 fsync ,并且强制写入为假
if (server.aof_fsync == AOF_FSYNC_EVERYSEC && !force) {
/* With this append fsync policy we do background fsyncing.
*
* 当 fsync 策略为每秒钟一次时, fsync 在后台执行。
*
* If the fsync is still in progress we can try to delay
* the write for a couple of seconds.
*
* 如果后台仍在执行 FSYNC ,那么我们可以延迟写操作一两秒
* (如果强制执行 write 的话,服务器主线程将阻塞在 write 上面)
*/
if (sync_in_progress) {
// 有 fsync 正在后台进行 。。。
if (server.aof_flush_postponed_start == 0) {
/* No previous write postponinig, remember that we are
* postponing the flush and return.
*
* 前面没有推迟过 write 操作,这里将推迟写操作的时间记录下来
* 然后就返回,不执行 write 或者 fsync
*/
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.
*
* 如果之前已经因为 fsync 而推迟了 write 操作
* 但是推迟的时间不超过 2 秒,那么直接返回
* 不执行 write 或者 fsync
*/
return;
}
/* Otherwise fall trough, and go write since we can't wait
* over two seconds.
*
* 如果后台还有 fsync 在执行,并且 write 已经推迟 >= 2 秒
* 那么执行写操作(write 将被阻塞)
*/
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.
*
* 执行到这里,程序会对 AOF 文件进行写入。
*
* 清零延迟 write 的时间记录
*/
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.
*
* 执行单个 write 操作,如果写入设备是物理的话,那么这个操作应该是原子的
*
* 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
*
* 当然,如果出现像电源中断这样的不可抗现象,那么 AOF 文件也是可能会出现问题的
* 这时就要用 redis-check-aof 程序来进行修复。
*/
nwritten = write(server.aof_fd,server.aof_buf,sdslen(server.aof_buf));
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. */
// 将日志的记录频率限制在每行 AOF_WRITE_LOG_ERROR_RATE 秒
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. */
// 如果写入出错,那么尝试将该情况写入到日志里面
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));
}
// 尝试移除新追加的不完整内容
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. */
// 处理写入 AOF 文件时出现的错误
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. */
// 写入成功,更新最后写入状态
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;
}
}
// 更新写入后的 AOF 文件大小
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 AOF 缓存的大小足够小的话,那么重用这个缓存,
* 否则的话,释放 AOF 缓存。
*/
if ((sdslen(server.aof_buf)+sdsavail(server.aof_buf)) < 4000) {
// 清空缓存中的内容,等待重用
sdsclear(server.aof_buf);
} else {
// 释放缓存
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 选项为开启状态,
* 并且有 BGSAVE 或者 BGREWRITEAOF 正在进行的话,
* 那么不执行 fsync
*/
if (server.aof_no_fsync_on_rewrite &&
(server.aof_child_pid != -1 || server.rdb_child_pid != -1))
return;
/* Perform the fsync if needed. */
// 总是执行 fsnyc
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 */
// 更新最后一次执行 fsnyc 的时间
server.aof_last_fsync = server.unixtime;
// 策略为每秒 fsnyc ,并且距离上次 fsync 已经超过 1 秒
} else if ((server.aof_fsync == AOF_FSYNC_EVERYSEC &&
server.unixtime > server.aof_last_fsync)) {
// 放到后台执行
if (!sync_in_progress) aof_background_fsync(server.aof_fd);
// 更新最后一次执行 fsync 的时间
server.aof_last_fsync = server.unixtime;
}
// 其实上面无论执行 if 部分还是 else 部分都要更新 fsync 的时间
// 可以将代码挪到下面来
// server.aof_last_fsync = server.unixtime;
}
flushAppendOnlyFile函数的行为由服务器配置的appendfsync选项的值来决定“
always:服务器在每个事件循环都要将aof_buf缓冲区中的所有内容写入并同步到AOF文件,效率最慢但最安全
everysec:服务器在每个事件循环都要将aof_buf缓冲区中的所有内容写入到AOF文件,如果上次同步AOF文件的时间距离现在超过1s,那么再次对AOF文件进行同步,并且这个同步操作是由一个线程专门负责执行的
no:服务器在每个事件循环都要将aof_buf缓冲区中的所有内容写入到AOF文件,但不对AOF文件进行同步,何时同步由操作系统决定,速度最快,安全性最低
- 默认为everysec
用户调用write函数,将一些数据写入到文件的时候,操作系统通常会将写入数据暂时保存在一个内存缓冲区中,等到缓冲区的空间被填满、或者超过了指定的时限之后,才真正地将缓冲区中的数据写入到磁盘。
虽然提高了效率,但为写入数据带来了安全问题,如果计算机发生停机,那么保存在内存缓冲区里面的写入数据将会丢失。
redis提供了fsync和fdatasync两个同步函数,它们可以强制让操作系统立即将缓冲区中的数据写入到硬盘中,从而确保写入数据的安全性。
AOF文件的载入与数据还原
redis读取AOF文件并还原数据库状态的详细步骤如下:
创建一个不带网络连接的伪客户端(fake client):因为redis的命令只能在客户端上下文中执行,而载入AOF文件时所使用的命令直接来源于AOF文件而不是网络连接,所以服务器使用了一个没有网络连接的伪客户端来执行AOF文件保存的写命令,伪客户端执行命令的效果和带网络连接的客户端执行命令的效果完全一样。
从AOF文件中分析并读取一条写命令
- 使用伪客户端执行被读出的写命令
- 一直执行步骤2和步骤3,直到AOF文件中的所有写命令都被处理完毕为止
AOF重写
为了解决AOF文件体积膨胀问题,redis提供了AOF文件重写(rewrite)功能。通过该功能,Redis服务器可以创建一个新的AOF文件来替代现有的AOF文件,新旧两个AOF文件所保存的数据库状态相同,但新AOF文件不会包含任何浪费空间的冗余命令,所以新AOF文件的体积通常会比旧AOF文件体积要小得多。
AOF文件重写并不需要对现有的AOF文件进行任何读取、分析或写入操作,这个功能是通过读取服务器当前的数据库状态来实现的。
首先从数据库中读取键现在的值,然后用一条命令去记录键值对,代替之前记录这个键值对的多条命令,这就是AOF重写功能的实现原理。
rewriteAppendOnlyFile函数的实现:
/* Write a sequence of commands able to fully rebuild the dataset into
* "filename". Used both by REWRITEAOF and BGREWRITEAOF.
*
* 将一个足以还原当前数据集的命令序列写入到 filename 指定的文件中。
*
* 这个函数被 REWRITEAOF 和 BGREWRITEAOF 两个命令调用。
* (REWRITEAOF 似乎已经是一个废弃的命令)
*
* 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.
*
* 为了最小化重建数据集所需执行的命令数量,
* Redis 会尽可能地使用接受可变参数数量的命令,比如 RPUSH 、SADD 和 ZADD 等。
*
* 不过单个命令每次处理的元素数量不能超过 REDIS_AOF_REWRITE_ITEMS_PER_CMD 。
*/
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.
*
* 创建临时文件
*
* 注意这里创建的文件名和 rewriteAppendOnlyFileBackground() 创建的文件名稍有不同
*/
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;
}
// 初始化文件 io
rioInitWithFile(&aof,fp);
// 设置每写入 REDIS_AOF_AUTOSYNC_BYTES 字节
// 就执行一次 FSYNC
// 防止缓存中积累太多命令内容,造成 I/O 阻塞时间过长
if (server.aof_rewrite_incremental_fsync)
rioSetAutoSync(&aof,REDIS_AOF_AUTOSYNC_BYTES);
// 遍历所有数据库
for (j = 0; j < server.dbnum; j++) {
char selectcmd[] = "*2\r\n$6\r\nSELECT\r\n";
redisDb *db = server.db+j;
// 指向键空间
dict *d = db->dict;
if (dictSize(d) == 0) continue;
// 创建键空间迭代器
di = dictGetSafeIterator(d);
if (!di) {
fclose(fp);
return REDIS_ERR;
}
/* SELECT the new DB
*
* 首先写入 SELECT 命令,确保之后的数据会被插入到正确的数据库上
*/
if (rioWrite(&aof,selectcmd,sizeof(selectcmd)-1) == 0) goto werr;
if (rioWriteBulkLongLong(&aof,j) == 0) goto werr;
/* Iterate this DB writing every entry
*
* 遍历数据库所有键,并通过命令将它们的当前状态(值)记录到新 AOF 文件中
*/
while((de = dictNext(di)) != NULL) {
sds keystr;
robj key, *o;
long long expiretime;
// 取出键
keystr = dictGetKey(de);
// 取出值
o = dictGetVal(de);
initStaticStringObject(key,keystr);
// 取出过期时间
expiretime = getExpire(db,&key);
/* If this key is already expired skip it
*
* 如果键已经过期,那么跳过它,不保存
*/
if (expiretime != -1 && expiretime < now) continue;
/* Save the key and associated value
*
* 根据值的类型,选择适当的命令来保存值
*/
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
*
* 保存键的过期时间
*/
if (expiretime != -1) {
char cmd[]="*3\r\n$9\r\nPEXPIREAT\r\n";
// 写入 PEXPIREAT expiretime 命令
if (rioWrite(&aof,cmd,sizeof(cmd)-1) == 0) goto werr;
if (rioWriteBulkObject(&aof,&key) == 0) goto werr;
if (rioWriteBulkLongLong(&aof,expiretime) == 0) goto werr;
}
}
// 释放迭代器
dictReleaseIterator(di);
}
/* Make sure data will not remain on the OS's output buffers */
// 冲洗并关闭新 AOF 文件
if (fflush(fp) == EOF) goto werr;
if (aof_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.
*
* 原子地改名,用重写后的新 AOF 文件覆盖旧 AOF 文件
*/
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;
}
AOF后台重写
将AOF重写程序放到子进程里执行,可以达到两个目的:
- 子进程进行AOF重写期间,服务器进程(父进程)可以继续处理命令请求
- 子进程带有服务器进程的数据副本,使用子进程而不是线程,可以在避免使用锁的情况下,保证数据的安全性
不过,子进程在进行AOF重写期间,服务器进程还需要继续处理命令请求,而新的命令可能会对所有的数据库状态进行修改,从而使得服务器当前的数据库状态和重写后的AOF文件所保存的数据库状态不一致。
为了解决这种数据不一致问题,redis服务器设置了一个AOF重写缓冲区,这个缓冲区在服务器创建子进程之后开始使用,当redis服务器执行完一个写命令之后,它会同时将这个写命令发送给AOF缓冲区和AOF重写缓冲区。
这也就是说,在子进程执行AOF重写期间,服务器进程需要执行以下三个工作:
- 执行客户端发来的命令
- 将执行后的写命令追加到AOF缓冲区
- 将执行后的写命令追加到AOF重写缓冲区
这样一来,可以保证:
- AOF缓冲区带内容会定期被写入和同步到AOF文件,对现有AOF文件的处理工作会如常进行
- 从创建子进程开始,服务器执行的所有写命令都被记录到AOF重写缓冲区里
当子进程完成AOF重写工作之后,它会向父进程发送一个信号,父进程在接到该信号之后,会调用一个 信号处理函数 ,并执行以下工作:
- 将AOF重写缓冲区中的所有内容写入到新AOF文件中,这时新AOF文件所保存的数据库状态和服务器当前的数据库状态一致
- 对新的AOF文件进行改名,原子地(atomic)覆盖现有的AOF文件,完成新旧两个AOF文件的替换
信号处理函数 执行完毕之后,父进程就可以继续像往常一样接受命令请求了。
在整个AOF后台重写过程中,只有 信号处理函数 执行时会对服务器进程(父进程)造成阻塞,其他时候,AOF后台重写都不会阻塞父进程,这将AOF重写对服务器性能造成的影响降到了最低。
rewriteAppendOnlyFileBackground函数的实现:
/* This is how rewriting of the append only file in background works:
*
* 以下是后台重写 AOF 文件(BGREWRITEAOF)的工作步骤:
*
* 1) The user calls BGREWRITEAOF
* 用户调用 BGREWRITEAOF
*
* 2) Redis calls this function, that forks():
* Redis 调用这个函数,它执行 fork() :
*
* 2a) the child rewrite the append only file in a temp file.
* 子进程在临时文件中对 AOF 文件进行重写
*
* 2b) the parent accumulates differences in server.aof_rewrite_buf.
* 父进程将新输入的写命令追加到 server.aof_rewrite_buf 中
*
* 3) When the child finished '2a' exists.
* 当步骤 2a 执行完之后,子进程结束
*
* 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!
*
* 父进程会捕捉子进程的退出信号,
* 如果子进程的退出状态是 OK 的话,
* 那么父进程将新输入命令的缓存追加到临时文件,
* 然后使用 rename(2) 对临时文件改名,用它代替旧的 AOF 文件,
* 至此,后台 AOF 重写完成。
*/
int rewriteAppendOnlyFileBackground(void) {
pid_t childpid;
long long start;
// 已经有进程在进行 AOF 重写了
if (server.aof_child_pid != -1) return REDIS_ERR;
// 记录 fork 开始前的时间,计算 fork 耗时用
start = ustime();
if ((childpid = fork()) == 0) {
char tmpfile[256];
/* Child */
// 关闭网络连接 fd
closeListeningSockets(0);
// 为进程设置名字,方便记认
redisSetProcTitle("redis-aof-rewrite");
// 创建临时文件,并进行 AOF 重写
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));
}
// 发送重写成功信号
exitFromChild(0);
} else {
// 发送重写失败信号
exitFromChild(1);
}
} else {
/* Parent */
// 记录执行 fork 所消耗的时间
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);
// 记录 AOF 重写的信息
server.aof_rewrite_scheduled = 0;
server.aof_rewrite_time_start = time(NULL);
server.aof_child_pid = childpid;
// 关闭字典自动 rehash
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.
*
* 将 aof_selected_db 设为 -1 ,
* 强制让 feedAppendOnlyFile() 下次执行时引发一个 SELECT 命令,
* 从而确保之后新添加的命令会设置到正确的数据库中
*/
server.aof_selected_db = -1;
replicationScriptCacheFlush();
return REDIS_OK;
}
return REDIS_OK; /* unreached */
}