Redis源码分析--AOF持久化
AOF持久化：
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。
一、结构实现：
redisServer中有关AOF持久化的字段：
list *aof_rewrite_buf_blocks; /* Hold changes during an AOF rewrite. */
sds aof_buf; /* AOF buffer, written before entering the event loop */
pid_t aof_child_pid; /* PID if rewriting process */
- L1：AOF缓冲区；
- L2：AOF重写缓冲区；
- L3：fork一个子进程来重写AOF文件，如果该字段不为-1，说明正在进行AOF重写；
二、命令追加：
服务器在执行一个命令后，将命令写入AOF缓冲区中，由命令传播[2]实现；
三、命令写入与同步：
在事件循环中，服务器可能会执行多条命令，AOF缓冲区中被插入许多内容。在进入下一次epoll_wait(2)调用阻塞时，我们需要将AOF缓冲区的内容写入到AOF文件中。
void aeMain(aeEventLoop *eventLoop) {
eventLoop->stop = 0;
while (!eventLoop->stop) {
if (eventLoop->beforesleep != NULL)
eventLoop->beforesleep(eventLoop);
aeProcessEvents(eventLoop, AE_ALL_EVENTS);
}
}
- L4：执行命令写入函数flushAppendOnlyFile：
void flushAppendOnlyFile(int force) {
ssize_t nwritten;
int sync_in_progress = 0;
if (sdslen(server.aof_buf) == 0) return;
if (server.aof_fsync == AOF_FSYNC_EVERYSEC)
/* 是否有fsync正在执行 */
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.");
}
}
/* If you are following this code path, then we are going to write so
* set reset the postponed flush sentinel to zero. */
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.
* 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 we
/* 服务器尝试一次性写入，如果不行，那么就放弃 */
nwritten = write(server.aof_fd,server.aof_buf,sdslen(server.aof_buf));
if (nwritten != (signed)sdslen(server.aof_buf)) {
/* Ooops, we are in troubles. The best thing to do for now is
* aborting instead of giving the illusion that everything is
* working as expected. */
if (nwritten == -1) {
redisLog(REDIS_WARNING,"Exiting on error writing to the append-only file: %s",strerror(errno));
} else {
redisLog(REDIS_WARNING,"Exiting on short write while writing to "
"the append-only file: %s (nwritten=%ld, "
"expected=%ld)",
strerror(errno),
(long)nwritten,
(long)sdslen(server.aof_buf));
/* 如果只写入了一部分，使用ftruncate函数放弃写入的部分 */
if (ftruncate(server.aof_fd, server.aof_current_size) == -1) {
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));
}
}
exit(1);
}
/* 一次性写入成功，更新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). */
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. */
/* 两种模式的差异 */
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 */
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;
}
}
- L41~L65：我们希望一次性写入AOF缓冲区中所有内容，否则就放弃这次写入；
- K84~L95：AOF持久化的同步[2]选项有三种：
- ALWAYS：每次事件循环中写入AOF缓冲区中所有内容，并进行一次同步（fsync）；如果出现故障停机，会丢失一个事件循环中执行的命令；
- EVERYSEC：每次事件循环中写入AOF缓冲区中所有内容，并且每秒都要在子线程中对AOF文件进行一次同步；如果出现故障停机，会丢失1s内执行的命令；
- NO：每次事件循环中写入AOF缓冲区中所有内容，同步则取决于操作系统何时执行；
四、AOF重写：
AOF重写（rewrite）可以解决AOF文件体积膨胀的问题：重写后的新AOF文件与旧AOF文件所保存的数据库状态一致，但新AOF文件不会包含任何浪费空间的冗余命令；
当AOF文件在后台重写时（BGREWRITEAOF）会创建一个新AOF文件，服务器可以继续处理命令请求（并更新旧的AOF文件），此时可能就会出现AOF文件和现有数据库状态的不一致。为了解决这种不一致，服务器会在AOF重写时，除了将命令插入AOF缓冲区（更新旧AOF文件），也会插入AOF重写缓冲区。当AOF文件。
服务器在执行bgrewriteaofCommand时执行rewriteAppendOnlyFileBackground函数：
-
Note：服务器后台执行BGSAVE命令时，BGREWRITEAOF命令会被推迟到BGSAVE命令执行完毕后执行，可以在serverCron中看到这一点；
这么做的原因是这两个命令都会执行大量的磁盘写入操作，同时执行这两个命令的性能不好；
int rewriteAppendOnlyFileBackground(void) {
pid_t childpid;
long long start;
if (server.aof_child_pid != -1) return REDIS_ERR;
start = ustime();
if ((childpid = fork()) == 0) {
char tmpfile[256];
/* Child */
closeListeningSockets(0);
redisSetProcTitle("redis-aof-rewrite");
snprintf(tmpfile,256,"temp-rewriteaof-bg-%d.aof", (int) getpid());
/* 执行重写操作 */
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));
}
/* 给父进程发送信号 */
exitFromChild(0);
} else {
/* 给父进程发送信号 */
exitFromChild(1);
}
} else {
/* Parent */
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);
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. */
/* 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 */
}
-
L15：子进程执行重写操作，遍历server的所有数据库，根据数据库状态来执行命令，从而减小AOF文件体积；
-
L24：子进程重写完成后用信号通知父进程，父进程仍有其他操作：
上文提到AOF后台重写时，服务器接收新的命令请求，可能出现新旧AOF文件出现数据不一致的状况；所以额外引入AOF重写缓冲区；
看一下父进程的操作（在serverCron中调用）：
void backgroundRewriteDoneHandler(int exitcode, int bysignal) {
if (!bysignal && exitcode == 0) {
int newfd, oldfd;
char tmpfile[256];
long long now = ustime();
redisLog(REDIS_NOTICE,
"Background AOF rewrite terminated with success");
/* Flush the differences accumulated by the parent to the
* rewritten AOF. */
snprintf(tmpfile,256,"temp-rewriteaof-bg-%d.aof",
(int)server.aof_child_pid);
/* AOF文件写入完成，打开文件*/
newfd = open(tmpfile,O_WRONLY|O_APPEND);
if (newfd == -1) {
redisLog(REDIS_WARNING,
"Unable to open the temporary AOF produced by the child: %s", strerror(errno));
goto cleanup;
}
/* 将AOF重写缓冲区中内容写入AOF文件 */
if (aofRewriteBufferWrite(newfd) == -1) {
redisLog(REDIS_WARNING,
"Error trying to flush the parent diff to the rewritten AOF: %s", strerror(errno));
close(newfd);
goto cleanup;
}
redisLog(REDIS_NOTICE,
"Parent diff successfully flushed to the rewritten AOF (%lu bytes)", aofRewriteBufferSize());
/* The only remaining thing to do is to rename the temporary file to
* the configured file and switch the file descriptor used to do AOF
* writes. We don't want close(2) or rename(2) calls to block the
* server on old file deletion.
*
* There are two possible scenarios:
*
* 1) AOF is DISABLED and this was a one time rewrite. The temporary
* file will be renamed to the configured file. When this file already
* exists, it will be unlinked, which may block the server.
*
* 2) AOF is ENABLED and the rewritten AOF will immediately start
* receiving writes. After the temporary file is renamed to the
* configured file, the original AOF file descriptor will be closed.
* Since this will be the last reference to that file, closing it
* causes the underlying file to be unlinked, which may block the
* server.
*
* To mitigate the blocking effect of the unlink operation (either
* caused by rename(2) in scenario 1, or by close(2) in scenario 2), we
* use a background thread to take care of this. First, we
* make scenario 1 identical to scenario 2 by opening the target file
* when it exists. The unlink operation after the rename(2) will then
* be executed upon calling close(2) for its descriptor. Everything to
* guarantee atomicity for this switch has already happened by then, so
* we don't care what the outcome or duration of that close operation
* is, as long as the file descriptor is released again. */
if (server.aof_fd == -1) {
/* AOF disabled */
/* Don't care if this fails: oldfd will be -1 and we handle that.
* One notable case of -1 return is if the old file does
* not exist. */
oldfd = open(server.aof_filename,O_RDONLY|O_NONBLOCK);
} else {
/* AOF enabled */
oldfd = -1; /* We'll set this to the current AOF filedes later. */
}
/* Rename the temporary file. This will not unlink the target file if
* it exists, because we reference it with "oldfd". */
if (rename(tmpfile,server.aof_filename) == -1) {
redisLog(REDIS_WARNING,
"Error trying to rename the temporary AOF file: %s", strerror(errno));
close(newfd);
if (oldfd != -1) close(oldfd);
goto cleanup;
}
if (server.aof_fd == -1) {
/* AOF disabled, we don't need to set the AOF file descriptor
* to this new file, so we can close it. */
close(newfd);
} else {
/* 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)
aof_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();
}
server.aof_lastbgrewrite_status = REDIS_OK;
redisLog(REDIS_NOTICE, "Background AOF rewrite finished successfully");
/* Change state from WAIT_REWRITE to ON if needed */
if (server.aof_state == REDIS_AOF_WAIT_REWRITE)
server.aof_state = REDIS_AOF_ON;
/* Asynchronously close the overwritten AOF. */
/* 异步关闭旧 AOF 文件 */
if (oldfd != -1) bioCreateBackgroundJob(REDIS_BIO_CLOSE_FILE,(void*)(long)oldfd,NULL,NULL);
redisLog(REDIS_VERBOSE,
"Background AOF rewrite signal handler took %lldus", ustime()-now);
} else if (!bysignal && exitcode != 0) {
server.aof_lastbgrewrite_status = REDIS_ERR;
redisLog(REDIS_WARNING,
"Background AOF rewrite terminated with error");
} else {
server.aof_lastbgrewrite_status = REDIS_ERR;
redisLog(REDIS_WARNING,
"Background AOF rewrite terminated by signal %d", bysignal);
}
cleanup:
aofRewriteBufferReset();
aofRemoveTempFile(server.aof_child_pid);
server.aof_child_pid = -1;
server.aof_rewrite_time_last = time(NULL)-server.aof_rewrite_time_start;
server.aof_rewrite_time_start = -1;
/* Schedule a new rewrite if we are waiting for it to switch the AOF ON. */
if (server.aof_state == REDIS_AOF_WAIT_REWRITE)
server.aof_rewrite_scheduled = 1;
}
- L22：AOF重写缓冲区的内容的写入，（该缓冲区也是在命令传播中被追加的[1]）；
- L32~L58、L111：异步关闭旧AOF文件描述符，避免阻塞！
