环境说明:redis源码版本 5.0.3;我在阅读源码过程做了注释,git地址:https://gitee.com/xiaoangg/redis_annotation
如有错误欢迎指正
参考书籍:《redis的设计与实现》
文章推荐:
redis源码阅读-一--sds简单动态字符串
redis源码阅读--二-链表
redis源码阅读--三-redis散列表的实现
redis源码浅析--四-redis跳跃表的实现
redis源码浅析--五-整数集合的实现
redis源码浅析--六-压缩列表
redis源码浅析--七-redisObject对象(下)(内存回收、共享)
redis源码浅析--八-数据库的实现
redis源码浅析--九-RDB持久化
redis源码浅析--十-AOF(append only file)持久化
redis源码浅析--十一.事件(上)文件事件
redis源码浅析--十一.事件(下)时间事件
redis源码浅析--十二.单机数据库的实现-客户端
redis源码浅析--十三.单机数据库的实现-服务端 - 时间事件
redis源码浅析--十三.单机数据库的实现-服务端 - redis服务器的初始化
redis源码浅析--十四.多机数据库的实现(一)--新老版本复制功能的区别与实现原理
redis源码浅析--十四.多机数据库的实现(二)--复制的实现SLAVEOF、PSYNY
redis源码浅析--十五.哨兵sentinel的设计与实现
redis源码浅析--十六.cluster集群的设计与实现
redis源码浅析--十七.发布与订阅的实现
redis源码浅析--十八.事务的实现
redis源码浅析--十九.排序的实现
redis源码浅析--二十.BIT MAP的实现
redis源码浅析--二十一.慢查询日志的实现
redis源码浅析--二十二.监视器的实现
目录
一.命令请求的执行过程
一个命令请求从发送到获得回复的过程中,客户端和服务器需要完成一系列操作。
举个例子:
1) 客户端向服务器发送命令请求SET KEY VALUE。
2)服务器接收并处理客户端发来的命令请求SETKEYVALUE,在数据库中进行设置操作,并产生命令回复OK。
3)服务器将命令回复OK发送给客户端。
4)客户端接收服务器返回的命令回复OK,并将这个回复打印给用户观看。
1.客户端发送命令请求
当用户在客户端中键入一个命令请求时,客户端会将这个命令请求转换成协议格式,然后通过连接到服务器的套接字,将协议格式的命令请求发送给服务器;
格式命令行的源码位于hiredis.c/redisFormatSdsCommandArgv
/**
* 格式化redis 命令
*/
/* Format a command according to the Redis protocol using an sds string and
* sdscatfmt for the processing of arguments. This function takes the
* number of arguments, an array with arguments and an array with their
* lengths. If the latter is set to NULL, strlen will be used to compute the
* argument lengths.
*/
int redisFormatSdsCommandArgv(sds *target, int argc, const char **argv,
const size_t *argvlen)
{
sds cmd;
unsigned long long totlen;
int j;
size_t len;
/* Abort on a NULL target */
if (target == NULL)
return -1;
/* Calculate our total size */
totlen = 1+countDigits(argc)+2;
for (j = 0; j < argc; j++) {
len = argvlen ? argvlen[j] : strlen(argv[j]);
totlen += bulklen(len);
}
/* Use an SDS string for command construction */
cmd = sdsempty();
if (cmd == NULL)
return -1;
/* We already know how much storage we need */
cmd = sdsMakeRoomFor(cmd, totlen);
if (cmd == NULL)
return -1;
/* Construct command */
cmd = sdscatfmt(cmd, "*%i\r\n", argc);
for (j=0; j < argc; j++) {
len = argvlen ? argvlen[j] : strlen(argv[j]);
cmd = sdscatfmt(cmd, "$%u\r\n", len);
cmd = sdscatlen(cmd, argv[j], len);
cmd = sdscatlen(cmd, "\r\n", sizeof("\r\n")-1);
}
assert(sdslen(cmd)==totlen);
*target = cmd;
return totlen;
}
如 SET KEY VALUE将被格式话为字符串*3\r\n$3\r\nSET\r\n$3\r\nKEY\r\n$5\r\nVALUE\r\n
2.服务端读取命令请求
当服务端和客户端之间的连接套接字可读时,服务端将调用命令处理函数执行命令处理工作;
读取命令函数(readQueryFromClient) 注册流程如下:
1.server.c/initServer()启动时监听socket ;
2.ae.c/aeCreateFileEvent()注册客户端连接请求处理函数acceptTcpHandler();
3.networking.c/createClient 创建一个新的客户端;
4.networking.c/readQueryFromClient 从连接中读取客户端发送的命令;
下面是对readQueryFromClient 函数做的注释:
/**
* 处理用户的命令请求
*/
void readQueryFromClient(aeEventLoop *el, int fd, void *privdata, int mask) {
client *c = (client*) privdata;
int nread, readlen;
size_t qblen;
UNUSED(el);
UNUSED(mask);
readlen = PROTO_IOBUF_LEN;
/* If this is a multi bulk request, and we are processing a bulk reply
* that is large enough, try to maximize the probability that the query
* buffer contains exactly the SDS string representing the object, even
* at the risk of requiring more read(2) calls. This way the function
* processMultiBulkBuffer() can avoid copying buffers to create the
* Redis Object representing the argument. */
if (c->reqtype == PROTO_REQ_MULTIBULK && c->multibulklen && c->bulklen != -1
&& c->bulklen >= PROTO_MBULK_BIG_ARG)
{
ssize_t remaining = (size_t)(c->bulklen+2)-sdslen(c->querybuf);
/* Note that the 'remaining' variable may be zero in some edge case,
* for example once we resume a blocked client after CLIENT PAUSE. */
if (remaining > 0 && remaining < readlen) readlen = remaining;
}
qblen = sdslen(c->querybuf);
//更新query_buf的峰值
if (c->querybuf_peak < qblen) c->querybuf_peak = qblen;
c->querybuf = sdsMakeRoomFor(c->querybuf, readlen); //扩容querybuf长度,确保可以存在新的命令请求;
//读取套接字中的命令请求;写入到query_buf中
nread = read(fd, c->querybuf+qblen, readlen);
if (nread == -1) {
if (errno == EAGAIN) {
return;
} else {
serverLog(LL_VERBOSE, "Reading from client: %s",strerror(errno));
freeClient(c);
return;
}
} else if (nread == 0) {
serverLog(LL_VERBOSE, "Client closed connection");
freeClient(c);
return;
} else if (c->flags & CLIENT_MASTER) {
/**
* 将查询缓冲区追加到主服务器的挂起(未应用)缓冲区。
* 我们稍后将使用这个缓冲区,以便在执行最后一个命令时应用字符串的副本。
*/
/* Append the query buffer to the pending (not applied) buffer
* of the master. We'll use this buffer later in order to have a
* copy of the string applied by the last command executed. */
c->pending_querybuf = sdscatlen(c->pending_querybuf,
c->querybuf+qblen,nread);
}
sdsIncrLen(c->querybuf,nread);//更新querybuf的长度
c->lastinteraction = server.unixtime;
if (c->flags & CLIENT_MASTER) c->read_reploff += nread;
server.stat_net_input_bytes += nread;
if (sdslen(c->querybuf) > server.client_max_querybuf_len) {
sds ci = catClientInfoString(sdsempty(),c), bytes = sdsempty();
bytes = sdscatrepr(bytes,c->querybuf,64);
serverLog(LL_WARNING,"Closing client that reached max query buffer length: %s (qbuf initial bytes: %s)", ci, bytes);
sdsfree(ci);
sdsfree(bytes);
freeClient(c);
return;
}
//todo 理解该段注释
/**
* 命令执行器
* 开始处理命令缓冲区。如果client是master,我们需要计算处理缓冲区前和处理缓冲去后的偏移量,
*/
/* Time to process the buffer. If the client is a master we need to
* compute the difference between the applied offset before and after
* processing the buffer, to understand how much of the replication stream
* was actually applied to the master state: this quantity, and its
* corresponding part of the replication stream, will be propagated to
* the sub-slaves and to the replication backlog. */
processInputBufferAndReplicate(c);
}
3.命令执行:查找命令实现
初始化命令表
redis初始化服务的时候,会将硬编码的命令填充到命令表中,执行流程:
1.service.c/initServerConfig
2.service.c/populateCommandTable
populateCommandTable 函数 会把硬编码的命令列表server.c/redisCommandTable 填充到server.commands中;
命令表是个字典,字典的键是命令的名字,字典的值则是server.h/redisCommand结构体;
redisComand结构记录一个命令的实现信息:
//命令格式 结构体
struct redisCommand {
char *name; //命令名称
redisCommandProc *proc; //名称处理函数
int arity; //命令的个数;假如该值是负N,代表该命令数大于等于N;注意命令本身也是一个参数
/**
* 字符串形似的标识值,用于记录该命令的属性;
* 如这个命令是读命令还是写命令,是否允许在数据载入时使用、是否允许在lua脚本中使用;
*/
char *sflags; /* Flags as string representation, one char per flag. */
/**
* 对sflags的二进制标识
*/
int flags; /* The actual flags, obtained from the 'sflags' field. */
/* Use a function to determine keys arguments in a command line.
* Used for Redis Cluster redirect. */
redisGetKeysProc *getkeys_proc;
/* What keys should be loaded in background when calling this command? */
int firstkey; /* The first argument that's a key (0 = no keys) */
int lastkey; /* The last argument that's a key */
int keystep; /* The step between first and last key */
//calls 服务器执行这个命令多少次;microseconds 服务区执行这个命令所耗费的总时长
long long microseconds, calls;
};
查找命令的实现
命令执行器做的做的第一件事就是根据客户端状态argv[0]参数,从命令表(command table)中查找命令的实现;
1.service.c/processCommand()
2.service.c/lookupCommand
lookupCommand命令查找函数就是从服务初始化的命令表中查找命令;
并将查找到命令赋值给客户端状态的cmd属性;
4.命令执行:执行预备操作
至此 服务器已经将执行命令函数redisCommand、参数argv,参数的个数agrc都保存到了客户端状态;
但是在执行命令之前,还要一些预备操作,以确保命令正确的执行:
- 检查命令是否存在,如客户端传入了一个不存在的命令;
- 检查参数数量是否正确,如set命令至少需要三个参数;
- 如果开启的身份验证,检查客户端是否通过了身份验证;
- 如果打开了maxmemory功能,执行命令前检查内存占用情况,并在有需要时进行内存回收,从而是要执行的命名顺利执行;
- 如果服务上一次执行了BGSAVE命令时出错,并且服务打开了stop-writes-on-bgsave-error功能,那么服务器拒绝写命令;
-
* 如果客户端SUBSCRIBE订阅频道或者正在用PSUBSCRITE订阅模式,客户端只允许行 * (P)SUBSCRIBE / (P)UNSUBSCRIBE / PING / QUIT
-
如果服务器因为执行lua脚本超时,那么只允许执行一部分命令;
-
.......
这里只列举了部分预检查操作,更多的检查操作可以阅读位于server.c/processCommand:
/**
* 处理命令请求
*/
/* If this function gets called we already read a whole
* command, arguments are in the client argv/argc fields.
* processCommand() execute the command or prepare the
* server for a bulk read from the client.
*
* If C_OK is returned the client is still alive and valid and
* other operations can be performed by the caller. Otherwise
* if C_ERR is returned the client was destroyed (i.e. after QUIT). */
int processCommand(client *c) {
/**
* QUIT命令需要单独处理
*/
/* The QUIT command is handled separately(单独的 分离的). Normal command procs will
* go through checking for replication and QUIT will cause trouble
* when FORCE_REPLICATION is enabled and would be implemented in
* a regular command proc. */
if (!strcasecmp(c->argv[0]->ptr,"quit")) {
addReply(c,shared.ok);
c->flags |= CLIENT_CLOSE_AFTER_REPLY;
return C_ERR;
}
//查找命令,并检查命令是否错误,如
/* Now lookup the command and check ASAP about trivial(琐碎的) error conditions
* such as wrong arity(参数数量), bad command name and so forth. */
c->cmd = c->lastcmd = lookupCommand(c->argv[0]->ptr);
//检查命令是否存在
if (!c->cmd) {
flagTransaction(c);
sds args = sdsempty();
int i;
for (i=1; i < c->argc && sdslen(args) < 128; i++)
args = sdscatprintf(args, "`%.*s`, ", 128-(int)sdslen(args), (char*)c->argv[i]->ptr);
addReplyErrorFormat(c,"unknown command `%s`, with args beginning with: %s",
(char*)c->argv[0]->ptr, args);
sdsfree(args);
return C_OK;
} else if ((c->cmd->arity > 0 && c->cmd->arity != c->argc) ||
(c->argc < -c->cmd->arity)) { //命令参数 数量不对
flagTransaction(c);
addReplyErrorFormat(c,"wrong number of arguments for '%s' command",
c->cmd->name);
return C_OK;
}
/*检查客户端是否通过了身份验证*/
/* Check if the user is authenticated */
if (server.requirepass && !c->authenticated && c->cmd->proc != authCommand)
{
flagTransaction(c);
addReply(c,shared.noautherr);
return C_OK;
}
/* If cluster is enabled perform the cluster redirection here.
* However we don't perform the redirection if:
* 1) The sender of this command is our master.
* 2) The command has no key arguments. */
if (server.cluster_enabled &&
!(c->flags & CLIENT_MASTER) &&
!(c->flags & CLIENT_LUA &&
server.lua_caller->flags & CLIENT_MASTER) &&
!(c->cmd->getkeys_proc == NULL && c->cmd->firstkey == 0 &&
c->cmd->proc != execCommand))
{
int hashslot;
int error_code;
clusterNode *n = getNodeByQuery(c,c->cmd,c->argv,c->argc,
&hashslot,&error_code);
if (n == NULL || n != server.cluster->myself) {
if (c->cmd->proc == execCommand) {
discardTransaction(c);
} else {
flagTransaction(c);
}
clusterRedirectClient(c,n,hashslot,error_code);
return C_OK;
}
}
/**
* 处理maxmemory指令。
*/
/* Handle the maxmemory directive.
*
* Note that we do not want to reclaim memory if we are here re-entering
* the event loop since there is a busy Lua script running in timeout
* condition, to avoid mixing the propagation of scripts with the
* propagation of DELs due to eviction. */
if (server.maxmemory && !server.lua_timedout) {
int out_of_memory = freeMemoryIfNeededAndSafe() == C_ERR;
/* freeMemoryIfNeeded may flush slave output buffers. This may result
* into a slave, that may be the active client, to be freed. */
if (server.current_client == NULL) return C_ERR;
/* It was impossible to free enough memory, and the command the client
* is trying to execute is denied during OOM conditions or the client
* is in MULTI/EXEC context? Error. */
if (out_of_memory &&
(c->cmd->flags & CMD_DENYOOM ||
(c->flags & CLIENT_MULTI && c->cmd->proc != execCommand))) {
flagTransaction(c);
addReply(c, shared.oomerr);
return C_OK;
}
}
/* Don't accept write commands if there are problems persisting on disk
* and if this is a master instance. */
int deny_write_type = writeCommandsDeniedByDiskError();
if (deny_write_type != DISK_ERROR_TYPE_NONE &&
server.masterhost == NULL &&
(c->cmd->flags & CMD_WRITE ||
c->cmd->proc == pingCommand))
{
flagTransaction(c);
if (deny_write_type == DISK_ERROR_TYPE_RDB)
addReply(c, shared.bgsaveerr);
else
addReplySds(c,
sdscatprintf(sdsempty(),
"-MISCONF Errors writing to the AOF file: %s\r\n",
strerror(server.aof_last_write_errno)));
return C_OK;
}
/* Don't accept write commands if there are not enough good slaves and
* user configured the min-slaves-to-write option. */
if (server.masterhost == NULL &&
server.repl_min_slaves_to_write &&
server.repl_min_slaves_max_lag &&
c->cmd->flags & CMD_WRITE &&
server.repl_good_slaves_count < server.repl_min_slaves_to_write)
{
flagTransaction(c);
addReply(c, shared.noreplicaserr);
return C_OK;
}
/* Don't accept write commands if this is a read only slave. But
* accept write commands if this is our master. */
if (server.masterhost && server.repl_slave_ro &&
!(c->flags & CLIENT_MASTER) &&
c->cmd->flags & CMD_WRITE)
{
addReply(c, shared.roslaveerr);
return C_OK;
}
/**
* 如果客户端SUBSCRIBE订阅频道或者正在用PSUBSCRITE订阅模式,客户端只孕育执行
* (P)SUBSCRIBE / (P)UNSUBSCRIBE / PING / QUIT
*/
/* Only allow SUBSCRIBE and UNSUBSCRIBE in the context of Pub/Sub */
if (c->flags & CLIENT_PUBSUB &&
c->cmd->proc != pingCommand &&
c->cmd->proc != subscribeCommand &&
c->cmd->proc != unsubscribeCommand &&
c->cmd->proc != psubscribeCommand &&
c->cmd->proc != punsubscribeCommand) {
addReplyError(c,"only (P)SUBSCRIBE / (P)UNSUBSCRIBE / PING / QUIT allowed in this context");
return C_OK;
}
/* Only allow commands with flag "t", such as INFO, SLAVEOF and so on,
* when slave-serve-stale-data is no and we are a slave with a broken
* link with master. */
if (server.masterhost && server.repl_state != REPL_STATE_CONNECTED &&
server.repl_serve_stale_data == 0 &&
!(c->cmd->flags & CMD_STALE))
{
flagTransaction(c);
addReply(c, shared.masterdownerr);
return C_OK;
}
/* Loading DB? Return an error if the command has not the
* CMD_LOADING flag. */
if (server.loading && !(c->cmd->flags & CMD_LOADING)) {
addReply(c, shared.loadingerr);
return C_OK;
}
/**
* 服务器因为执行lua脚本超时,
*/
/* Lua script too slow? Only allow a limited number of commands. */
if (server.lua_timedout &&
c->cmd->proc != authCommand &&
c->cmd->proc != replconfCommand &&
!(c->cmd->proc == shutdownCommand &&
c->argc == 2 &&
tolower(((char*)c->argv[1]->ptr)[0]) == 'n') &&
!(c->cmd->proc == scriptCommand &&
c->argc == 2 &&
tolower(((char*)c->argv[1]->ptr)[0]) == 'k'))
{
flagTransaction(c);
addReply(c, shared.slowscripterr);
return C_OK;
}
/* Exec the command */
if (c->flags & CLIENT_MULTI &&
c->cmd->proc != execCommand && c->cmd->proc != discardCommand &&
c->cmd->proc != multiCommand && c->cmd->proc != watchCommand)
{
queueMultiCommand(c);
addReply(c,shared.queued);
} else {
call(c,CMD_CALL_FULL);
c->woff = server.master_repl_offset;
if (listLength(server.ready_keys))
handleClientsBlockedOnKeys();
}
return C_OK;
}
5.命令执行:调用命令实现函数
命令执行的核心函数位于server.c/call方法;
前面的几步中,服务器已经将命令保存到了客户端状态的cmd属性了,参数保存到了argc和argv属性里;
所以可以将客户端状态传入命令的实现函数执行;client->cmd->proc(client);
命令的实现函数产生的相应的命令回复,这些回复会保存到客户端状态的buf属性和reply属性;
6.命令执行:执行后续工作
执行完命令后,服务器还会执行一些后续操作:
- 是否开启慢日志,写慢日志
- 记录命令执行次数和执行总时长,会被记录到redisCommand结构的microseconds, calls属性;
- 如何开始了aof持久化,写入aof缓冲区
- 其他服务正在复制这个服务,将这个命令传播给所有 slave服务器
server.c/call代码如下:
//call 是执行命令的核心方法
/* Call() is the core of Redis execution of a command.
*
* The following flags can be passed:
* CMD_CALL_NONE No flags.
* CMD_CALL_SLOWLOG Check command speed and log in the slow log if needed.
* CMD_CALL_STATS Populate command stats.
* CMD_CALL_PROPAGATE_AOF Append command to AOF if it modified the dataset
* or if the client flags are forcing propagation.
* CMD_CALL_PROPAGATE_REPL Send command to salves if it modified the dataset
* or if the client flags are forcing propagation.
* CMD_CALL_PROPAGATE Alias for PROPAGATE_AOF|PROPAGATE_REPL.
* CMD_CALL_FULL Alias for SLOWLOG|STATS|PROPAGATE.
*
* The exact propagation behavior depends on the client flags.
* Specifically:
*
* 1. If the client flags CLIENT_FORCE_AOF or CLIENT_FORCE_REPL are set
* and assuming the corresponding CMD_CALL_PROPAGATE_AOF/REPL is set
* in the call flags, then the command is propagated even if the
* dataset was not affected by the command.
* 2. If the client flags CLIENT_PREVENT_REPL_PROP or CLIENT_PREVENT_AOF_PROP
* are set, the propagation into AOF or to slaves is not performed even
* if the command modified the dataset.
*
* Note that regardless of the client flags, if CMD_CALL_PROPAGATE_AOF
* or CMD_CALL_PROPAGATE_REPL are not set, then respectively AOF or
* slaves propagation will never occur.
*
* Client flags are modified by the implementation of a given command
* using the following API:
*
* forceCommandPropagation(client *c, int flags);
* preventCommandPropagation(client *c);
* preventCommandAOF(client *c);
* preventCommandReplication(client *c);
*
*/
void call(client *c, int flags) {
long long dirty, start, duration;
int client_old_flags = c->flags;
struct redisCommand *real_cmd = c->cmd;
/* Sent the command to clients in MONITOR mode, only if the commands are
* not generated from reading an AOF. */
if (listLength(server.monitors) &&
!server.loading &&
!(c->cmd->flags & (CMD_SKIP_MONITOR|CMD_ADMIN)))
{
replicationFeedMonitors(c,server.monitors,c->db->id,c->argv,c->argc);
}
/* Initialization: clear the flags that must be set by the command on
* demand, and initialize the array for additional commands propagation. */
c->flags &= ~(CLIENT_FORCE_AOF|CLIENT_FORCE_REPL|CLIENT_PREVENT_PROP);
redisOpArray prev_also_propagate = server.also_propagate;
redisOpArrayInit(&server.also_propagate);
/* Call the command. */
dirty = server.dirty;
start = ustime(); //命令开始执行时间
c->cmd->proc(c); //执行命名
duration = ustime()-start;//命令结束时执行时间
dirty = server.dirty-dirty;
if (dirty < 0) dirty = 0;
/* When EVAL is called loading the AOF we don't want commands called
* from Lua to go into the slowlog or to populate statistics. */
if (server.loading && c->flags & CLIENT_LUA)
flags &= ~(CMD_CALL_SLOWLOG | CMD_CALL_STATS);
/* If the caller is Lua, we want to force the EVAL caller to propagate
* the script if the command flag or client flag are forcing the
* propagation. */
if (c->flags & CLIENT_LUA && server.lua_caller) {
if (c->flags & CLIENT_FORCE_REPL)
server.lua_caller->flags |= CLIENT_FORCE_REPL;
if (c->flags & CLIENT_FORCE_AOF)
server.lua_caller->flags |= CLIENT_FORCE_AOF;
}
/**
* 如果开启了慢日志,写慢日志
*/
/* Log the command into the Slow log if needed, and populate the
* per-command statistics that we show in INFO commandstats. */
if (flags & CMD_CALL_SLOWLOG && c->cmd->proc != execCommand) {
char *latency_event = (c->cmd->flags & CMD_FAST) ?
"fast-command" : "command";
latencyAddSampleIfNeeded(latency_event,duration/1000);
slowlogPushEntryIfNeeded(c,c->argv,c->argc,duration);
}
//记录命令的执行次数、总的执行耗时
if (flags & CMD_CALL_STATS) {
/* use the real command that was executed (cmd and lastamc) may be
* different, in case of MULTI-EXEC or re-written commands such as
* EXPIRE, GEOADD, etc. */
real_cmd->microseconds += duration;
real_cmd->calls++;
}
//将命令传播到AOF 和 复制链接中
/* Propagate the command into the AOF and replication link */
if (flags & CMD_CALL_PROPAGATE &&
(c->flags & CLIENT_PREVENT_PROP) != CLIENT_PREVENT_PROP)
{
int propagate_flags = PROPAGATE_NONE;
/* Check if the command operated changes in the data set. If so
* set for replication / AOF propagation. */
if (dirty) propagate_flags |= (PROPAGATE_AOF|PROPAGATE_REPL);
/* If the client forced AOF / replication of the command, set
* the flags regardless of the command effects on the data set. */
if (c->flags & CLIENT_FORCE_REPL) propagate_flags |= PROPAGATE_REPL;
if (c->flags & CLIENT_FORCE_AOF) propagate_flags |= PROPAGATE_AOF;
/* However prevent AOF / replication propagation if the command
* implementations called preventCommandPropagation() or similar,
* or if we don't have the call() flags to do so. */
if (c->flags & CLIENT_PREVENT_REPL_PROP ||
!(flags & CMD_CALL_PROPAGATE_REPL))
propagate_flags &= ~PROPAGATE_REPL;
if (c->flags & CLIENT_PREVENT_AOF_PROP ||
!(flags & CMD_CALL_PROPAGATE_AOF))
propagate_flags &= ~PROPAGATE_AOF;
/* Call propagate() only if at least one of AOF / replication
* propagation is needed. Note that modules commands handle replication
* in an explicit way, so we never replicate them automatically. */
if (propagate_flags != PROPAGATE_NONE && !(c->cmd->flags & CMD_MODULE))
propagate(c->cmd,c->db->id,c->argv,c->argc,propagate_flags);
}
/* Restore the old replication flags, since call() can be executed
* recursively. */
c->flags &= ~(CLIENT_FORCE_AOF|CLIENT_FORCE_REPL|CLIENT_PREVENT_PROP);
c->flags |= client_old_flags &
(CLIENT_FORCE_AOF|CLIENT_FORCE_REPL|CLIENT_PREVENT_PROP);
/* Handle the alsoPropagate() API to handle commands that want to propagate
* multiple separated commands. Note that alsoPropagate() is not affected
* by CLIENT_PREVENT_PROP flag. */
if (server.also_propagate.numops) {
int j;
redisOp *rop;
if (flags & CMD_CALL_PROPAGATE) {
for (j = 0; j < server.also_propagate.numops; j++) {
rop = &server.also_propagate.ops[j];
int target = rop->target;
/* Whatever the command wish is, we honor the call() flags. */
if (!(flags&CMD_CALL_PROPAGATE_AOF)) target &= ~PROPAGATE_AOF;
if (!(flags&CMD_CALL_PROPAGATE_REPL)) target &= ~PROPAGATE_REPL;
if (target)
propagate(rop->cmd,rop->dbid,rop->argv,rop->argc,target);
}
}
redisOpArrayFree(&server.also_propagate);
}
server.also_propagate = prev_also_propagate;
server.stat_numcommands++;
}
7.将命令回复发送给客户端
上面讲过,命令实现函数会将回复信息写入到输出缓冲区。
原本以为redis-server注册了一个可写事件,再绑定一个类似于writeHandler之类的处理器来写缓冲,发现并不是这样。
redis-server针对每个已经连接上的client维护了一个输出缓冲,用于缓存需要回复给client的内容。每次执行一个命令,如果产生了需要回复给客户端的内容就调用AddReply*相关的接口写到client的buf当中,然后在后续调用handleClientsWithPendingWrites()集中处理所有客户端的回复。在这个接口里面实际执行了write来将buf当中的内容写到网卡里,发给客户端,中间调用的是writeToClient,这个函数持续写数据,直到数据写完。
每次Redis进入事件驱动库的主循环时,在休眠准备好文件描述符之前,都会调用这个函数server.c/beforeSleep函数,beforeSleep函数调用了handleClientsWithPendingWrites将输出缓冲区中数据发送给客户端;