Redis 事务执行流程源码分析

一般事务执行流程为

# ./src/redis-cli 
127.0.0.1:6379> MULTI
OK
127.0.0.1:6379(TX)> set name molaifeng
QUEUED
127.0.0.1:6379(TX)> set hobby coding
QUEUED
127.0.0.1:6379(TX)> EXEC
1) OK
2) OK

结合源码分析如下

• 第一步 MULTI

就是给当前的客户端加上 CLIENT_MULTI 状态，当然了，如果当前客户端状态已经是 CLIENT_MULTI，说明已经有事务在执行了，那么就返回 MULTI calls can not be nested。

// multi.c
void multiCommand(client *c) {
    if (c->flags & CLIENT_MULTI) {
        addReplyError(c,"MULTI calls can not be nested");
        return;
    }
    c->flags |= CLIENT_MULTI;

    addReply(c,shared.ok);
}

• 第二步，发送命令

Redis 会在 processCommand 这个函数的最后判断，如果当前客户端状态已经是 CLIENT_MULTI，那么就加入 c->mstate.commands 事务队列，并返回 QUEUED。当然了，如果不是此状态，就正常调用 call 函数执行命令。

// server.c
int processCommand(client *c) {
	……
	/* Exec the command */
    if (c->flags & CLIENT_MULTI &&
        c->cmd->proc != execCommand && c->cmd->proc != discardCommand &&
        c->cmd->proc != multiCommand && c->cmd->proc != watchCommand &&
        c->cmd->proc != resetCommand)
    {
        queueMultiCommand(c);
        addReply(c,shared.queued);
    } else {
        call(c,CMD_CALL_FULL);
        c->woff = server.master_repl_offset;
        if (listLength(server.ready_keys))
            handleClientsBlockedOnKeys();
    }
    ……
}

第三步，EXEC

• 先判断当前客户端状态是否为 CLIENT_MULTI，否的话返回 EXEC without MULTI；
• 检查是否需要取消事务，比如 WATCH 监控的 key 已被修改，命令在入队时发生错误；
• 都无误的话，执行第二步中事务队列的命令（需要注意的是，在 Redis 6 版本中，由于加入了 ACL 权限功能，会验证目前用户拥有的命令权限）。

void execCommand(client *c) {
    int j;
    robj **orig_argv;
    int orig_argc;
    struct redisCommand *orig_cmd;
    int was_master = server.masterhost == NULL;

    if (!(c->flags & CLIENT_MULTI)) {
        addReplyError(c,"EXEC without MULTI");
        return;
    }

    /* Check if we need to abort the EXEC because:
     * 1) Some WATCHed key was touched.
     * 2) There was a previous error while queueing commands.
     * A failed EXEC in the first case returns a multi bulk nil object
     * (technically it is not an error but a special behavior), while
     * in the second an EXECABORT error is returned. */
    if (c->flags & (CLIENT_DIRTY_CAS|CLIENT_DIRTY_EXEC)) {
        addReply(c, c->flags & CLIENT_DIRTY_EXEC ? shared.execaborterr :
                                                   shared.nullarray[c->resp]);
        discardTransaction(c);
        return;
    }

    uint64_t old_flags = c->flags;

    /* we do not want to allow blocking commands inside multi */
    c->flags |= CLIENT_DENY_BLOCKING;

    /* Exec all the queued commands */
    unwatchAllKeys(c); /* Unwatch ASAP otherwise we'll waste CPU cycles */

    server.in_exec = 1;

    orig_argv = c->argv;
    orig_argc = c->argc;
    orig_cmd = c->cmd;
    addReplyArrayLen(c,c->mstate.count);
    for (j = 0; j < c->mstate.count; j++) {
        c->argc = c->mstate.commands[j].argc;
        c->argv = c->mstate.commands[j].argv;
        c->cmd = c->mstate.commands[j].cmd;

        /* ACL permissions are also checked at the time of execution in case
         * they were changed after the commands were queued. */
        int acl_errpos;
        int acl_retval = ACLCheckAllPerm(c,&acl_errpos);
        if (acl_retval != ACL_OK) {
            char *reason;
            switch (acl_retval) {
            case ACL_DENIED_CMD:
                reason = "no permission to execute the command or subcommand";
                break;
            case ACL_DENIED_KEY:
                reason = "no permission to touch the specified keys";
                break;
            case ACL_DENIED_CHANNEL:
                reason = "no permission to access one of the channels used "
                         "as arguments";
                break;
            default:
                reason = "no permission";
                break;
            }
            addACLLogEntry(c,acl_retval,acl_errpos,NULL);
            addReplyErrorFormat(c,
                "-NOPERM ACLs rules changed between the moment the "
                "transaction was accumulated and the EXEC call. "
                "This command is no longer allowed for the "
                "following reason: %s", reason);
        } else {
            call(c,server.loading ? CMD_CALL_NONE : CMD_CALL_FULL);
            serverAssert((c->flags & CLIENT_BLOCKED) == 0);
        }

        /* Commands may alter argc/argv, restore mstate. */
        c->mstate.commands[j].argc = c->argc;
        c->mstate.commands[j].argv = c->argv;
        c->mstate.commands[j].cmd = c->cmd;
    }

    // restore old DENY_BLOCKING value
    if (!(old_flags & CLIENT_DENY_BLOCKING))
        c->flags &= ~CLIENT_DENY_BLOCKING;

    c->argv = orig_argv;
    c->argc = orig_argc;
    c->cmd = orig_cmd;
    discardTransaction(c);

    /* Make sure the EXEC command will be propagated as well if MULTI
     * was already propagated. */
    if (server.propagate_in_transaction) {
        int is_master = server.masterhost == NULL;
        server.dirty++;
        /* If inside the MULTI/EXEC block this instance was suddenly
         * switched from master to slave (using the SLAVEOF command), the
         * initial MULTI was propagated into the replication backlog, but the
         * rest was not. We need to make sure to at least terminate the
         * backlog with the final EXEC. */
        if (server.repl_backlog && was_master && !is_master) {
            char *execcmd = "*1\r\n$4\r\nEXEC\r\n";
            feedReplicationBacklog(execcmd,strlen(execcmd));
        }
        afterPropagateExec();
    }

    server.in_exec = 0;
}

最后，再说下 DISCARD，也就是取消事务。

• 和 EXEC 一致，先判断当前客户端状态是否为 CLIENT_MULTI，否的话返回 DISCARD without MULTI；
• 清空并重新初始化 c->mstate.commands 事务队列；
• 取消当前客户端关于事务的状态，如 CLIENT_MULTI；
• 清空 c->watched_keys 观察键队列。

// multi.c
void discardCommand(client *c) {
    if (!(c->flags & CLIENT_MULTI)) {
        addReplyError(c,"DISCARD without MULTI");
        return;
    }
    discardTransaction(c);
    addReply(c,shared.ok);
}

void discardTransaction(client *c) {
    freeClientMultiState(c);
    initClientMultiState(c);
    c->flags &= ~(CLIENT_MULTI|CLIENT_DIRTY_CAS|CLIENT_DIRTY_EXEC);
    unwatchAllKeys(c);
}