memcached之网络模型详解

╰+攻爆jí腚メ 2022-05-25 05:36 189阅读 0赞

# 综述 #

主线程创建多个子线程(这些子线程也称为worker线程)，每一个线程都维持自己的事件循环，即每个线程都有自己的epoll，并且都会调用epoll\_wait函数进入事件监听状态。每一个worker线程(子线程)和主线程之间都用一条管道相互通信。每一个子线程都监听自己对应那条管道的读端。当主线程想和某一个worker线程进行通信，直接往对应的那条管道写入数据即可。  
模型的工作流程：主线程负责监听进程对外的TCP监听端口。当客户端申请连接connect到进程的时候，主线程负责接收accept客户端的连接请求。然后主线程选择其中一个worker线程，把客户端fd通过对应的管道传给worker线程。worker线程得到客户端的fd后负责和这个客户端进行一切的通信。以下是一个经典的模型。  
![这里写图片描述][70]

主线程通过epoll监听创建的监听套接字，然后有连接accept，并将对应的fd封装成CQ\_ITEM，通过轮询选定一个线程，然后给管道写，然后将其压入选定线程的连接队列中并通过子线程的epoll监听这个fd。完全就是上述过程。

# memcached实现上述网络模型 #

## 主线程 ##

首先看看main函数主进程大体过程：

int main (int argc, char **argv) {
       ........//一些变量省略
        if (!sanitycheck()) {
       //检查Libevent版本
            return EX_OSERR;
        }
        /* handle SIGINT */
        signal(SIGINT, sig_handler);//注册中断信号，给进程发送SIGINT信号直接退出。
    
        /* init settings */
        settings_init();//初始化一些设置
    
        /* 通过getopt 处理命令参数 .................... */
        if (hash_init(hash_type) != 0) {
       //初始化hash表
            fprintf(stderr, "Failed to initialize hash_algorithm!\n");
            exit(EX_USAGE);
        }
    
        /* initialize main thread libevent instance */
        main_base = event_init();//初始化Libevent的main_base，这个是全局的
    
        /* initialize other stuff */
        stats_init();
        assoc_init(settings.hashpower_init);
        conn_init();//连接队列初始化
        slabs_init(settings.maxbytes, settings.factor, preallocate);//slabs初始化
           /* start up worker threads if MT mode */
        thread_init(settings.num_threads, main_base);//初始化工作线程，主线程先创建工作线程。
           /* initialise clock event */
        clock_handler(0, 0, 0);
    /* create the listening socket, bind it, and init 在这里面主线程通过epoll监听listen fd*/
        if (settings.socketpath == NULL) {
            const char *portnumber_filename = getenv("MEMCACHED_PORT_FILENAME");
            char temp_portnumber_filename[PATH_MAX];
            FILE *portnumber_file = NULL;
    
            if (portnumber_filename != NULL) {
                snprintf(temp_portnumber_filename,
                         sizeof(temp_portnumber_filename),
                         "%s.lck", portnumber_filename);
    
                portnumber_file = fopen(temp_portnumber_filename, "a");
                if (portnumber_file == NULL) {
                    fprintf(stderr, "Failed to open \"%s\": %s\n",
                            temp_portnumber_filename, strerror(errno));
                }
            }
    
            errno = 0;
            if (settings.port && server_sockets(settings.port, tcp_transport,
                                               portnumber_file)) {
                vperror("failed to listen on TCP port %d", settings.port);
                exit(EX_OSERR);
            }
    
            /* * initialization order: first create the listening sockets * (may need root on low ports), then drop root if needed, * then daemonise if needed, then init libevent (in some cases * descriptors created by libevent wouldn't survive forking). */
    
            /* create the UDP listening socket and bind it */
            errno = 0;
            if (settings.udpport && server_sockets(settings.udpport, udp_transport,
                                                  portnumber_file)) {
                vperror("failed to listen on UDP port %d", settings.udpport);
                exit(EX_OSERR);
            }
    
            if (portnumber_file) {
                fclose(portnumber_file);
                rename(temp_portnumber_filename, portnumber_filename);
            }
        }
    
        /* enter the event loop 主线程进入epoll循环，持续监听外部连接*/
        if (event_base_loop(main_base, 0) != 0) {
            retval = EXIT_FAILURE;
        }//进入主线程的epoll循环
    }

上述已经将主线程做的事情都列举出来了，下面是main函数调用图，重点讲解图中红色框框里面的函数。  
![这里写图片描述][70 1]

注意上述主线程event\_base初始化，已经`server_sockets`函数调用创建监听fd事件。下面深入分析主线程是如何创建listen fd事件的。

//strdup()：
    //功 能: 将串拷贝到新建的位置处
    //strdup()在内部调用了malloc()为变量分配内存，不需要使用返回的字符串时，需要用free()释放相应的内存空间，否则会造成内存泄漏。
    
    
    //port是默认的11211或者用户使用-p选项设置的端口号 
    //主线程在main函数会调用本函数 
    static int server_sockets(int port, enum network_transport transport,  
                              FILE *portnumber_file) {  
    
        //settings.inter里面可能有多个IP地址.如果有多个那么将用逗号分隔 
        char *b;  
        int ret = 0;  
        //复制一个字符串，内部使用了malloc，避免下面的strtok_r函数修改(污染)全局变量settings.inter。 
        char *list = strdup(settings.inter);  
    
        //这个循环主要是处理多个IP的情况 
        for (char *p = strtok_r(list, ";,", &b);  
             p != NULL; //分割出一个个的ip,使用分号;作为分隔符 
             p = strtok_r(NULL, ";,", &b)) {  
            int the_port = port;  
            char *s = strchr(p, ':');//启动的可能使用-l ip:port 参数形式 
            //ip后面接着端口号，即指定ip的同时也指定了该ip的端口号 
            //此时采用ip后面的端口号，而不是采用-p指定的端口号 
            if (s != NULL) {  
                *s = '\0';//截断后面的端口号，使得p指向的字符串只是一个ip 
                ++s;  
                if (!safe_strtol(s, &the_port)) {
       //非法端口号参数值 
                    return 1;  
                }  
            }  
            if (strcmp(p, "*") == 0) {  
                p = NULL;  
            }  
            //处理其中一个IP。有p指定ip(或者hostname) 
            ret |= server_socket(p, the_port, transport, portnumber_file);  
        }  
        free(list);//释放临时内存 
        return ret;  
    }  
    
    
    static conn *listen_conn = NULL;//监听队列(可能要同时监听多个IP) 
    
    
     //interface是一个ip、hostname或者NULL。这个ip字符串后面没有端口号。端口号由参数port指出 
    static int server_socket(const char *interface,  
                             int port,  
                             enum network_transport transport,  
                             FILE *portnumber_file) {  
        int sfd;  
        struct linger ling = {
       0, 0};  
        struct addrinfo *ai;  
        struct addrinfo *next;  
        struct addrinfo hints = { .ai_flags = AI_PASSIVE,  
                                  .ai_family = AF_UNSPEC };  
        char port_buf[NI_MAXSERV];  
        int success = 0;  
        int flags =1;  
    
        hints.ai_socktype = IS_UDP(transport) ? SOCK_DGRAM : SOCK_STREAM;  
    
    
        snprintf(port_buf, sizeof(port_buf), "%d", port);  
        getaddrinfo(interface, port_buf, &hints, &ai);  
    
        //如果interface是一个hostname的话，那么可能就有多个ip 
        for (next= ai; next; next= next->ai_next) {  
            conn *listen_conn_add;  
    
            //创建一个套接字，然后设置为非阻塞的 
            sfd = new_socket(next);//调用socket函数 
            bind(sfd, next->ai_addr, next->ai_addrlen);  
    
            success++;  
            listen(sfd, settings.backlog);  
    
    
            if (!(listen_conn_add = conn_new(sfd, conn_listening,  
                                             EV_READ | EV_PERSIST, 1,  
                                             transport, main_base))) {  
                fprintf(stderr, "failed to create listening connection\n");  
                exit(EXIT_FAILURE);  
            }  
    
            //将要监听的多个conn放到一个监听队列里面 
            listen_conn_add->next = listen_conn;  
            listen_conn = listen_conn_add;  
    
        }  
    
        freeaddrinfo(ai);  
    
        /* Return zero iff we detected no errors in starting up connections */  
        return success == 0;  
    }  
    
    
    static int new_socket(struct addrinfo *ai) {  
        int sfd;  
        int flags;  
        sfd = socket(ai->ai_family, ai->ai_socktype, ai->ai_protocol);  
        flags = fcntl(sfd, F_GETFL, 0);  
        fcntl(sfd, F_SETFL, flags | O_NONBLOCK);  
    
        return sfd;  
    }

根据用户的IP和端口号建立一个socket，bind、listen监听客户端的到来。因为主线程申请的socket fd已经设置为非阻塞的，所以listen函数会立刻返回。在main函数中，主线程最终将调用`event_base_loop`函数进入事件监听循环，处理客户端的连接请求。注意上述  
`conn_new(sfd, conn_listening, EV_READ | EV_PERSIST, 1, transport, main_base))`这个调用。  
事件类型是`EV_READ | EV_PERSIST`。  
事件初始化状态是`conn_listening`正在监听。  
当主线程监听套接字就绪，会调用event\_handler函数进入状态机进行处理。后续会仔细讲解`event_handler`。

## work线程 ##

**1、连接队列**  
每个子进程都含有一个连接队列，用于保存每个网络连接需要的一些数据。连接队列通过链表实现，非常简单。

/* An item in the connection queue. */
    typedef struct conn_queue_item CQ_ITEM;
    struct conn_queue_item {
        int               sfd;//连接的socket fd
        enum conn_states  init_state;//连接的状态，这个状态非常重要，状态不同对应的处理也不同
        int               event_flags;//监听事件标志（读或者写）
        int               read_buffer_size;//
        enum network_transport     transport;//
        CQ_ITEM          *next;//指向下一个连接
    };
    
    /* A connection queue. */
    typedef struct conn_queue CQ;//一个连接队列
    struct conn_queue {
        CQ_ITEM *head;//指向队列的第一个节点。
        CQ_ITEM *tail;//指向队列的最后一个节点。
        pthread_mutex_t lock;//一个队列互斥量，用于线程间同步。
    };

因为多线程，所以主线程往某个worker线程的CQ队列里面push一个CQ\_ITEM的时候必然要加锁。

/* * Initializes a connection queue. 初始化连接队列头 */
    static void cq_init(CQ *cq) {
        pthread_mutex_init(&cq->lock, NULL);
        cq->head = NULL;
        cq->tail = NULL;
    }
    
    /* * Adds an item to a connection queue. 添加到队列尾部，链表插入很简单 */
    static void cq_push(CQ *cq, CQ_ITEM *item) {
        item->next = NULL;
    
        pthread_mutex_lock(&cq->lock);//必须上锁
        if (NULL == cq->tail)
            cq->head = item;
        else
            cq->tail->next = item;
        cq->tail = item;
        pthread_mutex_unlock(&cq->lock);//必须上锁
    }
    
    /* * * * Returns the item, or NULL if no item is available 返回链表头部节点 */
    static CQ_ITEM *cq_pop(CQ *cq) {
        CQ_ITEM *item;
    
        pthread_mutex_lock(&cq->lock);
        item = cq->head;
        if (NULL != item) {
            cq->head = item->next;
            if (NULL == cq->head)
                cq->tail = NULL;
        }
        pthread_mutex_unlock(&cq->lock);
    
        return item;
    }

这个链表实现起来比较简单，最后形成的一个连接队列如下图：  
![这里写图片描述][70 2]

**2、线程结构体**  
从上述网络模型图可以得知，每一个工作线程里面都含有一个连接队列，让此线程可以处理多个连接，并且线程需要监听管道的读、写事件等等，于是memcached为每一个线程创建一个结构体变量，将上述线程需要的资料包装起来。

typedef struct {
        pthread_t thread_id;        /* 线程ID*/
        struct event_base *base;    /* 单个线程使用event_base */
        struct event notify_event;  /* 线程监听管道读事件的event */
        int notify_receive_fd;      /* 管道的读fd */
        int notify_send_fd;         /* 管道的写fd */
        struct thread_stats stats;  /* 线程状态*/
        struct conn_queue *new_conn_queue; /* 连接队列的头（指向连接队列） */
        cache_t *suffix_cache;      /* suffix cache */
        uint8_t item_lock_type;     /* use fine-grained or global item lock */
    } LIBEVENT_THREAD;//传入pthread_create的结构体。

工作线程的数量`settings.num_threads`，通过命令行参数配置。并定义一个全局的线程结构体数组`static LIBEVENT_THREAD *threads;`，因为全局所以主线程和子线程都可以访问，当压入连接队列的时候就非常简单了。

static LIBEVENT_THREAD *threads;//全局，主和子线程都可以访问，这点对于将CQ_Item压入子线程对应的链接队列很重要。
    
    /* 多线程初始化，创建线程，并确定线程中的回调函数 nthreads通过命令行设定。 */
    void thread_init(int nthreads, struct event_base *main_base) { 
            .....
    
        //申请一个CQ_ITEM时需要加锁，后面会介绍 
        pthread_mutex_init(&cqi_freelist_lock, NULL);  
        cqi_freelist = NULL;  
        //仅仅列出与线程有关的初始化
        threads = calloc(nthreads, sizeof(LIBEVENT_THREAD));//分配线程对应的结构体
        if (! threads) {
            perror("Can't allocate thread descriptors");
            exit(1);
        }
    
        ......
    
        for (i = 0; i < nthreads; i++) {
       //为每个线程创建管道，并设定结构体成员
            int fds[2];
            if (pipe(fds)) {
                perror("Can't create notify pipe");
                exit(1);
            }
    
            threads[i].notify_receive_fd = fds[0];
            threads[i].notify_send_fd = fds[1];
    
            //每一个线程配一个event_base,并设置event监听notify_receive_fd的读事件 
            //同时还为这个线程分配一个conn_queue队列 
            setup_thread(&threads[i]);
            /* Reserve three fds for the libevent base, and two for the pipe */
            stats.reserved_fds += 5;
        }
    
        /* Create threads after we've done all the libevent setup. */
        for (i = 0; i < nthreads; i++) {
       //相当重要
        //创建线程，线程函数为worker_libevent, 线程参数为&threads[i] 
            create_worker(worker_libevent, &threads[i]);
        }
    }
    
    
    /* * 设定线程结构体成员变量 */
    static void setup_thread(LIBEVENT_THREAD *me) {
        me->base = event_init();//线程初始化event_base
        if (! me->base) {
            fprintf(stderr, "Can't allocate event base\n");
            exit(1);
        }
    
        /* Listen for notifications from other threads */
        event_set(&me->notify_event, me->notify_receive_fd,
                  EV_READ | EV_PERSIST, thread_libevent_process, me);//创建监听管道读事件，注意回调函数是thread_libevent_process，传入参数是LIBEVENT_THREAD 
    
        event_base_set(me->base, &me->notify_event);//将事件和当前线程event_base绑定
    
        if (event_add(&me->notify_event, 0) == -1) {
       //假如到epoll监听
            fprintf(stderr, "Can't monitor libevent notify pipe\n");
            exit(1);
        }
    
        me->new_conn_queue = malloc(sizeof(struct conn_queue));//连接队列头分配
        if (me->new_conn_queue == NULL) {
            perror("Failed to allocate memory for connection queue");
            exit(EXIT_FAILURE);
        }
        cq_init(me->new_conn_queue);//队列头初始化
    
        if (pthread_mutex_init(&me->stats.mutex, NULL) != 0) {
            perror("Failed to initialize mutex");
            exit(EXIT_FAILURE);
        }
    
        me->suffix_cache = cache_create("suffix", SUFFIX_SIZE, sizeof(char*),
                                        NULL, NULL);
        if (me->suffix_cache == NULL) {
            fprintf(stderr, "Failed to create suffix cache\n");
            exit(EXIT_FAILURE);
        }
    }
    
    
    
    
    /* * 前面初始化结构体参数，现在就是创建线程了，回调函数是worker_libevent，传入参数是LIBEVENT_THREAD线程参数 */
    static void create_worker(void *(*func)(void *), void *arg) {
        pthread_t       thread;
        pthread_attr_t  attr;
        int             ret;
    
        pthread_attr_init(&attr);
    
        if ((ret = pthread_create(&thread, &attr, func, arg)) != 0) {
            fprintf(stderr, "Can't create thread: %s\n",
                    strerror(ret));
            exit(1);
        }
    }

通过上述我们必须注意两个回调函数  
其一，每个线程监听管道可读的回调函数`thread_libevent_process，传入参数是LIBEVENT_THREAD`，这个回调函数处理主线程通过管道给子线性发生的信号。  
其二，每个线程运行的函数为`worker_libevent，传入参数是LIBEVENT_THREAD`，线程处理所以连接全部在此函数执行。  
下面仔细看看这个两个函数，这就是编写多线程程序的典型模范，可以好好学习，其是如何处理多线程的。

/*
     * 每个子线程的event_base循环
     */
    static void *worker_libevent(void *arg) {
        LIBEVENT_THREAD *me = arg;
    
        /* Any per-thread setup can happen here; thread_init() will block until
         * all threads have finished initializing.
         */
    
        /* set an indexable thread-specific memory item for the lock type.
         * this could be unnecessary if we pass the conn *c struct through
         * all item_lock calls...
         */
        me->item_lock_type = ITEM_LOCK_GRANULAR;
        pthread_setspecific(item_lock_type_key, &me->item_lock_type);
    
        register_thread_initialized();
    
        event_base_loop(me->base, 0);//子线程进入监听循环中，等待主线程写管道。
        return NULL;
    }

子线程主函数啥有没有干，就是一直进入监听循环。首先监听管道的读，然后建立主线程传进来的外部连接并将套接字假如到epoll，继续进入监听—处理—-监听循环。

/* 当子线程管道可读，此函数被调用 */ static void thread_libevent_process(int fd, short which, void *arg) { LIBEVENT_THREAD *me = arg; CQ_ITEM *item; char buf[1]; if (read(fd, buf, 1) != 1)//读取主线程写入管道的数据 if (settings.verbose > 0) fprintf(stderr, "Can't read from libevent pipe\n"); switch (buf[0]) { //主线程 case 'c': item = cq_pop(me->new_conn_queue);//新连接fd已经由主线程压入连接队列，在这里取出。然后子线程，epoll这个连接。cq_pop将删除conn_queue. if (NULL != item) { //将sfd加入到当前子线性的epoll。 conn *c = conn_new(item->sfd, item->init_state, item->event_flags, item->read_buffer_size, item->transport, me->base); if (c == NULL) { if (IS_UDP(item->transport)) { fprintf(stderr, "Can't listen for events on UDP socket\n"); exit(1); } else { if (settings.verbose > 0) { fprintf(stderr, "Can't listen for events on fd %d\n", item->sfd); } close(item->sfd); } } else { c->thread = me; } cqi_free(item); } break; /* we were told to flip the lock type and report in */ case 'l': me->item_lock_type = ITEM_LOCK_GRANULAR; register_thread_initialized(); break; case 'g': me->item_lock_type = ITEM_LOCK_GLOBAL; register_thread_initialized(); break; } }

从上面可知，主线程接收到连接后，将连接的fd压入到选定的子线程的连接队列。然后给这个子进程管道写入相应的字符，告诉子进程应该如何处理这个连接。  
并且每个子进程`new_conn_queue`队列里面存放着当前进程未处理（没有epoll）的连接。  
注意上述的`conn_new`新键了一个连接，然后将其加入到子线程epoll进行监听读。  
下面仔细讲解`conn_new`。

**3、连接结构体**  
memcached将每个连接都封装成一个结构体`struct conn`。并且子线程对创建连接fd的event，并将其加入到自己的event\_base中进行监听。  
事实上memcached为每一个socket fd(也就是一个连接)都创建一个conn结构体，用于管理这个socket fd(连接)。因为一个连接会有很多数据和状态信息，所以需要一个结构体来负责管理。  
在启动memcached之后就可以确定最多允许多少个客户端同时在线（所以子进程里面的连接总和同时在线）了。可以通过命令行参数设定，默认是1024，也就是最多同时处理1024个连接。**有了这个数值那么可以在一开始(conn\_init函数)，就动态申请一个数组。有新连接就从这个数组中分配一个元素即可，可以有效避免内存碎片**。

/** * The structure representing a connection into memcached. */
    typedef struct conn conn;
    struct conn {
        int    sfd;
        sasl_conn_t *sasl_conn;
        bool authenticated;
        enum conn_states  state;
        enum bin_substates substate;
        rel_time_t last_cmd_time;
        struct event event;
        short  ev_flags;
        short  which;   /** which events were just triggered */
    
        char   *rbuf;   /** buffer to read commands into */
        char   *rcurr;  /** but if we parsed some already, this is where we stopped */
        int    rsize;   /** total allocated size of rbuf */
        int    rbytes;  /** how much data, starting from rcur, do we have unparsed */
    
        char   *wbuf;
        char   *wcurr;
        int    wsize;
        int    wbytes;
        /** which state to go into after finishing current write */
        enum conn_states  write_and_go;
        void   *write_and_free; /** free this memory after finishing writing */
    
        char   *ritem;  /** when we read in an item's value, it goes here */
        int    rlbytes;
    
        /* data for the nread state */
    
        /** * item is used to hold an item structure created after reading the command * line of set/add/replace commands, but before we finished reading the actual * data. The data is read into ITEM_data(item) to avoid extra copying. */
    
        void   *item;     /* for commands set/add/replace */
    
        /* data for the swallow state */
        int    sbytes;    /* how many bytes to swallow */
    
        /* data for the mwrite state */
        struct iovec *iov;
        int    iovsize;   /* number of elements allocated in iov[] */
        int    iovused;   /* number of elements used in iov[] */
    
        struct msghdr *msglist;
        int    msgsize;   /* number of elements allocated in msglist[] */
        int    msgused;   /* number of elements used in msglist[] */
        int    msgcurr;   /* element in msglist[] being transmitted now */
        int    msgbytes;  /* number of bytes in current msg */
    
        item   **ilist;   /* list of items to write out */
        int    isize;
        item   **icurr;
        int    ileft;
    
        char   **suffixlist;
        int    suffixsize;
        char   **suffixcurr;
        int    suffixleft;
    
        enum protocol protocol;   /* which protocol this connection speaks */
        enum network_transport transport; /* what transport is used by this connection */
    
        /* data for UDP clients */
        int    request_id; /* Incoming UDP request ID, if this is a UDP "connection" */
        struct sockaddr_in6 request_addr; /* udp: Who sent the most recent request */
        socklen_t request_addr_size;
        unsigned char *hdrbuf; /* udp packet headers */
        int    hdrsize;   /* number of headers' worth of space is allocated */
    
        bool   noreply;   /* True if the reply should not be sent. */
        /* current stats command */
        struct {
            char *buffer;
            size_t size;
            size_t offset;
        } stats;
    
        /* Binary protocol stuff */
        /* This is where the binary header goes */
        protocol_binary_request_header binary_header;
        uint64_t cas; /* the cas to return */
        short cmd; /* current command being processed */
        int opaque;
        int keylen;
        conn   *next;     /* Used for generating a list of conn structures */
        LIBEVENT_THREAD *thread; /* Pointer to the thread object serving this connection */
    };

conn **conns;//指针的指针，conn[i]执向malloc(conn)。这样既不会内存碎片，也
    /* */
    static void conn_init(void) {
        /* We're unlikely to see an FD much higher than maxconns. */
        int next_fd = dup(1);//获取当前已经使用的fd的个数
        int headroom = 10;      /* 预留一些文件描述符 */
        struct rlimit rl;
        //settings.maxconns的默认值是1024. 
        max_fds = settings.maxconns + headroom + next_fd;
    
        /* But if possible, get the actual highest FD we can possibly ever see. */
        if (getrlimit(RLIMIT_NOFILE, &rl) == 0) {
            max_fds = rl.rlim_max;
        } else {
            fprintf(stderr, "Failed to query maximum file descriptor; "
                            "falling back to maxconns\n");
        }
    
        close(next_fd);
        //注意，申请的conn结构体数量是比settings.maxconns这个客户端同时在线数 
        //还要大的。因为memcached是直接用socket fd的值作为数组下标的。也正是 
        //这个原因，前面需要使用headroom预留一些空间给突发情况。 
        if ((conns = calloc(max_fds, sizeof(conn *))) == NULL) {
            fprintf(stderr, "Failed to allocate connection structures\n");
            /* This is unrecoverable so bail out early. */
            exit(1);
        }
    }

内存模型如下：  
![这里写图片描述][70 3]

//为sfd分配一个conn结构体，并且为这个sfd建立一个event，然后让base监听这个event 
    conn *conn_new(const int sfd, enum conn_states init_state,//init_state值为conn_listening 
                    const int event_flags,  
                    const int read_buffer_size, enum network_transport transport,  
                    struct event_base *base) {  
        conn *c;  
    
        assert(sfd >= 0 && sfd < max_fds);  
        c = conns[sfd];//直接使用下标，位置已经留好了。 
    
        if (NULL == c) {
       //之前没有哪个连接用过这个sfd值，需要申请一个conn结构体 
            if (!(c = (conn *)calloc(1, sizeof(conn)))) {  
                fprintf(stderr, "Failed to allocate connection object\n");  
                return NULL;  
            }  
    
            ...//初始化一些成员变量 
    
            c->sfd = sfd;  
            conns[sfd] = c; //将这个结构体交由conns数组管理 
        }  
    
        ...//初始化另外一些成员变量 
        c->state = init_state;//值为conn_listening， 
    
        //等同于event_assign。event的回调函数是event_handler 
        event_set(&c->event, sfd, event_flags, event_handler, (void *)c);  
        event_base_set(base, &c->event);  
        c->ev_flags = event_flags;  
    
        if (event_add(&c->event, 0) == -1) {
       //添加到event_base 
            perror("event_add");  
            return NULL;  
        }    
        return c;//返回连接指针 
    }

这里最需要注意注册的回调函数，事件类型以及传入的参数：  
`event_flags`表示事件类型，这个有主线程设定cq队列成员变量。  
`event_handler`是已建立连接的事件就绪调用的回调函数。  
`conn`是此回调函数传入的参数。

# 事件回调函数event\_handler #

event\_handler处理了监听和连接两种事件。

void event_handler(const int fd, const short which, void *arg) {
        conn *c;
    
        c = (conn *)arg;
        assert(c != NULL);
    
        c->which = which;//传入触发事件的类型
    
        /* sanity */
        if (fd != c->sfd) {
       //fd不正确，则错误。
            if (settings.verbose > 0)
                fprintf(stderr, "Catastrophic: event fd doesn't match conn fd!\n");
            conn_close(c);
            return;
        }
    
        drive_machine(c);//状态机处理，下面会详细讲解状态机的操作
    
        /* wait for next event */
        return;
    }

这是一个所有已连接套接字可读共同调用的回调函数，看起来很简单，但是里面通过一个状态机处理每个连接的套接字。下面仔细分析分析这个状态机。

/** * 首先每一个连接有12个状态。所以 */
    enum conn_states {
        conn_listening,  /**< the socket which listens for connections */
        conn_new_cmd,    /**< Prepare connection for next command */
        conn_waiting,    /**< waiting for a readable socket */
        conn_read,       /**< reading in a command line */
        conn_parse_cmd,  /**< try to parse a command from the input buffer */
        conn_write,      /**< writing out a simple response */
        conn_nread,      /**< reading in a fixed number of bytes */
        conn_swallow,    /**< swallowing unnecessary bytes w/o storing */
        conn_closing,    /**< closing this connection */
        conn_mwrite,     /**< writing out many items sequentially */
        conn_closed,     /**< connection is closed */
        conn_max_state   /**< Max state value (used for assertion) */
    };
    
            switch(c->state) {
            case conn_listening:
                addrlen = sizeof(addr);
    #ifdef HAVE_ACCEPT4
                if (use_accept4) {
                    sfd = accept4(c->sfd, (struct sockaddr *)&addr, &addrlen, SOCK_NONBLOCK);
                } else {
                    sfd = accept(c->sfd, (struct sockaddr *)&addr, &addrlen);
                }
    #else
                sfd = accept(c->sfd, (struct sockaddr *)&addr, &addrlen);
    #endif
                if (sfd == -1) {
                    if (use_accept4 && errno == ENOSYS) {
                        use_accept4 = 0;
                        continue;
                    }
                    perror(use_accept4 ? "accept4()" : "accept()");
                    if (errno == EAGAIN || errno == EWOULDBLOCK) {
                        /* these are transient, so don't log anything */
                        stop = true;
                    } else if (errno == EMFILE) {
                        if (settings.verbose > 0)
                            fprintf(stderr, "Too many open connections\n");
                        accept_new_conns(false);
                        stop = true;
                    } else {
                        perror("accept()");
                        stop = true;
                    }
                    break;
                }
                if (!use_accept4) {
                    if (fcntl(sfd, F_SETFL, fcntl(sfd, F_GETFL) | O_NONBLOCK) < 0) {
                        perror("setting O_NONBLOCK");
                        close(sfd);
                        break;
                    }
                }
    
                if (settings.maxconns_fast &&
                    stats.curr_conns + stats.reserved_fds >= settings.maxconns - 1) {
                    str = "ERROR Too many open connections\r\n";
                    res = write(sfd, str, strlen(str));
                    close(sfd);
                    STATS_LOCK();
                    stats.rejected_conns++;
                    STATS_UNLOCK();
                } else {
                    dispatch_conn_new(sfd, conn_new_cmd, EV_READ | EV_PERSIST,
                                         DATA_BUFFER_SIZE, tcp_transport);
                }
    
                stop = true;
                break;
    
            case conn_waiting:
                if (!update_event(c, EV_READ | EV_PERSIST)) {
                    if (settings.verbose > 0)
                        fprintf(stderr, "Couldn't update event\n");
                    conn_set_state(c, conn_closing);
                    break;
                }
    
                conn_set_state(c, conn_read);
                stop = true;
                break;
    
            case conn_read:
                res = IS_UDP(c->transport) ? try_read_udp(c) : try_read_network(c);
    
                switch (res) {
                case READ_NO_DATA_RECEIVED:
                    conn_set_state(c, conn_waiting);
                    break;
                case READ_DATA_RECEIVED:
                    conn_set_state(c, conn_parse_cmd);
                    break;
                case READ_ERROR:
                    conn_set_state(c, conn_closing);
                    break;
                case READ_MEMORY_ERROR: /* Failed to allocate more memory */
                    /* State already set by try_read_network */
                    break;
                }
                break;
    
            case conn_parse_cmd :
                if (try_read_command(c) == 0) {
                    /* wee need more data! */
                    conn_set_state(c, conn_waiting);
                }
    
                break;
    
            case conn_new_cmd:
                /* Only process nreqs at a time to avoid starving other connections */
    
                --nreqs;
                if (nreqs >= 0) {
                    reset_cmd_handler(c);
                } else {
                    pthread_mutex_lock(&c->thread->stats.mutex);
                    c->thread->stats.conn_yields++;
                    pthread_mutex_unlock(&c->thread->stats.mutex);
                    if (c->rbytes > 0) {
                        /* We have already read in data into the input buffer, so libevent will most likely not signal read events on the socket (unless more data is available. As a hack we should just put in a request to write data, because that should be possible ;-) */
                        if (!update_event(c, EV_WRITE | EV_PERSIST)) {
                            if (settings.verbose > 0)
                                fprintf(stderr, "Couldn't update event\n");
                            conn_set_state(c, conn_closing);
                            break;
                        }
                    }
                    stop = true;
                }
                break;
    
            case conn_nread:
                if (c->rlbytes == 0) {
                    complete_nread(c);
                    break;
                }
    
                /* Check if rbytes < 0, to prevent crash */
                if (c->rlbytes < 0) {
                    if (settings.verbose) {
                        fprintf(stderr, "Invalid rlbytes to read: len %d\n", c->rlbytes);
                    }
                    conn_set_state(c, conn_closing);
                    break;
                }
    
                /* first check if we have leftovers in the conn_read buffer */
                if (c->rbytes > 0) {
                    int tocopy = c->rbytes > c->rlbytes ? c->rlbytes : c->rbytes;
                    if (c->ritem != c->rcurr) {
                        memmove(c->ritem, c->rcurr, tocopy);
                    }
                    c->ritem += tocopy;
                    c->rlbytes -= tocopy;
                    c->rcurr += tocopy;
                    c->rbytes -= tocopy;
                    if (c->rlbytes == 0) {
                        break;
                    }
                }
    
                /* now try reading from the socket */
                res = read(c->sfd, c->ritem, c->rlbytes);
                if (res > 0) {
                    pthread_mutex_lock(&c->thread->stats.mutex);
                    c->thread->stats.bytes_read += res;
                    pthread_mutex_unlock(&c->thread->stats.mutex);
                    if (c->rcurr == c->ritem) {
                        c->rcurr += res;
                    }
                    c->ritem += res;
                    c->rlbytes -= res;
                    break;
                }
                if (res == 0) { /* end of stream */
                    conn_set_state(c, conn_closing);
                    break;
                }
                if (res == -1 && (errno == EAGAIN || errno == EWOULDBLOCK)) {
                    if (!update_event(c, EV_READ | EV_PERSIST)) {
                        if (settings.verbose > 0)
                            fprintf(stderr, "Couldn't update event\n");
                        conn_set_state(c, conn_closing);
                        break;
                    }
                    stop = true;
                    break;
                }
                /* otherwise we have a real error, on which we close the connection */
                if (settings.verbose > 0) {
                    fprintf(stderr, "Failed to read, and not due to blocking:\n"
                            "errno: %d %s \n"
                            "rcurr=%lx ritem=%lx rbuf=%lx rlbytes=%d rsize=%d\n",
                            errno, strerror(errno),
                            (long)c->rcurr, (long)c->ritem, (long)c->rbuf,
                            (int)c->rlbytes, (int)c->rsize);
                }
                conn_set_state(c, conn_closing);
                break;
    
            case conn_swallow:
                /* we are reading sbytes and throwing them away */
                if (c->sbytes == 0) {
                    conn_set_state(c, conn_new_cmd);
                    break;
                }
    
                /* first check if we have leftovers in the conn_read buffer */
                if (c->rbytes > 0) {
                    int tocopy = c->rbytes > c->sbytes ? c->sbytes : c->rbytes;
                    c->sbytes -= tocopy;
                    c->rcurr += tocopy;
                    c->rbytes -= tocopy;
                    break;
                }
    
                /* now try reading from the socket */
                res = read(c->sfd, c->rbuf, c->rsize > c->sbytes ? c->sbytes : c->rsize);
                if (res > 0) {
                    pthread_mutex_lock(&c->thread->stats.mutex);
                    c->thread->stats.bytes_read += res;
                    pthread_mutex_unlock(&c->thread->stats.mutex);
                    c->sbytes -= res;
                    break;
                }
                if (res == 0) { /* end of stream */
                    conn_set_state(c, conn_closing);
                    break;
                }
                if (res == -1 && (errno == EAGAIN || errno == EWOULDBLOCK)) {
                    if (!update_event(c, EV_READ | EV_PERSIST)) {
                        if (settings.verbose > 0)
                            fprintf(stderr, "Couldn't update event\n");
                        conn_set_state(c, conn_closing);
                        break;
                    }
                    stop = true;
                    break;
                }
                /* otherwise we have a real error, on which we close the connection */
                if (settings.verbose > 0)
                    fprintf(stderr, "Failed to read, and not due to blocking\n");
                conn_set_state(c, conn_closing);
                break;
    
            case conn_write:
                /* * We want to write out a simple response. If we haven't already, * assemble it into a msgbuf list (this will be a single-entry * list for TCP or a two-entry list for UDP). */
                if (c->iovused == 0 || (IS_UDP(c->transport) && c->iovused == 1)) {
                    if (add_iov(c, c->wcurr, c->wbytes) != 0) {
                        if (settings.verbose > 0)
                            fprintf(stderr, "Couldn't build response\n");
                        conn_set_state(c, conn_closing);
                        break;
                    }
                }
    
                /* fall through... */
    
            case conn_mwrite:
              if (IS_UDP(c->transport) && c->msgcurr == 0 && build_udp_headers(c) != 0) {
                if (settings.verbose > 0)
                  fprintf(stderr, "Failed to build UDP headers\n");
                conn_set_state(c, conn_closing);
                break;
              }
                switch (transmit(c)) {
                case TRANSMIT_COMPLETE:
                    if (c->state == conn_mwrite) {
                        conn_release_items(c);
                        /* XXX: I don't know why this wasn't the general case */
                        if(c->protocol == binary_prot) {
                            conn_set_state(c, c->write_and_go);
                        } else {
                            conn_set_state(c, conn_new_cmd);
                        }
                    } else if (c->state == conn_write) {
                        if (c->write_and_free) {
                            free(c->write_and_free);
                            c->write_and_free = 0;
                        }
                        conn_set_state(c, c->write_and_go);
                    } else {
                        if (settings.verbose > 0)
                            fprintf(stderr, "Unexpected state %d\n", c->state);
                        conn_set_state(c, conn_closing);
                    }
                    break;
    
                case TRANSMIT_INCOMPLETE:
                case TRANSMIT_HARD_ERROR:
                    break;                   /* Continue in state machine. */
    
                case TRANSMIT_SOFT_ERROR:
                    stop = true;
                    break;
                }
                break;
    
            case conn_closing:
                if (IS_UDP(c->transport))
                    conn_cleanup(c);
                else
                    conn_close(c);
                stop = true;
                break;
    
            case conn_closed:
                /* This only happens if dormando is an idiot. */
                abort();
                break;
    
            case conn_max_state:
                assert(false);
                break;
            }
        }

因为有各种状态的存在，使回调函数`event_handler`可以处理所有事件，当事件就绪时候，全部都会调用`event_handler`，然后`event_handler`通过连接状态的不同，选择不同的分支进行操作。这就是有限状态机的好处。

`conn_listening`：主线程将listen fd加入其epoll时候，状态是这个，当连接到来，会依据这个状态选择accept分支。

//主线程事件就绪执行的部分。accept连接即可。
    switch(c->state) {
            case conn_listening:
                addrlen = sizeof(addr);
                sfd = accept(c->sfd, (struct sockaddr *)&addr, &addrlen);
                if (sfd == -1) {
                    if (use_accept4 && errno == ENOSYS) {
                        use_accept4 = 0;
                        continue;
                    }
                    perror(use_accept4 ? "accept4()" : "accept()");
                    if (errno == EAGAIN || errno == EWOULDBLOCK) {
                        /* these are transient, so don't log anything */
                        stop = true;
                    } else if (errno == EMFILE) {
                        if (settings.verbose > 0)
                            fprintf(stderr, "Too many open connections\n");
                        accept_new_conns(false);
                        stop = true;
                    } else {
                        perror("accept()");
                        stop = true;
                    }
                    break;
                }
                if (!use_accept4) {
                    if (fcntl(sfd, F_SETFL, fcntl(sfd, F_GETFL) | O_NONBLOCK) < 0) {
                        perror("setting O_NONBLOCK");
                        close(sfd);
                        break;
                    }
                }
    
                if (settings.maxconns_fast &&
                    stats.curr_conns + stats.reserved_fds >= settings.maxconns - 1) {
                    str = "ERROR Too many open connections\r\n";
                    res = write(sfd, str, strlen(str));
                    close(sfd);
                    STATS_LOCK();
                    stats.rejected_conns++;
                    STATS_UNLOCK();
                } else {
                    //选定一个worker线程，new一个CQ_ITEM，把这个CQ_ITEM仍给这个线程. 
                    dispatch_conn_new(sfd, conn_new_cmd, EV_READ | EV_PERSIST,
                                         DATA_BUFFER_SIZE, tcp_transport);
                }
    
                stop = true;
                break;
    
    
    
    /* 主线程，选择一个子线程，并通过写管道通知子线程。 */
    void dispatch_conn_new(int sfd, enum conn_states init_state, int event_flags,
                           int read_buffer_size, enum network_transport transport) {
        CQ_ITEM *item = cqi_new();//申请CQ_ITEM.
        char buf[1];
        if (item == NULL) {
            close(sfd);
            /* given that malloc failed this may also fail, but let's try */
            fprintf(stderr, "Failed to allocate memory for connection object\n");
            return ;
        }
    
        int tid = (last_thread + 1) % settings.num_threads;//轮询很简单。一个一个给连接。
    
        LIBEVENT_THREAD *thread = threads + tid;//线程获取结构体。
    
        last_thread = tid;
    
        item->sfd = sfd;
        item->init_state = init_state;//conn_new_cmd
        item->event_flags = event_flags;//EV_READ | EV_PERSIST
        item->read_buffer_size = read_buffer_size;
        item->transport = transport;
    
        cq_push(thread->new_conn_queue, item);//将连接压入子线程对象的连接队列。
    
        MEMCACHED_CONN_DISPATCH(sfd, thread->thread_id);
        buf[0] = 'c';
        if (write(thread->notify_send_fd, buf, 1) != 1) {
       //往子线程管道写入一字节表示通知
            perror("Writing to thread notify pipe");
        }
    }

这里一定要理解`dispatch_conn_new`做的操作：

1、新键一个CQ\_ITEM元素，并通过轮询选择合适线程，并压入其连接队列。

2、通过写对应子线程管道通知子线程。

**3、为什么每个子线程需要维护一个连接队列？**

> **当工作线程正在处理一个时间较长的get请求时**，这时主线程通过轮训已经分配给当前工作线程3个待处理连接(加入了队列，并往管道写了3个‘c’字符)，。这是管道可读就绪。工作线程再次从`epoll_wait`返回之后，从管道仅仅读取一字节，因为默认epoll是水平触发。所以下次继续可读，直到从管道读完所有字节并将其连接。这样就可以完全保证工作线程可以处理完所有的连接，丝毫没有问题。这就是多线程程序的优势所在，开销比进程小，仅仅需要一些简单的同步处理。例如上述读写CQ队列，就需要加锁。

[70]: /images/20220525/87187d00caa448ccbb72f5b6fdf46667.png
[70 1]: /images/20220525/5cdc45e112ac4e55b85d6ebe5f9733f0.png
[70 2]: /images/20220525/ac3a570e13894e6abdd0d619d0028f3d.png
[70 3]: /images/20220525/7722386960304e1e97185aaa5098ec87.png