Linux 下epoll 網絡模型

爲何須要epoll?

基於select 的I/O 複用技術速度過慢，從代碼上分析，最主要的兩點是

1. 每次調用select 函數是都須要向改函數傳遞對象信息
2. 須要遍歷全部文件描述符才能獲取有變化的文件描述符

epoll 不須要以上兩點操做

epoll 函數介紹

epoll_create

/* Creates an epoll instance.  Returns an fd for the new instance.
   The "size" parameter is a hint specifying the number of file
   descriptors to be associated with the new instance.  The fd
   returned by epoll_create() should be closed with close().  */
extern int epoll_create (int __size) __THROW;

epoll_ctl

/* Manipulate an epoll instance "epfd". Returns 0 in case of success,
   -1 in case of error ( the "errno" variable will contain the
   specific error code ) The "op" parameter is one of the EPOLL_CTL_*
   constants defined above. The "fd" parameter is the target of the
   operation. The "event" parameter describes which events the caller
   is interested in and any associated user data.  */
extern int epoll_ctl (int __epfd, int __op, int __fd,
		      struct epoll_event *__event) __THROW;

epoll_wait

/* Wait for events on an epoll instance "epfd". Returns the number of
   triggered events returned in "events" buffer. Or -1 in case of
   error with the "errno" variable set to the specific error code. The
   "events" parameter is a buffer that will contain triggered
   events. The "maxevents" is the maximum number of events to be
   returned ( usually size of "events" ). The "timeout" parameter
   specifies the maximum wait time in milliseconds (-1 == infinite).

   This function is a cancellation point and therefore not marked with
   __THROW.  */
extern int epoll_wait (int __epfd, struct epoll_event *__events,
		       int __maxevents, int __timeout);

epoll_event

struct epoll_event
{
  uint32_t events;	/* Epoll events */
  epoll_data_t data;	/* User data variable */
} __EPOLL_PACKED;

epoll_data_t

typedef union epoll_data
{
  void *ptr;
  int fd;
  uint32_t u32;
  uint64_t u64;
} epoll_data_t;

利用epoll I/O 複用的服務端

服務端

1. 創建套接字
2. 綁定端口
3. 監聽客戶端請求狀態
4. 設置epollfd
5. 調用epoll_wait
   • 若是是服務端套接字發生變化，說明有新的鏈接，調用accept 函數受理
   • 若是不是服務端套接字發生變化，則響應客戶端
6. 關閉

代碼以下：

epoll.c

#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
#include <arpa/inet.h>
#include <sys/socket.h>
#include <sys/epoll.h>

#define BUF_SIZE 100
#define EPOLL_SIZE 50

void error_handling(char *message)
{
    fputs(message, stderr);
    fputc('\n', stderr);
    exit(1);
}
int main(int argc, char *argv[])
{
    int serv_sock, clnt_sock;
    struct sockaddr_in serv_adr, clnt_adr;
    socklen_t adr_sz;
    int str_len, i;
    char buf[BUF_SIZE];

    struct epoll_event *ep_events;
    struct epoll_event event;
    int epfd, event_cnt;

    if (argc != 2)
    {
        printf("Usage : %s <port> \n", argv[0]);
        exit(1);
    }
    serv_sock = socket(PF_INET, SOCK_STREAM, 0);
    memset(&serv_adr, 0, sizeof(serv_adr));
    serv_adr.sin_family = AF_INET;
    serv_adr.sin_addr.s_addr = htonl(INADDR_ANY);
    serv_adr.sin_port = htons(atoi(argv[1]));

    if (bind(serv_sock, (struct sockaddr *)&serv_adr, sizeof(serv_adr)) == -1)
        error_handling("bind error");
    if (listen(serv_sock, 5) == -1)
        error_handling("listen error");

    epfd = epoll_create(EPOLL_SIZE); //可忽略這個參數，填入的參數爲操做系統參考
    ep_events = malloc(sizeof(struct epoll_event) * EPOLL_SIZE);

    event.events = EPOLLIN; //讀取數據
    event.data.fd = serv_sock;
    epoll_ctl(epfd, EPOLL_CTL_ADD, serv_sock, &event); //epoll例程epfd 中添加文件描述符 serv_sock，目的是監聽 enevt 中的事件

    while (1)
    {
        event_cnt = epoll_wait(epfd, ep_events, EPOLL_SIZE, -1); //獲取改變了的文件描述符，返回數量
        if (event_cnt == -1)
        {
            puts("epoll_wait error");
            break;
        }

        for (i = 0; i < event_cnt; i++)
        {
            if (ep_events[i].data.fd == serv_sock) //客戶端請求鏈接
            {
                adr_sz = sizeof(clnt_adr);
                clnt_sock = accept(serv_sock, (struct sockaddr *)&clnt_adr, &adr_sz);
                event.events = EPOLLIN;
                event.data.fd = clnt_sock; //把客戶端套接字添加進去
                epoll_ctl(epfd, EPOLL_CTL_ADD, clnt_sock, &event);
                printf("connected client : %d \n", clnt_sock);
            }
            else //客戶端套接字
            {
                str_len = read(ep_events[i].data.fd, buf, BUF_SIZE);
                if (str_len == 0)
                {
                    epoll_ctl(epfd, EPOLL_CTL_DEL, ep_events[i].data.fd, NULL); //從epoll中刪除套接字
                    close(ep_events[i].data.fd);
                    printf("closed client : %d \n", ep_events[i].data.fd);
                }
                else
                {
                    printf("Message from client: %s\n", buf); 
                    write(ep_events[i].data.fd, buf, str_len);
                }
            }
        }
    }
    close(serv_sock);
    close(epfd);

    return 0;
}

client.c

#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
#include <arpa/inet.h>
#include <sys/socket.h>

#define BUF_SIZE 100
void error_handling(char *message)
{
    fputs(message, stderr);
    fputc('\n', stderr);
    exit(1);
}

int main(int argc, char *argv[])
{
    int sock;
    char message[BUF_SIZE]="Hello World";
    int str_len;
    struct sockaddr_in serv_adr;

    if (argc != 3)
    {
        printf("Usage : %s <IP> <port>\n", argv[0]);
        exit(1);
    }

    sock = socket(PF_INET, SOCK_STREAM, 0);
    if (sock == -1)
        error_handling("socket error");

    memset(&serv_adr, 0, sizeof(serv_adr));
    serv_adr.sin_family = AF_INET;
    serv_adr.sin_addr.s_addr = inet_addr(argv[1]);
    serv_adr.sin_port = htons(atoi(argv[2]));

    if (connect(sock, (struct sockaddr *)&serv_adr, sizeof(serv_adr)) == -1)
        error_handling("connect error!");
    else
        puts("Connected...........");

  
    write(sock, message, strlen(message));
    str_len = read(sock, message, BUF_SIZE - 1);
    message[str_len] = 0;
    printf("Message from server: %s\n", message); 
    close(sock);
    return 0;
}

運行結果

connected client : 5 
Message from client: Hello World
closed client : 5 

Connected...........
Message from server: Hello World

epoll 的兩種觸發模式

條件觸發和邊緣觸發的區別在於發生時間的時間點

1.條件觸發 LT

epoll 默認以條件觸發方式工做

條件觸發時只要輸入緩衝區任有數據須要讀取，就會註冊新的事件

測試代碼：

ltServer.c

#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
#include <arpa/inet.h>
#include <sys/socket.h>
#include <sys/epoll.h>

#define BUF_SIZE 3
#define EPOLL_SIZE 50
void error_handling(char *message)
{
    fputs(message, stderr);
    fputc('\n', stderr);
    exit(1);
}


int main(int argc, char *argv[])
{
    int serv_sock, clnt_sock;
    struct sockaddr_in serv_adr, clnt_adr;
    socklen_t adr_sz;
    int str_len, i;
    char buf[BUF_SIZE];

    struct epoll_event *ep_events;
    struct epoll_event event;
    int epfd, event_cnt;

    if (argc != 2)
    {
        printf("Usage : %s <port> \n", argv[0]);
        exit(1);
    }
    serv_sock = socket(PF_INET, SOCK_STREAM, 0);
    memset(&serv_adr, 0, sizeof(serv_adr));
    serv_adr.sin_family = AF_INET;
    serv_adr.sin_addr.s_addr = htonl(INADDR_ANY);
    serv_adr.sin_port = htons(atoi(argv[1]));

    if (bind(serv_sock, (struct sockaddr *)&serv_adr, sizeof(serv_adr)) == -1)
        error_handling("bind error");
    if (listen(serv_sock, 5) == -1)
        error_handling("listen error");

    epfd = epoll_create(EPOLL_SIZE); 
    ep_events = malloc(sizeof(struct epoll_event) * EPOLL_SIZE);

    event.events = EPOLLIN; 
    event.data.fd = serv_sock;
    epoll_ctl(epfd, EPOLL_CTL_ADD, serv_sock, &event); 

    while (1)
    {
        event_cnt = epoll_wait(epfd, ep_events, EPOLL_SIZE, -1); //獲取改變了的文件描述符，返回數量

        if (event_cnt == -1)
        {
            puts("epoll_wait error");
            break;
        }

        puts("call epoll_wait");
        for (i = 0; i < event_cnt; i++)
        {

            if (ep_events[i].data.fd == serv_sock) 
            {
                adr_sz = sizeof(clnt_adr);
                clnt_sock = accept(serv_sock, (struct sockaddr *)&clnt_adr, &adr_sz);
                event.events = EPOLLIN;
                event.data.fd = clnt_sock; 
                epoll_ctl(epfd, EPOLL_CTL_ADD, clnt_sock, &event);
                printf("connected client : %d \n", clnt_sock);
            }
            else 
            {
                str_len = read(ep_events[i].data.fd, buf, BUF_SIZE);
                if (str_len == 0)
                {
                    epoll_ctl(epfd, EPOLL_CTL_DEL, ep_events[i].data.fd, NULL); //從epoll中刪除套接字
                    close(ep_events[i].data.fd);
                    printf("closed client : %d \n", ep_events[i].data.fd);
                }
                else
                {
                    printf("Message from client: %s\n", buf); 
                    write(ep_events[i].data.fd, buf, str_len);
                }
            }
        }
    }
    close(serv_sock);
    close(epfd);

    return 0;
}

client.c

#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
#include <arpa/inet.h>
#include <sys/socket.h>

#define BUF_SIZE 1024
void error_handling(char *message)
{
    fputs(message, stderr);
    fputc('\n', stderr);
    exit(1);
}

int main(int argc, char *argv[])
{
    //sock
    int sock;
    char message[BUF_SIZE];
    int str_len;
    struct sockaddr_in serv_adr;

    if (argc != 3)
    {
        printf("Usage : %s <IP> <port>\n", argv[0]);
        exit(1);
    }

    sock = socket(PF_INET, SOCK_STREAM, 0);
    if (sock == -1)
        error_handling("socket error");

    memset(&serv_adr, 0, sizeof(serv_adr));
    serv_adr.sin_family = AF_INET;
    serv_adr.sin_addr.s_addr = inet_addr(argv[1]);
    serv_adr.sin_port = htons(atoi(argv[2]));

    if (connect(sock, (struct sockaddr *)&serv_adr, sizeof(serv_adr)) == -1)
        error_handling("connect error!");
    else
        puts("Connected...........");

    while (1)
    {
        fputs("Input message: ", stdout);
        fgets(message, BUF_SIZE, stdin);
        write(sock, message, strlen(message));
        str_len = read(sock, message, BUF_SIZE - 1);
        message[str_len] = 0;
        printf("Message from server: %s\n", message);
    }
    close(sock);
    return 0;
}

測試結果

call epoll_wait
connected client : 5 
call epoll_wait
Message from client: abc
call epoll_wait
Message from client: def
call epoll_wait
Message from client: g


Connected...........
Input message: abcdefg
Message from server: abcdefg

2.邊緣觸發

在邊緣觸發模式中輸入緩衝收到數據時僅註冊一次該事件。
也就是說會一次性讀完全部數據或者一次性寫徹底部數據，那麼在使用邊緣觸發時許將套接字改成非阻塞模式，不然可能由於較長的I/O 時間引發服務的卡頓。

測試代碼：

etServer.c

#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
#include <arpa/inet.h>
#include <sys/socket.h>
#include <sys/epoll.h>
#include <fcntl.h>
#include <errno.h>

#define BUF_SIZE 3 
#define EPOLL_SIZE 50
void error_handling(char *message)
{
    fputs(message, stderr);
    fputc('\n', stderr);
    exit(1);
}
void setnonblockingmode(int fd)
{
    int flag = fcntl(fd, F_GETFL, 0);
    fcntl(fd, F_SETFL, flag | O_NONBLOCK);
}

int main(int argc, char *argv[])
{
    int serv_sock, clnt_sock;
    struct sockaddr_in serv_adr, clnt_adr;
    socklen_t adr_sz;
    int str_len, i;
    char buf[BUF_SIZE];

    struct epoll_event *ep_events;
    struct epoll_event event;
    int epfd, event_cnt;

    if (argc != 2)
    {
        printf("Usage : %s <port> \n", argv[0]);
        exit(1);
    }
    serv_sock = socket(PF_INET, SOCK_STREAM, 0);
    memset(&serv_adr, 0, sizeof(serv_adr));
    serv_adr.sin_family = AF_INET;
    serv_adr.sin_addr.s_addr = htonl(INADDR_ANY);
    serv_adr.sin_port = htons(atoi(argv[1]));

    if (bind(serv_sock, (struct sockaddr *)&serv_adr, sizeof(serv_adr)) == -1)
        error_handling("bind error");
    if (listen(serv_sock, 5) == -1)
        error_handling("listen error");

    epfd = epoll_create(EPOLL_SIZE); 
    ep_events = malloc(sizeof(struct epoll_event) * EPOLL_SIZE);

    setnonblockingmode(serv_sock);
    event.events = EPOLLIN; 
    event.data.fd = serv_sock;
    epoll_ctl(epfd, EPOLL_CTL_ADD, serv_sock, &event); 
    while (1)
    {
        event_cnt = epoll_wait(epfd, ep_events, EPOLL_SIZE, -1); 
        if (event_cnt == -1)
        {
            puts("epoll_wait error");
            break;
        }

        puts("call epoll_wait");
        for (i = 0; i < event_cnt; i++)
        {
            if (ep_events[i].data.fd == serv_sock) 
            {
                adr_sz = sizeof(clnt_adr);
                clnt_sock = accept(serv_sock, (struct sockaddr *)&clnt_adr, &adr_sz);
                setnonblockingmode(clnt_sock);    
                event.events = EPOLLIN | EPOLLET; 
                event.data.fd = clnt_sock;       
                epoll_ctl(epfd, EPOLL_CTL_ADD, clnt_sock, &event);
                printf("connected client : %d \n", clnt_sock);
            }
            else 
            {
                while (1)
                {
                    str_len = read(ep_events[i].data.fd, buf, BUF_SIZE);
                    if (str_len == 0)
                    {
                        epoll_ctl(epfd, EPOLL_CTL_DEL, ep_events[i].data.fd, NULL); //從epoll中刪除套接字
                        close(ep_events[i].data.fd);
                        printf("closed client : %d \n", ep_events[i].data.fd);
                        break;
                    }
                    else if (str_len < 0)
                    {
                        if (errno == EAGAIN) //read 返回-1 且 errno 值爲 EAGAIN ，意味讀取了輸入緩衝的所有數據
                            break;
                    }
                    else
                    {
                        printf("Message from client: %s\n", buf); 
                        write(ep_events[i].data.fd, buf, str_len);
                    }
                }
            }
        }
    }
    close(serv_sock);
    close(epfd);

    return 0;
}

client.c

#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
#include <arpa/inet.h>
#include <sys/socket.h>

#define BUF_SIZE 1024
void error_handling(char *message)
{
    fputs(message, stderr);
    fputc('\n', stderr);
    exit(1);
}

int main(int argc, char *argv[])
{
    //sock
    int sock;
    char message[BUF_SIZE];
    int str_len;
    struct sockaddr_in serv_adr;

    if (argc != 3)
    {
        printf("Usage : %s <IP> <port>\n", argv[0]);
        exit(1);
    }

    sock = socket(PF_INET, SOCK_STREAM, 0);
    if (sock == -1)
        error_handling("socket error");

    memset(&serv_adr, 0, sizeof(serv_adr));
    serv_adr.sin_family = AF_INET;
    serv_adr.sin_addr.s_addr = inet_addr(argv[1]);
    serv_adr.sin_port = htons(atoi(argv[2]));

    if (connect(sock, (struct sockaddr *)&serv_adr, sizeof(serv_adr)) == -1)
        error_handling("connect error!");
    else
        puts("Connected...........");

    while (1)
    {
        fputs("Input message: ", stdout);
        fgets(message, BUF_SIZE, stdin);
        write(sock, message, strlen(message));
        str_len = read(sock, message, BUF_SIZE - 1);
        message[str_len] = 0;
        printf("Message from server: %s\n", message);
    }
    close(sock);
    return 0;
}

測試結果

call epoll_wait
connected client : 5 
call epoll_wait
Message from client: abc
Message from client: def
Message from client: fg
call epoll_wait
closed client : 5 

Connected...........
Input message: abcdeffg
Message from server: abcdeffg
Input message: ^C

邊緣觸發

分離了接受數據和處理數據的時間點 （一次性接受完數據，當有多個類別數據傳輸時能夠保持各個類別數據的獨立性，完整性由TCP保證）