《深入理解计算机系统》实验八Proxy Lab

前言

新年快乐。欢迎来到本书的最后一个实验。

《深入理解计算机系统》实验八Proxy Lab下载和官方文档机翻请看：
https://blog.csdn.net/weixin_43362650/article/details/122770330

我觉得这个文档对整个实验很有帮助。

实验任务

编写一个简单的HTTP代理服务器

代理服务器英文全称是Proxy Server，其功能就是代理网络用户去取得网络信息。形象的说：它是网络信息的中转站。在一般情况下，我们使用网络浏览器直接去连接其他Internet站点取得网络信息时，须送出Request信号来得到回答，然后对方再把信息以bit方式传送回来。代理服务器是介于浏览器和Web服务器之间的一台服务器，有了它之后，浏览器不是直接到Web服务器去取回网页而是向代理服务器发出请求，Request信号会先送到代理服务器，由代理服务器来取回浏览器所需要的信息并传送给你的浏览器。–百度百科

原本客户端与服务器的关系。

加上代理后就是

代理服务器要做的就是接收客户端发送的请求，经过自己的处理后发送请求到服务端，服务端响应的数据到代理服务器后转发回给客户端。

本实验的代理服务器分为3个阶段

第一部分：实现顺序web代理第二部分：处理多个并发请求第三部分：缓存web对象第一部分：实现顺序web代理

代码如下(详情看注释)

#include 
#include "csapp.h"


#define MAX_CACHE_SIZE 1049000
#define MAX_OBJECT_SIZE 102400


static const char *user_agent_hdr = "User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:10.0.3) Gecko/20120305 Firefox/10.0.3rn";

void doit(int clientfd);
int parse_uri(char *uri,char *hostname,char *path,char *port,char *request_head);
void read_requesthdrs(rio_t *rp,int fd);
void return_content(int serverfd, int clientfd);


int main(int argc,char **argv)
{
    int listenfd,connfd;
    char hostname[MAXLINE],port[MAXLINE];
    socklen_t clientlen;
    struct sockaddr_storage clientaddr;

    if(argc != 2){
        fprintf(stderr, "usage: %s n", argv[0]);
        exit(1);
    }

    
    listenfd = Open_listenfd(argv[1]);
    while(1){
        clientlen = sizeof(clientaddr);

        
        connfd = Accept(listenfd,(SA *)&clientaddr,&clientlen);

        
        Getnameinfo((SA *)&clientaddr,clientlen,hostname,MAXLINE,port,MAXLINE,0);
        printf("Accepted connection from (%s, %s)n",hostname,port);
        doit(connfd);
        Close(connfd);
    }
}


void doit(int clientfd){

    char buf[MAXLINE],method[MAXLINE],uri[MAXLINE],version[MAXLINE];
    char hostname[MAXLINE],path[MAXLINE],port[MAXLINE],request_head[MAXLINE];
    int serverfd;
    rio_t rio;

    
    Rio_readinitb(&rio,clientfd);
    Rio_readlineb(&rio,buf,MAXLINE);
    sscanf(buf,"%s %s %s",method,uri,version);
    if(strcasecmp(method,"GET")){
        printf("Not implemented");
        return;
    }

    
    parse_uri(uri,hostname,path,port,request_head);

    
    serverfd = Open_clientfd(hostname,port);

    
    Rio_writen(serverfd,request_head,strlen(request_head));
    read_requesthdrs(&rio,serverfd);

    
    return_content(serverfd,clientfd);


}


int parse_uri(char *uri,char *hostname,char *path,char *port,char *request_head){

    sprintf(port,"80");     //默认值

    char *end,*bp;
    char *tail = uri+strlen(uri);   //uri的最后一个字符，不是''。

    char *bg = strstr(uri,"//");

    bg = (bg!=NULL ? bg+2 : uri);   //取hostname的开头。

    end = bg;                        
    //取hostname的结尾。
    while(*end != '/' && *end != ':') end++;
    strncpy(hostname,bg,end-bg);

    bp = end + 1;                   //取port的开头
    if(*end == ':'){                //==':'说明uri中有port
        end++;
        bp = strstr(bg,"/");        //取port的结尾

        strncpy(port,end,bp-end);   
        end = bp;                   //取uri的开头
    }
    strncpy(path,end,(int)(tail-end)+1);

    
    sprintf(request_head,"GET %s HTTP/1.0rnHost: %srn",path,hostname);
    
    return 1;
}


void read_requesthdrs(rio_t *rp,int fd){
    
    char buf[MAXLINE];

    sprintf(buf, "%s", user_agent_hdr);
    Rio_writen(fd, buf, strlen(buf));
    sprintf(buf, "Connection: closern");
    Rio_writen(fd, buf, strlen(buf));
    sprintf(buf, "Proxy-Connection: closern");
    Rio_writen(fd, buf, strlen(buf));

    
    for(Rio_readlineb(rp,buf,MAXLINE);strcmp(buf,"rn");Rio_readlineb(rp,buf,MAXLINE)){
        if(strncmp("Host",buf,4) == 0 || strncmp("User-Agent",buf,10) == 0
            || strncmp("Connection",buf,10) == 0 || strncmp("Proxy-Connection",buf,16) == 0)
                continue;
        printf("%s",buf);
        Rio_writen(fd,buf,strlen(buf));
    }
    Rio_writen(fd,buf,strlen(buf));
    return;
}


void return_content(int serverfd, int clientfd){

    size_t n;
    char buf[MAXLINE];
    rio_t srio;

    Rio_readinitb(&srio,serverfd);
    while((n = Rio_readlineb(&srio,buf,MAXLINE)) != 0){
        Rio_writen(clientfd,buf,n);
    }
    
}

编译

可能有些环境没安装好，我第一次就是没有“curl”。

linux> apt-get install  curl

运行

可以看到第一部分已经完成。

第二部分：处理多个并发请求

参考《CS:APP3e》12.3.8 基于线程的并发服务器修改第一部分的代码(修改了main函数和添加了thread函数)

#include 
#include "csapp.h"


#define MAX_CACHE_SIZE 1049000
#define MAX_OBJECT_SIZE 102400


static const char *user_agent_hdr = "User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:10.0.3) Gecko/20120305 Firefox/10.0.3rn";

void doit(int clientfd);
int parse_uri(char *uri,char *hostname,char *path,char *port,char *request_head);
void read_requesthdrs(rio_t *rp,int fd);
void return_content(int serverfd, int clientfd);
void *thread(void *vargp);


int main(int argc,char **argv)
{
    int listenfd;
    int *connfd;        
    char hostname[MAXLINE],port[MAXLINE];
    socklen_t clientlen;
    struct sockaddr_storage clientaddr;
    pthread_t tid;

    if(argc != 2){
        fprintf(stderr, "usage: %s n", argv[0]);
        exit(1);
    }

    
    listenfd = Open_listenfd(argv[1]);
    while(1){
        clientlen = sizeof(clientaddr);

        connfd = Malloc(sizeof(int));

        
        *connfd = Accept(listenfd,(SA *)&clientaddr,&clientlen);

        
        Getnameinfo((SA *)&clientaddr,clientlen,hostname,MAXLINE,port,MAXLINE,0);
        printf("Accepted connection from (%s, %s)n",hostname,port);

        
        Pthread_create(&tid,NULL,thread,connfd);
    }
}

void *thread(void *vargp){
    int connfd = *((int *)vargp);
    Pthread_detach(pthread_self());
    Free(vargp);
    doit(connfd);
    Close(connfd);
    return NULL;
}


void doit(int clientfd){

    char buf[MAXLINE],method[MAXLINE],uri[MAXLINE],version[MAXLINE];
    char hostname[MAXLINE],path[MAXLINE],port[MAXLINE],request_head[MAXLINE];
    int serverfd;
    rio_t rio;

    
    Rio_readinitb(&rio,clientfd);
    Rio_readlineb(&rio,buf,MAXLINE);
    sscanf(buf,"%s %s %s",method,uri,version);
    if(strcasecmp(method,"GET")){
        printf("Not implemented");
        return;
    }

    
    parse_uri(uri,hostname,path,port,request_head);

    
    serverfd = Open_clientfd(hostname,port);

    
    Rio_writen(serverfd,request_head,strlen(request_head));
    read_requesthdrs(&rio,serverfd);

    
    return_content(serverfd,clientfd);


}


int parse_uri(char *uri,char *hostname,char *path,char *port,char *request_head){

    sprintf(port,"80");     //默认值

    char *end,*bp;
    char *tail = uri+strlen(uri);   //uri的最后一个字符，不是''。

    char *bg = strstr(uri,"//");

    bg = (bg!=NULL ? bg+2 : uri);   //取hostname的开头。

    end = bg;                        
    //取hostname的结尾。
    while(*end != '/' && *end != ':') end++;
    strncpy(hostname,bg,end-bg);

    bp = end + 1;                   //取port的开头
    if(*end == ':'){                //==':'说明uri中有port
        end++;
        bp = strstr(bg,"/");        //取port的结尾

        strncpy(port,end,bp-end);   
        end = bp;                   //取uri的开头
    }
    strncpy(path,end,(int)(tail-end)+1);

    
    sprintf(request_head,"GET %s HTTP/1.0rnHost: %srn",path,hostname);
    
    return 1;
}


void read_requesthdrs(rio_t *rp,int fd){
    
    char buf[MAXLINE];

    sprintf(buf, "%s", user_agent_hdr);
    Rio_writen(fd, buf, strlen(buf));
    sprintf(buf, "Connection: closern");
    Rio_writen(fd, buf, strlen(buf));
    sprintf(buf, "Proxy-Connection: closern");
    Rio_writen(fd, buf, strlen(buf));

    
    for(Rio_readlineb(rp,buf,MAXLINE);strcmp(buf,"rn");Rio_readlineb(rp,buf,MAXLINE)){
        if(strncmp("Host",buf,4) == 0 || strncmp("User-Agent",buf,10) == 0
            || strncmp("Connection",buf,10) == 0 || strncmp("Proxy-Connection",buf,16) == 0)
                continue;
        printf("%s",buf);
        Rio_writen(fd,buf,strlen(buf));
    }
    Rio_writen(fd,buf,strlen(buf));
    return;
}


void return_content(int serverfd, int clientfd){

    size_t n;
    char buf[MAXLINE];
    rio_t srio;

    Rio_readinitb(&srio,serverfd);
    while((n = Rio_readlineb(&srio,buf,MAXLINE)) != 0){
        Rio_writen(clientfd,buf,n);
    }

}

运行

可以看到第二部分已经完成

第三部分：缓存web对象

采用读者优先，代码如下

#include 
#include "csapp.h"


#define MAX_CACHE_SIZE 1049000
#define MAX_OBJECT_SIZE 102400
#define MAX_CACHE 10


static const char *user_agent_hdr = "User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:10.0.3) Gecko/20120305 Firefox/10.0.3rn";

void doit(int clientfd);
int parse_uri(char *uri,char *hostname,char *path,char *port,char *request_head);
void read_requesthdrs(rio_t *rp,int fd);
void return_content(int serverfd, int clientfd,char *url);
void *thread(void *vargp);
int maxlrucache();


struct RWLOCK_T{
    sem_t lock;         //基本锁
    sem_t writeLock;    //写着锁
    int readcnt;        //读者个数
};


struct CACHE{
    int lruNumber;                  //引用次数，根据大小排位。大的表示最近引用过
    char url[MAXLINE];              //通过url唯一标识对应content
    char content[MAX_OBJECT_SIZE];
};

struct CACHE cache[MAX_CACHE];      //缓存，最多有MAX_CACHE个
struct RWLOCK_T* rw;                //读写者锁指针

void rwlock_init();                     //初始化读写者锁指针
char *readcache(char *url);             //读缓存
void writecache(char *buf,char *url);   //写缓存


int main(int argc,char **argv)
{
    int listenfd;
    int *connfd;        
    char hostname[MAXLINE],port[MAXLINE];
    socklen_t clientlen;
    struct sockaddr_storage clientaddr;
    pthread_t tid;

    if(argc != 2){
        fprintf(stderr, "usage: %s n", argv[0]);
        exit(1);
    }

    rw = Malloc(sizeof(struct RWLOCK_T));
    rwlock_init();

    
    listenfd = Open_listenfd(argv[1]);
    while(1){
        clientlen = sizeof(clientaddr);

        connfd = Malloc(sizeof(int));

        
        *connfd = Accept(listenfd,(SA *)&clientaddr,&clientlen);

        
        Getnameinfo((SA *)&clientaddr,clientlen,hostname,MAXLINE,port,MAXLINE,0);
        printf("Accepted connection from (%s, %s)n",hostname,port);

        
        Pthread_create(&tid,NULL,thread,connfd);
    }
}

void *thread(void *vargp){
    int connfd = *((int *)vargp);
    Pthread_detach(pthread_self());
    Free(vargp);
    doit(connfd);
    Close(connfd);
    return NULL;
}


void doit(int clientfd){

    char buf[MAXLINE],method[MAXLINE],uri[MAXLINE],version[MAXLINE];
    char hostname[MAXLINE],path[MAXLINE],port[MAXLINE],request_head[MAXLINE];
    int serverfd;
    rio_t rio;

    
    Rio_readinitb(&rio,clientfd);
    Rio_readlineb(&rio,buf,MAXLINE);
    sscanf(buf,"%s %s %s",method,uri,version);
    if(strcasecmp(method,"GET")){
        printf("Not implemented");
        return;
    }

    char *content = readcache(uri);
    if(content != NULL){
        Rio_writen(clientfd,content,strlen(content));
        free(content);
    }else{
        
        parse_uri(uri,hostname,path,port,request_head);

        
        serverfd = Open_clientfd(hostname,port);

        
        Rio_writen(serverfd,request_head,strlen(request_head));
        read_requesthdrs(&rio,serverfd);

        
        return_content(serverfd,clientfd,uri);

    }


}


int parse_uri(char *uri,char *hostname,char *path,char *port,char *request_head){

    sprintf(port,"80");     //默认值

    char *end,*bp;
    char *tail = uri+strlen(uri);   //uri的最后一个字符，不是''。

    char *bg = strstr(uri,"//");

    bg = (bg!=NULL ? bg+2 : uri);   //取hostname的开头。

    end = bg;                        
    //取hostname的结尾。
    while(*end != '/' && *end != ':') end++;
    strncpy(hostname,bg,end-bg);

    bp = end + 1;                   //取port的开头
    if(*end == ':'){                //==':'说明uri中有port
        end++;
        bp = strstr(bg,"/");        //取port的结尾

        strncpy(port,end,bp-end);   
        end = bp;                   //取uri的开头
    }
    strncpy(path,end,(int)(tail-end)+1);

    
    sprintf(request_head,"GET %s HTTP/1.0rnHost: %srn",path,hostname);
    
    return 1;
}


void read_requesthdrs(rio_t *rp,int fd){
    
    char buf[MAXLINE];

    sprintf(buf, "%s", user_agent_hdr);
    Rio_writen(fd, buf, strlen(buf));
    sprintf(buf, "Connection: closern");
    Rio_writen(fd, buf, strlen(buf));
    sprintf(buf, "Proxy-Connection: closern");
    Rio_writen(fd, buf, strlen(buf));

    
    for(Rio_readlineb(rp,buf,MAXLINE);strcmp(buf,"rn");Rio_readlineb(rp,buf,MAXLINE)){
        if(strncmp("Host",buf,4) == 0 || strncmp("User-Agent",buf,10) == 0
            || strncmp("Connection",buf,10) == 0 || strncmp("Proxy-Connection",buf,16) == 0)
                continue;
        printf("%s",buf);
        Rio_writen(fd,buf,strlen(buf));
    }
    Rio_writen(fd,buf,strlen(buf));
    return;
}


void return_content(int serverfd, int clientfd,char *uri){

    size_t n,size = 0;
    char buf[MAXLINE],content[MAX_OBJECT_SIZE];
    rio_t srio;

    Rio_readinitb(&srio,serverfd);
    while((n = Rio_readlineb(&srio,buf,MAXLINE)) != 0){
        Rio_writen(clientfd,buf,n);

        if(n + size <= MAX_OBJECT_SIZE){
            sprintf(content + size,"%s",buf);
            size += n;
        }else{
            size = MAX_OBJECT_SIZE + 1;
        }

    }

    writecache(content,uri);

}



void rwlock_init(){
    rw->readcnt = 0;
    sem_init(&rw->lock,0,1);
    sem_init(&rw->writeLock,0,1);
}

void writecache(char *buf,char *url){
    sem_wait(&rw->writeLock);           //等待获得写者锁
    int index;
    
    for(index = 0;index < MAX_CACHE;index++){
        if(cache[index].lruNumber == 0){
            break;
        }
    }

    
    if(index == MAX_CACHE){
        int minlru = cache[0].lruNumber;

        
        for(int i = 1;i < MAX_CACHE;i++){
            if(cache[i].lruNumber < minlru){
                minlru = cache[i].lruNumber;
                index = i;
            }
        }
    }

    cache[index].lruNumber = maxlrucache()+1;
    strcpy(cache[index].url,url);
    strcpy(cache[index].content,buf);
    sem_post(&rw->writeLock);           //释放锁

    return;

}

char *readcache(char *url){
    sem_wait(&rw->lock);            //读者等待并获取锁
    if(rw->readcnt == 1)            
        sem_wait(&rw->writeLock);   //读者在读，不允许有写者
    rw->readcnt++;                  
    sem_post(&rw->lock);            //释放锁

    char *content = NULL;
    for(int i = 0;i < MAX_CACHE;i++){
        
        if(strcmp(url,cache[i].url) == 0){
            content = (char *)Malloc(strlen(cache[i].content));
            strcpy(content,cache[i].content);
            int maxlru = maxlrucache();     //获取最大的lru
            cache[i].lruNumber = maxlru+1;  //+1成最大的lru
            break;
        }
    }

    sem_wait(&rw->lock);            //等待并获取锁  
    rw->readcnt--;
    if(rw->readcnt == 0)            //没有读者了，释放写者锁
        sem_post(&rw->writeLock);
    sem_post(&rw->lock);            //释放锁
    return content;
}

int maxlrucache(){
    int i;
    int max=0;
    for(i = 0;i max){
            max = cache[i].lruNumber;
        }
    }
    return max;
}

运行结果

可以看到第三部分已经完成

结语

本实验的检测分数不是太严格，实现基本功能就可以满分了。比如我把锁部分的代码删除一样也是满分，所有上面的代码不一定是严格正确的。

《深入理解计算机系统》实验八Proxy Lab

Linux相关栏目本月热门文章