0%

健壮的I/O(RIO)

在上篇Unix系统级I/O中,我们介绍了有关在Unix环境下读取和写入文件的函数readwrite,也提到了标准I/O在进行网络I/O时的局限性。但是在某些地方,直接使用readwrite往往会出现不足值,比如在复杂的网络环境中读取socket。如果想让我们的程序更加的可靠,就需要反复的调用readwrite去处理,知道传送完所需要的字节。在csapp一书中,给我们提供了一个健壮可靠的I/O包来自动处理这种不足值的情况,称为RIO(Robust I/O)。本文主要整理RIO提供的函数备忘。

详细代码及用法示例可以在这里找到。

无缓冲区的rio

rio_readnrio_writenreadwrite用法基本一致,只是rio_readn会不断尝试读出,直到读取出n个字节或遇到EOF或出错;rio_writen函数绝不会返回一个不足值,它会不断尝试写入直到写入全部字节或者出错。由于没有缓冲区的存在,rio_readnrio_writen可以任意交替使用。

1
2
3
4
5
6
7
#include "rio.h"

ssize_t rio_readn(int fd, void *buf, size_t n);
/* 返回:若成功则为传送的字节数,若为EOF则为0,若出错则为-1 */

ssize_t rio_writen(int fd, void *buf, size_t n);
/* 返回:若成功则为传送的字节数,若出错则为-1 */

函数定义如下:

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
ssize_t rio_readn(int fd, void *usrbuf, size_t n)
{
size_t nleft = n;
ssize_t nread;
char *bufp = usrbuf;

while (nleft > 0) {
if ((nread = read(fd, bufp, nleft)) < 0) {
if(errno == EINTR) /* Interrupted by big handler return */
nread = 0; /* and call read() again */
else
return -1; /* errno set by read() */
}
else if (nread == 0)
break; /* EOF */
nleft -= nread;
bufp += nread;
}
return (n - nleft); /* return >= 0 */
}

ssize_t rio_writen(int fd, void *usrbuf, size_t n)
{
size_t nleft = n;
ssize_t nwritten;
char *bufp = usrbuf;

while (nleft > 0) {
if ((nwritten = write(fd, bufp, nleft)) <= 0) {
if(errno == EINTR) /* Interrupted by big handler return */
nwritten = 0; /* and call write() again */
else
return -1; /* errno set by write() */
}
nleft -= nwritten;
bufp += nwritten;
}
return n;
}

带缓冲区的rio

带缓冲区的rio所包含的函数如下:

1
2
3
4
5
6
7
8
#include "rio.h"

void rio_readinitb(rio_t *rp, int fd);
/* 返回:无 */

ssize_t rio_readlineb(rio_t *rp, void *usrbuf, size_t maxlen);
ssize_t rio_readnb(rio_t *rp, void *usrbuf, size_t n);
/* 返回:若成功则为读的字节数,若为EOF则为0,若出错则为-1 */

带缓冲区的rio由一个rio_t的结构体管理,其形式如下:

1
2
3
4
5
6
7
8
#define RIO_BUFSIZE 8192

typedef struct {
int rio_fd; /* 描述符 */
int rio_cnt; /* 缓冲区中还未读的字节数 */
char *rio_bufptr; /* 缓冲区中下一个未读的字节 */
char rio_buf[RIO_BUFSIZE]; /* 缓冲区 */
} rio_t;

在使用带缓冲区的rio时,每打开一个描述符,都需要使用rio_readinitb来对rio_t进行初始化:

1
2
3
4
5
void rio_readinitb(rio_t *rp, int fd) {
rp->rio_fd = fd;
rp->rio_cnt = 0;
rp->rio_bufptr = rp->rio_buf;
}

对缓冲区的控制主要由rio_read来完成:

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
static ssize_t rio_read(rio_t *rp, char *usrbuf, size_t n) {
int cnt;

while (rp->rio_cnt <= 0) { /* Refill if buf is empty */
rp->rio_cnt = read(rp->rio_fd, rp->rio_buf, sizeof(rp->rio_buf));
if (rp->rio_cnt < 0) {
if (errno != EINTR) /* Interrupted by sig handler return */
return -1;
} else if (rp->rio_cnt == 0) /* EOF */
return 0;
else
rp->rio_bufptr = rp->rio_buf; /* Reset buffer ptr */
}

/* Copy min(n, rp->rio_cnt) bytes from internal buf to user buf */
cnt = n;
if (rp->rio_cnt < n)
cnt = rp->rio_cnt;
memcpy(usrbuf, rp->rio_bufptr, cnt);
rp->rio_bufptr += cnt;
rp->rio_cnt -= cnt;
return cnt;
}

rio_read函数由static关键字修饰成静态函数,这对与一个函数来说,说明这个函数只对声明它的文件可见,且不同的文件可以声明相同名的静态函数。

rio_readlinebrio_readnb的具体实现如下:

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
ssize_t rio_readnb(rio_t *rp, void *usrbuf, size_t n) {
size_t nleft = n;
ssize_t nread;
char *bufp = usrbuf;

while (nleft > 0) {
if ((nread = rio_read(rp, bufp, nleft)) < 0)
return -1; /* errno set by read() */
else if (nread == 0)
break; /* EOF */
nleft -= nread;
bufp += nread;
}
return (n - nleft); /* return >= 0 */
}

ssize_t rio_readlineb(rio_t *rp, void *usrbuf, size_t maxlen) {
int n, rc;
char c, *bufp = usrbuf;

for (n = 1; n < maxlen; n++) {
if ((rc = rio_read(rp, &c, 1)) == 1) {
*bufp++ = c;
if (c == '\n') {
n++;
break;
}
} else if (rc == 0) {
if (n == 1)
return 0; /* EOF, no data read */
else
break; /* EOF, some data was read */
} else
return -1; /* Error */
}
*bufp = 0;
return n - 1;
}