Question

编写一个程序，打开一个现有文件，用O_APPEND标志写入，和然后在写入一些数据之前寻找文件的开头。在哪里数据出现在文件中？为什么呢？

这是我的代码：

main() {
    int fd = open("test.txt", O_WRONLY | O_APPEND);

    lseek(fd, 0, SEEK_SET);
    write(fd, "abc", 3);
    close(fd);
}

并且已经尝试过，发现数据已写入文件的末尾，我想了解为什么？因为我表示O_APPEND标志没有那么简单我认为

Answer 1

当您使用O_APPEND打开文件时，无论当前文件指针来自最新的lseek(2)调用或最新的读/写操作，所有数据都会写入结尾。来自open(2) documentation：

O_APPEND
该文件以追加模式打开。在每个write(2)之前，文件偏移量位于文件的末尾，就像使用lseek(2)一样。

如果要将数据写入文件的末尾，然后在以后开始写入数据，请在不使用O_APPEND的情况下将其打开，使用fstat(2)获取文件大小（st_size成员在struct stat）内，然后寻找该偏移来写结束。

Answer 2

实际上，O_APPEND仅影响write的行为，而不影响read的行为。无论lseek如何更改文件的当前位置，write始终为append-only。

当open文件O_RDWR | O_APPEND时，read仍将从文件开头开始。

在open（man 2 open）的手册中，

O_APPEND 该文件以追加模式打开。在每次写入（2）之前，文件偏移量位于文件的末尾。

在write（man 2 write）的手册中，

如果设置了文件状态标志的O_APPEND标志，则为文件偏移量应在每次写入之前设置到文件的末尾。

在Linux内核fs/ext4 syscall write -> vfs_write -> ext4_file_write_iter中， ext4_file_write_iter会致电ext4_write_checks

然后致电generic_write_checks

您会找到设置pos = file.size

的地方

/* FIXME: this is for backwards compatibility with 2.4 */
if (iocb->ki_flags & IOCB_APPEND)
    iocb->ki_pos = i_size_read(inode);
pos = iocb->ki_pos;

以下演示可以验证它。

cat open_append.cc
#include <fcntl.h>
#include <sys/stat.h>
#include <unistd.h>
#include <errno.h>
#include <string.h>

#include <string>
#include <iostream>

int main(int argc, char *argv[]) {
  std::string path = "./test.txt";
  std::string content = "hello_world";
  std::string read_buf(content.size(), 0x0);
  struct stat st_buf;
  ssize_t bytes_read = -1;
  ssize_t bytes_write = -1;
  int ret = -1;
  off_t cur_off = -1;
  int fd = ::open(path.c_str(), O_CREAT | O_RDWR | O_TRUNC, 0644);
  if (fd < 0) {
    std::cerr << "open err path " << path
              << " errno " << errno << std::endl;
    return -1;
  }
  std::cout << "open ok path " << path
            << " fd " << fd << std::endl;

  // Step 1 write some data into an empty file
  bytes_write = ::write(fd, content.data(), content.size());
  if (bytes_write < 0) {
    std::cerr << "write err fd " << fd
              << " errno " << errno << std::endl;
    goto out;
  }
  std::cout << "write ok fd " << fd
            << " data " << content
            << " nbytes " << bytes_write << std::endl;
  ::close(fd);

  // Step 2 open the file again with O_APPEND
  fd = -1;
  fd = ::open(path.c_str(), O_CREAT | O_RDWR | O_APPEND, 0644);
  if (fd < 0) {
    std::cerr << "open again err path " << path
              << " errno " << errno << std::endl;
    return -1;
  }
  std::cout << "open again ok path " << path
            << " fd " << fd << std::endl;

  // Step 3 the current position of the file NOT affected by O_APPEND
  cur_off = ::lseek(fd, 0, SEEK_CUR);
  if (cur_off < 0) {
    std::cerr << "lseek err SEEK_CUR fd " << fd
              << " errno " << errno << std::endl;
    goto out;
  }
  // cur_off expected to be 0
  std::cout << "lseek ok SEEK_CUR fd " << fd
            << " cur_off " << cur_off << std::endl;

  // Step 4  the read will start from the beginning of the file
  bytes_read = read(fd, (char*)read_buf.data(), content.size());
  if (bytes_read < 0) {
    std::cerr << "read err fd " << fd
              << " errno " << errno << std::endl;
    goto out;
  }
  std::cout << "read ok fd " << fd
            << " data " << read_buf
            << " nbytes " << bytes_read << std::endl;

  // Step 5 change the position to the half of the file size
  cur_off = ::lseek(fd, content.size() / 2, SEEK_SET);
  if (cur_off < 0) {
    std::cerr << "lseek err SEEK_SET fd " << fd
              << " errno " << errno << std::endl;
    goto out;
  }
  // cur_off expected to be content.size() / 2
  std::cout << "lseek ok SEEK_SET fd " << fd
            << " cur_off " << cur_off << std::endl;

  // Step 6 write will append data from the end of the file
  // the current position is ignored
  bytes_write = ::write(fd, content.data(), content.size());
  if (bytes_write < 0) {
    std::cerr << "append write err fd " << fd
              << " errno " << errno << std::endl;
    goto out;
  }
  std::cout << "append write ok fd " << fd
            << " append data " << content
            << " append nbytes " << bytes_write << std::endl;

  // Step 7 the file size is double content.size()
  memset((void*)&st_buf, 0x0, sizeof(struct stat));
  ret = lstat(path.c_str(), &st_buf);
  if (ret < 0) {
    std::cerr << "lstat err path " << path
              << " errno " << errno << std::endl;
    goto out;
  }
  std::cout << "lstat ok path " << path
            << " st_size " << st_buf.st_size << std::endl;
  ret = 0;

out:
  if (fd >= 0) {
    close(fd);
  }
  return ret;
}

输出结果

open ok path ./test.txt fd 3
write ok fd 3 data hello_world nbytes 11
open again ok path ./test.txt fd 3
lseek ok SEEK_CUR fd 3 cur_off 0
read ok fd 3 data hello_world nbytes 11
lseek ok SEEK_SET fd 3 cur_off 5
append write ok fd 3 append data hello_world append nbytes 11
lstat ok path ./test.txt st_size 22

Answer 3

O_APPEND标志强制文件指针仅指向文件末尾。所以如果你从文件的开头做lseek，它会将更新的文件指针位置作为文件的开头，即旧文件的结束位置。

O_APPEND标志和lseek

3 个答案: