Why is data written to a file opened with O_APPEND flag, always written at the end, even with `lseek`?
When you open a file with O_APPEND
, all data gets written to the end, regardless of whatever the current file pointer is from the latest call to lseek(2)
or the latest read/write operation. From the open(2)
documentation:
O_APPEND
The file is opened in append mode. Before eachwrite(2)
, the file offset is positioned at the end of the file, as if withlseek(2)
.
If you want to write data the end of the file and then the beginning of it later, open it up without O_APPEND
, use fstat(2)
to get the file size (st_size
member within struct stat
), and then seek to that offset to write the end.
In effect, O_APPEND only affects the behavior of write
, but not that of read
. Whatever how the current position of a file is changed by lseek
, write
will always append-only
.
When you open
a file with O_RDWR | O_APPEND
, read
will still start from the beginning of the file.
In the manual of open
(man 2 open
),
O_APPEND The file is opened in append mode. Before each write(2), the file offset is positioned at the end of the file.
In the manual of write
(man 2 write
),
If the O_APPEND flag of the file status flags is set, the file offset shall be set to the end of the file prior to each write.
In the Linux kernel fs/ext4 syscall write
-> vfs_write
-> ext4_file_write_iter
,
the ext4_file_write_iter
will call ext4_write_checks
then call generic_write_checks
you will find the place where setting the pos
= file.size
/* 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;
The following demo can verify it.
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;
}
Output result
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