On Mon, Aug 25, 2025 at 02:07:15PM +0200, Jan Kara wrote:

On Fri 22-08-25 18:57:08, Ritesh Harjani wrote:

quoted

Keith Busch [off-list ref] writes:

quoted

  - EXT4 falls back to buffered io for writes but not for reads.

++linux-ext4 to get any historical context behind why the difference of
behaviour in reads v/s writes for EXT4 DIO. 

Hum, how did you test? Because in the basic testing I did (with vanilla
kernel) I get EINVAL when doing unaligned DIO write in ext4... We should be
falling back to buffered IO only if the underlying file itself does not
support any kind of direct IO.

Simple test case (dio-offset-test.c) below.

I also ran this on vanilla kernel and got these results:

  # mkfs.ext4 /dev/vda
  # mount /dev/vda /mnt/ext4/
  # make dio-offset-test
  # ./dio-offset-test /mnt/ext4/foobar
  write: Success
  read: Invalid argument

I tracked the "write: Success" down to ext4's handling for the "special"
-ENOTBLK error after ext4_want_directio_fallback() returns "true".

dio-offset-test.c:
---
#ifndef _GNU_SOURCE
#define _GNU_SOURCE
#endif

#include <sys/uio.h>
#include <err.h>
#include <errno.h>
#include <fcntl.h>
#include <stdlib.h>
#include <stdio.h>
#include <unistd.h>

int main(int argc, char **argv)
{
	unsigned int pagesize;
	struct iovec iov[2];
	int ret, fd;
	void *buf;

	if (argc < 2)
		err(EINVAL, "usage: %s <file>", argv[0]);
	
	pagesize = sysconf(_SC_PAGE_SIZE);
	ret = posix_memalign((void **)&buf, pagesize, 2 * pagesize);
	if (ret)
		err(errno, "%s: failed to allocate buf", __func__);
	
	fd = open(argv[1], O_RDWR | O_CREAT | O_TRUNC | O_DIRECT);
	if (fd < 0)
		err(errno, "%s: failed to open %s", __func__, argv[1]);
	
	iov[0].iov_base = buf;
	iov[0].iov_len = 256;
	iov[1].iov_base = buf + pagesize;
	iov[1].iov_len = 256;
	ret = pwritev(fd, iov, 2, 0);
	perror("write");
	
	ret = preadv(fd, iov, 2, 0);
	perror("read");
	
	return 0;
}
--