Re: [RFC PATCH] f2fs: preserve direct write semantics when buffering is forced

[Jaegeuk Kim]

On 02/20, Hans Holmberg wrote:
> In some cases, e.g. for zoned block devices, direct writes are
> forced into buffered writes that will populate the page cache
> and be written out just like buffered io.
> 
> Direct reads, on the other hand, is supported for the zoned
> block device case. This has the effect that applications
> built for direct io will fill up the page cache with data
> that will never be read, and that is a waste of resources.
> 
> If we agree that this is a problem, how do we fix it?
> 
> A) Supporting proper direct writes for zoned block devices would
> be the best, but it is currently not supported (probably for
> a good but non-obvious reason). Would it be feasible to
> implement proper direct IO?
> 
> B) Avoid the cost of keeping unwanted data by syncing and throwing
> out the cached pages for buffered O_DIRECT writes before completion.
> 
> This patch implements B) by reusing the code for how partial
> block writes are flushed out on the "normal" direct write path.
> 
> Note that this changes the performance characteristics of f2fs
> quite a bit.
> 
> Direct IO performance for zoned block devices is lower for
> small writes after this patch, but this should be expected
> with direct IO and in line with how f2fs behaves on top of
> conventional block devices.
> 
> Another open question is if the flushing should be done for
> all cases where buffered writes are forced.
> 
> Signed-off-by: Hans Holmberg <hans.holmberg@xxxxxxx>
> ---
>  fs/f2fs/file.c | 38 ++++++++++++++++++++++++++++++--------
>  1 file changed, 30 insertions(+), 8 deletions(-)
> 
> diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
> index ecbc8c135b49..4e57c37bce35 100644
> --- a/fs/f2fs/file.c
> +++ b/fs/f2fs/file.c
> @@ -4513,6 +4513,19 @@ static const struct iomap_dio_ops f2fs_iomap_dio_write_ops = {
>  	.end_io = f2fs_dio_write_end_io,
>  };
>  
> +static void f2fs_flush_buffered_write(struct address_space *mapping,
> +				      loff_t start_pos, loff_t end_pos)
> +{
> +	int ret;
> +
> +	ret = filemap_write_and_wait_range(mapping, start_pos, end_pos);
> +	if (ret < 0)
> +		return;
> +	invalidate_mapping_pages(mapping,
> +				 start_pos >> PAGE_SHIFT,
> +				 end_pos >> PAGE_SHIFT);
> +}
> +
>  static ssize_t f2fs_dio_write_iter(struct kiocb *iocb, struct iov_iter *from,
>  				   bool *may_need_sync)
>  {
> @@ -4612,14 +4625,9 @@ static ssize_t f2fs_dio_write_iter(struct kiocb *iocb, struct iov_iter *from,
>  
>  			ret += ret2;
>  
> -			ret2 = filemap_write_and_wait_range(file->f_mapping,
> -							    bufio_start_pos,
> -							    bufio_end_pos);
> -			if (ret2 < 0)
> -				goto out;
> -			invalidate_mapping_pages(file->f_mapping,
> -						 bufio_start_pos >> PAGE_SHIFT,
> -						 bufio_end_pos >> PAGE_SHIFT);
> +			f2fs_flush_buffered_write(file->f_mapping,
> +						  bufio_start_pos,
> +						  bufio_end_pos);
>  		}
>  	} else {
>  		/* iomap_dio_rw() already handled the generic_write_sync(). */
> @@ -4717,8 +4725,22 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
>  	inode_unlock(inode);
>  out:
>  	trace_f2fs_file_write_iter(inode, orig_pos, orig_count, ret);
> +
>  	if (ret > 0 && may_need_sync)
>  		ret = generic_write_sync(iocb, ret);
> +
> +	/* If buffered IO was forced, flush and drop the data from
> +	 * the page cache to preserve O_DIRECT semantics
> +	 */
> +	if (ret > 0 && !dio && (iocb->ki_flags & IOCB_DIRECT)) {
> +		struct file *file = iocb->ki_filp;
> +		loff_t end_pos = orig_pos + ret - 1;
> +
> +		f2fs_flush_buffered_write(file->f_mapping,
> +					  orig_pos,
> +					  end_pos);

I applied a minor change:

        /* If buffered IO was forced, flush and drop the data from
         * the page cache to preserve O_DIRECT semantics
         */
-       if (ret > 0 && !dio && (iocb->ki_flags & IOCB_DIRECT)) {
-               struct file *file = iocb->ki_filp;
-               loff_t end_pos = orig_pos + ret - 1;
-
-               f2fs_flush_buffered_write(file->f_mapping,
+       if (ret > 0 && !dio && (iocb->ki_flags & IOCB_DIRECT))
+               f2fs_flush_buffered_write(iocb->ki_filp->f_mapping,
                                          orig_pos,
-                                         end_pos);
-       }
+                                         orig_pos + ret - 1);

        return ret;
 }


> +	}
> +
>  	return ret;
>  }
>  
> -- 
> 2.25.1