Ocfs2 devel - Dec 2017 - [PATCH v2] ocfs2: fall back to buffer IO when append dio is disabled with file hole existing

The intention of this patch is to provide an option to ocfs2 users whether
to allocate disk space while doing dio write.

Whether to make ocfs2 fall back to buffer io is up to ocfs2 users through
toggling append-dio feature. It rather makes ocfs2 configurable and
flexible.

So if something bad happens to dio write with space allocation, we can
still make ocfs2 fall back to buffer io. It's an option not a mandatory
action.:)

Besides, append-dio feature is key to whether to allocate space with dio
writing. So writing to file hole and enlarging file(appending file) should
have the same reflection to append-dio feature.

Signed-off-by: Changwei Ge <ge.changwei at h3c.com>
---
  fs/ocfs2/aops.c | 53 ++++++++++++++++++++++++++++++++++++++++++++++++++---
  1 file changed, 50 insertions(+), 3 deletions(-)

diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index d151632..32e60c0 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -2414,12 +2414,52 @@ static int ocfs2_dio_end_io(struct kiocb *iocb,
  	return ret;
  }
  
+/*
+ * Will look for holes and unwritten extents in the range starting at
+ * pos for count bytes (inclusive).
+ * Return value 1 indicates hole exists, 0 not exists, others indicate error.
+ */
+static int ocfs2_range_has_holes(struct inode *inode, loff_t pos,
+				 size_t count)
+{
+	int ret = 0;
+	unsigned int extent_flags;
+	u32 cpos, clusters, extent_len, phys_cpos;
+	struct super_block *sb = inode->i_sb;
+
+	cpos = pos >> OCFS2_SB(sb)->s_clustersize_bits;
+	clusters = ocfs2_clusters_for_bytes(sb, pos + count) - cpos;
+
+	while (clusters) {
+		ret = ocfs2_get_clusters(inode, cpos, &phys_cpos, &extent_len,
+					 &extent_flags);
+		if (ret < 0) {
+			mlog_errno(ret);
+			goto out;
+		}
+
+		if (phys_cpos == 0) {
+			ret = 1;
+			goto out;
+		}
+
+		if (extent_len > clusters)
+			extent_len = clusters;
+
+		clusters -= extent_len;
+		cpos += extent_len;
+	}
+out:
+	return ret;
+}
+
  static ssize_t ocfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
  {
  	struct file *file = iocb->ki_filp;
  	struct inode *inode = file->f_mapping->host;
  	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
  	get_block_t *get_block;
+	int ret;
  
  	/*
  	 * Fallback to buffered I/O if we see an inode without
@@ -2429,9 +2469,16 @@ static ssize_t ocfs2_direct_IO(struct kiocb *iocb, struct
iov_iter *iter)
  		return 0;
  
  	/* Fallback to buffered I/O if we do not support append dio. */
-	if (iocb->ki_pos + iter->count > i_size_read(inode) &&
-	    !ocfs2_supports_append_dio(osb))
-		return 0;
+	if (!ocfs2_supports_append_dio(osb)) {
+		if (iocb->ki_pos + iter->count > i_size_read(inode))
+			return 0;
+
+		ret = ocfs2_range_has_holes(inode, iocb->ki_pos, iter->count);
+		if (ret == 1)
+			return 0;
+		else if (ret < 0)
+			return ret;
+	}
  
  	if (iov_iter_rw(iter) == READ)
  		get_block = ocfs2_lock_get_block;
-- 
2.7.4

Hi Changwei,

On 2017/12/26 15:03, Changwei Ge wrote:
> The intention of this patch is to provide an option to ocfs2 users whether
> to allocate disk space while doing dio write.
> 
> Whether to make ocfs2 fall back to buffer io is up to ocfs2 users through
> toggling append-dio feature. It rather makes ocfs2 configurable and
> flexible.
>
It is too strange to make ocfs2 fall back to buffer io by toggling append-dio
feature.
> So if something bad happens to dio write with space allocation, we can
> still make ocfs2 fall back to buffer io. It's an option not a mandatory
> action.:)
Now the ocfs2 supports fill holes during direct io whether or not supporting
append-dio feature
and we can directly fix the problem.
I think it is meaningless to provide an temporary option to turn off it.
> 
> Besides, append-dio feature is key to whether to allocate space with dio
> writing. So writing to file hole and enlarging file(appending file) should
> have the same reflection to append-dio feature.
> 
> Signed-off-by: Changwei Ge <ge.changwei at h3c.com>
> ---
>   fs/ocfs2/aops.c | 53
++++++++++++++++++++++++++++++++++++++++++++++++++---
>   1 file changed, 50 insertions(+), 3 deletions(-)
> 
> diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
> index d151632..32e60c0 100644
> --- a/fs/ocfs2/aops.c
> +++ b/fs/ocfs2/aops.c
> @@ -2414,12 +2414,52 @@ static int ocfs2_dio_end_io(struct kiocb *iocb,
>   	return ret;
>   }
>   
> +/*
> + * Will look for holes and unwritten extents in the range starting at
> + * pos for count bytes (inclusive).
> + * Return value 1 indicates hole exists, 0 not exists, others indicate
error.
> + */
> +static int ocfs2_range_has_holes(struct inode *inode, loff_t pos,
> +				 size_t count)
> +{
> +	int ret = 0;
> +	unsigned int extent_flags;
> +	u32 cpos, clusters, extent_len, phys_cpos;
> +	struct super_block *sb = inode->i_sb;
> +
> +	cpos = pos >> OCFS2_SB(sb)->s_clustersize_bits;
> +	clusters = ocfs2_clusters_for_bytes(sb, pos + count) - cpos;
> +
> +	while (clusters) {
> +		ret = ocfs2_get_clusters(inode, cpos, &phys_cpos, &extent_len,
> +					 &extent_flags);
> +		if (ret < 0) {
> +			mlog_errno(ret);
> +			goto out;
> +		}
> +
> +		if (phys_cpos == 0) {
> +			ret = 1;
> +			goto out;
> +		}
> +
> +		if (extent_len > clusters)
> +			extent_len = clusters;
> +
> +		clusters -= extent_len;
> +		cpos += extent_len;
> +	}
> +out:
> +	return ret;
> +}
> +
>   static ssize_t ocfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
>   {
>   	struct file *file = iocb->ki_filp;
>   	struct inode *inode = file->f_mapping->host;
>   	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
>   	get_block_t *get_block;
> +	int ret;
>   
>   	/*
>   	 * Fallback to buffered I/O if we see an inode without
> @@ -2429,9 +2469,16 @@ static ssize_t ocfs2_direct_IO(struct kiocb *iocb,
struct iov_iter *iter)
>   		return 0;
>   
>   	/* Fallback to buffered I/O if we do not support append dio. */
> -	if (iocb->ki_pos + iter->count > i_size_read(inode) &&
> -	    !ocfs2_supports_append_dio(osb))
> -		return 0;
> +	if (!ocfs2_supports_append_dio(osb)) {
> +		if (iocb->ki_pos + iter->count > i_size_read(inode))
> +			return 0;
> +
> +		ret = ocfs2_range_has_holes(inode, iocb->ki_pos, iter->count);
> +		if (ret == 1)
> +			return 0;
> +		else if (ret < 0)
> +			return ret;
> +	}
>   
>   	if (iov_iter_rw(iter) == READ)
>   		get_block = ocfs2_lock_get_block;
>