Re: [RFC 1/1] ext4: Optimize ext4 DAX overwrites
On 8/20/20 6:23 PM, Jan Kara wrote:
On Thu 20-08-20 17:06:28, Ritesh Harjani wrote:
Currently in case of DAX, we are starting a transaction
everytime for IOMAP_WRITE case. This can be optimized
away in case of an overwrite (where the blocks were already
allocated). This could give a significant performance boost
for multi-threaded random writes.
Reported-by: Dan Williams
Signed-off-by: Ritesh Harjani
Thanks for returning to this and I'm glad to see how much this helped :)
BTW, I'd suspect there could be also significant contention and cache line
bouncing on j_state_lock and transaction's atomic counters...
ok, will try and profile to see if this happens.
---
fs/ext4/ext4.h | 1 +
fs/ext4/file.c | 2 +-
fs/ext4/inode.c | 8 +++-
3 files changed, 9 insertions(+), 2 deletions(-)
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 42f5060f3cdf..9a2138afc751 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -3232,6 +3232,7 @@ extern const struct dentry_operations ext4_dentry_ops;
extern const struct inode_operations ext4_file_inode_operations;
extern const struct file_operations ext4_file_operations;
extern loff_t ext4_llseek(struct file *file, loff_t offset, int origin);
+extern bool ext4_overwrite_io(struct inode *inode, loff_t pos, loff_t len);
/* inline.c */
extern int ext4_get_max_inline_size(struct inode *inode);
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 2a01e31a032c..51cd92ac1758 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -188,7 +188,7 @@ ext4_extending_io(struct inode *inode, loff_t offset,
size_t len)
}
/* Is IO overwriting allocated and initialized blocks? */
-static bool ext4_overwrite_io(struct inode *inode, loff_t pos, loff_t len)
+bool ext4_overwrite_io(struct inode *inode, loff_t pos, loff_t len)
{
struct ext4_map_blocks map;
unsigned int blkbits = inode->i_blkbits;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 10dd470876b3..f0ac0ee9e991 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -3423,6 +3423,7 @@ static int ext4_iomap_begin(struct inode *inode, loff_t
offset, loff_t length,
int ret;
struct ext4_map_blocks map;
u8 blkbits = inode->i_blkbits;
+ bool overwrite = false;
if ((offset >> blkbits) > EXT4_MAX_LOGICAL_BLOCK)
return -EINVAL;
@@ -3430,6 +3431,9 @@ static int ext4_iomap_begin(struct inode *inode, loff_t
offset, loff_t length,
if (WARN_ON_ONCE(ext4_has_inline_data(inode)))
return -ERANGE;
+ if (IS_DAX(inode) && (flags & IOMAP_WRITE) &&
+ ext4_overwrite_io(inode, offset, length))
+ overwrite = true;
So the patch looks correct but using ext4_overwrite_io() seems a bit
foolish since under the hood it does ext4_map_blocks() only to be able to
decide whether to call ext4_map_blocks() once again with exactly the same
arguments :). So I'd rather slightly refactor the code in
ext4_iomap_begin() to avoid this double calling of ext4_map_blocks() for
the fast path.
Yes, agreed. Looking at the numbers I was excited to post out the RFC
for discussion. Will make above changes and post. :)
With DIO, we need to detect overwrite case early in
ext4_dio_write_iter() to determine whether we need shared or excl.
locks - so probably for DIO case we still need overwrite check in
ext4_dio_write_iter()
Thanks for review!!
-ritesh
Honza
/*
* Calculate the first and last logical blocks respectively.
*/
@@ -3437,13 +3441,15 @@ static int ext4_iomap_begin(struct inode *inode, loff_t
offset, loff_t length,
map.m_len = min_t(loff_t, (offset + length - 1) >> blkbits,
EXT4_MAX_LOGICAL_BLOCK) - map.m_lblk + 1;
- if (flags & IOMAP_WRITE)
+ if ((flags & IOMAP_WRITE) && !overwrite)
ret = ext4_iomap_alloc(inode, , flags);
else
ret = ext4_map_blocks(NULL, inode, , 0);
if (ret < 0)
return ret;
+ if (IS_DAX(inode) && overwrite)
+ WARN_ON(!(map.m_flags & EXT4_MAP_MAPPED));
ext4_set_iomap(inode, iomap, , offset, length);
--
2.25.4
Re: [RFC 1/1] ext4: Optimize ext4 DAX overwrites
On Thu 20-08-20 17:06:28, Ritesh Harjani wrote:
> Currently in case of DAX, we are starting a transaction
> everytime for IOMAP_WRITE case. This can be optimized
> away in case of an overwrite (where the blocks were already
> allocated). This could give a significant performance boost
> for multi-threaded random writes.
>
> Reported-by: Dan Williams
> Signed-off-by: Ritesh Harjani
Thanks for returning to this and I'm glad to see how much this helped :)
BTW, I'd suspect there could be also significant contention and cache line
bouncing on j_state_lock and transaction's atomic counters...
> ---
> fs/ext4/ext4.h | 1 +
> fs/ext4/file.c | 2 +-
> fs/ext4/inode.c | 8 +++-
> 3 files changed, 9 insertions(+), 2 deletions(-)
>
> diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
> index 42f5060f3cdf..9a2138afc751 100644
> --- a/fs/ext4/ext4.h
> +++ b/fs/ext4/ext4.h
> @@ -3232,6 +3232,7 @@ extern const struct dentry_operations ext4_dentry_ops;
> extern const struct inode_operations ext4_file_inode_operations;
> extern const struct file_operations ext4_file_operations;
> extern loff_t ext4_llseek(struct file *file, loff_t offset, int origin);
> +extern bool ext4_overwrite_io(struct inode *inode, loff_t pos, loff_t len);
>
> /* inline.c */
> extern int ext4_get_max_inline_size(struct inode *inode);
> diff --git a/fs/ext4/file.c b/fs/ext4/file.c
> index 2a01e31a032c..51cd92ac1758 100644
> --- a/fs/ext4/file.c
> +++ b/fs/ext4/file.c
> @@ -188,7 +188,7 @@ ext4_extending_io(struct inode *inode, loff_t offset,
> size_t len)
> }
>
> /* Is IO overwriting allocated and initialized blocks? */
> -static bool ext4_overwrite_io(struct inode *inode, loff_t pos, loff_t len)
> +bool ext4_overwrite_io(struct inode *inode, loff_t pos, loff_t len)
> {
> struct ext4_map_blocks map;
> unsigned int blkbits = inode->i_blkbits;
> diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
> index 10dd470876b3..f0ac0ee9e991 100644
> --- a/fs/ext4/inode.c
> +++ b/fs/ext4/inode.c
> @@ -3423,6 +3423,7 @@ static int ext4_iomap_begin(struct inode *inode, loff_t
> offset, loff_t length,
> int ret;
> struct ext4_map_blocks map;
> u8 blkbits = inode->i_blkbits;
> + bool overwrite = false;
>
> if ((offset >> blkbits) > EXT4_MAX_LOGICAL_BLOCK)
> return -EINVAL;
> @@ -3430,6 +3431,9 @@ static int ext4_iomap_begin(struct inode *inode, loff_t
> offset, loff_t length,
> if (WARN_ON_ONCE(ext4_has_inline_data(inode)))
> return -ERANGE;
>
> + if (IS_DAX(inode) && (flags & IOMAP_WRITE) &&
> + ext4_overwrite_io(inode, offset, length))
> + overwrite = true;
So the patch looks correct but using ext4_overwrite_io() seems a bit
foolish since under the hood it does ext4_map_blocks() only to be able to
decide whether to call ext4_map_blocks() once again with exactly the same
arguments :). So I'd rather slightly refactor the code in
ext4_iomap_begin() to avoid this double calling of ext4_map_blocks() for
the fast path.
Honza
> /*
>* Calculate the first and last logical blocks respectively.
>*/
> @@ -3437,13 +3441,15 @@ static int ext4_iomap_begin(struct inode *inode,
> loff_t offset, loff_t length,
> map.m_len = min_t(loff_t, (offset + length - 1) >> blkbits,
> EXT4_MAX_LOGICAL_BLOCK) - map.m_lblk + 1;
>
> - if (flags & IOMAP_WRITE)
> + if ((flags & IOMAP_WRITE) && !overwrite)
> ret = ext4_iomap_alloc(inode, , flags);
> else
> ret = ext4_map_blocks(NULL, inode, , 0);
>
> if (ret < 0)
> return ret;
> + if (IS_DAX(inode) && overwrite)
> + WARN_ON(!(map.m_flags & EXT4_MAP_MAPPED));
>
> ext4_set_iomap(inode, iomap, , offset, length);
>
> --
> 2.25.4
>
--
Jan Kara
SUSE Labs, CR
[RFC 1/1] ext4: Optimize ext4 DAX overwrites
Currently in case of DAX, we are starting a transaction
everytime for IOMAP_WRITE case. This can be optimized
away in case of an overwrite (where the blocks were already
allocated). This could give a significant performance boost
for multi-threaded random writes.
Reported-by: Dan Williams
Signed-off-by: Ritesh Harjani
---
fs/ext4/ext4.h | 1 +
fs/ext4/file.c | 2 +-
fs/ext4/inode.c | 8 +++-
3 files changed, 9 insertions(+), 2 deletions(-)
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 42f5060f3cdf..9a2138afc751 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -3232,6 +3232,7 @@ extern const struct dentry_operations ext4_dentry_ops;
extern const struct inode_operations ext4_file_inode_operations;
extern const struct file_operations ext4_file_operations;
extern loff_t ext4_llseek(struct file *file, loff_t offset, int origin);
+extern bool ext4_overwrite_io(struct inode *inode, loff_t pos, loff_t len);
/* inline.c */
extern int ext4_get_max_inline_size(struct inode *inode);
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 2a01e31a032c..51cd92ac1758 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -188,7 +188,7 @@ ext4_extending_io(struct inode *inode, loff_t offset,
size_t len)
}
/* Is IO overwriting allocated and initialized blocks? */
-static bool ext4_overwrite_io(struct inode *inode, loff_t pos, loff_t len)
+bool ext4_overwrite_io(struct inode *inode, loff_t pos, loff_t len)
{
struct ext4_map_blocks map;
unsigned int blkbits = inode->i_blkbits;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 10dd470876b3..f0ac0ee9e991 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -3423,6 +3423,7 @@ static int ext4_iomap_begin(struct inode *inode, loff_t
offset, loff_t length,
int ret;
struct ext4_map_blocks map;
u8 blkbits = inode->i_blkbits;
+ bool overwrite = false;
if ((offset >> blkbits) > EXT4_MAX_LOGICAL_BLOCK)
return -EINVAL;
@@ -3430,6 +3431,9 @@ static int ext4_iomap_begin(struct inode *inode, loff_t
offset, loff_t length,
if (WARN_ON_ONCE(ext4_has_inline_data(inode)))
return -ERANGE;
+ if (IS_DAX(inode) && (flags & IOMAP_WRITE) &&
+ ext4_overwrite_io(inode, offset, length))
+ overwrite = true;
/*
* Calculate the first and last logical blocks respectively.
*/
@@ -3437,13 +3441,15 @@ static int ext4_iomap_begin(struct inode *inode, loff_t
offset, loff_t length,
map.m_len = min_t(loff_t, (offset + length - 1) >> blkbits,
EXT4_MAX_LOGICAL_BLOCK) - map.m_lblk + 1;
- if (flags & IOMAP_WRITE)
+ if ((flags & IOMAP_WRITE) && !overwrite)
ret = ext4_iomap_alloc(inode, , flags);
else
ret = ext4_map_blocks(NULL, inode, , 0);
if (ret < 0)
return ret;
+ if (IS_DAX(inode) && overwrite)
+ WARN_ON(!(map.m_flags & EXT4_MAP_MAPPED));
ext4_set_iomap(inode, iomap, , offset, length);
--
2.25.4
