[PATCH] f2fs: readahead node block in F2FS_GET_BLOCK_PRECACHE mode

[PATCH] f2fs: readahead node block in F2FS_GET_BLOCK_PRECACHE mode

[Yunji Kang]

In f2fs_precache_extents(), For large files, It requires reading many
node blocks. Instead of reading each node block with synchronous I/O,
this patch applies readahead so that node blocks can be fetched in
advance.

It reduces the overhead of repeated sync reads and improves efficiency
when precaching extents of large files.

I created a file with the same largest extent and executed the test.
For this experiment, I set the file's largest extent with an offset of 0
and a size of 1GB. I configured the remaining area with 100MB extents.

5GB test file:
dd if=/dev/urandom of=test1 bs=1m count=5120
cp test1 test2
fsync test1
dd if=test1 of=test2 bs=1m skip=1024 seek=1024 count=100 conv=notrunc
dd if=test1 of=test2 bs=1m skip=1224 seek=1224 count=100 conv=notrunc
...
dd if=test1 of=test2 bs=1m skip=5024 seek=5024 count=100 conv=notrunc
reboot

I also created 10GB and 20GB files with large extents using the same
method.

ioctl(F2FS_IOC_PRECACHE_EXTENTS) test results are as follows:
  +-----------+---------+---------+-----------+
  | File size | Before  | After   | Reduction |
  +-----------+---------+---------+-----------+
  | 5GB       | 101.8ms | 72.1ms  | 29.2%     |
  | 10GB      | 222.9ms | 149.5ms | 32.9%     |
  | 20GB      | 446.2ms | 276.3ms | 38.1%     |
  +-----------+---------+---------+-----------+
Tested on a 256GB mobile device with an SM8750 chipset.

Reviewed-by: Sungjong Seo <sj1557.seo@samsung.com>
Reviewed-by: Sunmin Jeong <s_min.jeong@samsung.com>
Signed-off-by: Yunji Kang <yunji0.kang@samsung.com>
---
 fs/f2fs/data.c | 3 +++
 fs/f2fs/f2fs.h | 1 +
 fs/f2fs/node.c | 4 +++-
 3 files changed, 7 insertions(+), 1 deletion(-)

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 7961e0ddfca3..ab3117e3b24a 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -1572,6 +1572,9 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map, int flag)
 	pgofs =	(pgoff_t)map->m_lblk;
 	end = pgofs + maxblocks;
 
+	if (flag == F2FS_GET_BLOCK_PRECACHE)
+		mode = LOOKUP_NODE_PRECACHE;
+
 next_dnode:
 	if (map->m_may_create) {
 		if (f2fs_lfs_mode(sbi))
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 9d3bc9633c1d..3ce41528d48e 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -651,6 +651,7 @@ enum {
 					 * look up a node with readahead called
 					 * by get_data_block.
 					 */
+	LOOKUP_NODE_PRECACHE,		/* look up a node for F2FS_GET_BLOCK_PRECACHE */
 };
 
 #define DEFAULT_RETRY_IO_COUNT	8	/* maximum retry read IO or flush count */
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 4254db453b2d..50be167e5c59 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -860,7 +860,9 @@ int f2fs_get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode)
 			set_nid(parent, offset[i - 1], nids[i], i == 1);
 			f2fs_alloc_nid_done(sbi, nids[i]);
 			done = true;
-		} else if (mode == LOOKUP_NODE_RA && i == level && level > 1) {
+		} else if ((mode == LOOKUP_NODE_RA ||
+				(mode == LOOKUP_NODE_PRECACHE && offset[i - 1] % MAX_RA_NODE == 0))
+				&& i == level && level > 1) {
 			nfolio[i] = f2fs_get_node_folio_ra(parent, offset[i - 1]);
 			if (IS_ERR(nfolio[i])) {
 				err = PTR_ERR(nfolio[i]);
-- 
2.34.1

Re: [PATCH] f2fs: readahead node block in F2FS_GET_BLOCK_PRECACHE mode

[Chao Yu]

On 9/17/25 13:52, Yunji Kang wrote:
> In f2fs_precache_extents(), For large files, It requires reading many
> node blocks. Instead of reading each node block with synchronous I/O,
> this patch applies readahead so that node blocks can be fetched in
> advance.
> 
> It reduces the overhead of repeated sync reads and improves efficiency
> when precaching extents of large files.
> 
> I created a file with the same largest extent and executed the test.
> For this experiment, I set the file's largest extent with an offset of 0
> and a size of 1GB. I configured the remaining area with 100MB extents.
> 
> 5GB test file:
> dd if=/dev/urandom of=test1 bs=1m count=5120
> cp test1 test2
> fsync test1
> dd if=test1 of=test2 bs=1m skip=1024 seek=1024 count=100 conv=notrunc
> dd if=test1 of=test2 bs=1m skip=1224 seek=1224 count=100 conv=notrunc
> ...
> dd if=test1 of=test2 bs=1m skip=5024 seek=5024 count=100 conv=notrunc
> reboot
> 
> I also created 10GB and 20GB files with large extents using the same
> method.
> 
> ioctl(F2FS_IOC_PRECACHE_EXTENTS) test results are as follows:
>   +-----------+---------+---------+-----------+
>   | File size | Before  | After   | Reduction |
>   +-----------+---------+---------+-----------+
>   | 5GB       | 101.8ms | 72.1ms  | 29.2%     |
>   | 10GB      | 222.9ms | 149.5ms | 32.9%     |
>   | 20GB      | 446.2ms | 276.3ms | 38.1%     |
>   +-----------+---------+---------+-----------+
> Tested on a 256GB mobile device with an SM8750 chipset.
> 
> Reviewed-by: Sungjong Seo <sj1557.seo@samsung.com>
> Reviewed-by: Sunmin Jeong <s_min.jeong@samsung.com>
> Signed-off-by: Yunji Kang <yunji0.kang@samsung.com>
> ---
>  fs/f2fs/data.c | 3 +++
>  fs/f2fs/f2fs.h | 1 +
>  fs/f2fs/node.c | 4 +++-
>  3 files changed, 7 insertions(+), 1 deletion(-)
> 
> diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
> index 7961e0ddfca3..ab3117e3b24a 100644
> --- a/fs/f2fs/data.c
> +++ b/fs/f2fs/data.c
> @@ -1572,6 +1572,9 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map, int flag)
>  	pgofs =	(pgoff_t)map->m_lblk;
>  	end = pgofs + maxblocks;
>  
> +	if (flag == F2FS_GET_BLOCK_PRECACHE)
> +		mode = LOOKUP_NODE_PRECACHE;
> +
>  next_dnode:
>  	if (map->m_may_create) {
>  		if (f2fs_lfs_mode(sbi))
> diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
> index 9d3bc9633c1d..3ce41528d48e 100644
> --- a/fs/f2fs/f2fs.h
> +++ b/fs/f2fs/f2fs.h
> @@ -651,6 +651,7 @@ enum {
>  					 * look up a node with readahead called
>  					 * by get_data_block.
>  					 */
> +	LOOKUP_NODE_PRECACHE,		/* look up a node for F2FS_GET_BLOCK_PRECACHE */
>  };
>  
>  #define DEFAULT_RETRY_IO_COUNT	8	/* maximum retry read IO or flush count */
> diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
> index 4254db453b2d..50be167e5c59 100644
> --- a/fs/f2fs/node.c
> +++ b/fs/f2fs/node.c
> @@ -860,7 +860,9 @@ int f2fs_get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode)
>  			set_nid(parent, offset[i - 1], nids[i], i == 1);
>  			f2fs_alloc_nid_done(sbi, nids[i]);
>  			done = true;
> -		} else if (mode == LOOKUP_NODE_RA && i == level && level > 1) {
> +		} else if ((mode == LOOKUP_NODE_RA ||

Does this change the logic for mode = LOOKUP_NODE_RA?

Not sure, do you mean this?

	if ((i == level && level > 1) &&
		(mode == LOOKUP_NODE_RA ||
		(mode == LOOKUP_NODE_PRECACHE &&
		offset[i - 1] % MAX_RA_NODE == 0)))

Thanks,

> +				(mode == LOOKUP_NODE_PRECACHE && offset[i - 1] % MAX_RA_NODE == 0))
> +				&& i == level && level > 1) {
>  			nfolio[i] = f2fs_get_node_folio_ra(parent, offset[i - 1]);
>  			if (IS_ERR(nfolio[i])) {
>  				err = PTR_ERR(nfolio[i]);

RE: [PATCH] f2fs: readahead node block in F2FS_GET_BLOCK_PRECACHE mode

[Yunji Kang]

> > In f2fs_precache_extents(), For large files, It requires reading many
> > node blocks. Instead of reading each node block with synchronous I/O,
> > this patch applies readahead so that node blocks can be fetched in
> > advance.
> >
> > It reduces the overhead of repeated sync reads and improves efficiency
> > when precaching extents of large files.
> >
> > I created a file with the same largest extent and executed the test.
> > For this experiment, I set the file's largest extent with an offset of
> > 0 and a size of 1GB. I configured the remaining area with 100MB extents.
> >
> > 5GB test file:
> > dd if=/dev/urandom of=test1 bs=1m count=5120 cp test1 test2 fsync
> > test1 dd if=test1 of=test2 bs=1m skip=1024 seek=1024 count=100
> > conv=notrunc dd if=test1 of=test2 bs=1m skip=1224 seek=1224 count=100
> > conv=notrunc ...
> > dd if=test1 of=test2 bs=1m skip=5024 seek=5024 count=100 conv=notrunc
> > reboot
> >
> > I also created 10GB and 20GB files with large extents using the same
> > method.
> >
> > ioctl(F2FS_IOC_PRECACHE_EXTENTS) test results are as follows:
> >   +-----------+---------+---------+-----------+
> >   | File size | Before  | After   | Reduction |
> >   +-----------+---------+---------+-----------+
> >   | 5GB       | 101.8ms | 72.1ms  | 29.2%     |
> >   | 10GB      | 222.9ms | 149.5ms | 32.9%     |
> >   | 20GB      | 446.2ms | 276.3ms | 38.1%     |
> >   +-----------+---------+---------+-----------+
> > Tested on a 256GB mobile device with an SM8750 chipset.
> >
> > Reviewed-by: Sungjong Seo <sj1557.seo@samsung.com>
> > Reviewed-by: Sunmin Jeong <s_min.jeong@samsung.com>
> > Signed-off-by: Yunji Kang <yunji0.kang@samsung.com>
> > ---
> >  fs/f2fs/data.c | 3 +++
> >  fs/f2fs/f2fs.h | 1 +
> >  fs/f2fs/node.c | 4 +++-
> >  3 files changed, 7 insertions(+), 1 deletion(-)
> >
> > diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index
> > 7961e0ddfca3..ab3117e3b24a 100644
> > --- a/fs/f2fs/data.c
> > +++ b/fs/f2fs/data.c
> > @@ -1572,6 +1572,9 @@ int f2fs_map_blocks(struct inode *inode, struct
> f2fs_map_blocks *map, int flag)
> >  	pgofs =	(pgoff_t)map->m_lblk;
> >  	end = pgofs + maxblocks;
> >
> > +	if (flag == F2FS_GET_BLOCK_PRECACHE)
> > +		mode = LOOKUP_NODE_PRECACHE;
> > +
> >  next_dnode:
> >  	if (map->m_may_create) {
> >  		if (f2fs_lfs_mode(sbi))
> > diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index
> > 9d3bc9633c1d..3ce41528d48e 100644
> > --- a/fs/f2fs/f2fs.h
> > +++ b/fs/f2fs/f2fs.h
> > @@ -651,6 +651,7 @@ enum {
> >  					 * look up a node with readahead called
> >  					 * by get_data_block.
> >  					 */
> > +	LOOKUP_NODE_PRECACHE,		/* look up a node for
> F2FS_GET_BLOCK_PRECACHE */
> >  };
> >
> >  #define DEFAULT_RETRY_IO_COUNT	8	/* maximum retry read IO or flush
> count */
> > diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index
> > 4254db453b2d..50be167e5c59 100644
> > --- a/fs/f2fs/node.c
> > +++ b/fs/f2fs/node.c
> > @@ -860,7 +860,9 @@ int f2fs_get_dnode_of_data(struct dnode_of_data *dn,
> pgoff_t index, int mode)
> >  			set_nid(parent, offset[i - 1], nids[i], i == 1);
> >  			f2fs_alloc_nid_done(sbi, nids[i]);
> >  			done = true;
> > -		} else if (mode == LOOKUP_NODE_RA && i == level && level > 1)
> {
> > +		} else if ((mode == LOOKUP_NODE_RA ||
> 
> Does this change the logic for mode = LOOKUP_NODE_RA?
> 
> Not sure, do you mean this?
> 
> 	if ((i == level && level > 1) &&
> 		(mode == LOOKUP_NODE_RA ||
> 		(mode == LOOKUP_NODE_PRECACHE &&
> 		offset[i - 1] % MAX_RA_NODE == 0)))
> 
> Thanks,
> 
> > +				(mode == LOOKUP_NODE_PRECACHE && offset[i - 1] %
> MAX_RA_NODE == 0))
> > +				&& i == level && level > 1) {
> >  			nfolio[i] = f2fs_get_node_folio_ra(parent, offset[i -
> 1]);
> >  			if (IS_ERR(nfolio[i])) {
> >  				err = PTR_ERR(nfolio[i]);

I think the code has the same meaning.
The version you wrote looks more readable, so would it be okay if I change the patch with your code?

Also, I did not change the logic for mode = LOOKUP_NODE_RA; I only added a condition for when readahead is performed.

Thanks.

Re: [PATCH] f2fs: readahead node block in F2FS_GET_BLOCK_PRECACHE mode

[Chao Yu]

On 9/18/25 12:55, Yunji Kang wrote:
>>> In f2fs_precache_extents(), For large files, It requires reading many
>>> node blocks. Instead of reading each node block with synchronous I/O,
>>> this patch applies readahead so that node blocks can be fetched in
>>> advance.
>>>
>>> It reduces the overhead of repeated sync reads and improves efficiency
>>> when precaching extents of large files.
>>>
>>> I created a file with the same largest extent and executed the test.
>>> For this experiment, I set the file's largest extent with an offset of
>>> 0 and a size of 1GB. I configured the remaining area with 100MB extents.
>>>
>>> 5GB test file:
>>> dd if=/dev/urandom of=test1 bs=1m count=5120 cp test1 test2 fsync
>>> test1 dd if=test1 of=test2 bs=1m skip=1024 seek=1024 count=100
>>> conv=notrunc dd if=test1 of=test2 bs=1m skip=1224 seek=1224 count=100
>>> conv=notrunc ...
>>> dd if=test1 of=test2 bs=1m skip=5024 seek=5024 count=100 conv=notrunc
>>> reboot
>>>
>>> I also created 10GB and 20GB files with large extents using the same
>>> method.
>>>
>>> ioctl(F2FS_IOC_PRECACHE_EXTENTS) test results are as follows:
>>>   +-----------+---------+---------+-----------+
>>>   | File size | Before  | After   | Reduction |
>>>   +-----------+---------+---------+-----------+
>>>   | 5GB       | 101.8ms | 72.1ms  | 29.2%     |
>>>   | 10GB      | 222.9ms | 149.5ms | 32.9%     |
>>>   | 20GB      | 446.2ms | 276.3ms | 38.1%     |
>>>   +-----------+---------+---------+-----------+
>>> Tested on a 256GB mobile device with an SM8750 chipset.
>>>
>>> Reviewed-by: Sungjong Seo <sj1557.seo@samsung.com>
>>> Reviewed-by: Sunmin Jeong <s_min.jeong@samsung.com>
>>> Signed-off-by: Yunji Kang <yunji0.kang@samsung.com>
>>> ---
>>>  fs/f2fs/data.c | 3 +++
>>>  fs/f2fs/f2fs.h | 1 +
>>>  fs/f2fs/node.c | 4 +++-
>>>  3 files changed, 7 insertions(+), 1 deletion(-)
>>>
>>> diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index
>>> 7961e0ddfca3..ab3117e3b24a 100644
>>> --- a/fs/f2fs/data.c
>>> +++ b/fs/f2fs/data.c
>>> @@ -1572,6 +1572,9 @@ int f2fs_map_blocks(struct inode *inode, struct
>> f2fs_map_blocks *map, int flag)
>>>  	pgofs =	(pgoff_t)map->m_lblk;
>>>  	end = pgofs + maxblocks;
>>>
>>> +	if (flag == F2FS_GET_BLOCK_PRECACHE)
>>> +		mode = LOOKUP_NODE_PRECACHE;
>>> +
>>>  next_dnode:
>>>  	if (map->m_may_create) {
>>>  		if (f2fs_lfs_mode(sbi))
>>> diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index
>>> 9d3bc9633c1d..3ce41528d48e 100644
>>> --- a/fs/f2fs/f2fs.h
>>> +++ b/fs/f2fs/f2fs.h
>>> @@ -651,6 +651,7 @@ enum {
>>>  					 * look up a node with readahead called
>>>  					 * by get_data_block.
>>>  					 */
>>> +	LOOKUP_NODE_PRECACHE,		/* look up a node for
>> F2FS_GET_BLOCK_PRECACHE */
>>>  };
>>>
>>>  #define DEFAULT_RETRY_IO_COUNT	8	/* maximum retry read IO or flush
>> count */
>>> diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index
>>> 4254db453b2d..50be167e5c59 100644
>>> --- a/fs/f2fs/node.c
>>> +++ b/fs/f2fs/node.c
>>> @@ -860,7 +860,9 @@ int f2fs_get_dnode_of_data(struct dnode_of_data *dn,
>> pgoff_t index, int mode)
>>>  			set_nid(parent, offset[i - 1], nids[i], i == 1);
>>>  			f2fs_alloc_nid_done(sbi, nids[i]);
>>>  			done = true;
>>> -		} else if (mode == LOOKUP_NODE_RA && i == level && level > 1)
>> {
>>> +		} else if ((mode == LOOKUP_NODE_RA ||
>>
>> Does this change the logic for mode = LOOKUP_NODE_RA?
>>
>> Not sure, do you mean this?
>>
>> 	if ((i == level && level > 1) &&
>> 		(mode == LOOKUP_NODE_RA ||
>> 		(mode == LOOKUP_NODE_PRECACHE &&
>> 		offset[i - 1] % MAX_RA_NODE == 0)))
>>
>> Thanks,
>>
>>> +				(mode == LOOKUP_NODE_PRECACHE && offset[i - 1] %
>> MAX_RA_NODE == 0))
>>> +				&& i == level && level > 1) {
>>>  			nfolio[i] = f2fs_get_node_folio_ra(parent, offset[i -
>> 1]);
>>>  			if (IS_ERR(nfolio[i])) {
>>>  				err = PTR_ERR(nfolio[i]);
> 
> I think the code has the same meaning.
> The version you wrote looks more readable, so would it be okay if I change the patch with your code?

Sure, please go ahead.

> 
> Also, I did not change the logic for mode = LOOKUP_NODE_RA; I only added a condition for when readahead is performed.

Oh, I see, I missed the parenthesis, sorry.

Thanks,

> 
> Thanks.
>