[RFC PATCH] ext4: Update i_diskzie during writepage for delayed allocation.

[RFC PATCH] ext4: Update i_diskzie during writepage for delayed allocation.

[Aneesh Kumar K.V]

We need to update i_disksize after allocating blocks. writepages
already does this. Update writepage to also  update i_disksize.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
 fs/ext4/inode.c |   40 +++++++++++++++++++++++++++++++++++++++-
 1 files changed, 39 insertions(+), 1 deletions(-)

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 79930df..50d700f 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1488,6 +1488,44 @@ out:
 
 	return ret;
 }
+/* FIXME!! only support data=writeback mode */
+static int ext4_da_writepage(struct page *page,
+				struct writeback_control *wbc)
+{
+	struct inode *inode = page->mapping->host;
+	handle_t *handle = NULL;
+	int ret = 0;
+	int err;
+
+	if (ext4_journal_current_handle())
+		goto out_fail;
+
+	handle = ext4_journal_start(inode, ext4_writepage_trans_blocks(inode));
+	if (IS_ERR(handle)) {
+		ret = PTR_ERR(handle);
+		goto out_fail;
+	}
+
+	if (test_opt(inode->i_sb, NOBH) && ext4_should_writeback_data(inode))
+		ret = nobh_writepage(page, ext4_get_block, wbc);
+	else
+		ret = block_write_full_page(page, ext4_get_block, wbc);
+
+	if (!ret && inode->i_size > EXT4_I(inode)->i_disksize) {
+		EXT4_I(inode)->i_disksize = inode->i_size;
+		ext4_mark_inode_dirty(handle, inode);
+	}
+
+	err = ext4_journal_stop(handle);
+	if (!ret)
+		ret = err;
+	return ret;
+
+out_fail:
+	redirty_page_for_writepage(wbc, page);
+	unlock_page(page);
+	return ret;
+}
 
 static int ext4_da_writepages(struct address_space *mapping,
 				struct writeback_control *wbc)
@@ -2015,7 +2053,7 @@ static const struct address_space_operations ext4_journalled_aops = {
 static const struct address_space_operations ext4_da_aops = {
 	.readpage	= ext4_readpage,
 	.readpages	= ext4_readpages,
-	.writepage	= ext4_writeback_writepage,
+	.writepage	= ext4_da_writepage,
 	.writepages	= ext4_da_writepages,
 	.sync_page	= block_sync_page,
 	.write_begin	= ext4_da_write_begin,
-- 
1.5.5.rc0.16.g02b00.dirty

[RFC PATCH] ext4: Return unwritten buffer head when trying to read from prealloc space.

[Aneesh Kumar K.V]

ext4_ext_get_blocks  returns number of blocks allocated with buffer head
unmapped for a read from prealloc space. This is needed so that delayed
allocation doesn't do block reservation for prealloc space since the blocks
are already resevred on disk. Fix ext4_ext_get_blocks to not return greater
than max_blocks and also mark the buffer head unwritten. Some code path tries
to read the block if buffer_head is not new and no uptodate. Marking the buffer
head unwritten avoid this reading.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
 fs/ext4/extents.c |   14 +++++++++++++-
 1 files changed, 13 insertions(+), 1 deletions(-)

diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index d6ae40a..edd1bf2 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -2600,8 +2600,20 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
 			}
 			if (create == EXT4_CREATE_UNINITIALIZED_EXT)
 				goto out;
-			if (!create)
+			if (!create) {
+				/*
+				 * We have blocks reserved already. We
+				 * return allocated blocks so that delalloc
+				 * won't do block reservation for us. But
+				 * the buffer head will be unmapped so that
+				 * a read from the block return 0
+				 */
+				if (allocated > max_blocks)
+					allocated = max_blocks;
+				/* mark the buffer unwritten */
+				__set_bit(BH_Unwritten, &bh_result->b_state);
 				goto out2;
+			}
 
 			ret = ext4_ext_convert_to_initialized(handle, inode,
 								path, iblock,
-- 
1.5.5.rc0.16.g02b00.dirty

Re: [RFC PATCH] ext4: Update i_diskzie during writepage for delayed allocation.

[Mingming Cao]

On Fri, 2008-03-21 at 11:48 +0530, Aneesh Kumar K.V wrote:
> We need to update i_disksize after allocating blocks. writepages
> already does this. Update writepage to also  update i_disksize.
> 

I agree that we should update the i_disk size after the allocation, to
avoid possible exposing stale data in case of fs crash happened after
the metadata hit to disk but before data being written out.

> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
> ---
>  fs/ext4/inode.c |   40 +++++++++++++++++++++++++++++++++++++++-
>  1 files changed, 39 insertions(+), 1 deletions(-)
> 
> diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
> index 79930df..50d700f 100644
> --- a/fs/ext4/inode.c
> +++ b/fs/ext4/inode.c
> @@ -1488,6 +1488,44 @@ out:
> 
>  	return ret;
>  }
> +/* FIXME!! only support data=writeback mode */
> +static int ext4_da_writepage(struct page *page,
> +				struct writeback_control *wbc)
> +{
> +	struct inode *inode = page->mapping->host;
> +	handle_t *handle = NULL;
> +	int ret = 0;
> +	int err;
> +
> +	if (ext4_journal_current_handle())
> +		goto out_fail;
> +
> +	handle = ext4_journal_start(inode, ext4_writepage_trans_blocks(inode));
> +	if (IS_ERR(handle)) {
> +		ret = PTR_ERR(handle);
> +		goto out_fail;
> +	}
> +
> +	if (test_opt(inode->i_sb, NOBH) && ext4_should_writeback_data(inode))
> +		ret = nobh_writepage(page, ext4_get_block, wbc);
> +	else
> +		ret = block_write_full_page(page, ext4_get_block, wbc);
> +
> +	if (!ret && inode->i_size > EXT4_I(inode)->i_disksize) {
> +		EXT4_I(inode)->i_disksize = inode->i_size;
> +		ext4_mark_inode_dirty(handle, inode);
> +	}
> +
> +	err = ext4_journal_stop(handle);
> +	if (!ret)
> +		ret = err;
> +	return ret;
> +
> +out_fail:
> +	redirty_page_for_writepage(wbc, page);
> +	unlock_page(page);
> +	return ret;
> +}
> 
>  static int ext4_da_writepages(struct address_space *mapping,
>  				struct writeback_control *wbc)
> @@ -2015,7 +2053,7 @@ static const struct address_space_operations ext4_journalled_aops = {
>  static const struct address_space_operations ext4_da_aops = {
>  	.readpage	= ext4_readpage,
>  	.readpages	= ext4_readpages,
> -	.writepage	= ext4_writeback_writepage,
> +	.writepage	= ext4_da_writepage,
>  	.writepages	= ext4_da_writepages,
>  	.sync_page	= block_sync_page,
>  	.write_begin	= ext4_da_write_begin,

Re: [RFC PATCH] ext4: Return unwritten buffer head when trying to read from prealloc space.

[Mingming Cao]

On Fri, 2008-03-21 at 11:48 +0530, Aneesh Kumar K.V wrote:
> ext4_ext_get_blocks  returns number of blocks allocated with buffer head
> unmapped for a read from prealloc space. This is needed so that delayed
> allocation doesn't do block reservation for prealloc space since the blocks
> are already resevred on disk. Fix ext4_ext_get_blocks to not return greater
> than max_blocks and also mark the buffer head unwritten. Some code path tries
> to read the block if buffer_head is not new and no uptodate. Marking the buffer
> head unwritten avoid this reading.
> 

Seems this patch fixes two bugs together, it would be nice to split to
two as they cause two different problems.

To fix the bh->b_size warning solof founds for delayed allocation, I
would say we need to fix it in ext4_get_blocks_handle() (for indirect
files) and ext4_ext_get_blocks()(for extent files) both, not allowing
returning b_size greater than what the caller asking for. Also, the
patch below seems only address the preallocation map case, we need to
fix in in general block lookup case.

> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
> ---
>  fs/ext4/extents.c |   14 +++++++++++++-
>  1 files changed, 13 insertions(+), 1 deletions(-)
> 
> diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
> index d6ae40a..edd1bf2 100644
> --- a/fs/ext4/extents.c
> +++ b/fs/ext4/extents.c
> @@ -2600,8 +2600,20 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
>  			}
>  			if (create == EXT4_CREATE_UNINITIALIZED_EXT)
>  				goto out;
> -			if (!create)
> +			if (!create) {
> +				/*
> +				 * We have blocks reserved already. We
> +				 * return allocated blocks so that delalloc
> +				 * won't do block reservation for us. But
> +				 * the buffer head will be unmapped so that
> +				 * a read from the block return 0
> +				 */
> +				if (allocated > max_blocks)
> +					allocated = max_blocks;
> +				/* mark the buffer unwritten */
> +				__set_bit(BH_Unwritten, &bh_result->b_state);
>  				goto out2;
> +			}
> 
>  			ret = ext4_ext_convert_to_initialized(handle, inode,
>  								path, iblock,

Re: [RFC PATCH] ext4: Return unwritten buffer head when trying to read from prealloc space.

[Aneesh Kumar K.V]

On Fri, Mar 21, 2008 at 03:13:58PM -0700, Mingming Cao wrote:
> On Fri, 2008-03-21 at 11:48 +0530, Aneesh Kumar K.V wrote:
> > ext4_ext_get_blocks  returns number of blocks allocated with buffer head
> > unmapped for a read from prealloc space. This is needed so that delayed
> > allocation doesn't do block reservation for prealloc space since the blocks
> > are already resevred on disk. Fix ext4_ext_get_blocks to not return greater
> > than max_blocks and also mark the buffer head unwritten. Some code path tries
> > to read the block if buffer_head is not new and no uptodate. Marking the buffer
> > head unwritten avoid this reading.
> > 
> 
> Seems this patch fixes two bugs together, it would be nice to split to
> two as they cause two different problems.

Split patches here.

http://www.radian.org/~kvaneesh/ext4/patches-to-patchqueue/

> 
> To fix the bh->b_size warning solof founds for delayed allocation, I
> would say we need to fix it in ext4_get_blocks_handle() (for indirect
> files) and ext4_ext_get_blocks()(for extent files) both, not allowing
> returning b_size greater than what the caller asking for. Also, the
> patch below seems only address the preallocation map case, we need to
> fix in in general block lookup case.
> 

ext4_ext_get_blocks already make sure we doesn't return > max_blocks.
for normal allocation.

2694 out:
2695         if (allocated > max_blocks)
2696                 allocated = max_blocks;


-aneesh

Re: [RFC PATCH] ext4: Return unwritten buffer head when trying to read from prealloc space.

[Mingming Cao]

On Mon, 2008-03-24 at 13:41 +0530, Aneesh Kumar K.V wrote:
> On Fri, Mar 21, 2008 at 03:13:58PM -0700, Mingming Cao wrote:
> > On Fri, 2008-03-21 at 11:48 +0530, Aneesh Kumar K.V wrote:
> > > ext4_ext_get_blocks  returns number of blocks allocated with buffer head
> > > unmapped for a read from prealloc space. This is needed so that delayed
> > > allocation doesn't do block reservation for prealloc space since the blocks
> > > are already resevred on disk. Fix ext4_ext_get_blocks to not return greater
> > > than max_blocks and also mark the buffer head unwritten. Some code path tries
> > > to read the block if buffer_head is not new and no uptodate. Marking the buffer
> > > head unwritten avoid this reading.
> > > 
> > 
> > Seems this patch fixes two bugs together, it would be nice to split to
> > two as they cause two different problems.
> 
> Split patches here.
> 
> http://www.radian.org/~kvaneesh/ext4/patches-to-patchqueue/
> 
I will pick them up in patch queue.
> > 
> > To fix the bh->b_size warning solof founds for delayed allocation, I
> > would say we need to fix it in ext4_get_blocks_handle() (for indirect
> > files) and ext4_ext_get_blocks()(for extent files) both, not allowing
> > returning b_size greater than what the caller asking for. Also, the
> > patch below seems only address the preallocation map case, we need to
> > fix in in general block lookup case.
> > 
> 
> ext4_ext_get_blocks already make sure we doesn't return > max_blocks.
> for normal allocation.
> 
> 2694 out:
> 2695         if (allocated > max_blocks)
> 2696                 allocated = max_blocks;
> 

Oh I see, I missed that.

Regards,
Mingming
> 
> -aneesh