[V2,3/3] ext4: quota handling for delayed allocation

ext4: quota reservation for delayed allocation

Uses quota reservation/claim/release to handle quota properly for delayed
allocation in the three steps: 1) quotas are reserved when data being copied
to cache when block allocation is defered 2) when new blocks are allocated.
reserved quotas are converted to the real allocated quota, 2) over-booked
quotas for metadata blocks are released back.


Signed-off-by: Mingming Cao <cmm@us.ibm.com>
---
 fs/ext4/inode.c   |   25 ++++++++++++++++++++++++-
 fs/ext4/mballoc.c |   18 +++++++++---------
 fs/ext4/super.c   |    2 ++
 3 files changed, 35 insertions(+), 10 deletions(-)



--
To unsubscribe from this list: send the line "unsubscribe linux-ext4" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

On Fri, 31 Oct 2008 14:27:31 -0700
Mingming Cao <cmm@us.ibm.com> wrote:

> ext4: quota reservation for delayed allocation
> 
> Uses quota reservation/claim/release to handle quota properly for delayed
> allocation in the three steps: 1) quotas are reserved when data being copied
> to cache when block allocation is defered 2) when new blocks are allocated.
> reserved quotas are converted to the real allocated quota, 2) over-booked
> quotas for metadata blocks are released back.
> 
> 
> Signed-off-by: Mingming Cao <cmm@us.ibm.com>
> ---
>  fs/ext4/inode.c   |   25 ++++++++++++++++++++++++-
>  fs/ext4/mballoc.c |   18 +++++++++---------
>  fs/ext4/super.c   |    2 ++
>  3 files changed, 35 insertions(+), 10 deletions(-)
> 
> Index: linux-2.6.28-rc2/fs/ext4/inode.c
> ===================================================================
> --- linux-2.6.28-rc2.orig/fs/ext4/inode.c	2008-10-29 13:26:55.000000000 -0700
> +++ linux-2.6.28-rc2/fs/ext4/inode.c	2008-10-30 14:25:47.000000000 -0700
> @@ -994,7 +994,9 @@ static void ext4_da_update_reserve_space
>  {
>  	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
>  	int total, mdb, mdb_free;
> +	int claim_quota, free_quota = 0;
>  
> +	claim_quota = used;
>  	spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
>  	/* recalculate the number of metablocks still need to be reserved */
>  	total = EXT4_I(inode)->i_reserved_data_blocks - used;
> @@ -1007,6 +1009,8 @@ static void ext4_da_update_reserve_space
>  	if (mdb_free) {
>  		/* Account for allocated meta_blocks */
>  		mdb_free -= EXT4_I(inode)->i_allocated_meta_blocks;
> +		free_quota = mdb_free;
> +		claim_quota += EXT4_I(inode)->i_allocated_meta_blocks;
>  
>  		/* update fs dirty blocks counter */
>  		percpu_counter_sub(&sbi->s_dirtyblocks_counter, mdb_free);
> @@ -1017,8 +1021,14 @@ static void ext4_da_update_reserve_space
>  	/* update per-inode reservations */
>  	BUG_ON(used  > EXT4_I(inode)->i_reserved_data_blocks);
>  	EXT4_I(inode)->i_reserved_data_blocks -= used;
> -
>  	spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
> +
> +	/*
> +	 * free those over-booking quota for metadata blocks
> +	 */
> +
> +	if (free_quota)
> +		DQUOT_RELEASE_RSV_BLOCK(inode, free_quota);
>  }
>  
>  /*
> @@ -1514,8 +1524,8 @@ static int ext4_journalled_write_end(str
>  static int ext4_da_reserve_space(struct inode *inode, int nrblocks)
>  {
>  	int retries = 0;
> -       struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
> -       unsigned long md_needed, mdblocks, total = 0;
> +	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
> +	unsigned long md_needed, mdblocks, total = 0;
>  
>  	/*
>  	 * recalculate the amount of metadata blocks to reserve
> @@ -1531,12 +1541,23 @@ repeat:
>  	md_needed = mdblocks - EXT4_I(inode)->i_reserved_meta_blocks;
>  	total = md_needed + nrblocks;
>  
> +	/*
> +	 * Make quota reservation here, to prevent quota overflow
> +	 * later.Real quota accounting is done at pages writeout
> +	 * time

"Make the quota reservation here to prevent quota overflow later.  Real
quota accounting is performed and page writeout time."


> +	 */
> +	 if (DQUOT_RESERVE_BLOCK(inode, total)) {
> +		spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
> +		return -EDQUOT;
> +	}

Mangled whitespace.  checkpatch seems to miss this (but you didn't run
checkpatch anyway.  Please do so?)

>  	if (ext4_claim_free_blocks(sbi, total)) {
>  		spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
>  		if (ext4_should_retry_alloc(inode->i_sb, &retries)) {
>  			yield();
>  			goto repeat;
>  		}
> +		DQUOT_RELEASE_RSV_BLOCK(inode,total);
>  		return -ENOSPC;
>  	}
>  	EXT4_I(inode)->i_reserved_data_blocks += nrblocks;
> @@ -1590,6 +1611,8 @@ static void ext4_da_release_space(struct
>  	BUG_ON(mdb > EXT4_I(inode)->i_reserved_meta_blocks);
>  	EXT4_I(inode)->i_reserved_meta_blocks = mdb;
>  	spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
> +
> +	DQUOT_RELEASE_RSV_BLOCK(inode, release);
>  }

DQUOT_RESERVE_BLOCK needs i_block_reservation_lock?  And
DQUOT_RELEASE_RSV_BLOCK does not?  Seems peculiar.

Please see if we can avoid the bad multiple-return-statements?

This function evaluates EXT4_I(inode) many times.  I'd suggest that you
look at caching the result of that expression in a local variable, see
if that results in improved code generation on common architectures.

>  static void ext4_da_page_release_reservation(struct page *page,
> Index: linux-2.6.28-rc2/fs/ext4/super.c
> ===================================================================
> --- linux-2.6.28-rc2.orig/fs/ext4/super.c	2008-10-29 13:26:55.000000000 -0700
> +++ linux-2.6.28-rc2/fs/ext4/super.c	2008-10-29 14:00:27.000000000 -0700
> @@ -795,6 +795,9 @@ static struct dquot_operations ext4_quot
>  	.initialize	= ext4_dquot_initialize,
>  	.drop		= ext4_dquot_drop,
>  	.alloc_space	= dquot_alloc_space,
> +	.reserve_space	= dquot_reserve_space,
> +	.claim_space	= dquot_claim_space,
> +	.release_rsv	= dquot_release_reserved_space,
>  	.alloc_inode	= dquot_alloc_inode,
>  	.free_space	= dquot_free_space,
>  	.free_inode	= dquot_free_inode,
> Index: linux-2.6.28-rc2/fs/ext4/mballoc.c
> ===================================================================
> --- linux-2.6.28-rc2.orig/fs/ext4/mballoc.c	2008-10-29 13:26:55.000000000 -0700
> +++ linux-2.6.28-rc2/fs/ext4/mballoc.c	2008-10-30 14:30:39.000000000 -0700
> @@ -2887,9 +2887,11 @@ ext4_mb_mark_diskspace_used(struct ext4_
>  	if (!(ac->ac_flags & EXT4_MB_DELALLOC_RESERVED))
>  		/* release all the reserved blocks if non delalloc */
>  		percpu_counter_sub(&sbi->s_dirtyblocks_counter, reserv_blks);
> -	else
> +	else {
>  		percpu_counter_sub(&sbi->s_dirtyblocks_counter,
>  						ac->ac_b_ex.fe_len);
> +		DQUOT_CLAIM_BLOCK(ac->ac_inode, ac->ac_b_ex.fe_len);
> +	}
>  
>  	if (sbi->s_log_groups_per_flex) {
>  		ext4_group_t flex_group = ext4_flex_group(sbi,
> @@ -4286,15 +4288,24 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t
>  	struct ext4_sb_info *sbi;
>  	struct super_block *sb;
>  	ext4_fsblk_t block = 0;
> -	unsigned long inquota;
> +	unsigned long inquota = 0;
>  	unsigned long reserv_blks = 0;
>  
>  	sb = ar->inode->i_sb;
>  	sbi = EXT4_SB(sb);
>  
> -	if (!EXT4_I(ar->inode)->i_delalloc_reserved_flag) {
> +	/*
> +	 * For delayed allocation, we could skip the ENOSPC and
> +	 * EDQUOT check, as blocks and quotas have been already
> +	 * reserved when data being copied to cache

"when data was copied into pagecache"?

> +	 */
> +	if (EXT4_I(ar->inode)->i_delalloc_reserved_flag)
> +		ar->flags |= EXT4_MB_DELALLOC_RESERVED;
> +	else {
>  		/*
> -		 * With delalloc we already reserved the blocks
> +		 * Without delayed allocation we need to verify
> +		 * there is enough free blocks to do block allocation
> +		 * and under the quota limits

I don't understand the "and under the quota limits" bit.  What is this
referring to?

The comment needs a bit of attention.

>  		 */
>  		while (ar->len && ext4_claim_free_blocks(sbi, ar->len)) {
>  			/* let others to free the space */
> @@ -4306,19 +4317,16 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t
>  			return 0;
>  		}
>  		reserv_blks = ar->len;
> +		while (ar->len && DQUOT_ALLOC_BLOCK(ar->inode, ar->len)) {
> +			ar->flags |= EXT4_MB_HINT_NOPREALLOC;
> +			ar->len--;
> +		}

What's this doing?  Trying increasingly small quota allocations until
one of them succeeds?  This sounds like a good way to burn up a large
number of cycles.

Isn't there some way we can be smarter about this?  Surely the quota
layer knows exactly how many blocks we can reserve.

> +		if (ar->len == 0) {
> +			*errp = -EDQUOT;
> +			return 0;
> +		}
> +		inquota = ar->len;
>  	}
> -	while (ar->len && DQUOT_ALLOC_BLOCK(ar->inode, ar->len)) {
> -		ar->flags |= EXT4_MB_HINT_NOPREALLOC;
> -		ar->len--;
> -	}

Oh, it already sucked :)

> -	if (ar->len == 0) {
> -		*errp = -EDQUOT;
> -		return 0;
> -	}
> -	inquota = ar->len;
> -
> -	if (EXT4_I(ar->inode)->i_delalloc_reserved_flag)
> -		ar->flags |= EXT4_MB_DELALLOC_RESERVED;
>  
>  	ac = kmem_cache_alloc(ext4_ac_cachep, GFP_NOFS);
>  	if (!ac) {
> @@ -4380,7 +4388,7 @@ repeat:
>  out2:
>  	kmem_cache_free(ext4_ac_cachep, ac);
>  out1:
> -	if (ar->len < inquota)
> +	if (inquota && ar->len < inquota)
>  		DQUOT_FREE_BLOCK(ar->inode, inquota - ar->len);
>  
>  	return block;
> 
--
To unsubscribe from this list: send the line "unsubscribe linux-ext4" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Andrew Morton wrote:
> On Fri, 31 Oct 2008 14:27:31 -0700
> Mingming Cao <cmm@us.ibm.com> wrote:
> 
>> ext4: quota reservation for delayed allocation
>>
>> Index: linux-2.6.28-rc2/fs/ext4/inode.c
>> ===================================================================
>> --- linux-2.6.28-rc2.orig/fs/ext4/inode.c	2008-10-29 13:26:55.000000000 -0700
>> +++ linux-2.6.28-rc2/fs/ext4/inode.c	2008-10-30 14:25:47.000000000 -0700
>> @@ -1531,12 +1541,23 @@ repeat:
>>  	md_needed = mdblocks - EXT4_I(inode)->i_reserved_meta_blocks;
>>  	total = md_needed + nrblocks;
>>  
>> +	/*
>> +	 * Make quota reservation here, to prevent quota overflow
>> +	 * later.Real quota accounting is done at pages writeout
>> +	 * time
> 
> "Make the quota reservation here to prevent quota overflow later.  Real
> quota accounting is performed and page writeout time."

s/and/at/
---