Re: [PATCH v2 07/12] ext4: add fields that are needed to track changed files

[Andreas Dilger <adilger@dilger.ca>]

[-- Attachment #1: Type: text/plain, Size: 6109 bytes --]

On Aug 8, 2019, at 9:45 PM, Harshad Shirwadkar <harshadshirwadkar@gmail.com> wrote:
> 
> Ext4's fast commit feature tracks changed files and maintains them in
> a queue. We also remember for each file the logical block range that
> needs to be committed. This patch adds these fields to ext4_inode_info
> and ext4_sb_info and also adds initialization calls.
> 
> Signed-off-by: Harshad Shirwadkar <harshadshirwadkar@gmail.com>
> 
> ---
> 
> Changelog:
> 
> V2: Converted s_fc_lock from mutex to spinlock to improve parallelism
>    performance.
> ---
> fs/ext4/ext4.h      | 34 ++++++++++++++++++++++++++++++++++
> fs/ext4/ext4_jbd2.c | 13 +++++++++++++
> fs/ext4/ext4_jbd2.h |  2 ++
> fs/ext4/inode.c     |  1 +
> fs/ext4/super.c     |  7 +++++++
> 5 files changed, 57 insertions(+)
> 
> diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
> index becbda38b7db..0d15d4539dda 100644
> --- a/fs/ext4/ext4.h
> +++ b/fs/ext4/ext4.h
> @@ -921,6 +921,27 @@ enum {
> 	I_DATA_SEM_QUOTA,
> };
> 
> +/*
> + * Ext4 fast commit inode specific information
> + */
> +struct ext4_fast_commit_inode_info {
> +	/* TID / SUB-TID when old_i_size and i_size were recorded */
> +	tid_t fc_tid;
> +	tid_t fc_subtid;
> +
> +	/*
> +	 * Start of logical block range that needs to be committed in this fast
> +	 * commit
> +	 */
> +	loff_t fc_lblk_start;
> +
> +	/*
> +	 * End of logical block range that needs to be committed in this fast
> +	 * commit
> +	 */
> +	loff_t fc_lblk_end;

Since these are logical block numbers within the journal, they certainly
don't need to be 64-bit values.  loff_t is for byte offsets, this should
use ext4_lblk_t, which will also reduce the size of the struct by 8 bytes.

> +};
> +
> 
> /*
>  * fourth extended file system inode data in memory
> @@ -955,6 +976,9 @@ struct ext4_inode_info {
> 
> 	struct list_head i_orphan;	/* unlinked but open inodes */
> 
> +	struct list_head i_fc_list;	/* inodes that need fast commit */

This comment should document what lock is protecting this list, along
with the other fields.

> +	struct ext4_fast_commit_inode_info i_fc;

Since this increases the size of the inode, does it affect the number of
inodes that can fit into one page of ext4_inode_cachep?

> 	/*
> 	 * i_disksize keeps track of what the inode size is ON DISK, not
> 	 * in memory.  During truncate, i_size is set to the new size by
> @@ -1529,6 +1553,16 @@ struct ext4_sb_info {
> 	/* Barrier between changing inodes' journal flags and writepages ops. */
> 	struct percpu_rw_semaphore s_journal_flag_rwsem;
> 	struct dax_device *s_daxdev;
> +
> +	/* Ext4 fast commit stuff */
> +	bool fc_replay;			/* Fast commit replay in progress */
> +	struct list_head s_fc_q;	/* Inodes that need fast commit. */

This comment should document what lock is protecting this list, along
with the other fields.

> +	__u32 s_fc_q_cnt;		/* Number of inodes in the fc queue */
> +	bool s_fc_eligible;		/*
> +					 * Are changes after the last commit
> +					 * eligible for fast commit?
> +					 */

It is slightly more space efficient to put the bool values together
rather than interleaving them between 64-bit values.

> +	spinlock_t s_fc_lock;
> };
> 
> static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb)
> diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c
> index 7c70b08d104c..75b6db808837 100644
> --- a/fs/ext4/ext4_jbd2.c
> +++ b/fs/ext4/ext4_jbd2.c
> @@ -330,3 +330,16 @@ int __ext4_handle_dirty_super(const char *where, unsigned int line,
> 		mark_buffer_dirty(bh);
> 	return err;
> }
> +
> +void ext4_init_inode_fc_info(struct inode *inode)
> +{
> +	handle_t *handle = ext4_journal_current_handle();
> +	struct ext4_inode_info *ei = EXT4_I(inode);
> +
> +	memset(&ei->i_fc, 0, sizeof(ei->i_fc));
> +	if (ext4_handle_valid(handle)) {
> +		ei->i_fc.fc_tid = handle->h_transaction->t_tid;
> +		ei->i_fc.fc_subtid = handle->h_transaction->t_journal->j_subtid;
> +	}
> +	INIT_LIST_HEAD(&ei->i_fc_list);
> +}
> diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h
> index ef8fcf7d0d3b..2305c1acd415 100644
> --- a/fs/ext4/ext4_jbd2.h
> +++ b/fs/ext4/ext4_jbd2.h
> @@ -459,4 +459,6 @@ static inline int ext4_should_dioread_nolock(struct inode *inode)
> 	return 1;
> }
> 
> +void ext4_init_inode_fc_info(struct inode *inode);
> +
> #endif	/* _EXT4_JBD2_H */
> diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
> index 420fe3deed39..f230a888eddd 100644
> --- a/fs/ext4/inode.c
> +++ b/fs/ext4/inode.c
> @@ -4996,6 +4996,7 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
> 	for (block = 0; block < EXT4_N_BLOCKS; block++)
> 		ei->i_data[block] = raw_inode->i_block[block];
> 	INIT_LIST_HEAD(&ei->i_orphan);
> +	ext4_init_inode_fc_info(&ei->vfs_inode);
> 
> 	/*
> 	 * Set transaction id's of transactions that have to be committed
> diff --git a/fs/ext4/super.c b/fs/ext4/super.c
> index 6bab59ae81f7..0b833e9b61c1 100644
> --- a/fs/ext4/super.c
> +++ b/fs/ext4/super.c
> @@ -1100,6 +1100,7 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
> 	ei->i_datasync_tid = 0;
> 	atomic_set(&ei->i_unwritten, 0);
> 	INIT_WORK(&ei->i_rsv_conversion_work, ext4_end_io_rsv_work);
> +	ext4_init_inode_fc_info(&ei->vfs_inode);
> 	return &ei->vfs_inode;
> }
> 
> @@ -1139,6 +1140,7 @@ static void init_once(void *foo)
> 	init_rwsem(&ei->i_data_sem);
> 	init_rwsem(&ei->i_mmap_sem);
> 	inode_init_once(&ei->vfs_inode);
> +	ext4_init_inode_fc_info(&ei->vfs_inode);
> }
> 
> static int __init init_inodecache(void)
> @@ -4301,6 +4303,11 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
> 	INIT_LIST_HEAD(&sbi->s_orphan); /* unlinked but open files */
> 	mutex_init(&sbi->s_orphan_lock);
> 
> +	INIT_LIST_HEAD(&sbi->s_fc_q);
> +	sbi->s_fc_q_cnt = 0;
> +	sbi->s_fc_eligible = true;
> +	spin_lock_init(&sbi->s_fc_lock);
> +
> 	sb->s_root = NULL;
> 
> 	needs_recovery = (es->s_last_orphan != 0 ||
> --
> 2.23.0.rc1.153.gdeed80330f-goog
> 


Cheers, Andreas






[-- Attachment #2: Message signed with OpenPGP --]
[-- Type: application/pgp-signature, Size: 873 bytes --]