[PATCH] erofs-utils: use qsort() to sort dir->i_subdirs

[Gao Xiang]

Hi Weiwen,

On Thu, Apr 01, 2021 at 09:52:51PM +0800, Hu Weiwen wrote:
> Original implementation use insertion sort, and its time complexity is
> O(n^2). This patch use qsort instead. When I create a directory with
> 100k entries, this reduces the user space time from around 3 mins to
> 0.5s.
> 
> Create such a large directory for benchmark with:
> mkdir large; cd large; touch $(seq 100000);
> 
> Signed-off-by: Hu Weiwen <sehuww at mail.scut.edu.cn>

Thanks for your work. Yeah, it's another path that needs to be
optimized for huge dirs.

The overall looks good to me, some nits below...

> ---
>  lib/inode.c | 53 +++++++++++++++++++++++++++++++++--------------------
>  1 file changed, 33 insertions(+), 20 deletions(-)
> 
> diff --git a/lib/inode.c b/lib/inode.c
> index d52facf..9217127 100644
> --- a/lib/inode.c
> +++ b/lib/inode.c
> @@ -96,21 +96,6 @@ unsigned int erofs_iput(struct erofs_inode *inode)
>  	return 0;
>  }
>  
> -static int dentry_add_sorted(struct erofs_dentry *d, struct list_head *head)
> -{
> -	struct list_head *pos;
> -
> -	list_for_each(pos, head) {
> -		struct erofs_dentry *d2 =
> -			container_of(pos, struct erofs_dentry, d_child);
> -
> -		if (strcmp(d->name, d2->name) < 0)
> -			break;
> -	}
> -	list_add_tail(&d->d_child, pos);
> -	return 0;
> -}
> -
>  struct erofs_dentry *erofs_d_alloc(struct erofs_inode *parent,
>  				   const char *name)
>  {
> @@ -122,7 +107,7 @@ struct erofs_dentry *erofs_d_alloc(struct erofs_inode *parent,
>  	strncpy(d->name, name, EROFS_NAME_LEN - 1);
>  	d->name[EROFS_NAME_LEN - 1] = '\0';
>  
> -	dentry_add_sorted(d, &parent->i_subdirs);
> +	list_add_tail(&d->d_child, &parent->i_subdirs);
>  	return d;
>  }
>  
> @@ -156,10 +141,19 @@ static int __allocate_inode_bh_data(struct erofs_inode *inode,
>  	return 0;
>  }
>  
> +static int comp_subdir(const void *a, const void *b)
> +{
> +	const struct erofs_dentry *d_a, *d_b;
> +
> +	d_a = *((const struct erofs_dentry **)a);
> +	d_b = *((const struct erofs_dentry **)b);
> +	return strcmp(d_a->name, d_b->name);
> +}

How about just use `da' and `db' for size?

> +
> -int erofs_prepare_dir_file(struct erofs_inode *dir)
> +int erofs_prepare_dir_file(struct erofs_inode *dir, unsigned int nr_subdirs)
>  {
> -	struct erofs_dentry *d;
> -	unsigned int d_size, i_nlink;
> +	struct erofs_dentry *d, **all_d;
> +	unsigned int d_size, i_nlink, i;
>  	int ret;
>  
>  	/* dot is pointed to the current dir inode */
> @@ -172,6 +166,22 @@ int erofs_prepare_dir_file(struct erofs_inode *dir)
>  	d->inode = erofs_igrab(dir->i_parent);
>  	d->type = EROFS_FT_DIR;
>  
> +	/* sort subdirs */
> +	nr_subdirs += 2;
> +	all_d = malloc(nr_subdirs * sizeof(d));

maybe just use `sorted' name here?

> +	if (!all_d)
> +		return -ENOMEM;
> +	i = 0;
> +	list_for_each_entry(d, &dir->i_subdirs, d_child)

I think we could list_del here, and use list_for_each_entry

> +		all_d[i++] = d;
> +	DBG_BUGON(i != nr_subdirs);
> +	qsort(all_d, nr_subdirs, sizeof(d), comp_subdir);
> +	init_list_head(&dir->i_subdirs);

After list_del, no need to init_list_head again.
The another reason is that some list_add_tail implementation
could check elements isn't in a list first.

> +	for (i = 0; i < nr_subdirs; i++)
> +		list_add_tail(&all_d[i]->d_child, &dir->i_subdirs);
> +	free(all_d);
> +	all_d = NULL;

no need to NULLify it..

Thanks,
Gao Xiang