Re: [PATCH v2] erofs-utils: use qsort() to sort dir->i_subdirs

[Gao Xiang <hsiangkao@redhat.com>]

On Mon, Apr 05, 2021 at 05:38:16PM +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@mail.scut.edu.cn>

This patch looks good to me, will test it later.

> ---
>  lib/inode.c | 53 +++++++++++++++++++++++++++++++++--------------------
>  1 file changed, 33 insertions(+), 20 deletions(-)
> 
> diff --git a/lib/inode.c b/lib/inode.c
> index d52facf..ef55e88 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 *da, *db;
> +
> +	da = *((const struct erofs_dentry **)a);
> +	db = *((const struct erofs_dentry **)b);
> +	return strcmp(da->name, db->name);
> +}
> +
> -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, *n, **sorted_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;
> +	sorted_d = malloc(nr_subdirs * sizeof(d));
> +	if (!sorted_d)
> +		return -ENOMEM;
> +	i = 0;
> +	list_for_each_entry_safe(d, n, &dir->i_subdirs, d_child) {
> +		list_del(&d->d_child);
> +		sorted_d[i++] = d;
> +	}
> +	DBG_BUGON(i != nr_subdirs);
> +	qsort(sorted_d, nr_subdirs, sizeof(d), comp_subdir);
> +	for (i = 0; i < nr_subdirs; i++)
> +		list_add_tail(&sorted_d[i]->d_child, &dir->i_subdirs);
> +	free(sorted_d);
> +
>  	/* let's calculate dir size and update i_nlink */
>  	d_size = 0;
>  	i_nlink = 0;
> @@ -922,6 +932,7 @@ struct erofs_inode *erofs_mkfs_build_tree(struct erofs_inode *dir)
>  	DIR *_dir;
>  	struct dirent *dp;
>  	struct erofs_dentry *d;
> +	unsigned int nr_subdirs;
> 
>  	ret = erofs_prepare_xattr_ibody(dir);
>  	if (ret < 0)
> @@ -961,6 +972,7 @@ struct erofs_inode *erofs_mkfs_build_tree(struct erofs_inode *dir)
>  		return ERR_PTR(-errno);
>  	}
> 
> +	nr_subdirs = 0;
>  	while (1) {
>  		/*
>  		 * set errno to 0 before calling readdir() in order to
> @@ -984,6 +996,7 @@ struct erofs_inode *erofs_mkfs_build_tree(struct erofs_inode *dir)
>  			ret = PTR_ERR(d);
>  			goto err_closedir;
>  		}
> +		nr_subdirs++;
> 
>  		/* to count i_nlink for directories */
>  		d->type = (dp->d_type == DT_DIR ?
> @@ -996,7 +1009,7 @@ struct erofs_inode *erofs_mkfs_build_tree(struct erofs_inode *dir)
>  	}
>  	closedir(_dir);
> 
> -	ret = erofs_prepare_dir_file(dir);
> +	ret = erofs_prepare_dir_file(dir, nr_subdirs);
>  	if (ret)
>  		goto err;
> 
> --
> 2.25.1
>