lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20170302191006.GA4151@jaegeuk.local>
Date:   Thu, 2 Mar 2017 11:10:06 -0800
From:   Jaegeuk Kim <jaegeuk@...nel.org>
To:     Chao Yu <yuchao0@...wei.com>
Cc:     linux-f2fs-devel@...ts.sourceforge.net,
        linux-kernel@...r.kernel.org, chao@...nel.org
Subject: Re: [PATCH RFC] f2fs: combine nat_bits and free_nid_bitmap cache

Hi Chao,

On 03/01, Chao Yu wrote:
> Both nat_bits cache and free_nid_bitmap cache provide same functionality
> as a intermediate cache between free nid cache and disk, but with
> different granularity of indicating free nid range, and different
> persistence policy. nat_bits cache provides better persistence ability,
> and free_nid_bitmap provides better granularity.
> 
> In this patch we combine advantage of both caches, so finally policy of
> the intermediate cache would be:
> - init: load free nid status from nat_bits into free_nid_bitmap
> - lookup: scan free_nid_bitmap before load NAT blocks
> - update: update free_nid_bitmap in real-time
> - persistence: udpate and persist nat_bits in checkpoint
> 
> Signed-off-by: Chao Yu <yuchao0@...wei.com>
> ---
>  fs/f2fs/node.c | 109 +++++++++++++++++++++------------------------------------
>  1 file changed, 39 insertions(+), 70 deletions(-)
> 
> diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
> index 1a759d45b7e4..6c027b6833f4 100644
> --- a/fs/f2fs/node.c
> +++ b/fs/f2fs/node.c
> @@ -338,9 +338,6 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni,
>  		set_nat_flag(e, IS_CHECKPOINTED, false);
>  	__set_nat_cache_dirty(nm_i, e);
>  
> -	if (enabled_nat_bits(sbi, NULL) && new_blkaddr == NEW_ADDR)
> -		clear_bit_le(NAT_BLOCK_OFFSET(ni->nid), nm_i->empty_nat_bits);
> -
>  	/* update fsync_mark if its inode nat entry is still alive */
>  	if (ni->nid != ni->ino)
>  		e = __lookup_nat_cache(nm_i, ni->ino);
> @@ -1920,58 +1917,6 @@ static void scan_free_nid_bits(struct f2fs_sb_info *sbi)
>  	up_read(&nm_i->nat_tree_lock);
>  }
>  
> -static int scan_nat_bits(struct f2fs_sb_info *sbi)
> -{
> -	struct f2fs_nm_info *nm_i = NM_I(sbi);
> -	struct page *page;
> -	unsigned int i = 0;
> -	nid_t nid;
> -
> -	if (!enabled_nat_bits(sbi, NULL))
> -		return -EAGAIN;
> -
> -	down_read(&nm_i->nat_tree_lock);
> -check_empty:
> -	i = find_next_bit_le(nm_i->empty_nat_bits, nm_i->nat_blocks, i);
> -	if (i >= nm_i->nat_blocks) {
> -		i = 0;
> -		goto check_partial;
> -	}
> -
> -	for (nid = i * NAT_ENTRY_PER_BLOCK; nid < (i + 1) * NAT_ENTRY_PER_BLOCK;
> -									nid++) {
> -		if (unlikely(nid >= nm_i->max_nid))
> -			break;
> -		add_free_nid(sbi, nid, true);
> -	}
> -
> -	if (nm_i->nid_cnt[FREE_NID_LIST] >= MAX_FREE_NIDS)
> -		goto out;
> -	i++;
> -	goto check_empty;
> -
> -check_partial:
> -	i = find_next_zero_bit_le(nm_i->full_nat_bits, nm_i->nat_blocks, i);
> -	if (i >= nm_i->nat_blocks) {
> -		disable_nat_bits(sbi, true);
> -		up_read(&nm_i->nat_tree_lock);
> -		return -EINVAL;
> -	}
> -
> -	nid = i * NAT_ENTRY_PER_BLOCK;
> -	page = get_current_nat_page(sbi, nid);
> -	scan_nat_page(sbi, page, nid);
> -	f2fs_put_page(page, 1);
> -
> -	if (nm_i->nid_cnt[FREE_NID_LIST] < MAX_FREE_NIDS) {
> -		i++;
> -		goto check_partial;
> -	}
> -out:
> -	up_read(&nm_i->nat_tree_lock);
> -	return 0;
> -}
> -
>  static void __build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount)
>  {
>  	struct f2fs_nm_info *nm_i = NM_I(sbi);
> @@ -1993,21 +1938,6 @@ static void __build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount)
>  
>  		if (nm_i->nid_cnt[FREE_NID_LIST])
>  			return;
> -
> -		/* try to find free nids with nat_bits */
> -		if (!scan_nat_bits(sbi) && nm_i->nid_cnt[FREE_NID_LIST])
> -			return;
> -	}
> -
> -	/* find next valid candidate */
> -	if (enabled_nat_bits(sbi, NULL)) {
> -		int idx = find_next_zero_bit_le(nm_i->full_nat_bits,
> -					nm_i->nat_blocks, 0);
> -
> -		if (idx >= nm_i->nat_blocks)
> -			set_sbi_flag(sbi, SBI_NEED_FSCK);
> -		else
> -			nid = idx * NAT_ENTRY_PER_BLOCK;
>  	}
>  
>  	/* readahead nat pages to be scanned */
> @@ -2590,6 +2520,41 @@ static int __get_nat_bitmaps(struct f2fs_sb_info *sbi)
>  	return 0;
>  }
>  
> +inline void load_free_nid_bitmap(struct f2fs_sb_info *sbi)
> +{
> +	struct f2fs_nm_info *nm_i = NM_I(sbi);
> +	unsigned int i = 0;
> +	nid_t nid, last_nid;
> +
> +	for (i = 0; i < nm_i->nat_blocks; i++) {
> +		i = find_next_bit_le(nm_i->empty_nat_bits, nm_i->nat_blocks, i);
> +		if (i >= nm_i->nat_blocks)
> +			break;
> +
> +		set_bit_le(i, nm_i->nat_block_bitmap);
> +
> +		nid = i * NAT_ENTRY_PER_BLOCK;
> +		last_nid = (i + 1) * NAT_ENTRY_PER_BLOCK;
> +
> +		for (; nid < last_nid; nid++)
> +			update_free_nid_bitmap(sbi, nid, true, true);
> +	}
> +
> +	for (i = 0; i < nm_i->nat_blocks; i++) {
> +		i = find_next_bit_le(nm_i->full_nat_bits, nm_i->nat_blocks, i);
> +		if (i >= nm_i->nat_blocks)
> +			break;
> +
> +		set_bit_le(i, nm_i->nat_block_bitmap);
> +
> +		nid = i * NAT_ENTRY_PER_BLOCK;
> +		last_nid = (i + 1) * NAT_ENTRY_PER_BLOCK;
> +
> +		for (; nid < last_nid; nid++)
> +			update_free_nid_bitmap(sbi, nid, false, true);
> +	}
> +}
> +
>  static int init_node_manager(struct f2fs_sb_info *sbi)
>  {
>  	struct f2fs_super_block *sb_raw = F2FS_RAW_SUPER(sbi);
> @@ -2672,6 +2637,10 @@ int init_free_nid_cache(struct f2fs_sb_info *sbi)
>  
>  	spin_lock_init(&nm_i->free_nid_lock);
>  
> +	/* load free nid status from nat_bits table */
> +	if (enabled_nat_bits(sbi, NULL))
> +		load_free_nid_bitmap(sbi);

This should be done after init_free_nid_cache() to avoid NULL pointer access.
And, it shows little bit long latency during mount, so needs to take a look at
bit ops.

Thanks,

> +
>  	return 0;
>  }
>  
> -- 
> 2.8.2.295.g3f1c1d0

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ