Re: [PATCH 2/4] btrfs: add support for 3-copy replication (raid1c3)

[Goffredo Baroncelli <kreijack@libero.it>]

As general comment, good to hear that something is moving around raid5/6 + write hole and multiple mirroring.
However I am guessing if this is time to simplify the RAID code. There are a lot of "if" which could be avoided using 
the values stored in the array "btrfs_raid_array[]".

Below some comments:

On 07/13/2018 08:46 PM, David Sterba wrote:
> Add new block group profile to store 3 copies in a simliar way that
> current RAID1 does. The profile name is temporary and may change in the
> future.
> 
> Signed-off-by: David Sterba <dsterba@suse.com>
> ---
>  fs/btrfs/extent-tree.c          |  6 +++++
>  fs/btrfs/relocation.c           |  1 +
>  fs/btrfs/scrub.c                |  3 ++-
>  fs/btrfs/super.c                |  3 +++
>  fs/btrfs/volumes.c              | 40 ++++++++++++++++++++++++++++-----
>  fs/btrfs/volumes.h              |  2 ++
>  include/uapi/linux/btrfs.h      |  3 ++-
>  include/uapi/linux/btrfs_tree.h |  3 +++
>  8 files changed, 53 insertions(+), 8 deletions(-)
> 
> diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
> index 4ffa64e288da..47f929dcc3d4 100644
> --- a/fs/btrfs/extent-tree.c
> +++ b/fs/btrfs/extent-tree.c
> @@ -7527,6 +7527,7 @@ static noinline int find_free_extent(struct btrfs_fs_info *fs_info,
>  		if (!block_group_bits(block_group, flags)) {
>  		    u64 extra = BTRFS_BLOCK_GROUP_DUP |
>  				BTRFS_BLOCK_GROUP_RAID1 |
> +				BTRFS_BLOCK_GROUP_RAID1C3 |
>  				BTRFS_BLOCK_GROUP_RAID5 |
>  				BTRFS_BLOCK_GROUP_RAID6 |
>  				BTRFS_BLOCK_GROUP_RAID10;

"extra" could be created iterating on btrfs_raid_array[] and considering only the item with ncopies > 1; or we could add 

#define BTRFS_BLOCK_GROUP_REDUNDANCY (BTRFS_BLOCK_GROUP_DUP| .....)

This constant could be used also below

> @@ -9330,6 +9331,8 @@ static u64 update_block_group_flags(struct btrfs_fs_info *fs_info, u64 flags)
>  
>  	num_devices = fs_info->fs_devices->rw_devices;
>  
> +	ASSERT(!(flags & BTRFS_BLOCK_GROUP_RAID1C3));
> +
>  	stripped = BTRFS_BLOCK_GROUP_RAID0 |
>  		BTRFS_BLOCK_GROUP_RAID5 | BTRFS_BLOCK_GROUP_RAID6 |
>  		BTRFS_BLOCK_GROUP_RAID1 | BTRFS_BLOCK_GROUP_RAID10;
> @@ -9647,6 +9650,8 @@ int btrfs_can_relocate(struct btrfs_fs_info *fs_info, u64 bytenr)
>  		min_free >>= 1;
>  	} else if (index == BTRFS_RAID_RAID1) {
>  		dev_min = 2;
> +	} else if (index == BTRFS_RAID_RAID1C3) {
> +		dev_min = 3;
>  	} else if (index == BTRFS_RAID_DUP) {
>  		/* Multiply by 2 */
>  		min_free <<= 1;

The "if"s above could be simplified as:

	dev_min = btrfs_raid_array[index].devs_min;
	if (index == BTRFS_RAID_DUP)
		min_free <<= 1;
	else if (index == BTRFS_RAID_RAID0)
		min_free = div64_u64(min_free, dev_min);
	else if (index == BTRFS_RAID_RAID10)
		min_free >>= 1;


> @@ -10141,6 +10146,7 @@ int btrfs_read_block_groups(struct btrfs_fs_info *info)
>  		if (!(get_alloc_profile(info, space_info->flags) &
>  		      (BTRFS_BLOCK_GROUP_RAID10 |
>  		       BTRFS_BLOCK_GROUP_RAID1 |
> +		       BTRFS_BLOCK_GROUP_RAID1C3 |
>  		       BTRFS_BLOCK_GROUP_RAID5 |
>  		       BTRFS_BLOCK_GROUP_RAID6 |
>  		       BTRFS_BLOCK_GROUP_DUP)))


See above about BTRFS_BLOCK_GROUP_REDUNDANCY

> diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
> index 879b76fa881a..fea9e7e96b87 100644
> --- a/fs/btrfs/relocation.c
> +++ b/fs/btrfs/relocation.c
> @@ -4339,6 +4339,7 @@ static void describe_relocation(struct btrfs_fs_info *fs_info,
>  		DESCRIBE_FLAG(METADATA, "metadata");

The code below, could be performed searching in the array btrfs_raid_array[] instead of checking each possibility

>  		DESCRIBE_FLAG(RAID0,    "raid0");
>  		DESCRIBE_FLAG(RAID1,    "raid1");
> +		DESCRIBE_FLAG(RAID1C3,  "raid1c3");
>  		DESCRIBE_FLAG(DUP,      "dup");
>  		DESCRIBE_FLAG(RAID10,   "raid10");
>  		DESCRIBE_FLAG(RAID5,    "raid5");



> diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
> index 572306036477..e9355759f2ec 100644
> --- a/fs/btrfs/scrub.c
> +++ b/fs/btrfs/scrub.c
> @@ -3388,7 +3388,8 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx,
>  		offset = map->stripe_len * (num / map->sub_stripes);
>  		increment = map->stripe_len * factor;
>  		mirror_num = num % map->sub_stripes + 1;
> -	} else if (map->type & BTRFS_BLOCK_GROUP_RAID1) {
> +	} else if (map->type & (BTRFS_BLOCK_GROUP_RAID1 |
> +				BTRFS_BLOCK_GROUP_RAID1C3)) {
>  		increment = map->stripe_len;
>  		mirror_num = num % map->num_stripes + 1;
>  	} else if (map->type & BTRFS_BLOCK_GROUP_DUP) {
> diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
> index 4f646b66cc06..86e6aa5ef788 100644
> --- a/fs/btrfs/super.c
> +++ b/fs/btrfs/super.c
> @@ -1977,6 +1977,9 @@ static int btrfs_calc_avail_data_space(struct btrfs_fs_info *fs_info,
>  	} else if (type & BTRFS_BLOCK_GROUP_RAID1) {
>  		min_stripes = 2;
>  		num_stripes = 2;
> +	} else if (type & BTRFS_BLOCK_GROUP_RAID1C3) {
> +		min_stripes = 3;
> +		num_stripes = 3;
>  	} else if (type & BTRFS_BLOCK_GROUP_RAID10) {
>  		min_stripes = 4;
>  		num_stripes = 4;

> diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
> index 45635f4d78c8..0920b31e999d 100644
> --- a/fs/btrfs/volumes.c
> +++ b/fs/btrfs/volumes.c
> @@ -116,6 +116,18 @@ const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES] = {
>  		.bg_flag	= BTRFS_BLOCK_GROUP_RAID6,
>  		.mindev_error	= BTRFS_ERROR_DEV_RAID6_MIN_NOT_MET,
>  	},
> +	[BTRFS_RAID_RAID1C3] = {
> +		.sub_stripes	= 1,
> +		.dev_stripes	= 1,
> +		.devs_max	= 0,
> +		.devs_min	= 3,
> +		.tolerated_failures = 2,
> +		.devs_increment	= 3,
> +		.ncopies	= 3,
> +		.raid_name	= "raid1c3",
> +		.bg_flag	= BTRFS_BLOCK_GROUP_RAID1C3,
> +		.mindev_error	= BTRFS_ERROR_DEV_RAID1C3_MIN_NOT_MET,
> +	},
>  };
>  
>  const char *get_raid_name(enum btrfs_raid_types type)
> @@ -3336,6 +3348,8 @@ static int chunk_drange_filter(struct extent_buffer *leaf,
>  	if (btrfs_chunk_type(leaf, chunk) & (BTRFS_BLOCK_GROUP_DUP |
>  	     BTRFS_BLOCK_GROUP_RAID1 | BTRFS_BLOCK_GROUP_RAID10)) {
>  		factor = num_stripes / 2;
> +	} else if (btrfs_chunk_type(leaf, chunk) & BTRFS_BLOCK_GROUP_RAID1C3) {
> +		factor = num_stripes / 3;
>  	} else if (btrfs_chunk_type(leaf, chunk) & BTRFS_BLOCK_GROUP_RAID5) {
>  		factor = num_stripes - 1;
>  	} else if (btrfs_chunk_type(leaf, chunk) & BTRFS_BLOCK_GROUP_RAID6) {

May be time to add two other fields to the btrfs_raid_array[] array ? I.e.:
	factor_div and factor_sub

	so factor could be computed as

	index = btrfs_bg_flags_to_raid_index(btrfs_chunk_type(leaf, chunk))
	factor = num_stripes / btrfs_raid_array[index].factor_div - btrfs_raid_array[index].factor_sub;

> @@ -3822,7 +3836,7 @@ int btrfs_balance(struct btrfs_fs_info *fs_info,
>  	if (num_devices > 1)
>  		allowed |= (BTRFS_BLOCK_GROUP_RAID0 | BTRFS_BLOCK_GROUP_RAID1);
>  	if (num_devices > 2)
> -		allowed |= BTRFS_BLOCK_GROUP_RAID5;
> +		allowed |= BTRFS_BLOCK_GROUP_RAID5 | BTRFS_BLOCK_GROUP_RAID1C3;
>  	if (num_devices > 3)
>  		allowed |= (BTRFS_BLOCK_GROUP_RAID10 |
>  			    BTRFS_BLOCK_GROUP_RAID6);

The "if"s  below could be replaced by a search in the btrfs_raid_array[]

> @@ -3856,6 +3870,7 @@ int btrfs_balance(struct btrfs_fs_info *fs_info,
>  
>  	/* allow to reduce meta or sys integrity only if force set */
>  	allowed = BTRFS_BLOCK_GROUP_DUP | BTRFS_BLOCK_GROUP_RAID1 |
> +			BTRFS_BLOCK_GROUP_RAID1C3 |
>  			BTRFS_BLOCK_GROUP_RAID10 |
>  			BTRFS_BLOCK_GROUP_RAID5 |
>  			BTRFS_BLOCK_GROUP_RAID6;

See above about BTRFS_BLOCK_GROUP_REDUNDANCY

> @@ -4787,8 +4802,11 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
>  	sort(devices_info, ndevs, sizeof(struct btrfs_device_info),
>  	     btrfs_cmp_device_info, NULL);
>  
> -	/* round down to number of usable stripes */
> -	ndevs = round_down(ndevs, devs_increment);
> +	/*
> +	 * Round down to number of usable stripes, devs_increment can be any
> +	 * number so we can't use round_down()
> +	 */
> +	ndevs -= ndevs % devs_increment;
>  
>  	if (ndevs < devs_min) {
>  		ret = -ENOSPC;
> @@ -5075,6 +5093,8 @@ static inline int btrfs_chunk_max_errors(struct map_lookup *map)
>  			 BTRFS_BLOCK_GROUP_RAID5 |
>  			 BTRFS_BLOCK_GROUP_DUP)) {
>  		max_errors = 1;
> +	} else if (map->type & BTRFS_BLOCK_GROUP_RAID1C3) {
> +		max_errors = 2;
>  	} else if (map->type & BTRFS_BLOCK_GROUP_RAID6) {
>  		max_errors = 2;
>  	} else {

Even in this case the ifs above could be replaced with something like:

	index = btrfs_bg_flags_to_raid_index(map->type)
	max_errors = btrfs_raid_array[index].ncopies-1;

> @@ -5163,7 +5183,8 @@ int btrfs_num_copies(struct btrfs_fs_info *fs_info, u64 logical, u64 len)
>  		return 1;
>  
>  	map = em->map_lookup;
> -	if (map->type & (BTRFS_BLOCK_GROUP_DUP | BTRFS_BLOCK_GROUP_RAID1))
> +	if (map->type & (BTRFS_BLOCK_GROUP_DUP | BTRFS_BLOCK_GROUP_RAID1 |
> +			 BTRFS_BLOCK_GROUP_RAID1C3))
>  		ret = map->num_stripes;
>  	else if (map->type & BTRFS_BLOCK_GROUP_RAID10)
>  		ret = map->sub_stripes;


With the exception of RAID6 case (which I don't understand), the ifs above could be replaced with

	index = btrfs_bg_flags_to_raid_index(map->type)
	ret = btrfs_raid_array[index].ncopies

> @@ -5237,7 +5258,9 @@ static int find_live_mirror(struct btrfs_fs_info *fs_info,
>  	struct btrfs_device *srcdev;
>  
>  	ASSERT((map->type &
> -		 (BTRFS_BLOCK_GROUP_RAID1 | BTRFS_BLOCK_GROUP_RAID10)));
> +		 (BTRFS_BLOCK_GROUP_RAID1 |
> +		  BTRFS_BLOCK_GROUP_RAID1C3 |
> +		  BTRFS_BLOCK_GROUP_RAID10)));
>  
>  	if (map->type & BTRFS_BLOCK_GROUP_RAID10)
>  		num_stripes = map->sub_stripes;
> @@ -5427,6 +5450,7 @@ static int __btrfs_map_block_for_discard(struct btrfs_fs_info *fs_info,
>  		div_u64_rem(stripe_nr_end - 1, factor, &last_stripe);
>  		last_stripe *= sub_stripes;
>  	} else if (map->type & (BTRFS_BLOCK_GROUP_RAID1 |
> +				BTRFS_BLOCK_GROUP_RAID1C3 |
>  				BTRFS_BLOCK_GROUP_DUP)) {
>  		num_stripes = map->num_stripes;
>  	} else {
> @@ -5792,7 +5816,8 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info,
>  				&stripe_index);
>  		if (!need_full_stripe(op))
>  			mirror_num = 1;
> -	} else if (map->type & BTRFS_BLOCK_GROUP_RAID1) {
> +	} else if (map->type & (BTRFS_BLOCK_GROUP_RAID1 |
> +				BTRFS_BLOCK_GROUP_RAID1C3)) {
>  		if (need_full_stripe(op))
>  			num_stripes = map->num_stripes;
>  		else if (mirror_num)
> @@ -6441,6 +6466,7 @@ static int btrfs_check_chunk_valid(struct btrfs_fs_info *fs_info,
>  	}
>  	if ((type & BTRFS_BLOCK_GROUP_RAID10 && sub_stripes != 2) ||
>  	    (type & BTRFS_BLOCK_GROUP_RAID1 && num_stripes < 1) ||
> +	    (type & BTRFS_BLOCK_GROUP_RAID1C3 && num_stripes < 3) ||
>  	    (type & BTRFS_BLOCK_GROUP_RAID5 && num_stripes < 2) ||
>  	    (type & BTRFS_BLOCK_GROUP_RAID6 && num_stripes < 3) ||
>  	    (type & BTRFS_BLOCK_GROUP_DUP && num_stripes > 2) ||


The check above could be translate in specific check for BTRFS_BLOCK_GROUP_DUP and BTRFS_BLOCK_GROUP_RAID10; for the other cases we could check that num_stripes is >= devs_min

> @@ -7389,5 +7415,7 @@ int btrfs_bg_type_to_factor(u64 flags)
>  	if (flags & (BTRFS_BLOCK_GROUP_DUP | BTRFS_BLOCK_GROUP_RAID1 |
>  		     BTRFS_BLOCK_GROUP_RAID10))
>  		return 2;
> +	if (flags & BTRFS_BLOCK_GROUP_RAID1C3)
> +		return 3;
>  	return 1;
>  }

Even the function above could be replaced with something more general

int btrfs_bg_type_to_factor(u64 flags) {
	if (flags & (BTRFS_BLOCK_GROUP_RAID5 | BTRFS_BLOCK_GROUP_RAID6))
		return 1;
	return btrfs_raid_array[btrfs_bg_flags_to_raid_index(flags)]
}


> diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
> index c7b9ad9733ea..5be624896dad 100644
> --- a/fs/btrfs/volumes.h
> +++ b/fs/btrfs/volumes.h
> @@ -537,6 +537,8 @@ static inline enum btrfs_raid_types btrfs_bg_flags_to_raid_index(u64 flags)
>  		return BTRFS_RAID_RAID10;
>  	else if (flags & BTRFS_BLOCK_GROUP_RAID1)
>  		return BTRFS_RAID_RAID1;
> +	else if (flags & BTRFS_BLOCK_GROUP_RAID1C3)
> +		return BTRFS_RAID_RAID1C3;
>  	else if (flags & BTRFS_BLOCK_GROUP_DUP)
>  		return BTRFS_RAID_DUP;
>  	else if (flags & BTRFS_BLOCK_GROUP_RAID0)

What about iterating on btrfs_raid_array[] in the above function

> diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h
> index 5ca1d21fc4a7..137952d3375d 100644
> --- a/include/uapi/linux/btrfs.h
> +++ b/include/uapi/linux/btrfs.h
> @@ -825,7 +825,8 @@ enum btrfs_err_code {
>  	BTRFS_ERROR_DEV_TGT_REPLACE,
>  	BTRFS_ERROR_DEV_MISSING_NOT_FOUND,
>  	BTRFS_ERROR_DEV_ONLY_WRITABLE,
> -	BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS
> +	BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS,
> +	BTRFS_ERROR_DEV_RAID1C3_MIN_NOT_MET,
>  };
>  
>  #define BTRFS_IOC_SNAP_CREATE _IOW(BTRFS_IOCTL_MAGIC, 1, \
> diff --git a/include/uapi/linux/btrfs_tree.h b/include/uapi/linux/btrfs_tree.h
> index aff1356c2bb8..fa75b63dd928 100644
> --- a/include/uapi/linux/btrfs_tree.h
> +++ b/include/uapi/linux/btrfs_tree.h
> @@ -836,6 +836,7 @@ struct btrfs_dev_replace_item {
>  #define BTRFS_BLOCK_GROUP_RAID10	(1ULL << 6)
>  #define BTRFS_BLOCK_GROUP_RAID5         (1ULL << 7)
>  #define BTRFS_BLOCK_GROUP_RAID6         (1ULL << 8)
> +#define BTRFS_BLOCK_GROUP_RAID1C3       (1ULL << 9)
>  #define BTRFS_BLOCK_GROUP_RESERVED	(BTRFS_AVAIL_ALLOC_BIT_SINGLE | \
>  					 BTRFS_SPACE_INFO_GLOBAL_RSV)
>  
> @@ -847,6 +848,7 @@ enum btrfs_raid_types {
>  	BTRFS_RAID_SINGLE,
>  	BTRFS_RAID_RAID5,
>  	BTRFS_RAID_RAID6,
> +	BTRFS_RAID_RAID1C3,
>  	BTRFS_NR_RAID_TYPES
>  };
>  
> @@ -856,6 +858,7 @@ enum btrfs_raid_types {
>  
>  #define BTRFS_BLOCK_GROUP_PROFILE_MASK	(BTRFS_BLOCK_GROUP_RAID0 |   \
>  					 BTRFS_BLOCK_GROUP_RAID1 |   \
> +					 BTRFS_BLOCK_GROUP_RAID1C3 | \
>  					 BTRFS_BLOCK_GROUP_RAID5 |   \
>  					 BTRFS_BLOCK_GROUP_RAID6 |   \
>  					 BTRFS_BLOCK_GROUP_DUP |     \
> 


-- 
gpg @keyserver.linux.it: Goffredo Baroncelli <kreijackATinwind.it>
Key fingerprint BBF5 1610 0B64 DAC6 5F7D  17B2 0EDA 9B37 8B82 E0B5