1. Patchew
  2. linux
  3. [PATCH v8 00/11] btrfs: introduce RAID stripe tree
  4. View patch

[PATCH v8 01/11] btrfs: add raid stripe tree definitions

Johannes Thumshirn posted 11 patches 2 years, 3 months ago
There is a newer version of this series
[PATCH v8 01/11] btrfs: add raid stripe tree definitions
Posted by Johannes Thumshirn 2 years, 3 months ago 
Add definitions for the raid stripe tree. This tree will hold information
about the on-disk layout of the stripes in a RAID set.

Each stripe extent has a 1:1 relationship with an on-disk extent item and
is doing the logical to per-drive physical address translation for the
extent item in question.

Signed-off-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
---
 fs/btrfs/accessors.h            | 10 ++++++++++
 fs/btrfs/locking.c              |  5 +++--
 include/uapi/linux/btrfs_tree.h | 33 +++++++++++++++++++++++++++++++--
 3 files changed, 44 insertions(+), 4 deletions(-)

diff --git a/fs/btrfs/accessors.h b/fs/btrfs/accessors.h
index f958eccff477..977ff160a024 100644
--- a/fs/btrfs/accessors.h
+++ b/fs/btrfs/accessors.h
@@ -306,6 +306,16 @@ BTRFS_SETGET_FUNCS(timespec_nsec, struct btrfs_timespec, nsec, 32);
 BTRFS_SETGET_STACK_FUNCS(stack_timespec_sec, struct btrfs_timespec, sec, 64);
 BTRFS_SETGET_STACK_FUNCS(stack_timespec_nsec, struct btrfs_timespec, nsec, 32);
 
+BTRFS_SETGET_FUNCS(stripe_extent_encoding, struct btrfs_stripe_extent, encoding, 8);
+BTRFS_SETGET_FUNCS(raid_stride_devid, struct btrfs_raid_stride, devid, 64);
+BTRFS_SETGET_FUNCS(raid_stride_physical, struct btrfs_raid_stride, physical, 64);
+BTRFS_SETGET_FUNCS(raid_stride_length, struct btrfs_raid_stride, length, 64);
+BTRFS_SETGET_STACK_FUNCS(stack_stripe_extent_encoding,
+			 struct btrfs_stripe_extent, encoding, 8);
+BTRFS_SETGET_STACK_FUNCS(stack_raid_stride_devid, struct btrfs_raid_stride, devid, 64);
+BTRFS_SETGET_STACK_FUNCS(stack_raid_stride_physical, struct btrfs_raid_stride, physical, 64);
+BTRFS_SETGET_STACK_FUNCS(stack_raid_stride_length, struct btrfs_raid_stride, length, 64);
+
 /* struct btrfs_dev_extent */
 BTRFS_SETGET_FUNCS(dev_extent_chunk_tree, struct btrfs_dev_extent, chunk_tree, 64);
 BTRFS_SETGET_FUNCS(dev_extent_chunk_objectid, struct btrfs_dev_extent,
diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c
index 6ac4fd8cc8dc..e7760d40feab 100644
--- a/fs/btrfs/locking.c
+++ b/fs/btrfs/locking.c
@@ -58,8 +58,8 @@
 
 static struct btrfs_lockdep_keyset {
 	u64			id;		/* root objectid */
-	/* Longest entry: btrfs-block-group-00 */
-	char			names[BTRFS_MAX_LEVEL][24];
+	/* Longest entry: btrfs-raid-stripe-tree-00 */
+	char			names[BTRFS_MAX_LEVEL][25];
 	struct lock_class_key	keys[BTRFS_MAX_LEVEL];
 } btrfs_lockdep_keysets[] = {
 	{ .id = BTRFS_ROOT_TREE_OBJECTID,	DEFINE_NAME("root")	},
@@ -74,6 +74,7 @@ static struct btrfs_lockdep_keyset {
 	{ .id = BTRFS_UUID_TREE_OBJECTID,	DEFINE_NAME("uuid")	},
 	{ .id = BTRFS_FREE_SPACE_TREE_OBJECTID,	DEFINE_NAME("free-space") },
 	{ .id = BTRFS_BLOCK_GROUP_TREE_OBJECTID, DEFINE_NAME("block-group") },
+	{ .id = BTRFS_RAID_STRIPE_TREE_OBJECTID,DEFINE_NAME("raid-stripe-tree") },
 	{ .id = 0,				DEFINE_NAME("tree")	},
 };
 
diff --git a/include/uapi/linux/btrfs_tree.h b/include/uapi/linux/btrfs_tree.h
index fc3c32186d7e..3fb758ce3ac0 100644
--- a/include/uapi/linux/btrfs_tree.h
+++ b/include/uapi/linux/btrfs_tree.h
@@ -4,9 +4,8 @@
 
 #include <linux/btrfs.h>
 #include <linux/types.h>
-#ifdef __KERNEL__
 #include <linux/stddef.h>
-#else
+#ifndef __KERNEL__
 #include <stddef.h>
 #endif
 
@@ -73,6 +72,9 @@
 /* Holds the block group items for extent tree v2. */
 #define BTRFS_BLOCK_GROUP_TREE_OBJECTID 11ULL
 
+/* tracks RAID stripes in block groups. */
+#define BTRFS_RAID_STRIPE_TREE_OBJECTID 12ULL
+
 /* device stats in the device tree */
 #define BTRFS_DEV_STATS_OBJECTID 0ULL
 
@@ -285,6 +287,8 @@
  */
 #define BTRFS_QGROUP_RELATION_KEY       246
 
+#define BTRFS_RAID_STRIPE_KEY		247
+
 /*
  * Obsolete name, see BTRFS_TEMPORARY_ITEM_KEY.
  */
@@ -719,6 +723,31 @@ struct btrfs_free_space_header {
 	__le64 num_bitmaps;
 } __attribute__ ((__packed__));
 
+struct btrfs_raid_stride {
+	/* btrfs device-id this raid extent lives on */
+	__le64 devid;
+	/* physical location on disk */
+	__le64 physical;
+	/* length of stride on this disk */
+	__le64 length;
+};
+
+#define BTRFS_STRIPE_DUP	0
+#define BTRFS_STRIPE_RAID0	1
+#define BTRFS_STRIPE_RAID1	2
+#define BTRFS_STRIPE_RAID1C3	3
+#define BTRFS_STRIPE_RAID1C4	4
+#define BTRFS_STRIPE_RAID5	5
+#define BTRFS_STRIPE_RAID6	6
+#define BTRFS_STRIPE_RAID10	7
+
+struct btrfs_stripe_extent {
+	__u8 encoding;
+	__u8 reserved[7];
+	/* array of raid strides this stripe is composed of */
+	__DECLARE_FLEX_ARRAY(struct btrfs_raid_stride, strides);
+};
+
 #define BTRFS_HEADER_FLAG_WRITTEN	(1ULL << 0)
 #define BTRFS_HEADER_FLAG_RELOC		(1ULL << 1)
 

-- 
2.41.0
Re: [PATCH v8 01/11] btrfs: add raid stripe tree definitions
Posted by David Sterba 2 years, 3 months ago 
On Mon, Sep 11, 2023 at 05:52:02AM -0700, Johannes Thumshirn wrote:
> Add definitions for the raid stripe tree. This tree will hold information
> about the on-disk layout of the stripes in a RAID set.
> 
> Each stripe extent has a 1:1 relationship with an on-disk extent item and
> is doing the logical to per-drive physical address translation for the
> extent item in question.
> 
> Signed-off-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
> ---
>  fs/btrfs/accessors.h            | 10 ++++++++++
>  fs/btrfs/locking.c              |  5 +++--
>  include/uapi/linux/btrfs_tree.h | 33 +++++++++++++++++++++++++++++++--
>  3 files changed, 44 insertions(+), 4 deletions(-)
> 
> diff --git a/fs/btrfs/accessors.h b/fs/btrfs/accessors.h
> index f958eccff477..977ff160a024 100644
> --- a/fs/btrfs/accessors.h
> +++ b/fs/btrfs/accessors.h
> @@ -306,6 +306,16 @@ BTRFS_SETGET_FUNCS(timespec_nsec, struct btrfs_timespec, nsec, 32);
>  BTRFS_SETGET_STACK_FUNCS(stack_timespec_sec, struct btrfs_timespec, sec, 64);
>  BTRFS_SETGET_STACK_FUNCS(stack_timespec_nsec, struct btrfs_timespec, nsec, 32);
>  
> +BTRFS_SETGET_FUNCS(stripe_extent_encoding, struct btrfs_stripe_extent, encoding, 8);

What is encoding referring to?

> +BTRFS_SETGET_FUNCS(raid_stride_devid, struct btrfs_raid_stride, devid, 64);
> +BTRFS_SETGET_FUNCS(raid_stride_physical, struct btrfs_raid_stride, physical, 64);
> +BTRFS_SETGET_FUNCS(raid_stride_length, struct btrfs_raid_stride, length, 64);
> +BTRFS_SETGET_STACK_FUNCS(stack_stripe_extent_encoding,
> +			 struct btrfs_stripe_extent, encoding, 8);
> +BTRFS_SETGET_STACK_FUNCS(stack_raid_stride_devid, struct btrfs_raid_stride, devid, 64);
> +BTRFS_SETGET_STACK_FUNCS(stack_raid_stride_physical, struct btrfs_raid_stride, physical, 64);
> +BTRFS_SETGET_STACK_FUNCS(stack_raid_stride_length, struct btrfs_raid_stride, length, 64);
> +
>  /* struct btrfs_dev_extent */
>  BTRFS_SETGET_FUNCS(dev_extent_chunk_tree, struct btrfs_dev_extent, chunk_tree, 64);
>  BTRFS_SETGET_FUNCS(dev_extent_chunk_objectid, struct btrfs_dev_extent,
> diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c
> index 6ac4fd8cc8dc..e7760d40feab 100644
> --- a/fs/btrfs/locking.c
> +++ b/fs/btrfs/locking.c
> @@ -58,8 +58,8 @@
>  
>  static struct btrfs_lockdep_keyset {
>  	u64			id;		/* root objectid */
> -	/* Longest entry: btrfs-block-group-00 */
> -	char			names[BTRFS_MAX_LEVEL][24];
> +	/* Longest entry: btrfs-raid-stripe-tree-00 */
> +	char			names[BTRFS_MAX_LEVEL][25];

Length of "btrfs-raid-stripe-tree-00" is 25, there should be +1 for the
NUL, also length aligned to at least 4 is better.

>  	struct lock_class_key	keys[BTRFS_MAX_LEVEL];
>  } btrfs_lockdep_keysets[] = {
>  	{ .id = BTRFS_ROOT_TREE_OBJECTID,	DEFINE_NAME("root")	},
> @@ -74,6 +74,7 @@ static struct btrfs_lockdep_keyset {
>  	{ .id = BTRFS_UUID_TREE_OBJECTID,	DEFINE_NAME("uuid")	},
>  	{ .id = BTRFS_FREE_SPACE_TREE_OBJECTID,	DEFINE_NAME("free-space") },
>  	{ .id = BTRFS_BLOCK_GROUP_TREE_OBJECTID, DEFINE_NAME("block-group") },
> +	{ .id = BTRFS_RAID_STRIPE_TREE_OBJECTID,DEFINE_NAME("raid-stripe-tree") },

The naming is without the "tree"

>  	{ .id = 0,				DEFINE_NAME("tree")	},
>  };
>  
> diff --git a/include/uapi/linux/btrfs_tree.h b/include/uapi/linux/btrfs_tree.h
> index fc3c32186d7e..3fb758ce3ac0 100644
> --- a/include/uapi/linux/btrfs_tree.h
> +++ b/include/uapi/linux/btrfs_tree.h
> @@ -4,9 +4,8 @@
>  
>  #include <linux/btrfs.h>
>  #include <linux/types.h>
> -#ifdef __KERNEL__
>  #include <linux/stddef.h>
> -#else
> +#ifndef __KERNEL__
>  #include <stddef.h>
>  #endif
>  
> @@ -73,6 +72,9 @@
>  /* Holds the block group items for extent tree v2. */
>  #define BTRFS_BLOCK_GROUP_TREE_OBJECTID 11ULL
>  
> +/* tracks RAID stripes in block groups. */

	Tracks ...

> +#define BTRFS_RAID_STRIPE_TREE_OBJECTID 12ULL
> +
>  /* device stats in the device tree */
>  #define BTRFS_DEV_STATS_OBJECTID 0ULL
>  
> @@ -285,6 +287,8 @@
>   */
>  #define BTRFS_QGROUP_RELATION_KEY       246
>  
> +#define BTRFS_RAID_STRIPE_KEY		247

Any particular reason you chose 247 for the key number? It does not
leave any gap after BTRFS_QGROUP_RELATION_KEY and before
BTRFS_BALANCE_ITEM_KEY. If this is related to extents then please find
more suitable group of keys where to put it.

> +
>  /*
>   * Obsolete name, see BTRFS_TEMPORARY_ITEM_KEY.
>   */
> @@ -719,6 +723,31 @@ struct btrfs_free_space_header {
>  	__le64 num_bitmaps;
>  } __attribute__ ((__packed__));
>  
> +struct btrfs_raid_stride {
> +	/* btrfs device-id this raid extent lives on */

Comments should be full sentences.

> +	__le64 devid;
> +	/* physical location on disk */
> +	__le64 physical;
> +	/* length of stride on this disk */
> +	__le64 length;
> +};

__attribute__ ((__packed__));

> +
> +#define BTRFS_STRIPE_DUP	0
> +#define BTRFS_STRIPE_RAID0	1
> +#define BTRFS_STRIPE_RAID1	2
> +#define BTRFS_STRIPE_RAID1C3	3
> +#define BTRFS_STRIPE_RAID1C4	4
> +#define BTRFS_STRIPE_RAID5	5
> +#define BTRFS_STRIPE_RAID6	6
> +#define BTRFS_STRIPE_RAID10	7

This is probably defining the on-disk format so some consistency is
desired, there are already the BTRFS_BLOCK_GROUP_* types, from which the
BTRFS_RAID_* are derive, so the BTRFS_STRIPE_* values should match the
order and ideally the values themselves if possible.

> +
> +struct btrfs_stripe_extent {
> +	__u8 encoding;
> +	__u8 reserved[7];
> +	/* array of raid strides this stripe is composed of */
> +	__DECLARE_FLEX_ARRAY(struct btrfs_raid_stride, strides);

Do we really whant to declare that as __DECLARE_FLEX_ARRAY? It's not a
standard macro and obscures the definition.


> +};
> +
>  #define BTRFS_HEADER_FLAG_WRITTEN	(1ULL << 0)
>  #define BTRFS_HEADER_FLAG_RELOC		(1ULL << 1)
>  
> 
> -- 
> 2.41.0
Re: [PATCH v8 01/11] btrfs: add raid stripe tree definitions
Posted by Damien Le Moal 2 years, 3 months ago 
On 9/11/23 21:52, Johannes Thumshirn wrote:
> Add definitions for the raid stripe tree. This tree will hold information
> about the on-disk layout of the stripes in a RAID set.
> 
> Each stripe extent has a 1:1 relationship with an on-disk extent item and
> is doing the logical to per-drive physical address translation for the
> extent item in question.
> 
> Signed-off-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
> ---
>  fs/btrfs/accessors.h            | 10 ++++++++++
>  fs/btrfs/locking.c              |  5 +++--
>  include/uapi/linux/btrfs_tree.h | 33 +++++++++++++++++++++++++++++++--
>  3 files changed, 44 insertions(+), 4 deletions(-)
> 
> diff --git a/fs/btrfs/accessors.h b/fs/btrfs/accessors.h
> index f958eccff477..977ff160a024 100644
> --- a/fs/btrfs/accessors.h
> +++ b/fs/btrfs/accessors.h
> @@ -306,6 +306,16 @@ BTRFS_SETGET_FUNCS(timespec_nsec, struct btrfs_timespec, nsec, 32);
>  BTRFS_SETGET_STACK_FUNCS(stack_timespec_sec, struct btrfs_timespec, sec, 64);
>  BTRFS_SETGET_STACK_FUNCS(stack_timespec_nsec, struct btrfs_timespec, nsec, 32);
>  
> +BTRFS_SETGET_FUNCS(stripe_extent_encoding, struct btrfs_stripe_extent, encoding, 8);
> +BTRFS_SETGET_FUNCS(raid_stride_devid, struct btrfs_raid_stride, devid, 64);
> +BTRFS_SETGET_FUNCS(raid_stride_physical, struct btrfs_raid_stride, physical, 64);
> +BTRFS_SETGET_FUNCS(raid_stride_length, struct btrfs_raid_stride, length, 64);
> +BTRFS_SETGET_STACK_FUNCS(stack_stripe_extent_encoding,
> +			 struct btrfs_stripe_extent, encoding, 8);
> +BTRFS_SETGET_STACK_FUNCS(stack_raid_stride_devid, struct btrfs_raid_stride, devid, 64);
> +BTRFS_SETGET_STACK_FUNCS(stack_raid_stride_physical, struct btrfs_raid_stride, physical, 64);
> +BTRFS_SETGET_STACK_FUNCS(stack_raid_stride_length, struct btrfs_raid_stride, length, 64);
> +
>  /* struct btrfs_dev_extent */
>  BTRFS_SETGET_FUNCS(dev_extent_chunk_tree, struct btrfs_dev_extent, chunk_tree, 64);
>  BTRFS_SETGET_FUNCS(dev_extent_chunk_objectid, struct btrfs_dev_extent,
> diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c
> index 6ac4fd8cc8dc..e7760d40feab 100644
> --- a/fs/btrfs/locking.c
> +++ b/fs/btrfs/locking.c
> @@ -58,8 +58,8 @@
>  
>  static struct btrfs_lockdep_keyset {
>  	u64			id;		/* root objectid */
> -	/* Longest entry: btrfs-block-group-00 */
> -	char			names[BTRFS_MAX_LEVEL][24];
> +	/* Longest entry: btrfs-raid-stripe-tree-00 */
> +	char			names[BTRFS_MAX_LEVEL][25];
>  	struct lock_class_key	keys[BTRFS_MAX_LEVEL];
>  } btrfs_lockdep_keysets[] = {
>  	{ .id = BTRFS_ROOT_TREE_OBJECTID,	DEFINE_NAME("root")	},
> @@ -74,6 +74,7 @@ static struct btrfs_lockdep_keyset {
>  	{ .id = BTRFS_UUID_TREE_OBJECTID,	DEFINE_NAME("uuid")	},
>  	{ .id = BTRFS_FREE_SPACE_TREE_OBJECTID,	DEFINE_NAME("free-space") },
>  	{ .id = BTRFS_BLOCK_GROUP_TREE_OBJECTID, DEFINE_NAME("block-group") },
> +	{ .id = BTRFS_RAID_STRIPE_TREE_OBJECTID,DEFINE_NAME("raid-stripe-tree") },
>  	{ .id = 0,				DEFINE_NAME("tree")	},
>  };
>  
> diff --git a/include/uapi/linux/btrfs_tree.h b/include/uapi/linux/btrfs_tree.h
> index fc3c32186d7e..3fb758ce3ac0 100644
> --- a/include/uapi/linux/btrfs_tree.h
> +++ b/include/uapi/linux/btrfs_tree.h
> @@ -4,9 +4,8 @@
>  
>  #include <linux/btrfs.h>
>  #include <linux/types.h>
> -#ifdef __KERNEL__
>  #include <linux/stddef.h>
> -#else
> +#ifndef __KERNEL__
>  #include <stddef.h>
>  #endif

This change seems unrelated to the RAID stripe tree. Should this be a patch on
its own ?

>  
> @@ -73,6 +72,9 @@
>  /* Holds the block group items for extent tree v2. */
>  #define BTRFS_BLOCK_GROUP_TREE_OBJECTID 11ULL
>  
> +/* tracks RAID stripes in block groups. */
> +#define BTRFS_RAID_STRIPE_TREE_OBJECTID 12ULL
> +
>  /* device stats in the device tree */
>  #define BTRFS_DEV_STATS_OBJECTID 0ULL
>  
> @@ -285,6 +287,8 @@
>   */
>  #define BTRFS_QGROUP_RELATION_KEY       246
>  
> +#define BTRFS_RAID_STRIPE_KEY		247
> +
>  /*
>   * Obsolete name, see BTRFS_TEMPORARY_ITEM_KEY.
>   */
> @@ -719,6 +723,31 @@ struct btrfs_free_space_header {
>  	__le64 num_bitmaps;
>  } __attribute__ ((__packed__));
>  
> +struct btrfs_raid_stride {
> +	/* btrfs device-id this raid extent lives on */
> +	__le64 devid;
> +	/* physical location on disk */
> +	__le64 physical;
> +	/* length of stride on this disk */
> +	__le64 length;
> +};
> +
> +#define BTRFS_STRIPE_DUP	0
> +#define BTRFS_STRIPE_RAID0	1
> +#define BTRFS_STRIPE_RAID1	2
> +#define BTRFS_STRIPE_RAID1C3	3
> +#define BTRFS_STRIPE_RAID1C4	4
> +#define BTRFS_STRIPE_RAID5	5
> +#define BTRFS_STRIPE_RAID6	6
> +#define BTRFS_STRIPE_RAID10	7
> +
> +struct btrfs_stripe_extent {
> +	__u8 encoding;
> +	__u8 reserved[7];
> +	/* array of raid strides this stripe is composed of */
> +	__DECLARE_FLEX_ARRAY(struct btrfs_raid_stride, strides);
> +};
> +
>  #define BTRFS_HEADER_FLAG_WRITTEN	(1ULL << 0)
>  #define BTRFS_HEADER_FLAG_RELOC		(1ULL << 1)
>  
> 

-- 
Damien Le Moal
Western Digital Research
Re: [PATCH v8 01/11] btrfs: add raid stripe tree definitions
Posted by Johannes Thumshirn 2 years, 3 months ago 
On 11.09.23 23:01, Damien Le Moal wrote:
>> diff --git a/include/uapi/linux/btrfs_tree.h b/include/uapi/linux/btrfs_tree.h
>> index fc3c32186d7e..3fb758ce3ac0 100644
>> --- a/include/uapi/linux/btrfs_tree.h
>> +++ b/include/uapi/linux/btrfs_tree.h
>> @@ -4,9 +4,8 @@
>>   
>>   #include <linux/btrfs.h>
>>   #include <linux/types.h>
>> -#ifdef __KERNEL__
>>   #include <linux/stddef.h>
>> -#else
>> +#ifndef __KERNEL__
>>   #include <stddef.h>
>>   #endif
> 
> This change seems unrelated to the RAID stripe tree. Should this be a patch on
> its own ?

Nope it isn't. This patch introduces a user of __DECLARE_FLEX_ARRAY() 
and without the moved ifdef userspace can't find the definition of it.

Patchew 2.1-devel-b67e4c2

© 2016 - 2025 Red Hat, Inc.