From: David Sterba <dsterba@suse.com>
To: linux-btrfs@vger.kernel.org
Cc: David Sterba <dsterba@suse.com>
Subject: [PATCH 2/4] btrfs: add support for 3-copy replication (raid1c3)
Date: Fri, 13 Jul 2018 20:46:31 +0200 [thread overview]
Message-ID: <7b570d84f5232322564e49f88990b733234c372c.1531503452.git.dsterba@suse.com> (raw)
In-Reply-To: <cover.1531503452.git.dsterba@suse.com>
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;
@@ -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;
@@ -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)))
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");
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) {
@@ -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);
@@ -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;
@@ -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 {
@@ -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;
@@ -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) ||
@@ -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;
}
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)
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 | \
--
2.18.0
next prev parent reply other threads:[~2018-07-13 19:02 UTC|newest]
Thread overview: 36+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-07-13 18:46 [PATCH 0/4] 3- and 4- copy RAID1 David Sterba
2018-07-13 18:46 ` [PATCH] btrfs-progs: add support for raid1c3 and raid1c4 David Sterba
2018-07-13 18:46 ` [PATCH 1/4] btrfs: refactor block group replication factor calculation to a helper David Sterba
2018-07-13 18:46 ` David Sterba [this message]
2018-07-13 21:02 ` [PATCH 2/4] btrfs: add support for 3-copy replication (raid1c3) Goffredo Baroncelli
2018-07-17 16:00 ` David Sterba
2018-07-13 18:46 ` [PATCH 3/4] btrfs: add support for 4-copy replication (raid1c4) David Sterba
2018-07-13 18:46 ` [PATCH 4/4] btrfs: add incompatibility bit for extended raid features David Sterba
2018-07-15 14:37 ` [PATCH 0/4] 3- and 4- copy RAID1 waxhead
2018-07-16 18:29 ` Goffredo Baroncelli
2018-07-16 18:49 ` Austin S. Hemmelgarn
2018-07-17 21:12 ` Duncan
2018-07-18 5:59 ` Goffredo Baroncelli
2018-07-18 7:20 ` Duncan
2018-07-18 8:39 ` Duncan
2018-07-18 12:45 ` Austin S. Hemmelgarn
2018-07-18 12:50 ` Hugo Mills
2018-07-19 21:22 ` waxhead
2018-07-18 12:50 ` Austin S. Hemmelgarn
2018-07-18 19:42 ` Goffredo Baroncelli
2018-07-19 11:43 ` Austin S. Hemmelgarn
2018-07-19 17:29 ` Goffredo Baroncelli
2018-07-19 19:10 ` Austin S. Hemmelgarn
2018-07-20 17:13 ` Goffredo Baroncelli
2018-07-20 18:33 ` Austin S. Hemmelgarn
2018-07-20 5:17 ` Andrei Borzenkov
2018-07-20 17:16 ` Goffredo Baroncelli
2018-07-20 18:38 ` Andrei Borzenkov
2018-07-20 18:41 ` Hugo Mills
2018-07-20 18:46 ` Austin S. Hemmelgarn
2018-07-16 21:51 ` waxhead
2018-07-15 14:46 ` Hugo Mills
2018-07-19 7:27 ` Qu Wenruo
2018-07-19 11:47 ` Austin S. Hemmelgarn
2018-07-20 16:42 ` David Sterba
2018-07-20 16:35 ` David Sterba
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=7b570d84f5232322564e49f88990b733234c372c.1531503452.git.dsterba@suse.com \
--to=dsterba@suse.com \
--cc=linux-btrfs@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).