From: Naohiro Aota <naohiro.aota@wdc.com>
To: linux-btrfs@vger.kernel.org, David Sterba <dsterba@suse.com>
Cc: Josef Bacik <josef@toxicpanda.com>,
Hannes Reinecke <hare@suse.com>,
linux-fsdevel@vger.kernel.org,
Naohiro Aota <naohiro.aota@wdc.com>,
Johannes Thumshirn <johannes.thumshirn@wdc.com>
Subject: [PATCH v10.1 38/41] btrfs: extend zoned allocator to use dedicated tree-log block group
Date: Wed, 11 Nov 2020 13:58:08 +0900 [thread overview]
Message-ID: <3d5be9c64060efb3b976e0288befad965b599269.1605070255.git.naohiro.aota@wdc.com> (raw)
In-Reply-To: <551fecb79909221d640f9d6d08f5ccc8487717be.1605007037.git.naohiro.aota@wdc.com>
This is the 1/3 patch to enable tree log on ZONED mode.
The tree-log feature does not work on ZONED mode as is. Blocks for a
tree-log tree are allocated mixed with other metadata blocks, and btrfs
writes and syncs the tree-log blocks to devices at the time of fsync(),
which is different timing from a global transaction commit. As a result,
both writing tree-log blocks and writing other metadata blocks become
non-sequential writes that ZONED mode must avoid.
We can introduce a dedicated block group for tree-log blocks so that
tree-log blocks and other metadata blocks can be separated write streams.
As a result, each write stream can now be written to devices separately.
"fs_info->treelog_bg" tracks the dedicated block group and btrfs assign
"treelog_bg" on-demand on tree-log block allocation time.
This commit extends the zoned block allocator to use the block group.
Signed-off-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com>
---
fs/btrfs/block-group.c | 7 ++++
fs/btrfs/ctree.h | 2 ++
fs/btrfs/extent-tree.c | 79 +++++++++++++++++++++++++++++++++++++++---
3 files changed, 84 insertions(+), 4 deletions(-)
I forgot to merge a patch to add the lock description...
diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index 04bb0602f1cc..d222f54eb0c1 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -939,6 +939,13 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
btrfs_return_cluster_to_free_space(block_group, cluster);
spin_unlock(&cluster->refill_lock);
+ if (btrfs_is_zoned(fs_info)) {
+ spin_lock(&fs_info->treelog_bg_lock);
+ if (fs_info->treelog_bg == block_group->start)
+ fs_info->treelog_bg = 0;
+ spin_unlock(&fs_info->treelog_bg_lock);
+ }
+
path = btrfs_alloc_path();
if (!path) {
ret = -ENOMEM;
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 8138e932b7cc..2fd7e58343ce 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -957,6 +957,8 @@ struct btrfs_fs_info {
/* Max size to emit ZONE_APPEND write command */
u64 max_zone_append_size;
struct mutex zoned_meta_io_lock;
+ spinlock_t treelog_bg_lock;
+ u64 treelog_bg;
#ifdef CONFIG_BTRFS_FS_REF_VERIFY
spinlock_t ref_verify_lock;
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 2ee21076b641..f50eea392b2f 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -3631,6 +3631,9 @@ struct find_free_extent_ctl {
bool have_caching_bg;
bool orig_have_caching_bg;
+ /* Allocation is called for tree-log */
+ bool for_treelog;
+
/* RAID index, converted from flags */
int index;
@@ -3859,6 +3862,22 @@ static int do_allocation_clustered(struct btrfs_block_group *block_group,
return find_free_extent_unclustered(block_group, ffe_ctl);
}
+/*
+ * Tree-log Block Group Locking
+ * ============================
+ *
+ * fs_info::treelog_bg_lock protects the fs_info::treelog_bg which
+ * indicates the starting address of a block group, which is reserved only
+ * for tree-log metadata.
+ *
+ * Lock nesting
+ * ============
+ *
+ * space_info::lock
+ * block_group::lock
+ * fs_info::treelog_bg_lock
+ */
+
/*
* Simple allocator for sequential only block group. It only allows
* sequential allocation. No need to play with trees. This function
@@ -3868,23 +3887,54 @@ static int do_allocation_zoned(struct btrfs_block_group *block_group,
struct find_free_extent_ctl *ffe_ctl,
struct btrfs_block_group **bg_ret)
{
+ struct btrfs_fs_info *fs_info = block_group->fs_info;
struct btrfs_space_info *space_info = block_group->space_info;
struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
u64 start = block_group->start;
u64 num_bytes = ffe_ctl->num_bytes;
u64 avail;
+ u64 bytenr = block_group->start;
+ u64 log_bytenr;
int ret = 0;
+ bool skip;
ASSERT(btrfs_is_zoned(block_group->fs_info));
+ /*
+ * Do not allow non-tree-log blocks in the dedicated tree-log block
+ * group, and vice versa.
+ */
+ spin_lock(&fs_info->treelog_bg_lock);
+ log_bytenr = fs_info->treelog_bg;
+ skip = log_bytenr && ((ffe_ctl->for_treelog && bytenr != log_bytenr) ||
+ (!ffe_ctl->for_treelog && bytenr == log_bytenr));
+ spin_unlock(&fs_info->treelog_bg_lock);
+ if (skip)
+ return 1;
+
spin_lock(&space_info->lock);
spin_lock(&block_group->lock);
+ spin_lock(&fs_info->treelog_bg_lock);
+
+ ASSERT(!ffe_ctl->for_treelog ||
+ block_group->start == fs_info->treelog_bg ||
+ fs_info->treelog_bg == 0);
if (block_group->ro) {
ret = 1;
goto out;
}
+ /*
+ * Do not allow currently using block group to be tree-log dedicated
+ * block group.
+ */
+ if (ffe_ctl->for_treelog && !fs_info->treelog_bg &&
+ (block_group->used || block_group->reserved)) {
+ ret = 1;
+ goto out;
+ }
+
avail = block_group->length - block_group->alloc_offset;
if (avail < num_bytes) {
ffe_ctl->max_extent_size = avail;
@@ -3892,6 +3942,9 @@ static int do_allocation_zoned(struct btrfs_block_group *block_group,
goto out;
}
+ if (ffe_ctl->for_treelog && !fs_info->treelog_bg)
+ fs_info->treelog_bg = block_group->start;
+
ffe_ctl->found_offset = start + block_group->alloc_offset;
block_group->alloc_offset += num_bytes;
spin_lock(&ctl->tree_lock);
@@ -3906,6 +3959,9 @@ static int do_allocation_zoned(struct btrfs_block_group *block_group,
ffe_ctl->search_start = ffe_ctl->found_offset;
out:
+ if (ret && ffe_ctl->for_treelog)
+ fs_info->treelog_bg = 0;
+ spin_unlock(&fs_info->treelog_bg_lock);
spin_unlock(&block_group->lock);
spin_unlock(&space_info->lock);
return ret;
@@ -4155,7 +4211,12 @@ static int prepare_allocation(struct btrfs_fs_info *fs_info,
return prepare_allocation_clustered(fs_info, ffe_ctl,
space_info, ins);
case BTRFS_EXTENT_ALLOC_ZONED:
- /* nothing to do */
+ if (ffe_ctl->for_treelog) {
+ spin_lock(&fs_info->treelog_bg_lock);
+ if (fs_info->treelog_bg)
+ ffe_ctl->hint_byte = fs_info->treelog_bg;
+ spin_unlock(&fs_info->treelog_bg_lock);
+ }
return 0;
default:
BUG();
@@ -4199,6 +4260,7 @@ static noinline int find_free_extent(struct btrfs_root *root,
struct find_free_extent_ctl ffe_ctl = {0};
struct btrfs_space_info *space_info;
bool full_search = false;
+ bool for_treelog = root->root_key.objectid == BTRFS_TREE_LOG_OBJECTID;
WARN_ON(num_bytes < fs_info->sectorsize);
@@ -4212,6 +4274,7 @@ static noinline int find_free_extent(struct btrfs_root *root,
ffe_ctl.orig_have_caching_bg = false;
ffe_ctl.found_offset = 0;
ffe_ctl.hint_byte = hint_byte_orig;
+ ffe_ctl.for_treelog = for_treelog;
ffe_ctl.policy = BTRFS_EXTENT_ALLOC_CLUSTERED;
/* For clustered allocation */
@@ -4286,8 +4349,15 @@ static noinline int find_free_extent(struct btrfs_root *root,
struct btrfs_block_group *bg_ret;
/* If the block group is read-only, we can skip it entirely. */
- if (unlikely(block_group->ro))
+ if (unlikely(block_group->ro)) {
+ if (btrfs_is_zoned(fs_info) && for_treelog) {
+ spin_lock(&fs_info->treelog_bg_lock);
+ if (block_group->start == fs_info->treelog_bg)
+ fs_info->treelog_bg = 0;
+ spin_unlock(&fs_info->treelog_bg_lock);
+ }
continue;
+ }
btrfs_grab_block_group(block_group, delalloc);
ffe_ctl.search_start = block_group->start;
@@ -4475,6 +4545,7 @@ int btrfs_reserve_extent(struct btrfs_root *root, u64 ram_bytes,
bool final_tried = num_bytes == min_alloc_size;
u64 flags;
int ret;
+ bool for_treelog = root->root_key.objectid == BTRFS_TREE_LOG_OBJECTID;
flags = get_alloc_profile_by_root(root, is_data);
again:
@@ -4498,8 +4569,8 @@ int btrfs_reserve_extent(struct btrfs_root *root, u64 ram_bytes,
sinfo = btrfs_find_space_info(fs_info, flags);
btrfs_err(fs_info,
- "allocation failed flags %llu, wanted %llu",
- flags, num_bytes);
+ "allocation failed flags %llu, wanted %llu treelog %d",
+ flags, num_bytes, for_treelog);
if (sinfo)
btrfs_dump_space_info(fs_info, sinfo,
num_bytes, 1);
--
2.27.0
next prev parent reply other threads:[~2020-11-11 4:58 UTC|newest]
Thread overview: 117+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-11-10 11:26 [PATCH v10 00/41] btrfs: zoned block device support Naohiro Aota
2020-11-10 11:26 ` [PATCH v10 01/41] block: add bio_add_zone_append_page Naohiro Aota
2020-11-10 17:20 ` Christoph Hellwig
2020-11-11 7:20 ` Johannes Thumshirn
2020-11-10 11:26 ` [PATCH v10 02/41] iomap: support REQ_OP_ZONE_APPEND Naohiro Aota
2020-11-10 17:25 ` Christoph Hellwig
2020-11-10 18:55 ` Darrick J. Wong
2020-11-10 19:01 ` Darrick J. Wong
2020-11-24 11:29 ` Christoph Hellwig
2020-11-30 18:11 ` Darrick J. Wong
2020-12-01 10:16 ` Johannes Thumshirn
2020-12-09 9:31 ` Christoph Hellwig
2020-12-09 10:08 ` Johannes Thumshirn
2020-12-09 10:10 ` hch
2020-12-09 10:16 ` Johannes Thumshirn
2020-12-09 13:38 ` Johannes Thumshirn
2020-12-11 7:26 ` Johannes Thumshirn
2020-12-11 21:24 ` Chaitanya Kulkarni
2020-12-12 10:22 ` Johannes Thumshirn
2020-11-10 11:26 ` [PATCH v10 03/41] btrfs: introduce ZONED feature flag Naohiro Aota
2020-11-19 21:31 ` David Sterba
2020-11-10 11:26 ` [PATCH v10 04/41] btrfs: get zone information of zoned block devices Naohiro Aota
2020-11-12 6:57 ` Anand Jain
2020-11-12 7:35 ` Johannes Thumshirn
2020-11-12 7:44 ` Damien Le Moal
2020-11-12 9:44 ` Anand Jain
2020-11-13 21:34 ` David Sterba
2020-11-12 9:39 ` Johannes Thumshirn
2020-11-12 12:57 ` Naohiro Aota
2020-11-18 11:17 ` Anand Jain
2020-11-30 11:16 ` Anand Jain
2020-11-25 21:47 ` David Sterba
2020-11-25 22:07 ` David Sterba
2020-11-25 23:50 ` Damien Le Moal
2020-11-26 14:11 ` David Sterba
2020-11-25 22:16 ` David Sterba
2020-11-10 11:26 ` [PATCH v10 05/41] btrfs: check and enable ZONED mode Naohiro Aota
2020-11-18 11:29 ` Anand Jain
2020-11-27 18:44 ` David Sterba
2020-11-30 12:12 ` Anand Jain
2020-11-30 13:15 ` Damien Le Moal
2020-12-01 2:19 ` Anand Jain
2020-12-01 2:29 ` Damien Le Moal
2020-12-01 5:53 ` Anand Jain
2020-12-01 6:09 ` Damien Le Moal
2020-12-01 7:12 ` Anand Jain
2020-12-01 10:45 ` Graham Cobb
2020-12-01 11:03 ` Damien Le Moal
2020-12-01 11:11 ` hch
2020-12-01 11:27 ` Damien Le Moal
2020-11-10 11:26 ` [PATCH v10 06/41] btrfs: introduce max_zone_append_size Naohiro Aota
2020-11-19 9:23 ` Anand Jain
2020-11-27 18:47 ` David Sterba
2020-11-10 11:26 ` [PATCH v10 07/41] btrfs: disallow space_cache in ZONED mode Naohiro Aota
2020-11-19 10:42 ` Anand Jain
2020-11-20 4:08 ` Anand Jain
2020-11-10 11:26 ` [PATCH v10 08/41] btrfs: disallow NODATACOW " Naohiro Aota
2020-11-20 4:17 ` Anand Jain
2020-11-23 17:21 ` David Sterba
2020-11-24 3:29 ` Anand Jain
2020-11-10 11:26 ` [PATCH v10 09/41] btrfs: disable fallocate " Naohiro Aota
2020-11-20 4:28 ` Anand Jain
2020-11-10 11:26 ` [PATCH v10 10/41] btrfs: disallow mixed-bg " Naohiro Aota
2020-11-20 4:32 ` Anand Jain
2020-11-10 11:26 ` [PATCH v10 11/41] btrfs: implement log-structured superblock for " Naohiro Aota
2020-11-23 17:46 ` David Sterba
2020-11-24 9:30 ` Johannes Thumshirn
2020-11-24 6:46 ` Anand Jain
2020-11-24 7:16 ` Hannes Reinecke
2020-11-10 11:26 ` [PATCH v10 12/41] btrfs: implement zoned chunk allocator Naohiro Aota
2020-11-24 11:36 ` Anand Jain
2020-11-25 1:57 ` Naohiro Aota
2020-11-25 7:17 ` Anand Jain
2020-11-25 11:48 ` Naohiro Aota
2020-11-25 9:59 ` Graham Cobb
2020-11-25 11:50 ` Naohiro Aota
2020-12-09 5:27 ` Anand Jain
2020-11-10 11:26 ` [PATCH v10 13/41] btrfs: verify device extent is aligned to zone Naohiro Aota
2020-11-27 6:27 ` Anand Jain
2020-11-10 11:26 ` [PATCH v10 14/41] btrfs: load zone's alloction offset Naohiro Aota
2020-12-08 9:54 ` Anand Jain
2020-11-10 11:26 ` [PATCH v10 15/41] btrfs: emulate write pointer for conventional zones Naohiro Aota
2020-11-10 11:26 ` [PATCH v10 16/41] btrfs: track unusable bytes for zones Naohiro Aota
2020-11-10 11:26 ` [PATCH v10 17/41] btrfs: do sequential extent allocation in ZONED mode Naohiro Aota
2020-11-10 11:26 ` [PATCH v10 18/41] btrfs: reset zones of unused block groups Naohiro Aota
2020-11-10 11:26 ` [PATCH v10 19/41] btrfs: redirty released extent buffers in ZONED mode Naohiro Aota
2020-11-10 11:26 ` [PATCH v10 20/41] btrfs: extract page adding function Naohiro Aota
2020-11-10 11:26 ` [PATCH v10 21/41] btrfs: use bio_add_zone_append_page for zoned btrfs Naohiro Aota
2020-11-10 11:26 ` [PATCH v10 22/41] btrfs: handle REQ_OP_ZONE_APPEND as writing Naohiro Aota
2020-11-10 11:26 ` [PATCH v10 23/41] btrfs: split ordered extent when bio is sent Naohiro Aota
2020-11-11 2:01 ` kernel test robot
2020-11-11 2:26 ` kernel test robot
2020-11-11 3:46 ` kernel test robot
2020-11-11 3:46 ` [RFC PATCH] btrfs: extract_ordered_extent() can be static kernel test robot
2020-11-11 4:12 ` [PATCH v10.1 23/41] btrfs: split ordered extent when bio is sent Naohiro Aota
2020-11-10 11:26 ` [PATCH v10 24/41] btrfs: extend btrfs_rmap_block for specifying a device Naohiro Aota
2020-11-10 11:26 ` [PATCH v10 25/41] btrfs: use ZONE_APPEND write for ZONED btrfs Naohiro Aota
2020-11-10 11:26 ` [PATCH v10 26/41] btrfs: enable zone append writing for direct IO Naohiro Aota
2020-11-10 11:26 ` [PATCH v10 27/41] btrfs: introduce dedicated data write path for ZONED mode Naohiro Aota
2020-11-10 11:26 ` [PATCH v10 28/41] btrfs: serialize meta IOs on " Naohiro Aota
2020-11-10 11:26 ` [PATCH v10 29/41] btrfs: wait existing extents before truncating Naohiro Aota
2020-11-10 11:26 ` [PATCH v10 30/41] btrfs: avoid async metadata checksum on ZONED mode Naohiro Aota
2020-11-10 11:26 ` [PATCH v10 31/41] btrfs: mark block groups to copy for device-replace Naohiro Aota
2020-11-10 11:26 ` [PATCH v10 32/41] btrfs: implement cloning for ZONED device-replace Naohiro Aota
2020-11-10 11:26 ` [PATCH v10 33/41] btrfs: implement copying " Naohiro Aota
2020-11-10 11:26 ` [PATCH v10 34/41] btrfs: support dev-replace in ZONED mode Naohiro Aota
2020-11-10 11:26 ` [PATCH v10 35/41] btrfs: enable relocation " Naohiro Aota
2020-11-10 11:26 ` [PATCH v10 36/41] btrfs: relocate block group to repair IO failure in ZONED Naohiro Aota
2020-11-10 11:26 ` [PATCH v10 37/41] btrfs: split alloc_log_tree() Naohiro Aota
2020-11-10 11:26 ` [PATCH v10 38/41] btrfs: extend zoned allocator to use dedicated tree-log block group Naohiro Aota
2020-11-11 4:58 ` Naohiro Aota [this message]
2020-11-10 11:26 ` [PATCH v10 39/41] btrfs: serialize log transaction on ZONED mode Naohiro Aota
2020-11-10 11:26 ` [PATCH v10 40/41] btrfs: reorder log node allocation Naohiro Aota
2020-11-10 11:26 ` [PATCH v10 41/41] btrfs: enable to mount ZONED incompat flag Naohiro Aota
2020-11-10 14:00 ` [PATCH v10 00/41] btrfs: zoned block device support Anand Jain
2020-11-11 5:07 ` Naohiro Aota
2020-11-27 19:28 ` 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=3d5be9c64060efb3b976e0288befad965b599269.1605070255.git.naohiro.aota@wdc.com \
--to=naohiro.aota@wdc.com \
--cc=dsterba@suse.com \
--cc=hare@suse.com \
--cc=johannes.thumshirn@wdc.com \
--cc=josef@toxicpanda.com \
--cc=linux-btrfs@vger.kernel.org \
--cc=linux-fsdevel@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).