From: Naohiro Aota <naohiro.aota@wdc.com>
To: linux-btrfs@vger.kernel.org, dsterba@suse.com
Cc: hare@suse.com, linux-fsdevel@vger.kernel.org,
Jens Axboe <axboe@kernel.dk>,
Christoph Hellwig <hch@infradead.org>,
"Darrick J. Wong" <darrick.wong@oracle.com>,
Naohiro Aota <naohiro.aota@wdc.com>,
Josef Bacik <josef@toxicpanda.com>,
Johannes Thumshirn <johannes.thumshirn@wdc.com>
Subject: [PATCH v13 40/42] btrfs: extend zoned allocator to use dedicated tree-log block group
Date: Fri, 22 Jan 2021 15:21:40 +0900 [thread overview]
Message-ID: <4449f11b454278c57ffd6592b634012675b1539b.1611295439.git.naohiro.aota@wdc.com> (raw)
In-Reply-To: <cover.1611295439.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.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com>
---
fs/btrfs/block-group.c | 2 ++
fs/btrfs/ctree.h | 2 ++
fs/btrfs/disk-io.c | 1 +
fs/btrfs/extent-tree.c | 75 +++++++++++++++++++++++++++++++++++++++---
fs/btrfs/zoned.h | 14 ++++++++
5 files changed, 90 insertions(+), 4 deletions(-)
diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index 56fab3d490b0..9f768c81d464 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -893,6 +893,8 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
btrfs_return_cluster_to_free_space(block_group, cluster);
spin_unlock(&cluster->refill_lock);
+ btrfs_clear_treelog_bg(block_group);
+
path = btrfs_alloc_path();
if (!path) {
ret = -ENOMEM;
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 4e9c55171ddb..2deb34a8d65d 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -973,6 +973,8 @@ 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/disk-io.c b/fs/btrfs/disk-io.c
index 2e2f09a46f45..c3b5cfe4d928 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -2722,6 +2722,7 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info)
spin_lock_init(&fs_info->super_lock);
spin_lock_init(&fs_info->buffer_lock);
spin_lock_init(&fs_info->unused_bgs_lock);
+ spin_lock_init(&fs_info->treelog_bg_lock);
rwlock_init(&fs_info->tree_mod_log_lock);
mutex_init(&fs_info->unused_bg_unpin_mutex);
mutex_init(&fs_info->delete_unused_bgs_mutex);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 1317f5d61024..fe8f1211f74c 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -3590,6 +3590,9 @@ 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;
@@ -3818,6 +3821,22 @@ 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
@@ -3827,23 +3846,54 @@ 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) {
if (ffe_ctl->max_extent_size < avail) {
@@ -3858,6 +3908,9 @@ 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);
@@ -3872,6 +3925,9 @@ 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;
@@ -4121,7 +4177,12 @@ 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();
@@ -4165,6 +4226,7 @@ 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);
@@ -4178,6 +4240,7 @@ 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 */
@@ -4252,8 +4315,11 @@ 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 (for_treelog)
+ btrfs_clear_treelog_bg(block_group);
continue;
+ }
btrfs_grab_block_group(block_group, delalloc);
ffe_ctl.search_start = block_group->start;
@@ -4441,6 +4507,7 @@ 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:
@@ -4464,8 +4531,8 @@ 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);
diff --git a/fs/btrfs/zoned.h b/fs/btrfs/zoned.h
index 8c203c0425e0..52789da61fa3 100644
--- a/fs/btrfs/zoned.h
+++ b/fs/btrfs/zoned.h
@@ -7,6 +7,7 @@
#include <linux/blkdev.h>
#include "volumes.h"
#include "disk-io.h"
+#include "block-group.h"
struct btrfs_zoned_device_info {
/*
@@ -292,4 +293,17 @@ static inline void btrfs_zoned_meta_io_unlock(struct btrfs_fs_info *fs_info)
mutex_unlock(&fs_info->zoned_meta_io_lock);
}
+static inline void btrfs_clear_treelog_bg(struct btrfs_block_group *bg)
+{
+ struct btrfs_fs_info *fs_info = bg->fs_info;
+
+ if (!btrfs_is_zoned(fs_info))
+ return;
+
+ spin_lock(&fs_info->treelog_bg_lock);
+ if (fs_info->treelog_bg == bg->start)
+ fs_info->treelog_bg = 0;
+ spin_unlock(&fs_info->treelog_bg_lock);
+}
+
#endif
--
2.27.0
next prev parent reply other threads:[~2021-01-22 6:33 UTC|newest]
Thread overview: 62+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-01-22 6:21 [PATCH v13 00/42] btrfs: zoned block device support Naohiro Aota
2021-01-22 6:21 ` [PATCH v13 01/42] block: add bio_add_zone_append_page Naohiro Aota
2021-01-23 2:50 ` Chaitanya Kulkarni
2021-01-23 3:08 ` Chaitanya Kulkarni
2021-01-25 17:31 ` Johannes Thumshirn
2021-01-22 6:21 ` [PATCH v13 02/42] iomap: support REQ_OP_ZONE_APPEND Naohiro Aota
2021-01-23 2:56 ` Chaitanya Kulkarni
2021-01-22 6:21 ` [PATCH v13 03/42] btrfs: defer loading zone info after opening trees Naohiro Aota
2021-01-22 6:21 ` [PATCH v13 04/42] btrfs: use regular SB location on emulated zoned mode Naohiro Aota
2021-01-22 6:21 ` [PATCH v13 05/42] btrfs: release path before calling into btrfs_load_block_group_zone_info Naohiro Aota
2021-01-22 14:57 ` Josef Bacik
2021-01-22 6:21 ` [PATCH v13 06/42] btrfs: do not load fs_info->zoned from incompat flag Naohiro Aota
2021-01-22 14:58 ` Josef Bacik
2021-01-22 6:21 ` [PATCH v13 07/42] btrfs: disallow fitrim in ZONED mode Naohiro Aota
2021-01-22 14:59 ` Josef Bacik
2021-01-22 6:21 ` [PATCH v13 08/42] btrfs: allow zoned mode on non-zoned block devices Naohiro Aota
2021-01-22 15:03 ` Josef Bacik
2021-01-22 6:21 ` [PATCH v13 09/42] btrfs: implement zoned chunk allocator Naohiro Aota
2021-01-22 6:21 ` [PATCH v13 10/42] btrfs: verify device extent is aligned to zone Naohiro Aota
2021-01-22 6:21 ` [PATCH v13 11/42] btrfs: load zone's allocation offset Naohiro Aota
2021-01-22 6:21 ` [PATCH v13 12/42] btrfs: calculate allocation offset for conventional zones Naohiro Aota
2021-01-22 15:07 ` Josef Bacik
2021-01-22 6:21 ` [PATCH v13 13/42] btrfs: track unusable bytes for zones Naohiro Aota
2021-01-22 15:11 ` Josef Bacik
2021-01-25 10:37 ` Johannes Thumshirn
2021-01-25 12:08 ` Johannes Thumshirn
2021-01-22 6:21 ` [PATCH v13 14/42] btrfs: do sequential extent allocation in ZONED mode Naohiro Aota
2021-01-22 6:21 ` [PATCH v13 15/42] btrfs: redirty released extent buffers " Naohiro Aota
2021-01-22 6:21 ` [PATCH v13 16/42] btrfs: advance allocation pointer after tree log node Naohiro Aota
2021-01-22 6:21 ` [PATCH v13 17/42] btrfs: enable to mount ZONED incompat flag Naohiro Aota
2021-01-22 6:21 ` [PATCH v13 18/42] btrfs: reset zones of unused block groups Naohiro Aota
2021-01-22 6:21 ` [PATCH v13 19/42] btrfs: extract page adding function Naohiro Aota
2021-01-22 6:21 ` [PATCH v13 20/42] btrfs: use bio_add_zone_append_page for zoned btrfs Naohiro Aota
2021-01-22 6:21 ` [PATCH v13 21/42] btrfs: handle REQ_OP_ZONE_APPEND as writing Naohiro Aota
2021-01-22 6:21 ` [PATCH v13 22/42] btrfs: split ordered extent when bio is sent Naohiro Aota
2021-01-22 15:22 ` Josef Bacik
2021-01-25 8:56 ` Johannes Thumshirn
2021-01-25 9:02 ` Johannes Thumshirn
2021-01-22 6:21 ` [PATCH v13 23/42] btrfs: check if bio spans across an ordered extent Naohiro Aota
2021-01-22 15:23 ` Josef Bacik
2021-01-22 6:21 ` [PATCH v13 24/42] btrfs: extend btrfs_rmap_block for specifying a device Naohiro Aota
2021-01-22 6:21 ` [PATCH v13 25/42] btrfs: cache if block-group is on a sequential zone Naohiro Aota
2021-01-22 6:21 ` [PATCH v13 26/42] btrfs: save irq flags when looking up an ordered extent Naohiro Aota
2021-01-22 15:24 ` Josef Bacik
2021-01-22 6:21 ` [PATCH v13 27/42] btrfs: use ZONE_APPEND write for ZONED btrfs Naohiro Aota
2021-01-22 15:29 ` Josef Bacik
2021-01-22 6:21 ` [PATCH v13 28/42] btrfs: enable zone append writing for direct IO Naohiro Aota
2021-01-22 6:21 ` [PATCH v13 29/42] btrfs: introduce dedicated data write path for ZONED mode Naohiro Aota
2021-01-22 6:21 ` [PATCH v13 30/42] btrfs: serialize meta IOs on " Naohiro Aota
2021-01-22 6:21 ` [PATCH v13 31/42] btrfs: wait existing extents before truncating Naohiro Aota
2021-01-22 6:21 ` [PATCH v13 32/42] btrfs: avoid async metadata checksum on ZONED mode Naohiro Aota
2021-01-22 6:21 ` [PATCH v13 33/42] btrfs: mark block groups to copy for device-replace Naohiro Aota
2021-01-22 6:21 ` [PATCH v13 34/42] btrfs: implement cloning for ZONED device-replace Naohiro Aota
2021-01-22 6:21 ` [PATCH v13 35/42] btrfs: implement copying " Naohiro Aota
2021-01-22 6:21 ` [PATCH v13 36/42] btrfs: support dev-replace in ZONED mode Naohiro Aota
2021-01-22 6:21 ` [PATCH v13 37/42] btrfs: enable relocation " Naohiro Aota
2021-01-22 6:21 ` [PATCH v13 38/42] btrfs: relocate block group to repair IO failure in ZONED Naohiro Aota
2021-01-22 6:21 ` [PATCH v13 39/42] btrfs: split alloc_log_tree() Naohiro Aota
2021-01-22 6:21 ` Naohiro Aota [this message]
2021-01-22 6:21 ` [PATCH v13 41/42] btrfs: serialize log transaction on ZONED mode Naohiro Aota
2021-01-22 15:37 ` Josef Bacik
2021-01-22 6:21 ` [PATCH v13 42/42] btrfs: reorder log node allocation Naohiro Aota
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=4449f11b454278c57ffd6592b634012675b1539b.1611295439.git.naohiro.aota@wdc.com \
--to=naohiro.aota@wdc.com \
--cc=axboe@kernel.dk \
--cc=darrick.wong@oracle.com \
--cc=dsterba@suse.com \
--cc=hare@suse.com \
--cc=hch@infradead.org \
--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).