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,
Naohiro Aota <naohiro.aota@wdc.com>
Subject: [PATCH v8 15/41] btrfs: emulate write pointer for conventional zones
Date: Fri, 2 Oct 2020 03:36:22 +0900 [thread overview]
Message-ID: <62d6c1774cf7ecffeacd66caec23d96dd4fdd70a.1601574234.git.naohiro.aota@wdc.com> (raw)
In-Reply-To: <dece91bca322ce44bed19f2b0f460fa5ded2e512.1601574234.git.naohiro.aota@wdc.com>
Conventional zones do not have a write pointer. So, we cannot use it to
determine the allocation offset if a block group contains a conventional
zone. Instead, we can consider the end of the last allocated extent int the
block group as an allocation offset.
Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com>
---
fs/btrfs/zoned.c | 119 ++++++++++++++++++++++++++++++++++++++++++++---
1 file changed, 113 insertions(+), 6 deletions(-)
diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index 33853f4d5a8b..3f65da0c4942 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -742,6 +742,104 @@ int btrfs_ensure_empty_zones(struct btrfs_device *device, u64 start, u64 size)
return 0;
}
+static int emulate_write_pointer(struct btrfs_block_group *cache,
+ u64 *offset_ret)
+{
+ struct btrfs_fs_info *fs_info = cache->fs_info;
+ struct btrfs_root *root = fs_info->extent_root;
+ struct btrfs_path *path;
+ struct extent_buffer *leaf;
+ struct btrfs_key search_key;
+ struct btrfs_key found_key;
+ int slot;
+ int ret;
+ u64 length;
+
+ path = btrfs_alloc_path();
+ if (!path)
+ return -ENOMEM;
+
+ search_key.objectid = cache->start + cache->length;
+ search_key.type = 0;
+ search_key.offset = 0;
+
+ ret = btrfs_search_slot(NULL, root, &search_key, path, 0, 0);
+ if (ret < 0)
+ goto out;
+ ASSERT(ret != 0);
+ slot = path->slots[0];
+ leaf = path->nodes[0];
+ ASSERT(slot != 0);
+ slot--;
+ btrfs_item_key_to_cpu(leaf, &found_key, slot);
+
+ if (found_key.objectid < cache->start) {
+ *offset_ret = 0;
+ } else if (found_key.type == BTRFS_BLOCK_GROUP_ITEM_KEY) {
+ struct btrfs_key extent_item_key;
+
+ if (found_key.objectid != cache->start) {
+ ret = -EUCLEAN;
+ goto out;
+ }
+
+ length = 0;
+
+ /* metadata may have METADATA_ITEM_KEY */
+ if (slot == 0) {
+ btrfs_set_path_blocking(path);
+ ret = btrfs_prev_leaf(root, path);
+ if (ret < 0)
+ goto out;
+ if (ret == 0) {
+ slot = btrfs_header_nritems(leaf) - 1;
+ btrfs_item_key_to_cpu(leaf, &extent_item_key,
+ slot);
+ }
+ } else {
+ btrfs_item_key_to_cpu(leaf, &extent_item_key, slot - 1);
+ ret = 0;
+ }
+
+ if (ret == 0 &&
+ extent_item_key.objectid == cache->start) {
+ if (extent_item_key.type == BTRFS_METADATA_ITEM_KEY)
+ length = fs_info->nodesize;
+ else if (extent_item_key.type == BTRFS_EXTENT_ITEM_KEY)
+ length = extent_item_key.offset;
+ else {
+ ret = -EUCLEAN;
+ goto out;
+ }
+ }
+
+ *offset_ret = length;
+ } else if (found_key.type == BTRFS_EXTENT_ITEM_KEY ||
+ found_key.type == BTRFS_METADATA_ITEM_KEY) {
+
+ if (found_key.type == BTRFS_EXTENT_ITEM_KEY)
+ length = found_key.offset;
+ else
+ length = fs_info->nodesize;
+
+ if (!(found_key.objectid >= cache->start &&
+ found_key.objectid + length <=
+ cache->start + cache->length)) {
+ ret = -EUCLEAN;
+ goto out;
+ }
+ *offset_ret = found_key.objectid + length - cache->start;
+ } else {
+ ret = -EUCLEAN;
+ goto out;
+ }
+ ret = 0;
+
+out:
+ btrfs_free_path(path);
+ return ret;
+}
+
int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache)
{
struct btrfs_fs_info *fs_info = cache->fs_info;
@@ -756,6 +854,7 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache)
int i;
unsigned int nofs_flag;
u64 *alloc_offsets = NULL;
+ u64 emulated_offset = 0;
u32 num_sequential = 0, num_conventional = 0;
if (!btrfs_fs_incompat(fs_info, ZONED))
@@ -856,12 +955,12 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache)
}
if (num_conventional > 0) {
- /*
- * Since conventional zones does not have write pointer, we
- * cannot determine alloc_offset from the pointer
- */
- ret = -EINVAL;
- goto out;
+ ret = emulate_write_pointer(cache, &emulated_offset);
+ if (ret || map->num_stripes == num_conventional) {
+ if (!ret)
+ cache->alloc_offset = emulated_offset;
+ goto out;
+ }
}
switch (map->type & BTRFS_BLOCK_GROUP_PROFILE_MASK) {
@@ -883,6 +982,14 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache)
}
out:
+ /* an extent is allocated after the write pointer */
+ if (num_conventional && emulated_offset > cache->alloc_offset) {
+ btrfs_err(fs_info,
+ "got wrong write pointer in BG %llu: %llu > %llu",
+ logical, emulated_offset, cache->alloc_offset);
+ ret = -EIO;
+ }
+
kfree(alloc_offsets);
free_extent_map(em);
--
2.27.0
next prev parent reply other threads:[~2020-10-01 18:38 UTC|newest]
Thread overview: 61+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-10-01 18:36 [PATCH v8 00/41] btrfs: zoned block device support Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 01/41] block: add bio_add_zone_append_page Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 02/41] btrfs: introduce ZONED feature flag Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 03/41] btrfs: Get zone information of zoned block devices Naohiro Aota
2020-10-13 15:53 ` David Sterba
2020-10-15 7:45 ` Johannes Thumshirn
2020-10-01 18:36 ` [PATCH v8 04/41] btrfs: Check and enable ZONED mode Naohiro Aota
2020-10-13 15:56 ` David Sterba
2020-10-28 14:49 ` Johannes Thumshirn
2020-10-13 16:13 ` David Sterba
2020-10-01 18:36 ` [PATCH v8 05/41] btrfs: introduce max_zone_append_size Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 06/41] btrfs: disallow space_cache in ZONED mode Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 07/41] btrfs: disallow NODATACOW " Naohiro Aota
2020-10-13 15:39 ` David Sterba
2020-10-21 8:53 ` Johannes Thumshirn
2020-10-01 18:36 ` [PATCH v8 08/41] btrfs: disable fallocate " Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 09/41] btrfs: disallow mixed-bg " Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 10/41] btrfs: disallow inode_cache " Naohiro Aota
2020-10-13 15:41 ` David Sterba
2020-10-22 6:48 ` Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 11/41] btrfs: implement log-structured superblock for " Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 12/41] btrfs: implement zoned chunk allocator Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 13/41] btrfs: verify device extent is aligned to zone Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 14/41] btrfs: load zone's alloction offset Naohiro Aota
2020-10-01 18:36 ` Naohiro Aota [this message]
2020-10-01 18:36 ` [PATCH v8 16/41] btrfs: track unusable bytes for zones Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 17/41] btrfs: do sequential extent allocation in ZONED mode Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 18/41] btrfs: reset zones of unused block groups Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 19/41] btrfs: redirty released extent buffers in ZONED mode Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 20/41] btrfs: extract page adding function Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 21/41] btrfs: use bio_add_zone_append_page for zoned btrfs Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 22/41] btrfs: handle REQ_OP_ZONE_APPEND as writing Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 23/41] btrfs: split ordered extent when bio is sent Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 24/41] btrfs: extend btrfs_rmap_block for specifying a device Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 25/41] btrfs: use ZONE_APPEND write for ZONED btrfs Naohiro Aota
2020-10-13 16:45 ` David Sterba
2020-10-01 18:36 ` [PATCH v8 26/41] btrfs: enable zone append writing for direct IO Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 27/41] btrfs: introduce dedicated data write path for ZONED mode Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 28/41] btrfs: serialize meta IOs on " Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 29/41] btrfs: wait existing extents before truncating Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 30/41] btrfs: avoid async metadata checksum on ZONED mode Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 31/41] btrfs: mark block groups to copy for device-replace Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 32/41] btrfs: implement cloning for ZONED device-replace Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 33/41] btrfs: implement copying " Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 34/41] btrfs: support dev-replace in ZONED mode Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 35/41] btrfs: enable relocation " Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 36/41] btrfs: relocate block group to repair IO failure in ZONED Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 37/41] btrfs: split alloc_log_tree() Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 38/41] btrfs: extend zoned allocator to use dedicated tree-log block group Naohiro Aota
2020-10-13 16:26 ` David Sterba
2020-10-15 7:21 ` Johannes Thumshirn
2020-10-01 18:36 ` [PATCH v8 39/41] btrfs: serialize log transaction on ZONED mode Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 40/41] btrfs: reorder log node allocation Naohiro Aota
2020-10-01 18:36 ` [PATCH v8 41/41] btrfs: enable to mount ZONED incompat flag Naohiro Aota
2020-10-02 13:39 ` [PATCH v8 01/41] block: add bio_add_zone_append_page Martin K. Petersen
2020-10-05 1:46 ` Damien Le Moal
2020-10-05 13:43 ` Christoph Hellwig
2020-10-06 1:26 ` Martin K. Petersen
2020-10-06 5:12 ` Damien Le Moal
2020-10-09 15:40 ` [PATCH v8 00/41] btrfs: zoned block device support Josef Bacik
2020-10-12 9:17 ` 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=62d6c1774cf7ecffeacd66caec23d96dd4fdd70a.1601574234.git.naohiro.aota@wdc.com \
--to=naohiro.aota@wdc.com \
--cc=dsterba@suse.com \
--cc=hare@suse.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).