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 19/41] btrfs: redirty released extent buffers in ZONED mode
Date: Fri, 2 Oct 2020 03:36:26 +0900 [thread overview]
Message-ID: <7c0ff07e2a2c5c98824348f7afe8f944637b4f90.1601574234.git.naohiro.aota@wdc.com> (raw)
In-Reply-To: <dece91bca322ce44bed19f2b0f460fa5ded2e512.1601574234.git.naohiro.aota@wdc.com>
Tree manipulating operations like merging nodes often release
once-allocated tree nodes. Btrfs cleans such nodes so that pages in the
node are not uselessly written out. On ZONED volumes, however, such
optimization blocks the following IOs as the cancellation of the write out
of the freed blocks breaks the sequential write sequence expected by the
device.
This patch introduces a list of clean and unwritten extent buffers that
have been released in a transaction. Btrfs redirty the buffer so that
btree_write_cache_pages() can send proper bios to the devices.
Besides it clears the entire content of the extent buffer not to confuse
raw block scanners e.g. btrfsck. By clearing the content,
csum_dirty_buffer() complains about bytenr mismatch, so avoid the checking
and checksum using newly introduced buffer flag EXTENT_BUFFER_NO_CHECK.
Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com>
---
fs/btrfs/disk-io.c | 8 ++++++++
fs/btrfs/extent-tree.c | 12 +++++++++++-
fs/btrfs/extent_io.c | 4 ++++
fs/btrfs/extent_io.h | 2 ++
fs/btrfs/transaction.c | 10 ++++++++++
fs/btrfs/transaction.h | 3 +++
fs/btrfs/tree-log.c | 6 ++++++
fs/btrfs/zoned.c | 37 +++++++++++++++++++++++++++++++++++++
fs/btrfs/zoned.h | 6 ++++++
9 files changed, 87 insertions(+), 1 deletion(-)
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 61b50a7df27b..c872f051b0a5 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -462,6 +462,12 @@ static int csum_dirty_buffer(struct btrfs_fs_info *fs_info, struct page *page)
return 0;
found_start = btrfs_header_bytenr(eb);
+
+ if (test_bit(EXTENT_BUFFER_NO_CHECK, &eb->bflags)) {
+ WARN_ON(found_start != 0);
+ return 0;
+ }
+
/*
* Please do not consolidate these warnings into a single if.
* It is useful to know what went wrong.
@@ -4614,6 +4620,8 @@ void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans,
EXTENT_DIRTY);
btrfs_destroy_pinned_extent(fs_info, &cur_trans->pinned_extents);
+ btrfs_free_redirty_list(cur_trans);
+
cur_trans->state =TRANS_STATE_COMPLETED;
wake_up(&cur_trans->commit_wait);
}
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index dbf178fee7c7..c0e4a577c61c 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -3421,8 +3421,10 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) {
ret = check_ref_cleanup(trans, buf->start);
- if (!ret)
+ if (!ret) {
+ btrfs_redirty_list_add(trans->transaction, buf);
goto out;
+ }
}
pin = 0;
@@ -3434,6 +3436,13 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
goto out;
}
+ if (btrfs_fs_incompat(fs_info, ZONED)) {
+ btrfs_redirty_list_add(trans->transaction, buf);
+ pin_down_extent(trans, cache, buf->start, buf->len, 1);
+ btrfs_put_block_group(cache);
+ goto out;
+ }
+
WARN_ON(test_bit(EXTENT_BUFFER_DIRTY, &buf->bflags));
btrfs_add_free_space(cache, buf->start, buf->len);
@@ -4767,6 +4776,7 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root,
__btrfs_tree_lock(buf, nest);
btrfs_clean_tree_block(buf);
clear_bit(EXTENT_BUFFER_STALE, &buf->bflags);
+ clear_bit(EXTENT_BUFFER_NO_CHECK, &buf->bflags);
btrfs_set_lock_blocking_write(buf);
set_extent_buffer_uptodate(buf);
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 60f5f68d892d..e91c504fe973 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -24,6 +24,7 @@
#include "rcu-string.h"
#include "backref.h"
#include "disk-io.h"
+#include "zoned.h"
static struct kmem_cache *extent_state_cache;
static struct kmem_cache *extent_buffer_cache;
@@ -4959,6 +4960,7 @@ __alloc_extent_buffer(struct btrfs_fs_info *fs_info, u64 start,
btrfs_leak_debug_add(&fs_info->eb_leak_lock, &eb->leak_list,
&fs_info->allocated_ebs);
+ INIT_LIST_HEAD(&eb->release_list);
spin_lock_init(&eb->refs_lock);
atomic_set(&eb->refs, 1);
@@ -5744,6 +5746,8 @@ void write_extent_buffer(const struct extent_buffer *eb, const void *srcv,
char *src = (char *)srcv;
unsigned long i = start >> PAGE_SHIFT;
+ WARN_ON(test_bit(EXTENT_BUFFER_NO_CHECK, &eb->bflags));
+
if (check_eb_range(eb, start, len))
return;
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index f39d02e7f7ef..5f2ccfd0205e 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -30,6 +30,7 @@ enum {
EXTENT_BUFFER_IN_TREE,
/* write IO error */
EXTENT_BUFFER_WRITE_ERR,
+ EXTENT_BUFFER_NO_CHECK,
};
/* these are flags for __process_pages_contig */
@@ -107,6 +108,7 @@ struct extent_buffer {
*/
wait_queue_head_t read_lock_wq;
struct page *pages[INLINE_EXTENT_BUFFER_PAGES];
+ struct list_head release_list;
#ifdef CONFIG_BTRFS_DEBUG
int spinning_writers;
atomic_t spinning_readers;
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 84b506de2c91..fb02668026c9 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -22,6 +22,7 @@
#include "qgroup.h"
#include "block-group.h"
#include "space-info.h"
+#include "zoned.h"
#define BTRFS_ROOT_TRANS_TAG 0
@@ -336,6 +337,8 @@ static noinline int join_transaction(struct btrfs_fs_info *fs_info,
spin_lock_init(&cur_trans->dirty_bgs_lock);
INIT_LIST_HEAD(&cur_trans->deleted_bgs);
spin_lock_init(&cur_trans->dropped_roots_lock);
+ INIT_LIST_HEAD(&cur_trans->releasing_ebs);
+ spin_lock_init(&cur_trans->releasing_ebs_lock);
list_add_tail(&cur_trans->list, &fs_info->trans_list);
extent_io_tree_init(fs_info, &cur_trans->dirty_pages,
IO_TREE_TRANS_DIRTY_PAGES, fs_info->btree_inode);
@@ -2346,6 +2349,13 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
goto scrub_continue;
}
+ /*
+ * At this point, we should have written the all tree blocks
+ * allocated in this transaction. So it's now safe to free the
+ * redirtyied extent buffers.
+ */
+ btrfs_free_redirty_list(cur_trans);
+
ret = write_all_supers(fs_info, 0);
/*
* the super is written, we can safely allow the tree-loggers
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index 858d9153a1cd..380e0aaa15b3 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -92,6 +92,9 @@ struct btrfs_transaction {
*/
atomic_t pending_ordered;
wait_queue_head_t pending_wait;
+
+ spinlock_t releasing_ebs_lock;
+ struct list_head releasing_ebs;
};
#define __TRANS_FREEZABLE (1U << 0)
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 56cbc1706b6f..5f585cf57383 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -20,6 +20,7 @@
#include "inode-map.h"
#include "block-group.h"
#include "space-info.h"
+#include "zoned.h"
/* magic values for the inode_only field in btrfs_log_inode:
*
@@ -2742,6 +2743,8 @@ static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans,
free_extent_buffer(next);
return ret;
}
+ btrfs_redirty_list_add(
+ trans->transaction, next);
} else {
if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &next->bflags))
clear_extent_buffer_dirty(next);
@@ -3277,6 +3280,9 @@ static void free_log_tree(struct btrfs_trans_handle *trans,
clear_extent_bits(&log->dirty_log_pages, 0, (u64)-1,
EXTENT_DIRTY | EXTENT_NEW | EXTENT_NEED_WAIT);
extent_io_tree_release(&log->log_csum_range);
+
+ if (trans && log->node)
+ btrfs_redirty_list_add(trans->transaction, log->node);
btrfs_put_root(log);
}
diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index 266daf7d60b7..88b45af60e4f 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -16,6 +16,7 @@
#include "rcu-string.h"
#include "disk-io.h"
#include "block-group.h"
+#include "transaction.h"
/* Maximum number of zones to report per blkdev_report_zones() call */
#define BTRFS_REPORT_NR_ZONES 4096
@@ -1017,3 +1018,39 @@ void btrfs_calc_zone_unusable(struct btrfs_block_group *cache)
*/
btrfs_free_excluded_extents(cache);
}
+
+void btrfs_redirty_list_add(struct btrfs_transaction *trans,
+ struct extent_buffer *eb)
+{
+ struct btrfs_fs_info *fs_info = eb->fs_info;
+
+ if (!btrfs_fs_incompat(fs_info, ZONED) ||
+ btrfs_header_flag(eb, BTRFS_HEADER_FLAG_WRITTEN) ||
+ !list_empty(&eb->release_list))
+ return;
+
+ set_extent_buffer_dirty(eb);
+ set_extent_bits_nowait(&trans->dirty_pages, eb->start,
+ eb->start + eb->len - 1, EXTENT_DIRTY);
+ memzero_extent_buffer(eb, 0, eb->len);
+ set_bit(EXTENT_BUFFER_NO_CHECK, &eb->bflags);
+
+ spin_lock(&trans->releasing_ebs_lock);
+ list_add_tail(&eb->release_list, &trans->releasing_ebs);
+ spin_unlock(&trans->releasing_ebs_lock);
+ atomic_inc(&eb->refs);
+}
+
+void btrfs_free_redirty_list(struct btrfs_transaction *trans)
+{
+ spin_lock(&trans->releasing_ebs_lock);
+ while (!list_empty(&trans->releasing_ebs)) {
+ struct extent_buffer *eb;
+
+ eb = list_first_entry(&trans->releasing_ebs,
+ struct extent_buffer, release_list);
+ list_del_init(&eb->release_list);
+ free_extent_buffer(eb);
+ }
+ spin_unlock(&trans->releasing_ebs_lock);
+}
diff --git a/fs/btrfs/zoned.h b/fs/btrfs/zoned.h
index e388189b28f0..32446135e882 100644
--- a/fs/btrfs/zoned.h
+++ b/fs/btrfs/zoned.h
@@ -47,6 +47,9 @@ int btrfs_reset_device_zone(struct btrfs_device *device, u64 physical,
int btrfs_ensure_empty_zones(struct btrfs_device *device, u64 start, u64 size);
int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache);
void btrfs_calc_zone_unusable(struct btrfs_block_group *cache);
+void btrfs_redirty_list_add(struct btrfs_transaction *trans,
+ struct extent_buffer *eb);
+void btrfs_free_redirty_list(struct btrfs_transaction *trans);
#else /* CONFIG_BLK_DEV_ZONED */
static inline int btrfs_get_dev_zone(struct btrfs_device *device, u64 pos,
struct blk_zone *zone)
@@ -113,6 +116,9 @@ static inline int btrfs_load_block_group_zone_info(
return 0;
}
static inline void btrfs_calc_zone_unusable(struct btrfs_block_group *cache) { }
+static inline void btrfs_redirty_list_add(struct btrfs_transaction *trans,
+ struct extent_buffer *eb) { }
+static inline void btrfs_free_redirty_list(struct btrfs_transaction *trans) { }
#endif
static inline bool btrfs_dev_is_sequential(struct btrfs_device *device, u64 pos)
--
2.27.0
next prev parent reply other threads:[~2020-10-01 18:39 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 ` [PATCH v8 15/41] btrfs: emulate write pointer for conventional zones Naohiro Aota
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 ` Naohiro Aota [this message]
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=7c0ff07e2a2c5c98824348f7afe8f944637b4f90.1601574234.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).