linux-btrfs.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Naohiro Aota <naohiro.aota@wdc.com>
To: linux-btrfs@vger.kernel.org, David Sterba <dsterba@suse.com>
Cc: Chris Mason <clm@fb.com>, Josef Bacik <josef@toxicpanda.com>,
	Nikolay Borisov <nborisov@suse.com>,
	Damien Le Moal <damien.lemoal@wdc.com>,
	Matias Bjorling <Matias.Bjorling@wdc.com>,
	Johannes Thumshirn <jthumshirn@suse.de>,
	Hannes Reinecke <hare@suse.com>,
	linux-fsdevel@vger.kernel.org,
	Naohiro Aota <naohiro.aota@wdc.com>
Subject: [PATCH v3 15/27] btrfs: redirty released extent buffers in sequential BGs
Date: Thu,  8 Aug 2019 18:30:26 +0900	[thread overview]
Message-ID: <20190808093038.4163421-16-naohiro.aota@wdc.com> (raw)
In-Reply-To: <20190808093038.4163421-1-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 HMZONED drives, 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 disk.

Besides it clear 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     |  5 +++++
 fs/btrfs/extent-tree.c | 11 ++++++++++-
 fs/btrfs/extent_io.c   |  2 ++
 fs/btrfs/extent_io.h   |  2 ++
 fs/btrfs/hmzoned.c     | 34 ++++++++++++++++++++++++++++++++++
 fs/btrfs/hmzoned.h     |  3 +++
 fs/btrfs/transaction.c | 10 ++++++++++
 fs/btrfs/transaction.h |  3 +++
 8 files changed, 69 insertions(+), 1 deletion(-)

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index a0a3709de2e6..e0a80997b6ee 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -513,6 +513,9 @@ static int csum_dirty_buffer(struct btrfs_fs_info *fs_info, struct page *page)
 	if (page != eb->pages[0])
 		return 0;
 
+	if (test_bit(EXTENT_BUFFER_NO_CHECK, &eb->bflags))
+		return 0;
+
 	found_start = btrfs_header_bytenr(eb);
 	/*
 	 * Please do not consolidate these warnings into a single if.
@@ -4577,6 +4580,8 @@ void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans,
 	btrfs_destroy_pinned_extent(fs_info,
 				    fs_info->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 de9d3028833e..bc95a73a762d 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -5084,8 +5084,10 @@ 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;
@@ -5097,6 +5099,13 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
 			goto out;
 		}
 
+		if (btrfs_fs_incompat(fs_info, HMZONED)) {
+			btrfs_redirty_list_add(trans->transaction, buf);
+			pin_down_extent(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);
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index aea990473392..4e67b16c9f80 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -23,6 +23,7 @@
 #include "rcu-string.h"
 #include "backref.h"
 #include "disk-io.h"
+#include "hmzoned.h"
 
 static struct kmem_cache *extent_state_cache;
 static struct kmem_cache *extent_buffer_cache;
@@ -4863,6 +4864,7 @@ __alloc_extent_buffer(struct btrfs_fs_info *fs_info, u64 start,
 	init_waitqueue_head(&eb->read_lock_wq);
 
 	btrfs_leak_debug_add(&eb->leak_list, &buffers);
+	INIT_LIST_HEAD(&eb->release_list);
 
 	spin_lock_init(&eb->refs_lock);
 	atomic_set(&eb->refs, 1);
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 401423b16976..c63b58438f90 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -58,6 +58,7 @@ enum {
 	EXTENT_BUFFER_IN_TREE,
 	/* write IO error */
 	EXTENT_BUFFER_WRITE_ERR,
+	EXTENT_BUFFER_NO_CHECK,
 };
 
 /* these are flags for __process_pages_contig */
@@ -186,6 +187,7 @@ 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/hmzoned.c b/fs/btrfs/hmzoned.c
index 5968ef621fa7..4c296d282e67 100644
--- a/fs/btrfs/hmzoned.c
+++ b/fs/btrfs/hmzoned.c
@@ -614,3 +614,37 @@ int btrfs_reset_device_zone(struct btrfs_device *device, u64 physical,
 
 	return ret;
 }
+
+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, HMZONED) ||
+	    btrfs_header_flag(eb, BTRFS_HEADER_FLAG_WRITTEN) ||
+	    !list_empty(&eb->release_list))
+		return;
+
+	set_extent_buffer_dirty(eb);
+	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/hmzoned.h b/fs/btrfs/hmzoned.h
index 9de26d6b8c4e..3a73c3c5e1da 100644
--- a/fs/btrfs/hmzoned.h
+++ b/fs/btrfs/hmzoned.h
@@ -36,6 +36,9 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group_cache *cache);
 int btrfs_reset_device_zone(struct btrfs_device *device, u64 physical,
 			    u64 length, u64 *bytes);
 int btrfs_hmzoned_check_metadata_space(struct btrfs_fs_info *fs_info);
+void btrfs_redirty_list_add(struct btrfs_transaction *trans,
+			    struct extent_buffer *eb);
+void btrfs_free_redirty_list(struct btrfs_transaction *trans);
 
 static inline bool btrfs_dev_is_sequential(struct btrfs_device *device, u64 pos)
 {
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index e3adb714c04b..45bd7c25bebf 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -19,6 +19,7 @@
 #include "volumes.h"
 #include "dev-replace.h"
 #include "qgroup.h"
+#include "hmzoned.h"
 
 #define BTRFS_ROOT_TRANS_TAG 0
 
@@ -257,6 +258,8 @@ 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);
@@ -2269,6 +2272,13 @@ 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 2c5a6f6e5bb0..09329d2901b7 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -85,6 +85,9 @@ struct btrfs_transaction {
 	spinlock_t dropped_roots_lock;
 	struct btrfs_delayed_ref_root delayed_refs;
 	struct btrfs_fs_info *fs_info;
+
+	spinlock_t releasing_ebs_lock;
+	struct list_head releasing_ebs;
 };
 
 #define __TRANS_FREEZABLE	(1U << 0)
-- 
2.22.0


  parent reply	other threads:[~2019-08-08  9:31 UTC|newest]

Thread overview: 39+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-08-08  9:30 [PATCH v3 00/27] btrfs zoned block device support Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 01/27] btrfs: introduce HMZONED feature flag Naohiro Aota
2019-08-16  4:49   ` Anand Jain
2019-08-08  9:30 ` [PATCH v3 02/27] btrfs: Get zone information of zoned block devices Naohiro Aota
2019-08-16  4:44   ` Anand Jain
2019-08-16 14:19     ` Damien Le Moal
2019-08-16 23:47       ` Anand Jain
2019-08-16 23:55         ` Damien Le Moal
2019-08-08  9:30 ` [PATCH v3 03/27] btrfs: Check and enable HMZONED mode Naohiro Aota
2019-08-16  5:46   ` Anand Jain
2019-08-16 14:23     ` Damien Le Moal
2019-08-16 23:56       ` Anand Jain
2019-08-17  0:05         ` Damien Le Moal
2019-08-20  5:07         ` Naohiro Aota
2019-08-20 13:05           ` David Sterba
2019-08-08  9:30 ` [PATCH v3 04/27] btrfs: disallow RAID5/6 in " Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 05/27] btrfs: disallow space_cache " Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 06/27] btrfs: disallow NODATACOW " Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 07/27] btrfs: disable tree-log " Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 08/27] btrfs: disable fallocate " Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 09/27] btrfs: align device extent allocation to zone boundary Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 10/27] btrfs: do sequential extent allocation in HMZONED mode Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 11/27] btrfs: make unmirroed BGs readonly only if we have at least one writable BG Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 12/27] btrfs: ensure metadata space available on/after degraded mount in HMZONED Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 13/27] btrfs: reset zones of unused block groups Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 14/27] btrfs: limit super block locations in HMZONED mode Naohiro Aota
2019-08-08  9:30 ` Naohiro Aota [this message]
2019-08-08  9:30 ` [PATCH v3 16/27] btrfs: serialize data allocation and submit IOs Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 17/27] btrfs: implement atomic compressed IO submission Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 18/27] btrfs: support direct write IO in HMZONED Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 19/27] btrfs: serialize meta IOs on HMZONED mode Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 20/27] btrfs: wait existing extents before truncating Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 21/27] btrfs: avoid async checksum/submit on HMZONED mode Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 22/27] btrfs: disallow mixed-bg in " Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 23/27] btrfs: disallow inode_cache " Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 24/27] btrfs: support dev-replace " Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 25/27] btrfs: enable relocation " Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 26/27] btrfs: relocate block group to repair IO failure in HMZONED Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 27/27] btrfs: enable to mount HMZONED incompat flag 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=20190808093038.4163421-16-naohiro.aota@wdc.com \
    --to=naohiro.aota@wdc.com \
    --cc=Matias.Bjorling@wdc.com \
    --cc=clm@fb.com \
    --cc=damien.lemoal@wdc.com \
    --cc=dsterba@suse.com \
    --cc=hare@suse.com \
    --cc=josef@toxicpanda.com \
    --cc=jthumshirn@suse.de \
    --cc=linux-btrfs@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=nborisov@suse.com \
    /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).