Linux-BTRFS Archive on lore.kernel.org
 help / color / Atom feed
From: Qu Wenruo <wqu@suse.com>
To: linux-btrfs@vger.kernel.org
Subject: [PATCH v4 3/7] btrfs: relocation: Delay reloc tree deletion after merge_reloc_roots()
Date: Tue, 15 Jan 2019 16:16:00 +0800
Message-ID: <20190115081604.785-4-wqu@suse.com> (raw)
In-Reply-To: <20190115081604.785-1-wqu@suse.com>

Relocation code will drop btrfs_root::reloc_root as soon as
merge_reloc_root() finishes.

However later qgroup code will need to access btrfs_root::reloc_root
after merge_reloc_root() for delayed subtree rescan.

So alter the timming of resetting btrfs_root:::reloc_root, make it
happens after transaction commit.

With this patch, we will introduce a new btrfs_root::state,
BTRFS_ROOT_DEAD_RELOC_TREE, to info part of btrfs_root::reloc_tree user
that although btrfs_root::reloc_tree is still non-NULL, but still it's
not used any more.

The lifespan of btrfs_root::reloc tree will become:
          Old behavior            |              New
------------------------------------------------------------------------
btrfs_init_reloc_root()      ---  | btrfs_init_reloc_root()      ---
  set reloc_root              |   |   set reloc_root              |
                              |   |                               |
                              |   |                               |
merge_reloc_root()            |   | merge_reloc_root()            |
|- btrfs_update_reloc_root() ---  | |- btrfs_update_reloc_root() -+-
     clear btrfs_root::reloc_root |      set ROOT_DEAD_RELOC_TREE |
                                  |      record root into dirty   |
                                  |      roots rbtree             |
                                  |                               |
                                  | reloc_block_group() Or        |
                                  | btrfs_recover_relocation()    |
                                  | | After transaction commit    |
                                  | |- clean_dirty_subvs()       ---
                                  |     clear btrfs_root::reloc_root

During ROOT_DEAD_RELOC_TREE set lifespan, the only user of
btrfs_root::reloc_tree should be qgroup.

And to co-operate this, also delayed btrfs_drop_snapshot() call on reloc
tree, btrfs_drop_snapshot() call will also be delayed to
clean_dirty_subvs().

This patch will increase the size of btrfs_root by 16 bytes.

Signed-off-by: Qu Wenruo <wqu@suse.com>
---
 fs/btrfs/ctree.h      | 15 ++++++++
 fs/btrfs/disk-io.c    |  1 +
 fs/btrfs/relocation.c | 85 ++++++++++++++++++++++++++++++++++---------
 3 files changed, 84 insertions(+), 17 deletions(-)

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 0a68cf7032f5..2c374dfb6aec 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -1195,6 +1195,13 @@ enum {
 	BTRFS_ROOT_MULTI_LOG_TASKS,
 	BTRFS_ROOT_DIRTY,
 	BTRFS_ROOT_DELETING,
+
+	/*
+	 * Reloc tree is orphan, only kept here for qgroup delayed subtree scan
+	 *
+	 * Set for the subvolume tree owning the reloc tree.
+	 */
+	BTRFS_ROOT_DEAD_RELOC_TREE,
 };
 
 /*
@@ -1307,6 +1314,14 @@ struct btrfs_root {
 	struct list_head ordered_root;
 	u64 nr_ordered_extents;
 
+	/*
+	 * Not empty if this subvolume root has gone through tree block swap
+	 * (relocation)
+	 *
+	 * Will be used by reloc_control::dirty_subv_roots.
+	 */
+	struct list_head reloc_dirty_list;
+
 	/*
 	 * Number of currently running SEND ioctls to prevent
 	 * manipulation with the read-only status via SUBVOL_SETFLAGS
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 8da2f380d3c0..bfefa1de0455 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1175,6 +1175,7 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info,
 	INIT_LIST_HEAD(&root->delalloc_root);
 	INIT_LIST_HEAD(&root->ordered_extents);
 	INIT_LIST_HEAD(&root->ordered_root);
+	INIT_LIST_HEAD(&root->reloc_dirty_list);
 	INIT_LIST_HEAD(&root->logged_list[0]);
 	INIT_LIST_HEAD(&root->logged_list[1]);
 	spin_lock_init(&root->inode_lock);
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 272b287f8cf0..1d5cfceb46c1 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -162,6 +162,8 @@ struct reloc_control {
 	struct mapping_tree reloc_root_tree;
 	/* list of reloc trees */
 	struct list_head reloc_roots;
+	/* list of subvolume trees who get relocated */
+	struct list_head dirty_subv_roots;
 	/* size of metadata reservation for merging reloc trees */
 	u64 merging_rsv_size;
 	/* size of relocated tree nodes */
@@ -1467,15 +1469,17 @@ int btrfs_update_reloc_root(struct btrfs_trans_handle *trans,
 	struct btrfs_root_item *root_item;
 	int ret;
 
-	if (!root->reloc_root)
+	if (test_bit(BTRFS_ROOT_DEAD_RELOC_TREE, &root->state) ||
+	    !root->reloc_root)
 		goto out;
 
 	reloc_root = root->reloc_root;
 	root_item = &reloc_root->root_item;
 
+	/* root->reloc_root will stay until current relocation finished */
 	if (fs_info->reloc_ctl->merge_reloc_tree &&
 	    btrfs_root_refs(root_item) == 0) {
-		root->reloc_root = NULL;
+		set_bit(BTRFS_ROOT_DEAD_RELOC_TREE, &root->state);
 		__del_reloc_root(reloc_root);
 	}
 
@@ -2120,6 +2124,58 @@ static int find_next_key(struct btrfs_path *path, int level,
 	return 1;
 }
 
+/*
+ * Helper to insert current subvolume root into reloc_control::dirty_subv_roots
+ */
+static void insert_dirty_subv(struct btrfs_trans_handle *trans,
+			      struct reloc_control *rc, struct btrfs_root *root)
+{
+	struct btrfs_root *reloc_root = root->reloc_root;
+	struct btrfs_root_item *reloc_root_item;
+	u64 root_objectid = root->root_key.objectid;
+
+	/* @root must be a file tree root with a valid reloc tree */
+	ASSERT(root_objectid != BTRFS_TREE_RELOC_OBJECTID);
+	ASSERT(reloc_root);
+
+	reloc_root_item = &reloc_root->root_item;
+	memset(&reloc_root_item->drop_progress, 0,
+		sizeof(reloc_root_item->drop_progress));
+	reloc_root_item->drop_level = 0;
+	btrfs_set_root_refs(reloc_root_item, 0);
+	btrfs_update_reloc_root(trans, root);
+
+	if (list_empty(&root->reloc_dirty_list)) {
+		btrfs_grab_fs_root(root);
+		list_add_tail(&root->reloc_dirty_list, &rc->dirty_subv_roots);
+	}
+	return;
+}
+
+static int clean_dirty_subvs(struct reloc_control *rc)
+{
+	struct btrfs_root *root;
+	struct btrfs_root *next;
+	int err = 0;
+	int ret;
+
+	list_for_each_entry_safe(root, next, &rc->dirty_subv_roots,
+				 reloc_dirty_list) {
+		struct btrfs_root *reloc_root = root->reloc_root;
+
+		clear_bit(BTRFS_ROOT_DEAD_RELOC_TREE, &root->state);
+		list_del_init(&root->reloc_dirty_list);
+		root->reloc_root = NULL;
+		if (reloc_root) {
+			ret = btrfs_drop_snapshot(reloc_root, NULL, 0, 1);
+			if (ret < 0 && !err)
+				err = ret;
+		}
+		btrfs_put_fs_root(root);
+	}
+	return err;
+}
+
 /*
  * merge the relocated tree blocks in reloc tree with corresponding
  * fs tree.
@@ -2259,13 +2315,8 @@ static noinline_for_stack int merge_reloc_root(struct reloc_control *rc,
 out:
 	btrfs_free_path(path);
 
-	if (err == 0) {
-		memset(&root_item->drop_progress, 0,
-		       sizeof(root_item->drop_progress));
-		root_item->drop_level = 0;
-		btrfs_set_root_refs(root_item, 0);
-		btrfs_update_reloc_root(trans, root);
-	}
+	if (err == 0)
+		insert_dirty_subv(trans, rc, root);
 
 	if (trans)
 		btrfs_end_transaction_throttle(trans);
@@ -2410,14 +2461,6 @@ void merge_reloc_roots(struct reloc_control *rc)
 		} else {
 			list_del_init(&reloc_root->root_list);
 		}
-
-		ret = btrfs_drop_snapshot(reloc_root, rc->block_rsv, 0, 1);
-		if (ret < 0) {
-			if (list_empty(&reloc_root->root_list))
-				list_add_tail(&reloc_root->root_list,
-					      &reloc_roots);
-			goto out;
-		}
 	}
 
 	if (found) {
@@ -4079,6 +4122,9 @@ static noinline_for_stack int relocate_block_group(struct reloc_control *rc)
 		goto out_free;
 	}
 	btrfs_commit_transaction(trans);
+	ret = clean_dirty_subvs(rc);
+	if (ret < 0 && !err)
+		err = ret;
 out_free:
 	btrfs_free_block_rsv(fs_info, rc->block_rsv);
 	btrfs_free_path(path);
@@ -4173,6 +4219,7 @@ static struct reloc_control *alloc_reloc_control(void)
 		return NULL;
 
 	INIT_LIST_HEAD(&rc->reloc_roots);
+	INIT_LIST_HEAD(&rc->dirty_subv_roots);
 	backref_cache_init(&rc->backref_cache);
 	mapping_tree_init(&rc->reloc_root_tree);
 	extent_io_tree_init(&rc->processed_blocks, NULL);
@@ -4468,6 +4515,10 @@ int btrfs_recover_relocation(struct btrfs_root *root)
 		goto out_free;
 	}
 	err = btrfs_commit_transaction(trans);
+
+	ret = clean_dirty_subvs(rc);
+	if (ret < 0 && !err)
+		err = ret;
 out_free:
 	kfree(rc);
 out:
-- 
2.20.1


  parent reply index

Thread overview: 24+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-01-15  8:15 [PATCH v4 0/7] btrfs: qgroup: Delay subtree scan to reduce overhead Qu Wenruo
2019-01-15  8:15 ` [PATCH v4 1/7] btrfs: qgroup: Move reserved data account from btrfs_delayed_ref_head to btrfs_qgroup_extent_record Qu Wenruo
2019-01-15  8:15 ` [PATCH v4 2/7] btrfs: qgroup: Don't trigger backref walk at delayed ref insert time Qu Wenruo
2019-01-15  8:16 ` Qu Wenruo [this message]
2019-01-22 16:32   ` [PATCH v4 3/7] btrfs: relocation: Delay reloc tree deletion after merge_reloc_roots() David Sterba
2019-01-23  6:01     ` Qu Wenruo
2019-01-15  8:16 ` [PATCH v4 4/7] btrfs: qgroup: Refactor btrfs_qgroup_trace_subtree_swap() Qu Wenruo
2019-01-22 16:38   ` David Sterba
2019-01-15  8:16 ` [PATCH v4 5/7] btrfs: qgroup: Introduce per-root swapped blocks infrastructure Qu Wenruo
2019-01-22 16:55   ` David Sterba
2019-01-22 23:07     ` Qu Wenruo
2019-01-24 18:44       ` David Sterba
2019-01-15  8:16 ` [PATCH v4 6/7] btrfs: qgroup: Use delayed subtree rescan for balance Qu Wenruo
2019-01-22 17:05   ` David Sterba
2019-01-15  8:16 ` [PATCH v4 7/7] btrfs: qgroup: Cleanup old subtree swap code Qu Wenruo
2019-01-15 17:26 ` [PATCH v4 0/7] btrfs: qgroup: Delay subtree scan to reduce overhead Josef Bacik
2019-01-16  0:31   ` Qu Wenruo
2019-01-16  1:07     ` Qu Wenruo
2019-01-16  1:15       ` Josef Bacik
2019-01-16  1:29         ` Qu Wenruo
2019-01-16  1:34           ` Josef Bacik
2019-01-16  1:36             ` Qu Wenruo
2019-01-22 16:28 ` David Sterba
2019-01-23  5:43   ` Qu Wenruo

Reply instructions:

You may reply publically 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=20190115081604.785-4-wqu@suse.com \
    --to=wqu@suse.com \
    --cc=linux-btrfs@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

Linux-BTRFS Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-btrfs/0 linux-btrfs/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-btrfs linux-btrfs/ https://lore.kernel.org/linux-btrfs \
		linux-btrfs@vger.kernel.org linux-btrfs@archiver.kernel.org
	public-inbox-index linux-btrfs


Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-btrfs


AGPL code for this site: git clone https://public-inbox.org/ public-inbox