Add new structures and functions for new qgroup reserve implement dirty
phase.
Which will focus on avoiding over-reserve as in that case, which means
for already reserved dirty space range, we won't reserve space again.
This patch adds the needed structure declaration and comments.
Signed-off-by: Qu Wenruo <quwenruo@xxxxxxxxxxxxxx>
---
fs/btrfs/btrfs_inode.h | 4 ++++
fs/btrfs/qgroup.c | 58 ++++++++++++++++++++++++++++++++++++++++++++++++++
fs/btrfs/qgroup.h | 3 +++
3 files changed, 65 insertions(+)
diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index 81220b2..e3ece65 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -24,6 +24,7 @@
#include "extent_io.h"
#include "ordered-data.h"
#include "delayed-inode.h"
+#include "qgroup.h"
/*
* ordered_data_close is set by truncate when a file that used
@@ -195,6 +196,9 @@ struct btrfs_inode {
struct timespec i_otime;
struct inode vfs_inode;
+
+ /* qgroup dirty map for data space reserve */
+ struct btrfs_qgroup_data_rsv_map *qgroup_rsv_map;
};
extern unsigned char btrfs_filetype_table[];
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index e9ace09..561c36d 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -91,6 +91,64 @@ struct btrfs_qgroup {
u64 new_refcnt;
};
+/*
+ * Record one range of reserved space.
+ */
+struct data_rsv_range {
+ struct rb_node node;
+ u64 start;
+ u64 len;
+};
+
+/*
+ * Record per inode reserved range.
+ * This is mainly used to resolve reserved space leaking problem.
+ * One of the cause is the mismatch with reserve and free.
+ *
+ * New qgroup will handle reserve in two phase.
+ * 1) Dirty phase.
+ * Pages are just marked dirty, but not written to disk.
+ * 2) Flushed phase
+ * Pages are written to disk, but transaction is not committed yet.
+ *
+ * At Diryt phase, we only need to focus on avoiding over-reserve.
+ *
+ * The idea is like below.
+ * 1) Write [0,8K)
+ * 0 4K 8K 12K 16K
+ * |////////////|
+ * Reserve +8K, total reserved: 8K
+ *
+ * 2) Write [0,4K)
+ * 0 4K 8K 12K 16K
+ * |////////////|
+ * Reserve 0, total reserved 8K
+ *
+ * 3) Write [12K,16K)
+ * 0 4K 8K 12K 16K
+ * |////////////| |///////|
+ * Reserve +4K, tocal reserved 12K
+ *
+ * 4) Flush [0,8K)
+ * Can happen without commit transaction, like fallocate will trigger the
+ * write.
+ * 0 4K 8K 12K 16K
+ * |///////|
+ * Reserve 0, tocal reserved 12K
+ * As the extent is written to disk, not dirty any longer, the range get
+ * removed.
+ * But as its delayed_refs is not run, its reserved space will not be freed.
+ * And things continue to Flushed phase.
+ *
+ * By this method, we can avoid over-reserve, which will lead to reserved
+ * space leak.
+ */
+struct btrfs_qgroup_data_rsv_map {
+ struct rb_root root;
+ u64 reserved;
+ spinlock_t lock;
+};
+
static void btrfs_qgroup_update_old_refcnt(struct btrfs_qgroup *qg, u64 seq,
int mod)
{
diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h
index 6387dcf..2f863a4 100644
--- a/fs/btrfs/qgroup.h
+++ b/fs/btrfs/qgroup.h
@@ -33,6 +33,9 @@ struct btrfs_qgroup_extent_record {
struct ulist *old_roots;
};
+/* For per-inode dirty range reserve */
+struct btrfs_qgroup_data_rsv_map;
+
int btrfs_quota_enable(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info);
int btrfs_quota_disable(struct btrfs_trans_handle *trans,
--
2.5.1
--
To unsubscribe from this list: send the line "unsubscribe linux-btrfs" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
