f2fs: fix to avoid broken of dnode block list
f2fs recovery flow is relying on dnode block link list, it means fsynced
file recovery depends on previous dnode's persistence in the list, so
during fsync() we should wait on all regular inode's dnode writebacked
before issuing flush.
By this way, we can avoid dnode block list being broken by out-of-order
IO submission due to IO scheduler or driver.
Sheng Yong helps to do the test with this patch:
Target:/data (f2fs, -)
64MB / 32768KB / 4KB / 8
1 / PERSIST / Index
Base:
SEQ-RD(MB/s) SEQ-WR(MB/s) RND-RD(IOPS) RND-WR(IOPS) Insert(TPS) Update(TPS) Delete(TPS)
1 867.82 204.15 41440.03 41370.54 680.8 1025.94 1031.08
2 871.87 205.87 41370.3 40275.2 791.14 1065.84 1101.7
3 866.52 205.69 41795.67 40596.16 694.69 1037.16 1031.48
Avg 868.7366667 205.2366667 41535.33333 40747.3 722.21 1042.98 1054.753333
After:
SEQ-RD(MB/s) SEQ-WR(MB/s) RND-RD(IOPS) RND-WR(IOPS) Insert(TPS) Update(TPS) Delete(TPS)
1 798.81 202.5 41143 40613.87 602.71 838.08 913.83
2 805.79 206.47 40297.2 41291.46 604.44 840.75 924.27
3 814.83 206.17 41209.57 40453.62 602.85 834.66 927.91
Avg 806.4766667 205.0466667 40883.25667 40786.31667 603.3333333 837.83 922.0033333
Patched/Original:
0.928332713 0.999074239 0.984300676 1.000957528 0.835398753 0.803303994 0.874141189
It looks like atomic write will suffer performance regression.
I suspect that the criminal is that we forcing to wait all dnode being in
storage cache before we issue PREFLUSH+FUA.
BTW, will commit ("f2fs: don't need to wait for node writes for atomic write")
cause the problem: we will lose data of last transaction after SPO, even if
atomic write return no error:
- atomic_open();
- write() P1, P2, P3;
- atomic_commit();
- writeback data: P1, P2, P3;
- writeback node: N1, N2, N3; <--- If N1, N2 is not writebacked, N3 with fsync_mark is
writebacked, In SPOR, we won't find N3 since node chain is broken, turns out that losing
last transaction.
- preflush + fua;
- power-cut
If we don't wait dnode writeback for atomic_write:
SEQ-RD(MB/s) SEQ-WR(MB/s) RND-RD(IOPS) RND-WR(IOPS) Insert(TPS) Update(TPS) Delete(TPS)
1 779.91 206.03 41621.5 40333.16 716.9 1038.21 1034.85
2 848.51 204.35 40082.44 39486.17 791.83 1119.96 1083.77
3 772.12 206.27 41335.25 41599.65 723.29 1055.07 971.92
Avg 800.18 205.55 41013.06333 40472.99333 744.0066667 1071.08 1030.18
Patched/Original:
0.92108464 1.001526693 0.987425886 0.993268102 1.030180511 1.026942031 0.976702294
SQLite's performance recovers.
Jaegeuk:
"Practically, I don't see db corruption becase of this. We can excuse to lose
the last transaction."
Finally, we decide to keep original implementation of atomic write interface
sematics that we don't wait all dnode writeback before preflush+fua submission.
Signed-off-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 3fba8e6..adee6af 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -230,6 +230,12 @@
struct inode *inode; /* vfs inode pointer */
};
+struct fsync_node_entry {
+ struct list_head list; /* list head */
+ struct page *page; /* warm node page pointer */
+ unsigned int seq_id; /* sequence id */
+};
+
/* for the bitmap indicate blocks to be discarded */
struct discard_entry {
struct list_head list; /* list head */
@@ -1155,6 +1161,11 @@
struct inode_management im[MAX_INO_ENTRY]; /* manage inode cache */
+ spinlock_t fsync_node_lock; /* for node entry lock */
+ struct list_head fsync_node_list; /* node list head */
+ unsigned int fsync_seg_id; /* sequence id */
+ unsigned int fsync_node_num; /* number of node entries */
+
/* for orphan inode, use 0'th array */
unsigned int max_orphans; /* max orphan inodes */
@@ -2856,6 +2867,10 @@
int f2fs_check_nid_range(struct f2fs_sb_info *sbi, nid_t nid);
bool f2fs_available_free_memory(struct f2fs_sb_info *sbi, int type);
+bool f2fs_in_warm_node_list(struct f2fs_sb_info *sbi, struct page *page);
+void f2fs_init_fsync_node_info(struct f2fs_sb_info *sbi);
+void f2fs_del_fsync_node_entry(struct f2fs_sb_info *sbi, struct page *page);
+void f2fs_reset_fsync_node_info(struct f2fs_sb_info *sbi);
int f2fs_need_dentry_mark(struct f2fs_sb_info *sbi, nid_t nid);
bool f2fs_is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid);
bool f2fs_need_inode_block_update(struct f2fs_sb_info *sbi, nid_t ino);
@@ -2865,7 +2880,8 @@
int f2fs_get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode);
int f2fs_truncate_inode_blocks(struct inode *inode, pgoff_t from);
int f2fs_truncate_xattr_node(struct inode *inode);
-int f2fs_wait_on_node_pages_writeback(struct f2fs_sb_info *sbi, nid_t ino);
+int f2fs_wait_on_node_pages_writeback(struct f2fs_sb_info *sbi,
+ unsigned int seq_id);
int f2fs_remove_inode_page(struct inode *inode);
struct page *f2fs_new_inode_page(struct inode *inode);
struct page *f2fs_new_node_page(struct dnode_of_data *dn, unsigned int ofs);
@@ -2874,7 +2890,8 @@
struct page *f2fs_get_node_page_ra(struct page *parent, int start);
void f2fs_move_node_page(struct page *node_page, int gc_type);
int f2fs_fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode,
- struct writeback_control *wbc, bool atomic);
+ struct writeback_control *wbc, bool atomic,
+ unsigned int *seq_id);
int f2fs_sync_node_pages(struct f2fs_sb_info *sbi,
struct writeback_control *wbc,
bool do_balance, enum iostat_type io_type);
@@ -2991,6 +3008,7 @@
void f2fs_update_dirty_page(struct inode *inode, struct page *page);
void f2fs_remove_dirty_inode(struct inode *inode);
int f2fs_sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type);
+void f2fs_wait_on_all_pages_writeback(struct f2fs_sb_info *sbi);
int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc);
void f2fs_init_ino_entry_info(struct f2fs_sb_info *sbi);
int __init f2fs_create_checkpoint_caches(void);