On 2022/2/15 7:27, Jaegeuk Kim wrote:
If one read IO is always failing, we can fall into an infinite loop in
f2fs_sync_dirty_inodes. This happens during xfstests/generic/475.
[ 142.803335] Buffer I/O error on dev dm-1, logical block 8388592, async page
read
...
[ 382.887210] submit_bio_noacct+0xdd/0x2a0
[ 382.887213] submit_bio+0x80/0x110
[ 382.887223] __submit_bio+0x4d/0x300 [f2fs]
[ 382.887282] f2fs_submit_page_bio+0x125/0x200 [f2fs]
[ 382.887299] __get_meta_page+0xc9/0x280 [f2fs]
[ 382.887315] f2fs_get_meta_page+0x13/0x20 [f2fs]
[ 382.887331] f2fs_get_node_info+0x317/0x3c0 [f2fs]
[ 382.887350] f2fs_do_write_data_page+0x327/0x6f0 [f2fs]
[ 382.887367] f2fs_write_single_data_page+0x5b7/0x960 [f2fs]
[ 382.887386] f2fs_write_cache_pages+0x302/0x890 [f2fs]
[ 382.887405] ? preempt_count_add+0x7a/0xc0
[ 382.887408] f2fs_write_data_pages+0xfd/0x320 [f2fs]
[ 382.887425] ? _raw_spin_unlock+0x1a/0x30
[ 382.887428] do_writepages+0xd3/0x1d0
[ 382.887432] filemap_fdatawrite_wbc+0x69/0x90
[ 382.887434] filemap_fdatawrite+0x50/0x70
[ 382.887437] f2fs_sync_dirty_inodes+0xa4/0x270 [f2fs]
[ 382.887453] f2fs_write_checkpoint+0x189/0x1640 [f2fs]
[ 382.887469] ? schedule_timeout+0x114/0x150
[ 382.887471] ? ttwu_do_activate+0x6d/0xb0
[ 382.887473] ? preempt_count_add+0x7a/0xc0
[ 382.887476] kill_f2fs_super+0xca/0x100 [f2fs]
[ 382.887491] deactivate_locked_super+0x35/0xa0
[ 382.887494] deactivate_super+0x40/0x50
[ 382.887497] cleanup_mnt+0x139/0x190
[ 382.887499] __cleanup_mnt+0x12/0x20
[ 382.887501] task_work_run+0x64/0xa0
[ 382.887505] exit_to_user_mode_prepare+0x1b7/0x1c0
[ 382.887508] syscall_exit_to_user_mode+0x27/0x50
[ 382.887510] do_syscall_64+0x48/0xc0
[ 382.887513] entry_SYSCALL_64_after_hwframe+0x44/0xae
Signed-off-by: Jaegeuk Kim <[email protected]>
---
Change log from v1:
- fix a regression to report EIO too early
fs/f2fs/checkpoint.c | 13 ++++++++-----
fs/f2fs/f2fs.h | 3 +++
2 files changed, 11 insertions(+), 5 deletions(-)
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index 203a1577942d..56c81c68ef71 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -1059,13 +1059,13 @@ int f2fs_sync_dirty_inodes(struct f2fs_sb_info *sbi,
enum inode_type type)
struct inode *inode;
struct f2fs_inode_info *fi;
bool is_dir = (type == DIR_INODE);
- unsigned long ino = 0;
+ unsigned long ino = 0, retry_count = DEFAULT_RETRY_SYNC_DIR_COUNT;
trace_f2fs_sync_dirty_inodes_enter(sbi->sb, is_dir,
get_pages(sbi, is_dir ?
F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA));
retry:
- if (unlikely(f2fs_cp_error(sbi))) {
+ if (unlikely(f2fs_cp_error(sbi) || (is_dir && !retry_count))) {
trace_f2fs_sync_dirty_inodes_exit(sbi->sb, is_dir,
get_pages(sbi, is_dir ?
F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA));
@@ -1096,10 +1096,13 @@ int f2fs_sync_dirty_inodes(struct f2fs_sb_info *sbi,
enum inode_type type)
iput(inode);
/* We need to give cpu to another writers. */
- if (ino == cur_ino)
- cond_resched();
- else
+ if (ino == cur_ino) {
+ retry_count--;
+ io_schedule_timeout(DEFAULT_IO_TIMEOUT);
+ } else {
+ retry_count = DEFAULT_RETRY_SYNC_DIR_COUNT;
ino = cur_ino;
+ }
} else {
/*
* We should submit bio, since it exists several
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index c9515c3c54fd..f40ef7b61965 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -577,6 +577,9 @@ enum {
/* maximum retry quota flush count */
#define DEFAULT_RETRY_QUOTA_FLUSH_COUNT 8
+/* maximum retry sync dirty inodes */
+#define DEFAULT_RETRY_SYNC_DIR_COUNT 3000
3000 * 20ms/round = 60sec
How about just trying 5 or 10 sec?
Thanks,
+
#define F2FS_LINK_MAX 0xffffffff /* maximum link count per file */
#define MAX_DIR_RA_PAGES 4 /* maximum ra pages of dir */
_______________________________________________
Linux-f2fs-devel mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel
