On 8/26/25 09:48, 王晓珺 wrote:
> 在 8/25/2025 10:08 AM, Chao Yu 写道:
>> On 8/20/25 15:54, Wang Xiaojun wrote:
>>> This patch fixes missing space reclamation during the recovery process.
>>>
>>> In the following scenarios, F2FS cannot reclaim truncated space.
>>> case 1:
>>> write file A, size is 1G | CP | truncate A to 1M | fsync A | SPO
>>>
>>> case 2:
>>> CP | write file A, size is 1G | fsync A | truncate A to 1M | fsync A |SPO
>>>
>>> During the recovery process, F2FS will recover file A,
>>> but the 1M-1G space cannot be reclaimed.
>>>
>>> But the combination of truncate and falloc complicates the recovery
>>> process.
>>> For example, in the following scenario:
>>> write fileA 2M | fsync | truncate 256K | falloc -k 256K 1M | fsync A | SPO
>>> The falloc (256K, 1M) need to be recovered as pre-allocated space.
>>>
>>> However in the following scenarios, the situation is the opposite.
>>> write fileA 2M | fsync | falloc -k 2M 10M | fsync A | truncate 256K |
>>> fsync A | SPO
>>> In this scenario, the space allocated by falloc needs to be truncated.
>>>
>>> During the recovery process, it is difficult to distinguish
>>> between the above two types of falloc.
>>>
>>> So in this case of falloc -k we need to trigger a checkpoint for fsync.
>>>
>>> Fixes: d624c96fb3249 ("f2fs: add recovery routines for roll-forward")
>>>
>>> Signed-off-by: Wang Xiaojun <[email protected]>
>>> ---
>>> v4: Trigger checkpoint for fsync after falloc -k
>>> v3: Add a Fixes line.
>>> v2: Apply Chao's suggestion from v1. No logical changes.
>>> v1: Fix missing space reclamation during the recovery process.
>>> ---
>>> fs/f2fs/checkpoint.c | 3 +++
>>> fs/f2fs/f2fs.h | 3 +++
>>> fs/f2fs/file.c | 8 ++++++--
>>> fs/f2fs/recovery.c | 18 +++++++++++++++++-
>>> 4 files changed, 29 insertions(+), 3 deletions(-)
>>>
>>> diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
>>> index db3831f7f2f5..775e3333097e 100644
>>> --- a/fs/f2fs/checkpoint.c
>>> +++ b/fs/f2fs/checkpoint.c
>>> @@ -1151,6 +1151,9 @@ static int f2fs_sync_inode_meta(struct f2fs_sb_info
>>> *sbi)
>>> if (inode) {
>>> sync_inode_metadata(inode, 0);
>>>
>>> + if (is_inode_flag_set(inode, FI_FALLOC_KEEP_SIZE))
>>> + clear_inode_flag(inode, FI_FALLOC_KEEP_SIZE);
>>> +
>>> /* it's on eviction */
>>> if (is_inode_flag_set(inode, FI_DIRTY_INODE))
>>> f2fs_update_inode_page(inode);
>>> diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
>>> index 46be7560548c..f5a54bc848d5 100644
>>> --- a/fs/f2fs/f2fs.h
>>> +++ b/fs/f2fs/f2fs.h
>>> @@ -459,6 +459,7 @@ struct fsync_inode_entry {
>>> struct inode *inode; /* vfs inode pointer */
>>> block_t blkaddr; /* block address locating the last fsync */
>>> block_t last_dentry; /* block address locating the last dentry */
>>> + loff_t max_i_size; /* previous max file size for truncate */
>>> };
>>>
>>> #define nats_in_cursum(jnl) (le16_to_cpu((jnl)->n_nats))
>>> @@ -835,6 +836,7 @@ enum {
>>> FI_ATOMIC_REPLACE, /* indicate atomic replace */
>>> FI_OPENED_FILE, /* indicate file has been opened */
>>> FI_DONATE_FINISHED, /* indicate page donation of file has been
>>> finished */
>>> + FI_FALLOC_KEEP_SIZE, /* file allocate reserved space and keep size */
>>> FI_MAX, /* max flag, never be used */
>>> };
>>>
>>> @@ -1193,6 +1195,7 @@ enum cp_reason_type {
>>> CP_SPEC_LOG_NUM,
>>> CP_RECOVER_DIR,
>>> CP_XATTR_DIR,
>>> + CP_FALLOC_FILE,
>>> };
>>>
>>> enum iostat_type {
>>> diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
>>> index 42faaed6a02d..f0820f817824 100644
>>> --- a/fs/f2fs/file.c
>>> +++ b/fs/f2fs/file.c
>>> @@ -236,6 +236,8 @@ static inline enum cp_reason_type
>>> need_do_checkpoint(struct inode *inode)
>>> else if (f2fs_exist_written_data(sbi, F2FS_I(inode)->i_pino,
>>> XATTR_DIR_INO))
>>> cp_reason = CP_XATTR_DIR;
>>> + else if (is_inode_flag_set(inode, FI_FALLOC_KEEP_SIZE))
>>> + cp_reason = CP_FALLOC_FILE;
>>>
>>> return cp_reason;
>>> }
>>> @@ -1953,10 +1955,12 @@ static int f2fs_expand_inode_data(struct inode
>>> *inode, loff_t offset,
>>> }
>>>
>>> if (new_size > i_size_read(inode)) {
>>> - if (mode & FALLOC_FL_KEEP_SIZE)
>>> + if (mode & FALLOC_FL_KEEP_SIZE) {
>>> + set_inode_flag(inode, FI_FALLOC_KEEP_SIZE);
>> Xiaojun,
>>
>> Well, what about this case?
>>
>> falloc -k ofs size file
>> flush all data and metadata of file
>
> Hi Chao,
> Flush all data and metadata of file, but without using fsync or CP?
Xiaojun,
I think so, or am I missing someting?
Thanks,
>
> Thanks,
>
>> evict inode
>> write file & fsync file won't trigger a checkpoint?
>>
>> Or am I missing something?
>>
>> Thanks,
>>
>>> file_set_keep_isize(inode);
>>> - else
>>> + } else {
>>> f2fs_i_size_write(inode, new_size);
>>> + }
>>> }
>>>
>>> return err;
>>> diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c
>>> index 4cb3a91801b4..68b62c8a74d3 100644
>>> --- a/fs/f2fs/recovery.c
>>> +++ b/fs/f2fs/recovery.c
>>> @@ -95,6 +95,7 @@ static struct fsync_inode_entry *add_fsync_inode(struct
>>> f2fs_sb_info *sbi,
>>> entry = f2fs_kmem_cache_alloc(fsync_entry_slab,
>>> GFP_F2FS_ZERO, true, NULL);
>>> entry->inode = inode;
>>> + entry->max_i_size = i_size_read(inode);
>>> list_add_tail(&entry->list, head);
>>>
>>> return entry;
>>> @@ -796,6 +797,7 @@ static int recover_data(struct f2fs_sb_info *sbi,
>>> struct list_head *inode_list,
>>> while (1) {
>>> struct fsync_inode_entry *entry;
>>> struct folio *folio;
>>> + loff_t i_size;
>>>
>>> if (!f2fs_is_valid_blkaddr(sbi, blkaddr, META_POR))
>>> break;
>>> @@ -828,6 +830,9 @@ static int recover_data(struct f2fs_sb_info *sbi,
>>> struct list_head *inode_list,
>>> break;
>>> }
>>> recovered_inode++;
>>> + i_size = i_size_read(entry->inode);
>>> + if (entry->max_i_size < i_size)
>>> + entry->max_i_size = i_size;
>>> }
>>> if (entry->last_dentry == blkaddr) {
>>> err = recover_dentry(entry->inode, folio, dir_list);
>>> @@ -844,8 +849,19 @@ static int recover_data(struct f2fs_sb_info *sbi,
>>> struct list_head *inode_list,
>>> }
>>> recovered_dnode++;
>>>
>>> - if (entry->blkaddr == blkaddr)
>>> + if (entry->blkaddr == blkaddr) {
>>> + i_size = i_size_read(entry->inode);
>>> + if (entry->max_i_size > i_size) {
>>> + err = f2fs_truncate_blocks(entry->inode,
>>> + i_size, false);
>>> + if (err) {
>>> + f2fs_folio_put(folio, true);
>>> + break;
>>> + }
>>> + f2fs_mark_inode_dirty_sync(entry->inode, true);
>>> + }
>>> list_move_tail(&entry->list, tmp_inode_list);
>>> + }
>>> next:
>>> ra_blocks = adjust_por_ra_blocks(sbi, ra_blocks, blkaddr,
>>> next_blkaddr_of_node(folio));
>
>
_______________________________________________
Linux-f2fs-devel mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel
