Re: [PATCH 3/5] f2fs: avoid stucking GC due to atomic write

[Chao Yu]

On 2018/4/20 11:12, Jaegeuk Kim wrote:
> On 04/18, Chao Yu wrote:
>> f2fs doesn't allow abuse on atomic write class interface, so except
>> limiting in-mem pages' total memory usage capacity, we need to limit
>> atomic-write usage as well when filesystem is seriously fragmented,
>> otherwise we may run into infinite loop during foreground GC because
>> target blocks in victim segment are belong to atomic opened file for
>> long time.
>>
>> Now, we will detect failure due to atomic write in foreground GC, if
>> the count exceeds threshold, we will drop all atomic written data in
>> cache, by this, I expect it can keep our system running safely to
>> prevent Dos attack.
>>
>> Signed-off-by: Chao Yu <yuchao0@xxxxxxxxxx>
>> ---
>>  fs/f2fs/f2fs.h    |  1 +
>>  fs/f2fs/file.c    |  5 +++++
>>  fs/f2fs/gc.c      | 27 +++++++++++++++++++++++----
>>  fs/f2fs/gc.h      |  3 +++
>>  fs/f2fs/segment.c |  1 +
>>  fs/f2fs/segment.h |  2 ++
>>  6 files changed, 35 insertions(+), 4 deletions(-)
>>
>> diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
>> index c1c3a1d11186..3453288d6a71 100644
>> --- a/fs/f2fs/f2fs.h
>> +++ b/fs/f2fs/f2fs.h
>> @@ -2249,6 +2249,7 @@ enum {
>>  	FI_EXTRA_ATTR,		/* indicate file has extra attribute */
>>  	FI_PROJ_INHERIT,	/* indicate file inherits projectid */
>>  	FI_PIN_FILE,		/* indicate file should not be gced */
>> +	FI_ATOMIC_REVOKE_REQUEST,/* indicate atomic committed data has been dropped */
>>  };
>>  
>>  static inline void __mark_inode_dirty_flag(struct inode *inode,
>> diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
>> index 7c90ded5a431..cddd9aee1bb2 100644
>> --- a/fs/f2fs/file.c
>> +++ b/fs/f2fs/file.c
>> @@ -1698,6 +1698,7 @@ static int f2fs_ioc_start_atomic_write(struct file *filp)
>>  skip_flush:
>>  	set_inode_flag(inode, FI_HOT_DATA);
>>  	set_inode_flag(inode, FI_ATOMIC_FILE);
>> +	clear_inode_flag(inode, FI_ATOMIC_REVOKE_REQUEST);
>>  	f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
>>  
>>  	F2FS_I(inode)->inmem_task = current;
>> @@ -1746,6 +1747,10 @@ static int f2fs_ioc_commit_atomic_write(struct file *filp)
>>  		ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 1, false);
>>  	}
>>  err_out:
>> +	if (is_inode_flag_set(inode, FI_ATOMIC_REVOKE_REQUEST)) {
>> +		clear_inode_flag(inode, FI_ATOMIC_REVOKE_REQUEST);
>> +		ret = -EINVAL;
>> +	}
>>  	up_write(&F2FS_I(inode)->dio_rwsem[WRITE]);
>>  	inode_unlock(inode);
>>  	mnt_drop_write_file(filp);
>> diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
>> index bfb7a4a3a929..495876ca62b6 100644
>> --- a/fs/f2fs/gc.c
>> +++ b/fs/f2fs/gc.c
>> @@ -135,6 +135,8 @@ int start_gc_thread(struct f2fs_sb_info *sbi)
>>  	gc_th->gc_urgent = 0;
>>  	gc_th->gc_wake= 0;
>>  
>> +	gc_th->atomic_file = 0;
>> +
>>  	sbi->gc_thread = gc_th;
>>  	init_waitqueue_head(&sbi->gc_thread->gc_wait_queue_head);
>>  	sbi->gc_thread->f2fs_gc_task = kthread_run(gc_thread_func, sbi,
>> @@ -603,7 +605,7 @@ static bool is_alive(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
>>   * This can be used to move blocks, aka LBAs, directly on disk.
>>   */
>>  static void move_data_block(struct inode *inode, block_t bidx,
>> -					unsigned int segno, int off)
>> +				int gc_type, unsigned int segno, int off)
>>  {
>>  	struct f2fs_io_info fio = {
>>  		.sbi = F2FS_I_SB(inode),
>> @@ -630,8 +632,10 @@ static void move_data_block(struct inode *inode, block_t bidx,
>>  	if (!check_valid_map(F2FS_I_SB(inode), segno, off))
>>  		goto out;
>>  
>> -	if (f2fs_is_atomic_file(inode))
>> +	if (f2fs_is_atomic_file(inode)) {
>> +		F2FS_I_SB(inode)->gc_thread->atomic_file++;
>>  		goto out;
>> +	}
>>  
>>  	if (f2fs_is_pinned_file(inode)) {
>>  		f2fs_pin_file_control(inode, true);
>> @@ -737,8 +741,10 @@ static void move_data_page(struct inode *inode, block_t bidx, int gc_type,
>>  	if (!check_valid_map(F2FS_I_SB(inode), segno, off))
>>  		goto out;
>>  
>> -	if (f2fs_is_atomic_file(inode))
>> +	if (f2fs_is_atomic_file(inode)) {
>> +		F2FS_I_SB(inode)->gc_thread->atomic_file++;
>>  		goto out;
>> +	}
>>  	if (f2fs_is_pinned_file(inode)) {
>>  		if (gc_type == FG_GC)
>>  			f2fs_pin_file_control(inode, true);
>> @@ -900,7 +906,8 @@ static void gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
>>  			start_bidx = start_bidx_of_node(nofs, inode)
>>  								+ ofs_in_node;
>>  			if (f2fs_encrypted_file(inode))
>> -				move_data_block(inode, start_bidx, segno, off);
>> +				move_data_block(inode, start_bidx, gc_type,
>> +								segno, off);
>>  			else
>>  				move_data_page(inode, start_bidx, gc_type,
>>  								segno, off);
>> @@ -1017,6 +1024,8 @@ int f2fs_gc(struct f2fs_sb_info *sbi, bool sync,
>>  		.ilist = LIST_HEAD_INIT(gc_list.ilist),
>>  		.iroot = RADIX_TREE_INIT(GFP_NOFS),
>>  	};
>> +	unsigned int last_atomic_file = sbi->gc_thread->atomic_file;
>> +	unsigned int skipped_round = 0, round = 0;
>>  
>>  	trace_f2fs_gc_begin(sbi->sb, sync, background,
>>  				get_pages(sbi, F2FS_DIRTY_NODES),
>> @@ -1068,11 +1077,21 @@ int f2fs_gc(struct f2fs_sb_info *sbi, bool sync,
>>  		sec_freed++;
>>  	total_freed += seg_freed;
>>  
>> +	if (gc_type == FG_GC) {
>> +		if (sbi->gc_thread->atomic_file > last_atomic_file)
>> +			skipped_round++;
>> +		last_atomic_file = sbi->gc_thread->atomic_file;
> 
> How about resetting ->atomic_file to zero?

Since we will show this stat number through sysfs entry, it'd better to keep its
data?

Thanks,

> 
>> +		round++;
>> +	}
>> +
>>  	if (gc_type == FG_GC)
>>  		sbi->cur_victim_sec = NULL_SEGNO;
>>  
>>  	if (!sync) {
>>  		if (has_not_enough_free_secs(sbi, sec_freed, 0)) {
>> +			if (skipped_round > MAX_SKIP_ATOMIC_COUNT &&
>> +				skipped_round * 2 >= round)
>> +				drop_inmem_pages_all(sbi);
>>  			segno = NULL_SEGNO;
>>  			goto gc_more;
>>  		}
>> diff --git a/fs/f2fs/gc.h b/fs/f2fs/gc.h
>> index b0045d4c8d1e..bc1d21d46ae7 100644
>> --- a/fs/f2fs/gc.h
>> +++ b/fs/f2fs/gc.h
>> @@ -39,6 +39,9 @@ struct f2fs_gc_kthread {
>>  	unsigned int gc_idle;
>>  	unsigned int gc_urgent;
>>  	unsigned int gc_wake;
>> +
>> +	/* for stuck statistic */
>> +	unsigned int atomic_file;
>>  };
>>  
>>  struct gc_inode_list {
>> diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
>> index d809f731bfd1..831cefa088bc 100644
>> --- a/fs/f2fs/segment.c
>> +++ b/fs/f2fs/segment.c
>> @@ -287,6 +287,7 @@ void drop_inmem_pages_all(struct f2fs_sb_info *sbi)
>>  	spin_unlock(&sbi->inode_lock[ATOMIC_FILE]);
>>  
>>  	if (inode) {
>> +		set_inode_flag(inode, FI_ATOMIC_REVOKE_REQUEST);
>>  		drop_inmem_pages(inode);
>>  		iput(inode);
>>  	}
>> diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h
>> index 492ad0c86fa9..7702b054689c 100644
>> --- a/fs/f2fs/segment.h
>> +++ b/fs/f2fs/segment.h
>> @@ -215,6 +215,8 @@ struct segment_allocation {
>>  #define IS_DUMMY_WRITTEN_PAGE(page)			\
>>  		(page_private(page) == (unsigned long)DUMMY_WRITTEN_PAGE)
>>  
>> +#define MAX_SKIP_ATOMIC_COUNT			16
>> +
>>  struct inmem_pages {
>>  	struct list_head list;
>>  	struct page *page;
>> -- 
>> 2.15.0.55.gc2ece9dc4de6
> 
> .
>