Re: [PATCH v5 1/1] ocfs2: split transactions in dio completion to avoid credit exhaustion

[Joseph Qi]

On 3/27/26 2:36 PM, Heming Zhao wrote:
> During ocfs2 dio operations, JBD2 may report warnings via following call trace:
> ocfs2_dio_end_io_write
>  ocfs2_mark_extent_written
>   ocfs2_change_extent_flag
>    ocfs2_split_extent
>     ocfs2_try_to_merge_extent
>      ocfs2_extend_rotate_transaction
>       ocfs2_extend_trans
>        jbd2__journal_restart
>         start_this_handle
>          output: JBD2: kworker/6:2 wants too many credits credits:5450 rsv_credits:0 max:5449
> 
> To prevent exceeding the credits limit, modify ocfs2_dio_end_io_write() to
> handle extents in a batch of transaction.
> 
> Additionally, relocate ocfs2_del_inode_from_orphan(). The orphan inode should
> only be removed from the orphan list after the extent tree update is complete.
> This ensures that if a crash occurs in the middle of extent tree updates, we
> won't leave stale blocks beyond EOF.
> 
> This patch also changes the logic for updating the inode size and removing
> orphan, making it similar to ext4_dio_write_end_io(). Both operations are
> performed only when everything looks good.
> 
> Finally, thanks to Jans and Joseph for providing the bug fix prototype and
> suggestions.
> 
> Suggested-by: Jan Kara <jack@xxxxxxx>
> Suggested-by: Joseph Qi <joseph.qi@xxxxxxxxxxxxxxxxx>
> Reviewed-by: Jan Kara <jack@xxxxxxx>
> Signed-off-by: Heming Zhao <heming.zhao@xxxxxxxx>
> ---
>  fs/ocfs2/aops.c | 63 +++++++++++++++++++++++++++----------------------
>  1 file changed, 35 insertions(+), 28 deletions(-)
> 
> diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
> index 09146b43d1f0..a542cd0a6f75 100644
> --- a/fs/ocfs2/aops.c
> +++ b/fs/ocfs2/aops.c
> @@ -37,6 +37,8 @@
>  #include "namei.h"
>  #include "sysfile.h"
>  
> +#define OCFS2_DIO_MARK_EXTENT_BATCH 200
> +
>  static int ocfs2_symlink_get_block(struct inode *inode, sector_t iblock,
>  				   struct buffer_head *bh_result, int create)
>  {
> @@ -2277,7 +2279,7 @@ static int ocfs2_dio_end_io_write(struct inode *inode,
>  	struct ocfs2_alloc_context *meta_ac = NULL;
>  	handle_t *handle = NULL;
>  	loff_t end = offset + bytes;
> -	int ret = 0, credits = 0;
> +	int ret = 0, credits = 0, batch = 0;
>  
>  	ocfs2_init_dealloc_ctxt(&dealloc);
>  
> @@ -2294,18 +2296,6 @@ static int ocfs2_dio_end_io_write(struct inode *inode,
>  		goto out;
>  	}
>  
> -	/* Delete orphan before acquire i_rwsem. */
> -	if (dwc->dw_orphaned) {
> -		BUG_ON(dwc->dw_writer_pid != task_pid_nr(current));
> -
> -		end = end > i_size_read(inode) ? end : 0;
> -
> -		ret = ocfs2_del_inode_from_orphan(osb, inode, di_bh,
> -				!!end, end);
> -		if (ret < 0)
> -			mlog_errno(ret);
> -	}
> -
>  	down_write(&oi->ip_alloc_sem);
>  	di = (struct ocfs2_dinode *)di_bh->b_data;
>  
> @@ -2326,24 +2316,25 @@ static int ocfs2_dio_end_io_write(struct inode *inode,
>  
>  	credits = ocfs2_calc_extend_credits(inode->i_sb, &di->id2.i_list);
>  
> -	handle = ocfs2_start_trans(osb, credits);
> -	if (IS_ERR(handle)) {
> -		ret = PTR_ERR(handle);
> -		mlog_errno(ret);
> -		goto unlock;
> -	}
> -	ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), di_bh,
> -				      OCFS2_JOURNAL_ACCESS_WRITE);
> -	if (ret) {
> -		mlog_errno(ret);
> -		goto commit;
> -	}
> -
>  	list_for_each_entry(ue, &dwc->dw_zero_list, ue_node) {
> +		if (!handle) {
> +			handle = ocfs2_start_trans(osb, credits);
> +			if (IS_ERR(handle)) {
> +				ret = PTR_ERR(handle);
> +				mlog_errno(ret);
> +				goto unlock;
> +			}
> +			ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), di_bh,
> +					OCFS2_JOURNAL_ACCESS_WRITE);
> +			if (ret) {
> +				mlog_errno(ret);
> +				goto commit;
> +			}
> +		}
>  		ret = ocfs2_assure_trans_credits(handle, credits);
>  		if (ret < 0) {
>  			mlog_errno(ret);
> -			break;
> +			goto commit;
>  		}
>  		ret = ocfs2_mark_extent_written(inode, &et, handle,
>  						ue->ue_cpos, 1,
> @@ -2351,7 +2342,13 @@ static int ocfs2_dio_end_io_write(struct inode *inode,
>  						meta_ac, &dealloc);
>  		if (ret < 0) {
>  			mlog_errno(ret);
> -			break;
> +			goto commit;
> +		}
> +
> +		if (++batch == OCFS2_DIO_MARK_EXTENT_BATCH) {
> +			ocfs2_commit_trans(osb, handle);
> +			handle = NULL;
> +			batch = 0;
>  		}
>  	}
>  
> @@ -2360,10 +2357,20 @@ static int ocfs2_dio_end_io_write(struct inode *inode,
>  		if (ret < 0)
>  			mlog_errno(ret);
>  	}
> +
>  commit:
>  	ocfs2_commit_trans(osb, handle);

We have to check 'handle' here to prevent NULL pointer dereference. e.g.
rightly after OCFS2_DIO_MARK_EXTENT_BATCH round.

And you've missed ocfs2_start_trans() and ocfs2_journal_access_di()
before ocfs2_set_inode_size().

Thanks,
Joseph


>  unlock:
>  	up_write(&oi->ip_alloc_sem);
> +
> +	/* everything looks good, let's start the cleanup */
> +	if (!ret && dwc->dw_orphaned) {
> +		BUG_ON(dwc->dw_writer_pid != task_pid_nr(current));
> +
> +		ret = ocfs2_del_inode_from_orphan(osb, inode, di_bh, 0, 0);
> +		if (ret < 0)
> +			mlog_errno(ret);
> +	}
>  	ocfs2_inode_unlock(inode, 1);
>  	brelse(di_bh);
>  out: