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

[Joseph Qi]

On 3/10/26 6:24 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 each extent in a separate 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 removes the only call to ocfs2_assure_trans_credits(), which
> was introduced by commit be346c1a6eeb ("ocfs2: fix DIO failure due to
> insufficient transaction credits").
> 
> Finally, thanks to Jans for providing the bug fix prototype and suggestions.
> 
> Suggested-by: Jan Kara <jack@xxxxxxx>
> Signed-off-by: Heming Zhao <heming.zhao@xxxxxxxx>
> ---
>  fs/ocfs2/aops.c | 56 ++++++++++++++++++++-----------------------------
>  1 file changed, 23 insertions(+), 33 deletions(-)
> 
> diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
> index 09146b43d1f0..50b4d474b88c 100644
> --- a/fs/ocfs2/aops.c
> +++ b/fs/ocfs2/aops.c
> @@ -2294,18 +2294,6 @@ 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;
>  
> @@ -2326,23 +2314,18 @@ 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) {
> -		ret = ocfs2_assure_trans_credits(handle, credits);
> -		if (ret < 0) {
> +		handle = ocfs2_start_trans(osb, credits);
> +		if (IS_ERR(handle)) {
> +			ret = PTR_ERR(handle);
> +			mlog_errno(ret);
> +			break;
> +		}
> +		ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), di_bh,
> +					      OCFS2_JOURNAL_ACCESS_WRITE);
> +		if (ret) {
>  			mlog_errno(ret);
> +			ocfs2_commit_trans(osb, handle);
>  			break;
>  		}
>  		ret = ocfs2_mark_extent_written(inode, &et, handle,
> @@ -2351,19 +2334,26 @@ static int ocfs2_dio_end_io_write(struct inode *inode,
>  						meta_ac, &dealloc);
>  		if (ret < 0) {
>  			mlog_errno(ret);
> +			ocfs2_commit_trans(osb, handle);
>  			break;
>  		}
> +		ocfs2_commit_trans(osb, handle);
>  	}
>  
> -	if (end > i_size_read(inode)) {
> -		ret = ocfs2_set_inode_size(handle, inode, di_bh, end);

dw_orphaned is only set if it allocates new clusters, see
ocfs2_dio_get_block():

	if (ocfs2_clusters_for_bytes(inode->i_sb, pos + total_len) >
	    ocfs2_clusters_for_bytes(inode->i_sb, i_size_read(inode)) &&
	    !dwc->dw_orphaned) {
		...
		dwc->dw_orphaned = 1;
	}

So in case extending a file within an existing cluster, it leaves
dwc->dw_orphaned = 0. Then i_size won't be updated here and the written
data is lost.

Thanks,
Joseph

> +unlock:
> +	up_write(&oi->ip_alloc_sem);
> +
> +	/* everything looks good, let's start the cleanup and update i_size */
> +	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);
>  	}
> -commit:
> -	ocfs2_commit_trans(osb, handle);
> -unlock:
> -	up_write(&oi->ip_alloc_sem);
>  	ocfs2_inode_unlock(inode, 1);
>  	brelse(di_bh);
>  out: