Re: [PATCH 1/2] xfs: trylock underlying buffer on dquot flush

[Brian Foster <bfoster@redhat.com>]

On Fri, Mar 27, 2020 at 08:45:28AM -0700, Darrick J. Wong wrote:
> On Thu, Mar 26, 2020 at 09:17:02AM -0400, Brian Foster wrote:
> > A dquot flush currently blocks on the buffer lock for the underlying
> > dquot buffer. In turn, this causes xfsaild to block rather than
> > continue processing other items in the meantime. Update
> > xfs_qm_dqflush() to trylock the buffer, similar to how inode buffers
> > are handled, and return -EAGAIN if the lock fails. Fix up any
> > callers that don't currently handle the error properly.
> > 
> > Signed-off-by: Brian Foster <bfoster@redhat.com>
> 
> Is xfs_qm_dquot_isolate returning LRU_RETRY an acceptable resolution (as
> opposed to, say, LRU_SKIP) for xfs_qm_dqflush returning -EAGAIN?
> 

Hmm.. this is reclaim so I suppose LRU_SKIP would be more appropriate
than retry (along with more consistent with the other trylock failures
in that function). Ok with something like the following?

@@ -461,7 +461,11 @@ xfs_qm_dquot_isolate(
 		spin_unlock(lru_lock);
 
 		error = xfs_qm_dqflush(dqp, &bp);
-		if (error)
+		if (error == -EAGAIN) {
+			xfs_dqunlock(dqp);
+			spin_lock(lru_lock);
+			goto out_miss_busy;
+		} else if (error)
 			goto out_unlock_dirty;
 
 		xfs_buf_delwri_queue(bp, &isol->buffers);

Brian

> --D
> 
> > ---
> >  fs/xfs/xfs_dquot.c      |  6 +++---
> >  fs/xfs/xfs_dquot_item.c |  3 ++-
> >  fs/xfs/xfs_qm.c         | 14 +++++++++-----
> >  3 files changed, 14 insertions(+), 9 deletions(-)
> > 
> > diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
> > index 711376ca269f..af2c8e5ceea0 100644
> > --- a/fs/xfs/xfs_dquot.c
> > +++ b/fs/xfs/xfs_dquot.c
> > @@ -1105,8 +1105,8 @@ xfs_qm_dqflush(
> >  	 * Get the buffer containing the on-disk dquot
> >  	 */
> >  	error = xfs_trans_read_buf(mp, NULL, mp->m_ddev_targp, dqp->q_blkno,
> > -				   mp->m_quotainfo->qi_dqchunklen, 0, &bp,
> > -				   &xfs_dquot_buf_ops);
> > +				   mp->m_quotainfo->qi_dqchunklen, XBF_TRYLOCK,
> > +				   &bp, &xfs_dquot_buf_ops);
> >  	if (error)
> >  		goto out_unlock;
> >  
> > @@ -1177,7 +1177,7 @@ xfs_qm_dqflush(
> >  
> >  out_unlock:
> >  	xfs_dqfunlock(dqp);
> > -	return -EIO;
> > +	return error;
> >  }
> >  
> >  /*
> > diff --git a/fs/xfs/xfs_dquot_item.c b/fs/xfs/xfs_dquot_item.c
> > index cf65e2e43c6e..baad1748d0d1 100644
> > --- a/fs/xfs/xfs_dquot_item.c
> > +++ b/fs/xfs/xfs_dquot_item.c
> > @@ -189,7 +189,8 @@ xfs_qm_dquot_logitem_push(
> >  		if (!xfs_buf_delwri_queue(bp, buffer_list))
> >  			rval = XFS_ITEM_FLUSHING;
> >  		xfs_buf_relse(bp);
> > -	}
> > +	} else if (error == -EAGAIN)
> > +		rval = XFS_ITEM_LOCKED;
> >  
> >  	spin_lock(&lip->li_ailp->ail_lock);
> >  out_unlock:
> > diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
> > index de1d2c606c14..68c778d25c48 100644
> > --- a/fs/xfs/xfs_qm.c
> > +++ b/fs/xfs/xfs_qm.c
> > @@ -121,12 +121,11 @@ xfs_qm_dqpurge(
> >  {
> >  	struct xfs_mount	*mp = dqp->q_mount;
> >  	struct xfs_quotainfo	*qi = mp->m_quotainfo;
> > +	int			error = -EAGAIN;
> >  
> >  	xfs_dqlock(dqp);
> > -	if ((dqp->dq_flags & XFS_DQ_FREEING) || dqp->q_nrefs != 0) {
> > -		xfs_dqunlock(dqp);
> > -		return -EAGAIN;
> > -	}
> > +	if ((dqp->dq_flags & XFS_DQ_FREEING) || dqp->q_nrefs != 0)
> > +		goto out_unlock;
> >  
> >  	dqp->dq_flags |= XFS_DQ_FREEING;
> >  
> > @@ -139,7 +138,6 @@ xfs_qm_dqpurge(
> >  	 */
> >  	if (XFS_DQ_IS_DIRTY(dqp)) {
> >  		struct xfs_buf	*bp = NULL;
> > -		int		error;
> >  
> >  		/*
> >  		 * We don't care about getting disk errors here. We need
> > @@ -149,6 +147,8 @@ xfs_qm_dqpurge(
> >  		if (!error) {
> >  			error = xfs_bwrite(bp);
> >  			xfs_buf_relse(bp);
> > +		} else if (error == -EAGAIN) {
> > +			goto out_unlock;
> >  		}
> >  		xfs_dqflock(dqp);
> >  	}
> > @@ -174,6 +174,10 @@ xfs_qm_dqpurge(
> >  
> >  	xfs_qm_dqdestroy(dqp);
> >  	return 0;
> > +
> > +out_unlock:
> > +	xfs_dqunlock(dqp);
> > +	return error;
> >  }
> >  
> >  /*
> > -- 
> > 2.21.1
> > 
>