Commit 0e8e2c63 authored by Dave Chinner's avatar Dave Chinner Committed by Darrick J. Wong
Browse files

xfs: allow multiple reclaimers per AG 



Inode reclaim will still throttle direct reclaim on the per-ag
reclaim locks. This is no longer necessary as reclaim can run
non-blocking now. Hence we can remove these locks so that we don't
arbitrarily block reclaimers just because there are more direct
reclaimers than there are AGs.

This can result in multiple reclaimers working on the same range of
an AG, but this doesn't cause any apparent issues. Optimising the
spread of concurrent reclaimers for best efficiency can be done in a
future patchset.

Signed-off-by: default avatarDave Chinner <dchinner@redhat.com>
Reviewed-by: default avatarDarrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: default avatarBrian Foster <bfoster@redhat.com>
Signed-off-by: default avatarDarrick J. Wong <darrick.wong@oracle.com>
parent 617825fe

fs/xfs/xfs_icache.c

+12 −19
Original line number Diff line number Diff line
@@ -1211,12 +1211,9 @@ xfs_reclaim_inodes_ag( 
	int			*nr_to_scan)

{

	struct xfs_perag	*pag;

	xfs_agnumber_t		ag;

	int			trylock = flags & SYNC_TRYLOCK;

	int			skipped;

	xfs_agnumber_t		ag = 0;

	int			skipped = 0;



	ag = 0;

	skipped = 0;

	while ((pag = xfs_perag_get_tag(mp, ag, XFS_ICI_RECLAIM_TAG))) {

		unsigned long	first_index = 0;

		int		done = 0;
@@ -1224,15 +1221,13 @@ xfs_reclaim_inodes_ag( 


		ag = pag->pag_agno + 1;



		if (trylock) {

			if (!mutex_trylock(&pag->pag_ici_reclaim_lock)) {

		/*

		 * If the cursor is not zero, we haven't scanned the whole AG

		 * so we might have skipped inodes here.

		 */

		first_index = READ_ONCE(pag->pag_ici_reclaim_cursor);

		if (first_index)

			skipped++;

				xfs_perag_put(pag);

				continue;

			}

			first_index = pag->pag_ici_reclaim_cursor;

		} else

			mutex_lock(&pag->pag_ici_reclaim_lock);



		do {

			struct xfs_inode *batch[XFS_LOOKUP_BATCH];
@@ -1298,11 +1293,9 @@ xfs_reclaim_inodes_ag( 


		} while (nr_found && !done && *nr_to_scan > 0);



		if (trylock && !done)

			pag->pag_ici_reclaim_cursor = first_index;

		else

			pag->pag_ici_reclaim_cursor = 0;

		mutex_unlock(&pag->pag_ici_reclaim_lock);

		if (done)

			first_index = 0;

		WRITE_ONCE(pag->pag_ici_reclaim_cursor, first_index);

		xfs_perag_put(pag);

	}

	return skipped;

fs/xfs/xfs_mount.c

+0 −4
Original line number Diff line number Diff line
@@ -148,7 +148,6 @@ xfs_free_perag( 
		ASSERT(atomic_read(&pag->pag_ref) == 0);

		xfs_iunlink_destroy(pag);

		xfs_buf_hash_destroy(pag);

		mutex_destroy(&pag->pag_ici_reclaim_lock);

		call_rcu(&pag->rcu_head, __xfs_free_perag);

	}

}
@@ -200,7 +199,6 @@ xfs_initialize_perag( 
		pag->pag_agno = index;

		pag->pag_mount = mp;

		spin_lock_init(&pag->pag_ici_lock);

		mutex_init(&pag->pag_ici_reclaim_lock);

		INIT_RADIX_TREE(&pag->pag_ici_root, GFP_ATOMIC);

		if (xfs_buf_hash_init(pag))

			goto out_free_pag;
@@ -242,7 +240,6 @@ xfs_initialize_perag( 
out_hash_destroy:

	xfs_buf_hash_destroy(pag);

out_free_pag:

	mutex_destroy(&pag->pag_ici_reclaim_lock);

	kmem_free(pag);

out_unwind_new_pags:

	/* unwind any prior newly initialized pags */
@@ -252,7 +249,6 @@ xfs_initialize_perag( 
			break;

		xfs_buf_hash_destroy(pag);

		xfs_iunlink_destroy(pag);

		mutex_destroy(&pag->pag_ici_reclaim_lock);

		kmem_free(pag);

	}

	return error;

fs/xfs/xfs_mount.h

+0 −1
Original line number Diff line number Diff line
@@ -354,7 +354,6 @@ typedef struct xfs_perag { 
	spinlock_t	pag_ici_lock;	/* incore inode cache lock */

	struct radix_tree_root pag_ici_root;	/* incore inode cache root */

	int		pag_ici_reclaimable;	/* reclaimable inodes */

	struct mutex	pag_ici_reclaim_lock;	/* serialisation point */

	unsigned long	pag_ici_reclaim_cursor;	/* reclaim restart point */



	/* buffer cache index */