提交 e176579e 编写于 作者: D Dave Chinner 提交者: Alex Elder

xfs: lockless per-ag lookups

When we start taking a reference to the per-ag for every cached
buffer in the system, kernel lockstat profiling on an 8-way create
workload shows the mp->m_perag_lock has higher acquisition rates
than the inode lock and has significantly more contention. That is,
it becomes the highest contended lock in the system.

The perag lookup is trivial to convert to lock-less RCU lookups
because perag structures never go away. Hence the only thing we need
to protect against is tree structure changes during a grow. This can
be done simply by replacing the locking in xfs_perag_get() with RCU
read locking. This removes the mp->m_perag_lock completely from this
path.
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NAlex Elder <aelder@sgi.com>
上级 bd32d25a
......@@ -150,17 +150,17 @@ xfs_inode_ag_iter_next_pag(
int found;
int ref;
spin_lock(&mp->m_perag_lock);
rcu_read_lock();
found = radix_tree_gang_lookup_tag(&mp->m_perag_tree,
(void **)&pag, *first, 1, tag);
if (found <= 0) {
spin_unlock(&mp->m_perag_lock);
rcu_read_unlock();
return NULL;
}
*first = pag->pag_agno + 1;
/* open coded pag reference increment */
ref = atomic_inc_return(&pag->pag_ref);
spin_unlock(&mp->m_perag_lock);
rcu_read_unlock();
trace_xfs_perag_get_reclaim(mp, pag->pag_agno, ref, _RET_IP_);
} else {
pag = xfs_perag_get(mp, *first);
......
......@@ -230,6 +230,9 @@ typedef struct xfs_perag {
rwlock_t pag_ici_lock; /* incore inode lock */
struct radix_tree_root pag_ici_root; /* incore inode cache root */
int pag_ici_reclaimable; /* reclaimable inodes */
/* for rcu-safe freeing */
struct rcu_head rcu_head;
#endif
int pagb_count; /* pagb slots in use */
} xfs_perag_t;
......
......@@ -199,6 +199,8 @@ xfs_uuid_unmount(
/*
* Reference counting access wrappers to the perag structures.
* Because we never free per-ag structures, the only thing we
* have to protect against changes is the tree structure itself.
*/
struct xfs_perag *
xfs_perag_get(struct xfs_mount *mp, xfs_agnumber_t agno)
......@@ -206,13 +208,13 @@ xfs_perag_get(struct xfs_mount *mp, xfs_agnumber_t agno)
struct xfs_perag *pag;
int ref = 0;
spin_lock(&mp->m_perag_lock);
rcu_read_lock();
pag = radix_tree_lookup(&mp->m_perag_tree, agno);
if (pag) {
ASSERT(atomic_read(&pag->pag_ref) >= 0);
ref = atomic_inc_return(&pag->pag_ref);
}
spin_unlock(&mp->m_perag_lock);
rcu_read_unlock();
trace_xfs_perag_get(mp, agno, ref, _RET_IP_);
return pag;
}
......@@ -227,10 +229,18 @@ xfs_perag_put(struct xfs_perag *pag)
trace_xfs_perag_put(pag->pag_mount, pag->pag_agno, ref, _RET_IP_);
}
STATIC void
__xfs_free_perag(
struct rcu_head *head)
{
struct xfs_perag *pag = container_of(head, struct xfs_perag, rcu_head);
ASSERT(atomic_read(&pag->pag_ref) == 0);
kmem_free(pag);
}
/*
* Free up the resources associated with a mount structure. Assume that
* the structure was initially zeroed, so we can tell which fields got
* initialized.
* Free up the per-ag resources associated with the mount structure.
*/
STATIC void
xfs_free_perag(
......@@ -242,10 +252,9 @@ xfs_free_perag(
for (agno = 0; agno < mp->m_sb.sb_agcount; agno++) {
spin_lock(&mp->m_perag_lock);
pag = radix_tree_delete(&mp->m_perag_tree, agno);
ASSERT(pag);
ASSERT(atomic_read(&pag->pag_ref) == 0);
spin_unlock(&mp->m_perag_lock);
kmem_free(pag);
ASSERT(pag);
call_rcu(&pag->rcu_head, __xfs_free_perag);
}
}
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册