diff mbox series

[13/14] maple_tree: Refine mas_preallocate() node calculations

Message ID 20230601021605.2823123-14-Liam.Howlett@oracle.com
State New
Headers
Series Reduce preallocations for maple tree |

Commit Message

Liam R. Howlett June 1, 2023, 2:16 a.m. UTC 
  Calculate the number of nodes based on the pending write action instead
of assuming the worst case.

This addresses a performance regression introduced in platforms that
have longer allocation timing.

Signed-off-by: Liam R. Howlett <Liam.Howlett@oracle.com>
---
 lib/maple_tree.c | 44 +++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 43 insertions(+), 1 deletion(-)

Comments

Peng Zhang June 2, 2023, 10:37 a.m. UTC | #1 
在 2023/6/1 10:16, Liam R. Howlett 写道:
> Calculate the number of nodes based on the pending write action instead
> of assuming the worst case.
> 
> This addresses a performance regression introduced in platforms that
> have longer allocation timing.
> 
> Signed-off-by: Liam R. Howlett <Liam.Howlett@oracle.com>
> ---
>   lib/maple_tree.c | 44 +++++++++++++++++++++++++++++++++++++++++++-
>   1 file changed, 43 insertions(+), 1 deletion(-)
> 
> diff --git a/lib/maple_tree.c b/lib/maple_tree.c
> index adf662bc413e..5ea211c3f186 100644
> --- a/lib/maple_tree.c
> +++ b/lib/maple_tree.c
> @@ -5541,9 +5541,51 @@ EXPORT_SYMBOL_GPL(mas_store_prealloc);
>    */
>   int mas_preallocate(struct ma_state *mas, void *entry, gfp_t gfp)
>   {
> +	MA_WR_STATE(wr_mas, mas, entry);
> +	unsigned char node_size;
> +	int request = 1;
If either mas_wr_append() or mas_wr_slot_store() succeeds,
or does a simple replacement, we don't need to make any allocations.
>   	int ret;
>   
> -	mas_node_count_gfp(mas, 1 + mas_mt_height(mas) * 3, gfp);
> +
> +	if (unlikely(!mas->index && mas->last == ULONG_MAX))
> +		goto ask_now;
> +
> +	mas_wr_store_setup(&wr_mas);
> +	wr_mas.content = mas_start(mas);
> +	/* Root expand */
> +	if (unlikely(mas_is_none(mas) || mas_is_ptr(mas)))
> +		goto ask_now;
> +
> +	if (unlikely(!mas_wr_walk(&wr_mas))) {
> +		/* Spanning store, use worst case for now */
> +		request = 1 + mas_mt_height(mas) * 3;
> +		goto ask_now;
> +	}
> +
> +	/* At this point, we are at the leaf node that needs to be altered. */
> +	/* Exact fit, no nodes needed. */
> +	if (wr_mas.r_min == mas->index && wr_mas.r_max == mas->last)
> +		return 0;
> +
> +	mas_wr_end_piv(&wr_mas);
> +	node_size = mas_wr_new_end(&wr_mas);
> +	if (node_size >= mt_slots[wr_mas.type]) {
> +		/* Split, worst case for now. */
> +		request = 1 + mas_mt_height(mas) * 2;
> +		goto ask_now;
> +	}
> +
> +	/* New root needs a singe node */
> +	if (unlikely(mte_is_root(mas->node)))
> +		goto ask_now;
> +
> +	/* Potential spanning rebalance collapsing a node, use worst-case */
> +	if (node_size  - 1 <= mt_min_slots[wr_mas.type])
> +		request = mas_mt_height(mas) * 2 - 1;
> +
> +	/* node store, slot store needs one node */
> +ask_now:
> +	mas_node_count_gfp(mas, request, gfp);
>   	mas->mas_flags |= MA_STATE_PREALLOC;
>   	if (likely(!mas_is_err(mas)))
>   		return 0;
Liam R. Howlett June 2, 2023, 6:53 p.m. UTC | #2 
* Peng Zhang <perlyzhang@gmail.com> [230602 06:37]:
> 
> 
> 在 2023/6/1 10:16, Liam R. Howlett 写道:
> > Calculate the number of nodes based on the pending write action instead
> > of assuming the worst case.
> > 
> > This addresses a performance regression introduced in platforms that
> > have longer allocation timing.
> > 
> > Signed-off-by: Liam R. Howlett <Liam.Howlett@oracle.com>
> > ---
> >   lib/maple_tree.c | 44 +++++++++++++++++++++++++++++++++++++++++++-
> >   1 file changed, 43 insertions(+), 1 deletion(-)
> > 
> > diff --git a/lib/maple_tree.c b/lib/maple_tree.c
> > index adf662bc413e..5ea211c3f186 100644
> > --- a/lib/maple_tree.c
> > +++ b/lib/maple_tree.c
> > @@ -5541,9 +5541,51 @@ EXPORT_SYMBOL_GPL(mas_store_prealloc);
> >    */
> >   int mas_preallocate(struct ma_state *mas, void *entry, gfp_t gfp)
> >   {
> > +	MA_WR_STATE(wr_mas, mas, entry);
> > +	unsigned char node_size;
> > +	int request = 1;
> If either mas_wr_append() or mas_wr_slot_store() succeeds,
> or does a simple replacement, we don't need to make any allocations.

Thanks for looking at this.

See below

> >   	int ret;
> > -	mas_node_count_gfp(mas, 1 + mas_mt_height(mas) * 3, gfp);
> > +
> > +	if (unlikely(!mas->index && mas->last == ULONG_MAX))
> > +		goto ask_now;
> > +
> > +	mas_wr_store_setup(&wr_mas);
> > +	wr_mas.content = mas_start(mas);
> > +	/* Root expand */
> > +	if (unlikely(mas_is_none(mas) || mas_is_ptr(mas)))
> > +		goto ask_now;
> > +
> > +	if (unlikely(!mas_wr_walk(&wr_mas))) {
> > +		/* Spanning store, use worst case for now */
> > +		request = 1 + mas_mt_height(mas) * 3;
> > +		goto ask_now;
> > +	}
> > +
> > +	/* At this point, we are at the leaf node that needs to be altered. */
> > +	/* Exact fit, no nodes needed. */
> > +	if (wr_mas.r_min == mas->index && wr_mas.r_max == mas->last)
> > +		return 0;

The exact fit (simple replacement) case is covered here.

> > +
> > +	mas_wr_end_piv(&wr_mas);
> > +	node_size = mas_wr_new_end(&wr_mas);

> > +	if (node_size >= mt_slots[wr_mas.type]) {
> > +		/* Split, worst case for now. */
> > +		request = 1 + mas_mt_height(mas) * 2;
> > +		goto ask_now;
> > +	}

I will look at adding the mas_wr_append() and mas_wr_slot_store()
checks as well.  I suspect it will need to live around here.

I'm debating a function that returns the type of store and saving it in
mas (wr_mas does not live beyond this function).  The mas store type
could be cleared unless mas_store_prealloc() is used.  This would avoid
duplicating this work on the actual write operation.

> > +
> > +	/* New root needs a singe node */
> > +	if (unlikely(mte_is_root(mas->node)))
> > +		goto ask_now;
> > +
> > +	/* Potential spanning rebalance collapsing a node, use worst-case */
> > +	if (node_size  - 1 <= mt_min_slots[wr_mas.type])
> > +		request = mas_mt_height(mas) * 2 - 1;
> > +
> > +	/* node store, slot store needs one node */
> > +ask_now:
> > +	mas_node_count_gfp(mas, request, gfp);
> >   	mas->mas_flags |= MA_STATE_PREALLOC;
> >   	if (likely(!mas_is_err(mas)))
> >   		return 0;
diff mbox series

Patch

diff --git a/lib/maple_tree.c b/lib/maple_tree.c
index adf662bc413e..5ea211c3f186 100644
--- a/lib/maple_tree.c
+++ b/lib/maple_tree.c
@@ -5541,9 +5541,51 @@  EXPORT_SYMBOL_GPL(mas_store_prealloc);
  */
 int mas_preallocate(struct ma_state *mas, void *entry, gfp_t gfp)
 {
+	MA_WR_STATE(wr_mas, mas, entry);
+	unsigned char node_size;
+	int request = 1;
 	int ret;
 
-	mas_node_count_gfp(mas, 1 + mas_mt_height(mas) * 3, gfp);
+
+	if (unlikely(!mas->index && mas->last == ULONG_MAX))
+		goto ask_now;
+
+	mas_wr_store_setup(&wr_mas);
+	wr_mas.content = mas_start(mas);
+	/* Root expand */
+	if (unlikely(mas_is_none(mas) || mas_is_ptr(mas)))
+		goto ask_now;
+
+	if (unlikely(!mas_wr_walk(&wr_mas))) {
+		/* Spanning store, use worst case for now */
+		request = 1 + mas_mt_height(mas) * 3;
+		goto ask_now;
+	}
+
+	/* At this point, we are at the leaf node that needs to be altered. */
+	/* Exact fit, no nodes needed. */
+	if (wr_mas.r_min == mas->index && wr_mas.r_max == mas->last)
+		return 0;
+
+	mas_wr_end_piv(&wr_mas);
+	node_size = mas_wr_new_end(&wr_mas);
+	if (node_size >= mt_slots[wr_mas.type]) {
+		/* Split, worst case for now. */
+		request = 1 + mas_mt_height(mas) * 2;
+		goto ask_now;
+	}
+
+	/* New root needs a singe node */
+	if (unlikely(mte_is_root(mas->node)))
+		goto ask_now;
+
+	/* Potential spanning rebalance collapsing a node, use worst-case */
+	if (node_size  - 1 <= mt_min_slots[wr_mas.type])
+		request = mas_mt_height(mas) * 2 - 1;
+
+	/* node store, slot store needs one node */
+ask_now:
+	mas_node_count_gfp(mas, request, gfp);
 	mas->mas_flags |= MA_STATE_PREALLOC;
 	if (likely(!mas_is_err(mas)))
 		return 0;