Re: [RFC PATCH 2/4] sched/fair: Make tg->load_avg per node
From: Peter Zijlstra
Date: Wed Jul 19 2023 - 07:54:34 EST
On Tue, Jul 18, 2023 at 09:41:18PM +0800, Aaron Lu wrote:
> +#if defined(CONFIG_FAIR_GROUP_SCHED) && defined(CONFIG_SMP)
> +static inline long tg_load_avg(struct task_group *tg)
> +{
> + long load_avg = 0;
> + int i;
> +
> + /*
> + * The only path that can give us a root_task_group
> + * here is from print_cfs_rq() thus unlikely.
> + */
> + if (unlikely(tg == &root_task_group))
> + return 0;
> +
> + for_each_node(i)
> + load_avg += atomic_long_read(&tg->node_info[i]->load_avg);
> +
> + return load_avg;
> +}
> +#endif
So I was working on something else numa and noticed that for_each_node()
(and most of the nodemask stuff) is quite moronic, afaict we should do
something like the below.
I now see Mike added the nr_node_ids thing fairly recent, but given
distros have NODES_SHIFT=10 and actual machines typically only have <=4
nodes, this would save a factor of 256 scanning.
Specifically, your for_each_node() would scan the full 1024 bit bitmap
looking for more bits that would never be there.
---
diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h
index 8d07116caaf1..c23c0889b8cf 100644
--- a/include/linux/nodemask.h
+++ b/include/linux/nodemask.h
@@ -109,7 +109,7 @@ extern nodemask_t _unused_nodemask_arg_;
__nodemask_pr_bits(maskp)
static inline unsigned int __nodemask_pr_numnodes(const nodemask_t *m)
{
- return m ? MAX_NUMNODES : 0;
+ return m ? nr_node_ids : 0;
}
static inline const unsigned long *__nodemask_pr_bits(const nodemask_t *m)
{
@@ -137,13 +137,13 @@ static inline void __node_clear(int node, volatile nodemask_t *dstp)
clear_bit(node, dstp->bits);
}
-#define nodes_setall(dst) __nodes_setall(&(dst), MAX_NUMNODES)
+#define nodes_setall(dst) __nodes_setall(&(dst), nr_node_ids)
static inline void __nodes_setall(nodemask_t *dstp, unsigned int nbits)
{
bitmap_fill(dstp->bits, nbits);
}
-#define nodes_clear(dst) __nodes_clear(&(dst), MAX_NUMNODES)
+#define nodes_clear(dst) __nodes_clear(&(dst), nr_node_ids)
static inline void __nodes_clear(nodemask_t *dstp, unsigned int nbits)
{
bitmap_zero(dstp->bits, nbits);
@@ -160,7 +160,7 @@ static inline bool __node_test_and_set(int node, nodemask_t *addr)
}
#define nodes_and(dst, src1, src2) \
- __nodes_and(&(dst), &(src1), &(src2), MAX_NUMNODES)
+ __nodes_and(&(dst), &(src1), &(src2), nr_node_ids)
static inline void __nodes_and(nodemask_t *dstp, const nodemask_t *src1p,
const nodemask_t *src2p, unsigned int nbits)
{
@@ -168,7 +168,7 @@ static inline void __nodes_and(nodemask_t *dstp, const nodemask_t *src1p,
}
#define nodes_or(dst, src1, src2) \
- __nodes_or(&(dst), &(src1), &(src2), MAX_NUMNODES)
+ __nodes_or(&(dst), &(src1), &(src2), nr_node_ids)
static inline void __nodes_or(nodemask_t *dstp, const nodemask_t *src1p,
const nodemask_t *src2p, unsigned int nbits)
{
@@ -176,7 +176,7 @@ static inline void __nodes_or(nodemask_t *dstp, const nodemask_t *src1p,
}
#define nodes_xor(dst, src1, src2) \
- __nodes_xor(&(dst), &(src1), &(src2), MAX_NUMNODES)
+ __nodes_xor(&(dst), &(src1), &(src2), nr_node_ids)
static inline void __nodes_xor(nodemask_t *dstp, const nodemask_t *src1p,
const nodemask_t *src2p, unsigned int nbits)
{
@@ -184,7 +184,7 @@ static inline void __nodes_xor(nodemask_t *dstp, const nodemask_t *src1p,
}
#define nodes_andnot(dst, src1, src2) \
- __nodes_andnot(&(dst), &(src1), &(src2), MAX_NUMNODES)
+ __nodes_andnot(&(dst), &(src1), &(src2), nr_node_ids)
static inline void __nodes_andnot(nodemask_t *dstp, const nodemask_t *src1p,
const nodemask_t *src2p, unsigned int nbits)
{
@@ -192,7 +192,7 @@ static inline void __nodes_andnot(nodemask_t *dstp, const nodemask_t *src1p,
}
#define nodes_complement(dst, src) \
- __nodes_complement(&(dst), &(src), MAX_NUMNODES)
+ __nodes_complement(&(dst), &(src), nr_node_ids)
static inline void __nodes_complement(nodemask_t *dstp,
const nodemask_t *srcp, unsigned int nbits)
{
@@ -200,7 +200,7 @@ static inline void __nodes_complement(nodemask_t *dstp,
}
#define nodes_equal(src1, src2) \
- __nodes_equal(&(src1), &(src2), MAX_NUMNODES)
+ __nodes_equal(&(src1), &(src2), nr_node_ids)
static inline bool __nodes_equal(const nodemask_t *src1p,
const nodemask_t *src2p, unsigned int nbits)
{
@@ -208,7 +208,7 @@ static inline bool __nodes_equal(const nodemask_t *src1p,
}
#define nodes_intersects(src1, src2) \
- __nodes_intersects(&(src1), &(src2), MAX_NUMNODES)
+ __nodes_intersects(&(src1), &(src2), nr_node_ids)
static inline bool __nodes_intersects(const nodemask_t *src1p,
const nodemask_t *src2p, unsigned int nbits)
{
@@ -216,33 +216,33 @@ static inline bool __nodes_intersects(const nodemask_t *src1p,
}
#define nodes_subset(src1, src2) \
- __nodes_subset(&(src1), &(src2), MAX_NUMNODES)
+ __nodes_subset(&(src1), &(src2), nr_node_ids)
static inline bool __nodes_subset(const nodemask_t *src1p,
const nodemask_t *src2p, unsigned int nbits)
{
return bitmap_subset(src1p->bits, src2p->bits, nbits);
}
-#define nodes_empty(src) __nodes_empty(&(src), MAX_NUMNODES)
+#define nodes_empty(src) __nodes_empty(&(src), nr_node_ids)
static inline bool __nodes_empty(const nodemask_t *srcp, unsigned int nbits)
{
return bitmap_empty(srcp->bits, nbits);
}
-#define nodes_full(nodemask) __nodes_full(&(nodemask), MAX_NUMNODES)
+#define nodes_full(nodemask) __nodes_full(&(nodemask), nr_node_ids)
static inline bool __nodes_full(const nodemask_t *srcp, unsigned int nbits)
{
return bitmap_full(srcp->bits, nbits);
}
-#define nodes_weight(nodemask) __nodes_weight(&(nodemask), MAX_NUMNODES)
+#define nodes_weight(nodemask) __nodes_weight(&(nodemask), nr_node_ids)
static inline int __nodes_weight(const nodemask_t *srcp, unsigned int nbits)
{
return bitmap_weight(srcp->bits, nbits);
}
#define nodes_shift_right(dst, src, n) \
- __nodes_shift_right(&(dst), &(src), (n), MAX_NUMNODES)
+ __nodes_shift_right(&(dst), &(src), (n), nr_node_ids)
static inline void __nodes_shift_right(nodemask_t *dstp,
const nodemask_t *srcp, int n, int nbits)
{
@@ -250,7 +250,7 @@ static inline void __nodes_shift_right(nodemask_t *dstp,
}
#define nodes_shift_left(dst, src, n) \
- __nodes_shift_left(&(dst), &(src), (n), MAX_NUMNODES)
+ __nodes_shift_left(&(dst), &(src), (n), nr_node_ids)
static inline void __nodes_shift_left(nodemask_t *dstp,
const nodemask_t *srcp, int n, int nbits)
{
@@ -385,7 +385,7 @@ static inline void __nodes_fold(nodemask_t *dstp, const nodemask_t *origp,
#if MAX_NUMNODES > 1
#define for_each_node_mask(node, mask) \
for ((node) = first_node(mask); \
- (node) < MAX_NUMNODES; \
+ (node) < nr_node_ids; \
(node) = next_node((node), (mask)))
#else /* MAX_NUMNODES == 1 */
#define for_each_node_mask(node, mask) \