Switch cpumask_local_spread() to use newly added sched_numa_find_nth_cpu(),
which takes into account distances to each node in the system.
For the following NUMA configuration:
root@debian:~# numactl -H
available: 4 nodes (0-3)
node 0 cpus: 0 1 2 3
node 0 size: 3869 MB
node 0 free: 3740 MB
node 1 cpus: 4 5
node 1 size: 1969 MB
node 1 free: 1937 MB
node 2 cpus: 6 7
node 2 size: 1967 MB
node 2 free: 1873 MB
node 3 cpus: 8 9 10 11 12 13 14 15
node 3 size: 7842 MB
node 3 free: 7723 MB
node distances:
node 0 1 2 3
0: 10 50 30 70
1: 50 10 70 30
2: 30 70 10 50
3: 70 30 50 10
The new cpumask_local_spread() traverses cpus for each node like this:
node 0: 0 1 2 3 6 7 4 5 8 9 10 11 12 13 14 15
node 1: 4 5 8 9 10 11 12 13 14 15 0 1 2 3 6 7
node 2: 6 7 0 1 2 3 8 9 10 11 12 13 14 15 4 5
node 3: 8 9 10 11 12 13 14 15 4 5 6 7 0 1 2 3
Signed-off-by: Yury Norov <yury.norov@xxxxxxxxx>
---
lib/cpumask.c | 12 ++----------
1 file changed, 2 insertions(+), 10 deletions(-)
diff --git a/lib/cpumask.c b/lib/cpumask.c
index c7c392514fd3..255974cd6734 100644
--- a/lib/cpumask.c
+++ b/lib/cpumask.c
@@ -110,7 +110,7 @@ void __init free_bootmem_cpumask_var(cpumask_var_t mask)
#endif
/**
- * cpumask_local_spread - select the i'th cpu with local numa cpu's first
+ * cpumask_local_spread - select the i'th cpu based on NUMA distances
* @i: index number
* @node: local numa_node
*
@@ -132,15 +132,7 @@ unsigned int cpumask_local_spread(unsigned int i, int node)
if (cpu < nr_cpu_ids)
return cpu;
} else {
- /* NUMA first. */
- cpu = cpumask_nth_and(i, cpu_online_mask, cpumask_of_node(node));
- if (cpu < nr_cpu_ids)
- return cpu;
-
- i -= cpumask_weight_and(cpu_online_mask, cpumask_of_node(node));
-
- /* Skip NUMA nodes, done above. */
- cpu = cpumask_nth_andnot(i, cpu_online_mask, cpumask_of_node(node));
+ cpu = sched_numa_find_nth_cpu(cpu_online_mask, i, node);
if (cpu < nr_cpu_ids)
return cpu;
}
--
2.34.1
