On Tue, Apr 12, 2022 at 12:13:19AM +0000, Wei Yang wrote:
> To make node order in round-robin in the same distance group, we add a
> penalty to the first node we got in each round.
>
> To get a round-robin order in the same distance group, we don't need to
> decrease the penalty since:
>
> * find_next_best_node() always iterates node in the same order
> * distance matters more then penalty in find_next_best_node()
> * in nodes with the same distance, the first one would be picked up
>
> So it is fine to increase same penalty when we get the first node in the
> same distance group. Since we just increase a constance of 1 to node
> penalty, it is not necessary to multiply MAX_NODE_LOAD for preference.
>
> [vbabka@xxxxxxx: suggests to remove MAX_NODE_LOAD]
>
> Signed-off-by: Wei Yang <richard.weiyang@xxxxxxxxx>
> CC: Vlastimil Babka <vbabka@xxxxxxx>
> CC: David Hildenbrand <david@xxxxxxxxxx>
> CC: Oscar Salvador <osalvador@xxxxxxx>
Acked-by: Oscar Salvador <osalvador@xxxxxxx>
> ---
> v3: merge into a single patch
> v2: adjust constant penalty to 1
> ---
> mm/page_alloc.c | 9 +++------
> 1 file changed, 3 insertions(+), 6 deletions(-)
>
> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index 5d71b8dcb5f4..0334c06a0a47 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -6170,7 +6170,6 @@ int numa_zonelist_order_handler(struct ctl_table *table, int write,
> }
>
>
> -#define MAX_NODE_LOAD (nr_online_nodes)
> static int node_load[MAX_NUMNODES];
>
> /**
> @@ -6217,7 +6216,7 @@ int find_next_best_node(int node, nodemask_t *used_node_mask)
> val += PENALTY_FOR_NODE_WITH_CPUS;
>
> /* Slight preference for less loaded node */
> - val *= (MAX_NODE_LOAD*MAX_NUMNODES);
> + val *= MAX_NUMNODES;
> val += node_load[n];
>
> if (val < min_val) {
> @@ -6283,13 +6282,12 @@ static void build_thisnode_zonelists(pg_data_t *pgdat)
> static void build_zonelists(pg_data_t *pgdat)
> {
> static int node_order[MAX_NUMNODES];
> - int node, load, nr_nodes = 0;
> + int node, nr_nodes = 0;
> nodemask_t used_mask = NODE_MASK_NONE;
> int local_node, prev_node;
>
> /* NUMA-aware ordering of nodes */
> local_node = pgdat->node_id;
> - load = nr_online_nodes;
> prev_node = local_node;
>
> memset(node_order, 0, sizeof(node_order));
> @@ -6301,11 +6299,10 @@ static void build_zonelists(pg_data_t *pgdat)
> */
> if (node_distance(local_node, node) !=
> node_distance(local_node, prev_node))
> - node_load[node] += load;
> + node_load[node] += 1;
>
> node_order[nr_nodes++] = node;
> prev_node = node;
> - load--;
> }
>
> build_zonelists_in_node_order(pgdat, node_order, nr_nodes);
> --
> 2.33.1
>
>
--
Oscar Salvador
SUSE Labs
