Commit 37931324 authored by Wei Yang's avatar Wei Yang Committed by akpm

mm/page_alloc: adding same penalty is enough to get round-robin order

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.

[richard.weiyang@gmail.com: remove remove MAX_NODE_LOAD, per Vlastimil]
  Link: https://lkml.kernel.org/r/20220412001319.7462-1-richard.weiyang@gmail.com
Link: https://lkml.kernel.org/r/20220123013537.20491-1-richard.weiyang@gmail.comSigned-off-by: default avatarWei Yang <richard.weiyang@gmail.com>
Signed-off-by: default avatarWei Yang <richard.weiyang@gmail.com>
Acked-by: default avatarVlastimil Babka <vbabka@suse.cz>
Acked-by: default avatarDavid Hildenbrand <david@redhat.com>
Acked-by: default avatarOscar Salvador <osalvador@suse.de>
Cc: David Rientjes <rientjes@google.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Krupa Ramakrishnan <krupa.ramakrishnan@amd.com>
Cc: Michal Hocko <mhocko@suse.com>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
parent 8d98e42f
...@@ -6171,7 +6171,6 @@ int numa_zonelist_order_handler(struct ctl_table *table, int write, ...@@ -6171,7 +6171,6 @@ int numa_zonelist_order_handler(struct ctl_table *table, int write,
} }
#define MAX_NODE_LOAD (nr_online_nodes)
static int node_load[MAX_NUMNODES]; static int node_load[MAX_NUMNODES];
/** /**
...@@ -6218,7 +6217,7 @@ int find_next_best_node(int node, nodemask_t *used_node_mask) ...@@ -6218,7 +6217,7 @@ int find_next_best_node(int node, nodemask_t *used_node_mask)
val += PENALTY_FOR_NODE_WITH_CPUS; val += PENALTY_FOR_NODE_WITH_CPUS;
/* Slight preference for less loaded node */ /* Slight preference for less loaded node */
val *= (MAX_NODE_LOAD*MAX_NUMNODES); val *= MAX_NUMNODES;
val += node_load[n]; val += node_load[n];
if (val < min_val) { if (val < min_val) {
...@@ -6284,13 +6283,12 @@ static void build_thisnode_zonelists(pg_data_t *pgdat) ...@@ -6284,13 +6283,12 @@ static void build_thisnode_zonelists(pg_data_t *pgdat)
static void build_zonelists(pg_data_t *pgdat) static void build_zonelists(pg_data_t *pgdat)
{ {
static int node_order[MAX_NUMNODES]; static int node_order[MAX_NUMNODES];
int node, load, nr_nodes = 0; int node, nr_nodes = 0;
nodemask_t used_mask = NODE_MASK_NONE; nodemask_t used_mask = NODE_MASK_NONE;
int local_node, prev_node; int local_node, prev_node;
/* NUMA-aware ordering of nodes */ /* NUMA-aware ordering of nodes */
local_node = pgdat->node_id; local_node = pgdat->node_id;
load = nr_online_nodes;
prev_node = local_node; prev_node = local_node;
memset(node_order, 0, sizeof(node_order)); memset(node_order, 0, sizeof(node_order));
...@@ -6302,11 +6300,10 @@ static void build_zonelists(pg_data_t *pgdat) ...@@ -6302,11 +6300,10 @@ static void build_zonelists(pg_data_t *pgdat)
*/ */
if (node_distance(local_node, node) != if (node_distance(local_node, node) !=
node_distance(local_node, prev_node)) node_distance(local_node, prev_node))
node_load[node] += load; node_load[node] += 1;
node_order[nr_nodes++] = node; node_order[nr_nodes++] = node;
prev_node = node; prev_node = node;
load--;
} }
build_zonelists_in_node_order(pgdat, node_order, nr_nodes); build_zonelists_in_node_order(pgdat, node_order, nr_nodes);
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment