The patch titled
Subject: lib: optimize cpumask_local_spread()
has been added to the -mm tree. Its filename is
lib-optimize-cpumask_local_spread.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/lib-optimize-cpumask_local_spread.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/lib-optimize-cpumask_local_spread.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: yuqi jin <jinyuqi@xxxxxxxxxx>
Subject: lib: optimize cpumask_local_spread()
In a multi-processor and NUMA system, I/O device may have many numa nodes
belonging to multiple cpus. When we get a local numa, it is better to
find the node closest to the local numa node, instead of choosing any
online cpu immediately.
For the current code, it only considers the local NUMA node and it doesn't
compute the distances between different NUMA nodes for the non-local NUMA
nodes. Let's optimize it and find the nearest node through NUMA distance.
The performance will be better if it returns the nearest node than a
random node.
When Parameter Server workload is tested using NIC device on Huawei
Kunpeng 920 SoC:
Without the patch, the performance is 22W QPS;
Added this patch, the performance become better and it is 26W QPS.
Link: http://lkml.kernel.org/r/1572863268-28585-1-git-send-email-zhangshaokun@xxxxxxxxxxxxx
Signed-off-by: yuqi jin <jinyuqi@xxxxxxxxxx>
Signed-off-by: Shaokun Zhang <zhangshaokun@xxxxxxxxxxxxx>
Cc: Mike Rapoport <rppt@xxxxxxxxxxxxx>
Cc: Paul Burton <paul.burton@xxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxx>
Cc: Michael Ellerman <mpe@xxxxxxxxxxxxxx>
Cc: Anshuman Khandual <anshuman.khandual@xxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
lib/cpumask.c | 93 +++++++++++++++++++++++++++++++++++++++++-------
1 file changed, 81 insertions(+), 12 deletions(-)
--- a/lib/cpumask.c~lib-optimize-cpumask_local_spread
+++ a/lib/cpumask.c
@@ -192,18 +192,39 @@ void __init free_bootmem_cpumask_var(cpu
}
#endif
-/**
- * cpumask_local_spread - select the i'th cpu with local numa cpu's first
- * @i: index number
- * @node: local numa_node
- *
- * This function selects an online CPU according to a numa aware policy;
- * local cpus are returned first, followed by non-local ones, then it
- * wraps around.
- *
- * It's not very efficient, but useful for setup.
- */
-unsigned int cpumask_local_spread(unsigned int i, int node)
+static void calc_node_distance(int *node_dist, int node)
+{
+ int i;
+
+ for (i = 0; i < nr_node_ids; i++)
+ node_dist[i] = node_distance(node, i);
+}
+
+static int find_nearest_node(int *node_dist, bool *used)
+{
+ int i, min_dist = node_dist[0], node_id = -1;
+
+ /* Choose the first unused node to compare */
+ for (i = 0; i < nr_node_ids; i++) {
+ if (used[i] == 0) {
+ min_dist = node_dist[i];
+ node_id = i;
+ break;
+ }
+ }
+
+ /* Compare and return the nearest node */
+ for (i = 0; i < nr_node_ids; i++) {
+ if (node_dist[i] < min_dist && used[i] == 0) {
+ min_dist = node_dist[i];
+ node_id = i;
+ }
+ }
+
+ return node_id;
+}
+
+static unsigned int __cpumask_local_spread(unsigned int i, int node)
{
int cpu;
@@ -231,4 +252,52 @@ unsigned int cpumask_local_spread(unsign
}
BUG();
}
+
+/**
+ * cpumask_local_spread - select the i'th cpu with local numa cpu's first
+ * @i: index number
+ * @node: local numa_node
+ *
+ * This function selects an online CPU according to a numa aware policy;
+ * local cpus are returned first, followed by the nearest non-local ones,
+ * then it wraps around.
+ *
+ * It's not very efficient, but useful for setup.
+ */
+unsigned int cpumask_local_spread(unsigned int i, int node)
+{
+ int node_dist[MAX_NUMNODES] = {0};
+ bool used[MAX_NUMNODES] = {0};
+ int cpu, j, id;
+
+ /* Wrap: we always want a cpu. */
+ i %= num_online_cpus();
+
+ if (node == NUMA_NO_NODE) {
+ for_each_cpu(cpu, cpu_online_mask)
+ if (i-- == 0)
+ return cpu;
+ } else {
+ if (nr_node_ids > MAX_NUMNODES)
+ return __cpumask_local_spread(i, node);
+
+ calc_node_distance(node_dist, node);
+ for (j = 0; j < nr_node_ids; j++) {
+ id = find_nearest_node(node_dist, used);
+ if (id < 0)
+ break;
+
+ for_each_cpu_and(cpu, cpumask_of_node(id),
+ cpu_online_mask)
+ if (i-- == 0)
+ return cpu;
+ used[id] = 1;
+ }
+
+ for_each_cpu(cpu, cpu_online_mask)
+ if (i-- == 0)
+ return cpu;
+ }
+ BUG();
+}
EXPORT_SYMBOL(cpumask_local_spread);
_
Patches currently in -mm which might be from jinyuqi@xxxxxxxxxx are
lib-optimize-cpumask_local_spread.patch
