sched/topology: Warn when NUMA diameter > 2

NUMA topologies where the shortest path between some two nodes requires
three or more hops (i.e. diameter > 2) end up being misrepresented in the
scheduler topology structures.

This is currently detected when booting a kernel with CONFIG_SCHED_DEBUG=y
+ sched_debug on the cmdline, although this will only yield a warning about
sched_group spans not matching sched_domain spans:

  ERROR: groups don't span domain->span

Add an explicit warning for that case, triggered regardless of
CONFIG_SCHED_DEBUG, and decorate it with an appropriate comment.

The topology described in the comment can be booted up on QEMU by appending
the following to your usual QEMU incantation:

    -smp cores=4 \
    -numa node,cpus=0,nodeid=0 -numa node,cpus=1,nodeid=1, \
    -numa node,cpus=2,nodeid=2, -numa node,cpus=3,nodeid=3, \
    -numa dist,src=0,dst=1,val=20, -numa dist,src=0,dst=2,val=30, \
    -numa dist,src=0,dst=3,val=40, -numa dist,src=1,dst=2,val=20, \
    -numa dist,src=1,dst=3,val=30, -numa dist,src=2,dst=3,val=20

A somewhat more realistic topology (6-node mesh) with the same affliction
can be conjured with:

    -smp cores=6 \
    -numa node,cpus=0,nodeid=0 -numa node,cpus=1,nodeid=1, \
    -numa node,cpus=2,nodeid=2, -numa node,cpus=3,nodeid=3, \
    -numa node,cpus=4,nodeid=4, -numa node,cpus=5,nodeid=5, \
    -numa dist,src=0,dst=1,val=20, -numa dist,src=0,dst=2,val=30, \
    -numa dist,src=0,dst=3,val=40, -numa dist,src=0,dst=4,val=30, \
    -numa dist,src=0,dst=5,val=20, \
    -numa dist,src=1,dst=2,val=20, -numa dist,src=1,dst=3,val=30, \
    -numa dist,src=1,dst=4,val=20, -numa dist,src=1,dst=5,val=30, \
    -numa dist,src=2,dst=3,val=20, -numa dist,src=2,dst=4,val=30, \
    -numa dist,src=2,dst=5,val=40, \
    -numa dist,src=3,dst=4,val=20, -numa dist,src=3,dst=5,val=30, \
    -numa dist,src=4,dst=5,val=20

Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Mel Gorman <mgorman@techsingularity.net>
Link: https://lore.kernel.org/lkml/jhjtux5edo2.mognet@arm.com

diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 90f3e5558fa21d5592022d5fdb3b35eada95cfb4..b296c1c6b961caad0a744f57dba041da3d18a63d 100644 (file)
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -675,6 +675,7 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
 {
        struct rq *rq = cpu_rq(cpu);
        struct sched_domain *tmp;
+       int numa_distance = 0;
 
        /* Remove the sched domains which do not contribute to scheduling. */
        for (tmp = sd; tmp; ) {
@@ -706,6 +707,38 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
                        sd->child = NULL;
        }
 
+       for (tmp = sd; tmp; tmp = tmp->parent)
+               numa_distance += !!(tmp->flags & SD_NUMA);
+
+       /*
+        * FIXME: Diameter >=3 is misrepresented.
+        *
+        * Smallest diameter=3 topology is:
+        *
+        *   node   0   1   2   3
+        *     0:  10  20  30  40
+        *     1:  20  10  20  30
+        *     2:  30  20  10  20
+        *     3:  40  30  20  10
+        *
+        *   0 --- 1 --- 2 --- 3
+        *
+        * NUMA-3       0-3             N/A             N/A             0-3
+        *  groups:     {0-2},{1-3}                                     {1-3},{0-2}
+        *
+        * NUMA-2       0-2             0-3             0-3             1-3
+        *  groups:     {0-1},{1-3}     {0-2},{2-3}     {1-3},{0-1}     {2-3},{0-2}
+        *
+        * NUMA-1       0-1             0-2             1-3             2-3
+        *  groups:     {0},{1}         {1},{2},{0}     {2},{3},{1}     {3},{2}
+        *
+        * NUMA-0       0               1               2               3
+        *
+        * The NUMA-2 groups for nodes 0 and 3 are obviously buggered, as the
+        * group span isn't a subset of the domain span.
+        */
+       WARN_ONCE(numa_distance > 2, "Shortest NUMA path spans too many nodes\n");
+
        sched_domain_debug(sd, cpu);
 
        rq_attach_root(rq, rd);