sched/topology: Add sched_group_capacity debugging

Add sgc::id to easier spot domain construction issues.

Take the opportunity to slightly rework the group printing, because
adding more "(id: %d)" strings makes the entire thing very hard to
read. Also the individual groups are very hard to separate, so add
explicit visual grouping, which allows replacing all the "(%s: %d)"
format things with shorter "%s=%d" variants.

Then fix up some inconsistencies in surrounding prints for domains.

The end result looks like:

  [] CPU0 attaching sched-domain(s):
  []  domain-0: span=0,4 level=DIE
  []   groups: 0:{ span=0 }, 4:{ span=4 }
  []   domain-1: span=0-1,3-5,7 level=NUMA
  []    groups: 0:{ span=0,4 mask=0,4 cap=2048 }, 1:{ span=1,5 mask=1,5 cap=2048 }, 3:{ span=3,7 mask=3,7 cap=2048 }
  []    domain-2: span=0-7 level=NUMA
  []     groups: 0:{ span=0-1,3-5,7 mask=0,4 cap=6144 }, 2:{ span=1-3,5-7 mask=2,6 cap=6144 }
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

kernel/sched/sched.h

@@ -1023,6 +1023,10 @@ struct sched_group_capacity {
 	unsigned long next_update;
 	int imbalance; /* XXX unrelated to capacity but shared group state */
 
+#ifdef CONFIG_SCHED_DEBUG
+	int id;
+#endif
+
 	unsigned long cpumask[0]; /* iteration mask */
 };
 

kernel/sched/topology.c

@@ -35,7 +35,7 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
 
 	cpumask_clear(groupmask);
 
-	printk(KERN_DEBUG "%*s domain %d: ", level, "", level);
+	printk(KERN_DEBUG "%*s domain-%d: ", level, "", level);
 
 	if (!(sd->flags & SD_LOAD_BALANCE)) {
 		printk("does not load-balance\n");
@@ -45,7 +45,7 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
 		return -1;
 	}
 
-	printk(KERN_CONT "span %*pbl level %s\n",
+	printk(KERN_CONT "span=%*pbl level=%s\n",
 	       cpumask_pr_args(sched_domain_span(sd)), sd->name);
 
 	if (!cpumask_test_cpu(cpu, sched_domain_span(sd))) {
@@ -80,18 +80,17 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
 
 		cpumask_or(groupmask, groupmask, sched_group_cpus(group));
 
-		printk(KERN_CONT " %*pbl",
-		       cpumask_pr_args(sched_group_cpus(group)));
+		printk(KERN_CONT " %d:{ span=%*pbl",
+				group->sgc->id,
+				cpumask_pr_args(sched_group_cpus(group)));
 
 		if ((sd->flags & SD_OVERLAP) && !cpumask_full(sched_group_mask(group))) {
-			printk(KERN_CONT " (mask: %*pbl)",
+			printk(KERN_CONT " mask=%*pbl",
 				cpumask_pr_args(sched_group_mask(group)));
 		}
 
-		if (group->sgc->capacity != SCHED_CAPACITY_SCALE) {
-			printk(KERN_CONT " (cpu_capacity: %lu)",
-				group->sgc->capacity);
-		}
+		if (group->sgc->capacity != SCHED_CAPACITY_SCALE)
+			printk(KERN_CONT " cap=%lu", group->sgc->capacity);
 
 		if (group == sd->groups && sd->child &&
 		    !cpumask_equal(sched_domain_span(sd->child),
@@ -99,6 +98,8 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
 			printk(KERN_ERR "ERROR: domain->groups does not match domain->child\n");
 		}
 
+		printk(KERN_CONT " }");
+
 		group = group->next;
 
 		if (group != sd->groups)
@@ -129,7 +130,7 @@ static void sched_domain_debug(struct sched_domain *sd, int cpu)
 		return;
 	}
 
-	printk(KERN_DEBUG "CPU%d attaching sched-domain:\n", cpu);
+	printk(KERN_DEBUG "CPU%d attaching sched-domain(s):\n", cpu);
 
 	for (;;) {
 		if (sched_domain_debug_one(sd, cpu, level, sched_domains_tmpmask))
@@ -1356,6 +1357,10 @@ static int __sdt_alloc(const struct cpumask *cpu_map)
 			if (!sgc)
 				return -ENOMEM;
 
+#ifdef CONFIG_SCHED_DEBUG
+			sgc->id = j;
+#endif
+
 			*per_cpu_ptr(sdd->sgc, j) = sgc;
 		}
 	}