sched: Validate assumptions in sched_init_numa()

Add some code to validate assumptions we're making and output
warnings if they are not.

If this trigger we want to know about it.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Alex Shi <lkml.alex@gmail.com>
Link: http://lkml.kernel.org/n/tip-6uc3wk5s9udxtdl9cnku0vtt@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
This commit is contained in:
Peter Zijlstra 2012-05-31 21:20:16 +02:00 committed by Ingo Molnar
parent c3decf0dfb
commit d039ac6080

View file

@ -5556,15 +5556,20 @@ static cpumask_var_t sched_domains_tmpmask; /* sched_domains_mutex */
#ifdef CONFIG_SCHED_DEBUG #ifdef CONFIG_SCHED_DEBUG
static __read_mostly int sched_domain_debug_enabled; static __read_mostly int sched_debug_enabled;
static int __init sched_domain_debug_setup(char *str) static int __init sched_debug_setup(char *str)
{ {
sched_domain_debug_enabled = 1; sched_debug_enabled = 1;
return 0; return 0;
} }
early_param("sched_debug", sched_domain_debug_setup); early_param("sched_debug", sched_debug_setup);
static inline bool sched_debug(void)
{
return sched_debug_enabled;
}
static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
struct cpumask *groupmask) struct cpumask *groupmask)
@ -5657,7 +5662,7 @@ static void sched_domain_debug(struct sched_domain *sd, int cpu)
{ {
int level = 0; int level = 0;
if (!sched_domain_debug_enabled) if (!sched_debug_enabled)
return; return;
if (!sd) { if (!sd) {
@ -5678,6 +5683,10 @@ static void sched_domain_debug(struct sched_domain *sd, int cpu)
} }
#else /* !CONFIG_SCHED_DEBUG */ #else /* !CONFIG_SCHED_DEBUG */
# define sched_domain_debug(sd, cpu) do { } while (0) # define sched_domain_debug(sd, cpu) do { } while (0)
static inline bool sched_debug(void)
{
return false;
}
#endif /* CONFIG_SCHED_DEBUG */ #endif /* CONFIG_SCHED_DEBUG */
static int sd_degenerate(struct sched_domain *sd) static int sd_degenerate(struct sched_domain *sd)
@ -6373,7 +6382,6 @@ static struct sched_domain_topology_level *sched_domain_topology = default_topol
#ifdef CONFIG_NUMA #ifdef CONFIG_NUMA
static int sched_domains_numa_levels; static int sched_domains_numa_levels;
static int sched_domains_numa_scale;
static int *sched_domains_numa_distance; static int *sched_domains_numa_distance;
static struct cpumask ***sched_domains_numa_masks; static struct cpumask ***sched_domains_numa_masks;
static int sched_domains_curr_level; static int sched_domains_curr_level;
@ -6438,6 +6446,42 @@ static const struct cpumask *sd_numa_mask(int cpu)
return sched_domains_numa_masks[sched_domains_curr_level][cpu_to_node(cpu)]; return sched_domains_numa_masks[sched_domains_curr_level][cpu_to_node(cpu)];
} }
static void sched_numa_warn(const char *str)
{
static int done = false;
int i,j;
if (done)
return;
done = true;
printk(KERN_WARNING "ERROR: %s\n\n", str);
for (i = 0; i < nr_node_ids; i++) {
printk(KERN_WARNING " ");
for (j = 0; j < nr_node_ids; j++)
printk(KERN_CONT "%02d ", node_distance(i,j));
printk(KERN_CONT "\n");
}
printk(KERN_WARNING "\n");
}
static bool find_numa_distance(int distance)
{
int i;
if (distance == node_distance(0, 0))
return true;
for (i = 0; i < sched_domains_numa_levels; i++) {
if (sched_domains_numa_distance[i] == distance)
return true;
}
return false;
}
static void sched_init_numa(void) static void sched_init_numa(void)
{ {
int next_distance, curr_distance = node_distance(0, 0); int next_distance, curr_distance = node_distance(0, 0);
@ -6445,7 +6489,6 @@ static void sched_init_numa(void)
int level = 0; int level = 0;
int i, j, k; int i, j, k;
sched_domains_numa_scale = curr_distance;
sched_domains_numa_distance = kzalloc(sizeof(int) * nr_node_ids, GFP_KERNEL); sched_domains_numa_distance = kzalloc(sizeof(int) * nr_node_ids, GFP_KERNEL);
if (!sched_domains_numa_distance) if (!sched_domains_numa_distance)
return; return;
@ -6456,23 +6499,41 @@ static void sched_init_numa(void)
* *
* Assumes node_distance(0,j) includes all distances in * Assumes node_distance(0,j) includes all distances in
* node_distance(i,j) in order to avoid cubic time. * node_distance(i,j) in order to avoid cubic time.
*
* XXX: could be optimized to O(n log n) by using sort()
*/ */
next_distance = curr_distance; next_distance = curr_distance;
for (i = 0; i < nr_node_ids; i++) { for (i = 0; i < nr_node_ids; i++) {
for (j = 0; j < nr_node_ids; j++) { for (j = 0; j < nr_node_ids; j++) {
int distance = node_distance(0, j); for (k = 0; k < nr_node_ids; k++) {
if (distance > curr_distance && int distance = node_distance(i, k);
(distance < next_distance ||
next_distance == curr_distance)) if (distance > curr_distance &&
next_distance = distance; (distance < next_distance ||
next_distance == curr_distance))
next_distance = distance;
/*
* While not a strong assumption it would be nice to know
* about cases where if node A is connected to B, B is not
* equally connected to A.
*/
if (sched_debug() && node_distance(k, i) != distance)
sched_numa_warn("Node-distance not symmetric");
if (sched_debug() && i && !find_numa_distance(distance))
sched_numa_warn("Node-0 not representative");
}
if (next_distance != curr_distance) {
sched_domains_numa_distance[level++] = next_distance;
sched_domains_numa_levels = level;
curr_distance = next_distance;
} else break;
} }
if (next_distance != curr_distance) {
sched_domains_numa_distance[level++] = next_distance; /*
sched_domains_numa_levels = level; * In case of sched_debug() we verify the above assumption.
curr_distance = next_distance; */
} else break; if (!sched_debug())
break;
} }
/* /*
* 'level' contains the number of unique distances, excluding the * 'level' contains the number of unique distances, excluding the