cpu核数和内存大小怎么搭配 cpu核数( 六 )

sd->level = child->level + 1;
sched_domain_level_max = max(sched_domain_level_max, sd->level);
child->parent = sd;
if (!cpumask_subset(sched_domain_span(child),
sched_domain_span(sd))) {
pr_err("BUG: arch topology borken\\n");
#ifdef CONFIG_SCHED_DEBUG
pr_err("the %s domain not a subset of the %s domain\\n",
child->name, sd->name);
#endif
/* Fixup, ensure @sd has at least @child CPUs. */
cpumask_or(sched_domain_span(sd),
sched_domain_span(sd),
sched_domain_span(child));
}
}
set_domain_attribute(sd, attr);
return sd;
}
其中sd_init函数完成对应sched_domain_topology_level对应层次的sched_domain的一些数据的填充以及sd_data中mask和flag的修改。
static struct sched_domain *
sd_init(struct sched_domain_topology_level *tl,
const struct cpumask *cpu_map,
struct sched_domain *child, int dflags, int cpu)
{
struct sd_data *sdd = &tl->data;
struct sched_domain *sd = *per_cpu_ptr(sdd->sd, cpu);
int sd_id, sd_weight, sd_flags = 0;
#ifdef CONFIG_NUMA
/*
* Ugly hack to pass state to sd_numa_mask()…
*/
sched_domains_curr_level = tl->numa_level;
#endif
sd_weight = cpumask_weight(tl->mask(cpu));
if (tl->sd_flags)
sd_flags = (*tl->sd_flags)();
if (WARN_ONCE(sd_flags & ~TOPOLOGY_SD_FLAGS,
"wrong sd_flags in topology description\\n"))
sd_flags &= TOPOLOGY_SD_FLAGS;
/* Apply detected topology flags */
sd_flags |= dflags;
*sd = (struct sched_domain){
.min_interval= sd_weight,
.max_interval= 2*sd_weight,
.busy_factor= 16,
.imbalance_pct= 117,
.cache_nice_tries= 0,
.flags= 1*SD_BALANCE_NEWIDLE
| 1*SD_BALANCE_EXEC
| 1*SD_BALANCE_FORK
| 0*SD_BALANCE_WAKE
| 1*SD_WAKE_AFFINE
| 0*SD_SHARE_CPUCAPACITY
| 0*SD_SHARE_PKG_RESOURCES
| 0*SD_SERIALIZE
| 1*SD_PREFER_SIBLING
| 0*SD_NUMA
| sd_flags
,
.last_balance= jiffies,
.balance_interval= sd_weight,
.max_newidle_lb_cost= 0,
.next_decay_max_lb_cost= jiffies,
.child= child,
#ifdef CONFIG_SCHED_DEBUG
.name= tl->name,
#endif
};
cpumask_and(sched_domain_span(sd), cpu_map, tl->mask(cpu));
sd_id = cpumask_first(sched_domain_span(sd));
/*
* Convert topological properties into behaviour.
*/
/* Don't attempt to spread across CPUs of different capacities. */
if ((sd->flags & SD_ASYM_CPUCAPACITY) && sd->child)
sd->child->flags &= ~SD_PREFER_SIBLING;
if (sd->flags & SD_SHARE_CPUCAPACITY) {
sd->imbalance_pct = 110;
} else if (sd->flags & SD_SHARE_PKG_RESOURCES) {
sd->imbalance_pct = 117;
sd->cache_nice_tries = 1;
#ifdef CONFIG_NUMA
} else if (sd->flags & SD_NUMA) {
sd->cache_nice_tries = 2;
sd->flags &= ~SD_PREFER_SIBLING;
sd->flags |= SD_SERIALIZE;
if (sched_domains_numa_distance[tl->numa_level] > node_reclaim_distance) {
sd->flags &= ~(SD_BALANCE_EXEC |
SD_BALANCE_FORK |
SD_WAKE_AFFINE);
}
#endif
} else {
sd->cache_nice_tries = 1;
}
/*
* For all levels sharing cache; connect a sched_domain_shared
* instance.
*/
if (sd->flags & SD_SHARE_PKG_RESOURCES) {
sd->shared = *per_cpu_ptr(sdd->sds, sd_id);
atomic_inc(&sd->shared->ref);
atomic_set(&sd->shared->nr_busy_cpus, sd_weight);
}
sd->private = sdd;
return sd;
}
这里可以看到，sched_domain中的成员往往是与调度中负载均衡操作相关的一些字段，例如min_interval是最小的load balance间隔，max_interval是最大的load balance间隔等等。