| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <1361164062-20111-10-git-send-email-alex.shi@intel.com>
Date: Mon, 18 Feb 2013 13:07:36 +0800
From: Alex Shi <alex.shi@...el.com>
To: torvalds@...ux-foundation.org, mingo@...hat.com,
peterz@...radead.org, tglx@...utronix.de,
akpm@...ux-foundation.org, arjan@...ux.intel.com, bp@...en8.de,
pjt@...gle.com, namhyung@...nel.org, efault@....de
Cc: vincent.guittot@...aro.org, gregkh@...uxfoundation.org,
preeti@...ux.vnet.ibm.com, viresh.kumar@...aro.org,
linux-kernel@...r.kernel.org, alex.shi@...el.com,
morten.rasmussen@....com
Subject: [patch v5 09/15] sched: add power aware scheduling in fork/exec/wake
This patch add power aware scheduling in fork/exec/wake. It try to
select cpu from the busiest while still has utilization group. That's
will save power since it leaves more groups idle in system.
The trade off is adding a power aware statistics collection in group
seeking. But since the collection just happened in power scheduling
eligible condition, the worst case of hackbench testing just drops
about 2% with powersaving/balance policy. No clear change for
performance policy.
The main function in this patch is get_cpu_for_power_policy(), that
will try to get a idlest cpu from the busiest while still has
utilization group, if the system is using power aware policy and
has such group.
I had tried to use rq utilisation in this balancing, but since the
utilisation need much time to accumulate itself(345ms). It's bad for
any burst balancing. So I use instant rq utilisation -- nr_running.
Signed-off-by: Alex Shi <alex.shi@...el.com>
---
kernel/sched/fair.c | 129 +++++++++++++++++++++++++++++++++++++++++++++++++---
1 file changed, 123 insertions(+), 6 deletions(-)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 287582b..b172678 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3362,26 +3362,134 @@ struct sg_lb_stats {
unsigned int group_utils; /* sum utilizations of group */
};
+static inline int
+fix_small_capacity(struct sched_domain *sd, struct sched_group *group);
+
+/*
+ * Try to collect the task running number and capacity of the group.
+ */
+static void get_sg_power_stats(struct sched_group *group,
+ struct sched_domain *sd, struct sg_lb_stats *sgs)
+{
+ int i;
+
+ for_each_cpu(i, sched_group_cpus(group)) {
+ struct rq *rq = cpu_rq(i);
+
+ sgs->group_utils += rq->nr_running;
+ }
+
+ sgs->group_capacity = DIV_ROUND_CLOSEST(group->sgp->power,
+ SCHED_POWER_SCALE);
+ if (!sgs->group_capacity)
+ sgs->group_capacity = fix_small_capacity(sd, group);
+ sgs->group_weight = group->group_weight;
+}
+
+/*
+ * Try to collect the task running number and capacity of the domain.
+ */
+static void get_sd_power_stats(struct sched_domain *sd,
+ struct task_struct *p, struct sd_lb_stats *sds)
+{
+ struct sched_group *group;
+ struct sg_lb_stats sgs;
+ int sd_min_delta = INT_MAX;
+ int cpu = task_cpu(p);
+
+ group = sd->groups;
+ do {
+ long g_delta;
+ unsigned long threshold;
+
+ if (!cpumask_test_cpu(cpu, sched_group_mask(group)))
+ continue;
+
+ memset(&sgs, 0, sizeof(sgs));
+ get_sg_power_stats(group, sd, &sgs);
+
+ if (sched_balance_policy == SCHED_POLICY_POWERSAVING)
+ threshold = sgs.group_weight;
+ else
+ threshold = sgs.group_capacity;
+
+ g_delta = threshold - sgs.group_utils;
+
+ if (g_delta > 0 && g_delta < sd_min_delta) {
+ sd_min_delta = g_delta;
+ sds->group_leader = group;
+ }
+
+ sds->sd_utils += sgs.group_utils;
+ sds->total_pwr += group->sgp->power;
+ } while (group = group->next, group != sd->groups);
+
+ sds->sd_capacity = DIV_ROUND_CLOSEST(sds->total_pwr,
+ SCHED_POWER_SCALE);
+}
+
+/*
+ * Execute power policy if this domain is not full.
+ */
+static inline int get_sd_sched_balance_policy(struct sched_domain *sd,
+ int cpu, struct task_struct *p, struct sd_lb_stats *sds)
+{
+ unsigned long threshold;
+
+ if (sched_balance_policy == SCHED_POLICY_PERFORMANCE)
+ return SCHED_POLICY_PERFORMANCE;
+
+ memset(sds, 0, sizeof(*sds));
+ get_sd_power_stats(sd, p, sds);
+
+ if (sched_balance_policy == SCHED_POLICY_POWERSAVING)
+ threshold = sd->span_weight;
+ else
+ threshold = sds->sd_capacity;
+
+ /* still can hold one more task in this domain */
+ if (sds->sd_utils < threshold)
+ return sched_balance_policy;
+
+ return SCHED_POLICY_PERFORMANCE;
+}
+
+/*
+ * If power policy is eligible for this domain, and it has task allowed cpu.
+ * we will select CPU from this domain.
+ */
+static int get_cpu_for_power_policy(struct sched_domain *sd, int cpu,
+ struct task_struct *p, struct sd_lb_stats *sds)
+{
+ int policy;
+ int new_cpu = -1;
+
+ policy = get_sd_sched_balance_policy(sd, cpu, p, sds);
+ if (policy != SCHED_POLICY_PERFORMANCE && sds->group_leader)
+ new_cpu = find_idlest_cpu(sds->group_leader, p, cpu);
+
+ return new_cpu;
+}
+
/*
- * sched_balance_self: balance the current task (running on cpu) in domains
+ * select_task_rq_fair: balance the current task (running on cpu) in domains
* that have the 'flag' flag set. In practice, this is SD_BALANCE_FORK and
* SD_BALANCE_EXEC.
*
- * Balance, ie. select the least loaded group.
- *
* Returns the target CPU number, or the same CPU if no balancing is needed.
*
* preempt must be disabled.
*/
static int
-select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flags)
+select_task_rq_fair(struct task_struct *p, int sd_flag, int flags)
{
struct sched_domain *tmp, *affine_sd = NULL, *sd = NULL;
int cpu = smp_processor_id();
int prev_cpu = task_cpu(p);
int new_cpu = cpu;
int want_affine = 0;
- int sync = wake_flags & WF_SYNC;
+ int sync = flags & WF_SYNC;
+ struct sd_lb_stats sds;
if (p->nr_cpus_allowed == 1)
return prev_cpu;
@@ -3407,11 +3515,20 @@ select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flags)
break;
}
- if (tmp->flags & sd_flag)
+ if (tmp->flags & sd_flag) {
sd = tmp;
+
+ new_cpu = get_cpu_for_power_policy(sd, cpu, p, &sds);
+ if (new_cpu != -1)
+ goto unlock;
+ }
}
if (affine_sd) {
+ new_cpu = get_cpu_for_power_policy(affine_sd, cpu, p, &sds);
+ if (new_cpu != -1)
+ goto unlock;
+
if (cpu != prev_cpu && wake_affine(affine_sd, p, sync))
prev_cpu = cpu;
--
1.7.12
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists