* [PATCH] sched: Prefer sibiling only if local group is under-utilized
@ 2017-03-22 17:57 Srikar Dronamraju
2017-03-23 7:42 ` Peter Zijlstra
` (2 more replies)
0 siblings, 3 replies; 4+ messages in thread
From: Srikar Dronamraju @ 2017-03-22 17:57 UTC (permalink / raw)
To: Ingo Molnar, Peter Zijlstra
Cc: Vincent Guittot, Mike Galbraith, Thomas Gleixner, LKML,
Srikar Dronamraju
If the child domain prefers tasks to go siblings, the local group could
end up pulling tasks to itself even if the local group is almost equally
loaded as the source group.
Lets assume a 4 core,smt==2 machine running 5 thread ebizzy workload.
Everytime, local group has capacity and source group has atleast 2 threads,
local group tries to pull the task. This causes the threads to constantly
move between different cores. This is even more profound if the cores have
more threads, like in Power 8, smt 8 mode.
Fix this by only allowing local group to pull a task, if the source group
has more number of tasks than the local group.
Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
---
Here are the relevant perf stat numbers of a 22 core,smt 8 Power 8 machine.
Without patch:
Performance counter stats for 'ebizzy -t 22 -S 100' (5 runs):
1,440 context-switches # 0.001 K/sec ( +- 1.26% )
366 cpu-migrations # 0.000 K/sec ( +- 5.58% )
3,933 page-faults # 0.002 K/sec ( +- 11.08% )
Performance counter stats for 'ebizzy -t 48 -S 100' (5 runs):
6,287 context-switches # 0.001 K/sec ( +- 3.65% )
3,776 cpu-migrations # 0.001 K/sec ( +- 4.84% )
5,702 page-faults # 0.001 K/sec ( +- 9.36% )
Performance counter stats for 'ebizzy -t 96 -S 100' (5 runs):
8,776 context-switches # 0.001 K/sec ( +- 0.73% )
2,790 cpu-migrations # 0.000 K/sec ( +- 0.98% )
10,540 page-faults # 0.001 K/sec ( +- 3.12% )
With patch:
Performance counter stats for 'ebizzy -t 22 -S 100' (5 runs):
1,133 context-switches # 0.001 K/sec ( +- 4.72% )
123 cpu-migrations # 0.000 K/sec ( +- 3.42% )
3,858 page-faults # 0.002 K/sec ( +- 8.52% )
Performance counter stats for 'ebizzy -t 48 -S 100' (5 runs):
2,169 context-switches # 0.000 K/sec ( +- 6.19% )
189 cpu-migrations # 0.000 K/sec ( +- 12.75% )
5,917 page-faults # 0.001 K/sec ( +- 8.09% )
Performance counter stats for 'ebizzy -t 96 -S 100' (5 runs):
5,333 context-switches # 0.001 K/sec ( +- 5.91% )
506 cpu-migrations # 0.000 K/sec ( +- 3.35% )
10,792 page-faults # 0.001 K/sec ( +- 7.75% )
---
kernel/sched/fair.c | 7 ++++---
1 file changed, 4 insertions(+), 3 deletions(-)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 6559d19..a6dd010 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -7496,6 +7496,7 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
{
struct sched_domain *child = env->sd->child;
struct sched_group *sg = env->sd->groups;
+ struct sg_lb_stats *local = &sds->local_stat;
struct sg_lb_stats tmp_sgs;
int load_idx, prefer_sibling = 0;
bool overload = false;
@@ -7512,7 +7513,7 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
local_group = cpumask_test_cpu(env->dst_cpu, sched_group_cpus(sg));
if (local_group) {
sds->local = sg;
- sgs = &sds->local_stat;
+ sgs = local;
if (env->idle != CPU_NEWLY_IDLE ||
time_after_eq(jiffies, sg->sgc->next_update))
@@ -7536,8 +7537,8 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
* the tasks on the system).
*/
if (prefer_sibling && sds->local &&
- group_has_capacity(env, &sds->local_stat) &&
- (sgs->sum_nr_running > 1)) {
+ group_has_capacity(env, local) &&
+ (sgs->sum_nr_running > local->sum_nr_running + 1)) {
sgs->group_no_capacity = 1;
sgs->group_type = group_classify(sg, sgs);
}
--
1.8.3.1
^ permalink raw reply related [flat|nested] 4+ messages in thread* Re: [PATCH] sched: Prefer sibiling only if local group is under-utilized
2017-03-22 17:57 [PATCH] sched: Prefer sibiling only if local group is under-utilized Srikar Dronamraju
@ 2017-03-23 7:42 ` Peter Zijlstra
2017-03-23 8:37 ` Vincent Guittot
2017-03-27 10:26 ` [tip:sched/core] sched/fair: " tip-bot for Srikar Dronamraju
2 siblings, 0 replies; 4+ messages in thread
From: Peter Zijlstra @ 2017-03-23 7:42 UTC (permalink / raw)
To: Srikar Dronamraju
Cc: Ingo Molnar, Vincent Guittot, Mike Galbraith, Thomas Gleixner,
LKML
On Wed, Mar 22, 2017 at 11:27:50PM +0530, Srikar Dronamraju wrote:
> @@ -7536,8 +7537,8 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
> * the tasks on the system).
> */
> if (prefer_sibling && sds->local &&
> - group_has_capacity(env, &sds->local_stat) &&
> - (sgs->sum_nr_running > 1)) {
> + group_has_capacity(env, local) &&
> + (sgs->sum_nr_running > local->sum_nr_running + 1)) {
> sgs->group_no_capacity = 1;
> sgs->group_type = group_classify(sg, sgs);
> }
Ah, yes that makes sense!
Thanks
^ permalink raw reply [flat|nested] 4+ messages in thread* Re: [PATCH] sched: Prefer sibiling only if local group is under-utilized
2017-03-22 17:57 [PATCH] sched: Prefer sibiling only if local group is under-utilized Srikar Dronamraju
2017-03-23 7:42 ` Peter Zijlstra
@ 2017-03-23 8:37 ` Vincent Guittot
2017-03-27 10:26 ` [tip:sched/core] sched/fair: " tip-bot for Srikar Dronamraju
2 siblings, 0 replies; 4+ messages in thread
From: Vincent Guittot @ 2017-03-23 8:37 UTC (permalink / raw)
To: Srikar Dronamraju
Cc: Ingo Molnar, Peter Zijlstra, Mike Galbraith, Thomas Gleixner,
LKML
On 22 March 2017 at 18:57, Srikar Dronamraju <srikar@linux.vnet.ibm.com> wrote:
> If the child domain prefers tasks to go siblings, the local group could
> end up pulling tasks to itself even if the local group is almost equally
> loaded as the source group.
>
> Lets assume a 4 core,smt==2 machine running 5 thread ebizzy workload.
> Everytime, local group has capacity and source group has atleast 2 threads,
> local group tries to pull the task. This causes the threads to constantly
> move between different cores. This is even more profound if the cores have
> more threads, like in Power 8, smt 8 mode.
>
> Fix this by only allowing local group to pull a task, if the source group
> has more number of tasks than the local group.
>
> Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Acked-by: Vincent Guittot <vincent.guittot@linaro.org>
> ---
> Here are the relevant perf stat numbers of a 22 core,smt 8 Power 8 machine.
>
> Without patch:
> Performance counter stats for 'ebizzy -t 22 -S 100' (5 runs):
>
> 1,440 context-switches # 0.001 K/sec ( +- 1.26% )
> 366 cpu-migrations # 0.000 K/sec ( +- 5.58% )
> 3,933 page-faults # 0.002 K/sec ( +- 11.08% )
>
> Performance counter stats for 'ebizzy -t 48 -S 100' (5 runs):
>
> 6,287 context-switches # 0.001 K/sec ( +- 3.65% )
> 3,776 cpu-migrations # 0.001 K/sec ( +- 4.84% )
> 5,702 page-faults # 0.001 K/sec ( +- 9.36% )
>
> Performance counter stats for 'ebizzy -t 96 -S 100' (5 runs):
>
> 8,776 context-switches # 0.001 K/sec ( +- 0.73% )
> 2,790 cpu-migrations # 0.000 K/sec ( +- 0.98% )
> 10,540 page-faults # 0.001 K/sec ( +- 3.12% )
>
> With patch:
> Performance counter stats for 'ebizzy -t 22 -S 100' (5 runs):
>
> 1,133 context-switches # 0.001 K/sec ( +- 4.72% )
> 123 cpu-migrations # 0.000 K/sec ( +- 3.42% )
> 3,858 page-faults # 0.002 K/sec ( +- 8.52% )
>
> Performance counter stats for 'ebizzy -t 48 -S 100' (5 runs):
>
> 2,169 context-switches # 0.000 K/sec ( +- 6.19% )
> 189 cpu-migrations # 0.000 K/sec ( +- 12.75% )
> 5,917 page-faults # 0.001 K/sec ( +- 8.09% )
>
> Performance counter stats for 'ebizzy -t 96 -S 100' (5 runs):
>
> 5,333 context-switches # 0.001 K/sec ( +- 5.91% )
> 506 cpu-migrations # 0.000 K/sec ( +- 3.35% )
> 10,792 page-faults # 0.001 K/sec ( +- 7.75% )
> ---
> kernel/sched/fair.c | 7 ++++---
> 1 file changed, 4 insertions(+), 3 deletions(-)
>
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index 6559d19..a6dd010 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -7496,6 +7496,7 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
> {
> struct sched_domain *child = env->sd->child;
> struct sched_group *sg = env->sd->groups;
> + struct sg_lb_stats *local = &sds->local_stat;
> struct sg_lb_stats tmp_sgs;
> int load_idx, prefer_sibling = 0;
> bool overload = false;
> @@ -7512,7 +7513,7 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
> local_group = cpumask_test_cpu(env->dst_cpu, sched_group_cpus(sg));
> if (local_group) {
> sds->local = sg;
> - sgs = &sds->local_stat;
> + sgs = local;
>
> if (env->idle != CPU_NEWLY_IDLE ||
> time_after_eq(jiffies, sg->sgc->next_update))
> @@ -7536,8 +7537,8 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
> * the tasks on the system).
> */
> if (prefer_sibling && sds->local &&
> - group_has_capacity(env, &sds->local_stat) &&
> - (sgs->sum_nr_running > 1)) {
> + group_has_capacity(env, local) &&
> + (sgs->sum_nr_running > local->sum_nr_running + 1)) {
> sgs->group_no_capacity = 1;
> sgs->group_type = group_classify(sg, sgs);
> }
> --
> 1.8.3.1
>
^ permalink raw reply [flat|nested] 4+ messages in thread* [tip:sched/core] sched/fair: Prefer sibiling only if local group is under-utilized
2017-03-22 17:57 [PATCH] sched: Prefer sibiling only if local group is under-utilized Srikar Dronamraju
2017-03-23 7:42 ` Peter Zijlstra
2017-03-23 8:37 ` Vincent Guittot
@ 2017-03-27 10:26 ` tip-bot for Srikar Dronamraju
2 siblings, 0 replies; 4+ messages in thread
From: tip-bot for Srikar Dronamraju @ 2017-03-27 10:26 UTC (permalink / raw)
To: linux-tip-commits
Cc: linux-kernel, mingo, tglx, efault, peterz, vincent.guittot,
torvalds, srikar, hpa
Commit-ID: 05b40e057734811ce452344fb3690d09965a7b6a
Gitweb: http://git.kernel.org/tip/05b40e057734811ce452344fb3690d09965a7b6a
Author: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
AuthorDate: Wed, 22 Mar 2017 23:27:50 +0530
Committer: Ingo Molnar <mingo@kernel.org>
CommitDate: Mon, 27 Mar 2017 10:22:26 +0200
sched/fair: Prefer sibiling only if local group is under-utilized
If the child domain prefers tasks to go siblings, the local group could
end up pulling tasks to itself even if the local group is almost equally
loaded as the source group.
Lets assume a 4 core,smt==2 machine running 5 thread ebizzy workload.
Everytime, local group has capacity and source group has atleast 2 threads,
local group tries to pull the task. This causes the threads to constantly
move between different cores. This is even more profound if the cores have
more threads, like in Power 8, smt 8 mode.
Fix this by only allowing local group to pull a task, if the source group
has more number of tasks than the local group.
Here are the relevant perf stat numbers of a 22 core,smt 8 Power 8 machine.
Without patch:
Performance counter stats for 'ebizzy -t 22 -S 100' (5 runs):
1,440 context-switches # 0.001 K/sec ( +- 1.26% )
366 cpu-migrations # 0.000 K/sec ( +- 5.58% )
3,933 page-faults # 0.002 K/sec ( +- 11.08% )
Performance counter stats for 'ebizzy -t 48 -S 100' (5 runs):
6,287 context-switches # 0.001 K/sec ( +- 3.65% )
3,776 cpu-migrations # 0.001 K/sec ( +- 4.84% )
5,702 page-faults # 0.001 K/sec ( +- 9.36% )
Performance counter stats for 'ebizzy -t 96 -S 100' (5 runs):
8,776 context-switches # 0.001 K/sec ( +- 0.73% )
2,790 cpu-migrations # 0.000 K/sec ( +- 0.98% )
10,540 page-faults # 0.001 K/sec ( +- 3.12% )
With patch:
Performance counter stats for 'ebizzy -t 22 -S 100' (5 runs):
1,133 context-switches # 0.001 K/sec ( +- 4.72% )
123 cpu-migrations # 0.000 K/sec ( +- 3.42% )
3,858 page-faults # 0.002 K/sec ( +- 8.52% )
Performance counter stats for 'ebizzy -t 48 -S 100' (5 runs):
2,169 context-switches # 0.000 K/sec ( +- 6.19% )
189 cpu-migrations # 0.000 K/sec ( +- 12.75% )
5,917 page-faults # 0.001 K/sec ( +- 8.09% )
Performance counter stats for 'ebizzy -t 96 -S 100' (5 runs):
5,333 context-switches # 0.001 K/sec ( +- 5.91% )
506 cpu-migrations # 0.000 K/sec ( +- 3.35% )
10,792 page-faults # 0.001 K/sec ( +- 7.75% )
Which show that in these workloads CPU migrations get reduced significantly.
Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
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: Vincent Guittot <vincent.guittot@linaro.org>
Link: http://lkml.kernel.org/r/1490205470-10249-1-git-send-email-srikar@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
kernel/sched/fair.c | 7 ++++---
1 file changed, 4 insertions(+), 3 deletions(-)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 03adf9f..31453d5 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -7565,6 +7565,7 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
{
struct sched_domain *child = env->sd->child;
struct sched_group *sg = env->sd->groups;
+ struct sg_lb_stats *local = &sds->local_stat;
struct sg_lb_stats tmp_sgs;
int load_idx, prefer_sibling = 0;
bool overload = false;
@@ -7581,7 +7582,7 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
local_group = cpumask_test_cpu(env->dst_cpu, sched_group_cpus(sg));
if (local_group) {
sds->local = sg;
- sgs = &sds->local_stat;
+ sgs = local;
if (env->idle != CPU_NEWLY_IDLE ||
time_after_eq(jiffies, sg->sgc->next_update))
@@ -7605,8 +7606,8 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
* the tasks on the system).
*/
if (prefer_sibling && sds->local &&
- group_has_capacity(env, &sds->local_stat) &&
- (sgs->sum_nr_running > 1)) {
+ group_has_capacity(env, local) &&
+ (sgs->sum_nr_running > local->sum_nr_running + 1)) {
sgs->group_no_capacity = 1;
sgs->group_type = group_classify(sg, sgs);
}
^ permalink raw reply related [flat|nested] 4+ messages in thread
end of thread, other threads:[~2017-03-27 10:31 UTC | newest]
Thread overview: 4+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2017-03-22 17:57 [PATCH] sched: Prefer sibiling only if local group is under-utilized Srikar Dronamraju
2017-03-23 7:42 ` Peter Zijlstra
2017-03-23 8:37 ` Vincent Guittot
2017-03-27 10:26 ` [tip:sched/core] sched/fair: " tip-bot for Srikar Dronamraju
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).