From: preeti@linux.vnet.ibm.com (Preeti U Murthy)
To: linux-arm-kernel@lists.infradead.org
Subject: [RFC PATCH 11/13] sched: Modify find_idlest_group to use PJT's metric
Date: Thu, 25 Oct 2012 15:56:06 +0530 [thread overview]
Message-ID: <20121025102605.21022.5545.stgit@preeti.in.ibm.com> (raw)
In-Reply-To: <20121025102045.21022.92489.stgit@preeti.in.ibm.com>
Additional parameters introduced to perform this function which are
calculated using PJT's metrics and its helpers.
Signed-off-by: Preeti U Murthy <preeti@linux.vnet.ibm.com>
---
kernel/sched/fair.c | 14 ++++++++++----
1 file changed, 10 insertions(+), 4 deletions(-)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index a5affbc..c64be1c1 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3173,11 +3173,13 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p,
int this_cpu, int load_idx)
{
struct sched_group *idlest = NULL, *group = sd->groups;
- unsigned long min_load = ULONG_MAX, this_load = 0;
+ unsigned long this_load = 0;
+ u64 min_sg_load = ~0ULL, this_sg_load = 0;/* Helpers for PJT's metrics */
int imbalance = 100 + (sd->imbalance_pct-100)/2;
do {
unsigned long load, avg_load;
+ u64 avg_sg_load;/* Helpers for PJT's metrics */
int local_group;
int i;
@@ -3191,6 +3193,7 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p,
/* Tally up the load of all CPUs in the group */
avg_load = 0;
+ avg_sg_load = 0;
for_each_cpu(i, sched_group_cpus(group)) {
/* Bias balancing toward cpus of our domain */
@@ -3200,20 +3203,23 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p,
load = target_load(i, load_idx);
avg_load += load;
+ avg_sg_load += cpu_rq(i)->cfs.runnable_load_avg;
}
/* Adjust by relative CPU power of the group */
avg_load = (avg_load * SCHED_POWER_SCALE) / group->sgp->power;
+ avg_sg_load = (avg_sg_load * SCHED_POWER_SCALE) / group->sgp->power;
if (local_group) {
this_load = avg_load;
- } else if (avg_load < min_load) {
- min_load = avg_load;
+ this_sg_load = avg_sg_load;
+ } else if (avg_sg_load < min_sg_load) {/* Decision changed to suit PJT's metric */
+ min_sg_load = avg_sg_load;
idlest = group;
}
} while (group = group->next, group != sd->groups);
- if (!idlest || 100*this_load < imbalance*min_load)
+ if (!idlest || 100*this_sg_load < imbalance*min_sg_load)
return NULL;
return idlest;
}
WARNING: multiple messages have this Message-ID (diff)
From: Preeti U Murthy <preeti@linux.vnet.ibm.com>
To: svaidy@linux.vnet.ibm.com, linux-kernel@vger.kernel.org
Cc: mingo@kernel.org, venki@google.com, robin.randhawa@arm.com,
linaro-dev@lists.linaro.org, a.p.zijlstra@chello.nl,
mjg59@srcf.ucam.org, viresh.kumar@linaro.org,
akpm@linux-foundation.org, amit.kucheria@linaro.org,
deepthi@linux.vnet.ibm.com, paul.mckenney@linaro.org,
arjan@linux.intel.com, paulmck@linux.vnet.ibm.com,
srivatsa.bhat@linux.vnet.ibm.com, vincent.guittot@linaro.org,
tglx@linutronix.de, Arvind.Chauhan@arm.com, pjt@google.com,
Morten.Rasmussen@arm.com, linux-arm-kernel@lists.infradead.org,
suresh.b.siddha@intel.com
Subject: [RFC PATCH 11/13] sched: Modify find_idlest_group to use PJT's metric
Date: Thu, 25 Oct 2012 15:56:06 +0530 [thread overview]
Message-ID: <20121025102605.21022.5545.stgit@preeti.in.ibm.com> (raw)
In-Reply-To: <20121025102045.21022.92489.stgit@preeti.in.ibm.com>
Additional parameters introduced to perform this function which are
calculated using PJT's metrics and its helpers.
Signed-off-by: Preeti U Murthy <preeti@linux.vnet.ibm.com>
---
kernel/sched/fair.c | 14 ++++++++++----
1 file changed, 10 insertions(+), 4 deletions(-)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index a5affbc..c64be1c1 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3173,11 +3173,13 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p,
int this_cpu, int load_idx)
{
struct sched_group *idlest = NULL, *group = sd->groups;
- unsigned long min_load = ULONG_MAX, this_load = 0;
+ unsigned long this_load = 0;
+ u64 min_sg_load = ~0ULL, this_sg_load = 0;/* Helpers for PJT's metrics */
int imbalance = 100 + (sd->imbalance_pct-100)/2;
do {
unsigned long load, avg_load;
+ u64 avg_sg_load;/* Helpers for PJT's metrics */
int local_group;
int i;
@@ -3191,6 +3193,7 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p,
/* Tally up the load of all CPUs in the group */
avg_load = 0;
+ avg_sg_load = 0;
for_each_cpu(i, sched_group_cpus(group)) {
/* Bias balancing toward cpus of our domain */
@@ -3200,20 +3203,23 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p,
load = target_load(i, load_idx);
avg_load += load;
+ avg_sg_load += cpu_rq(i)->cfs.runnable_load_avg;
}
/* Adjust by relative CPU power of the group */
avg_load = (avg_load * SCHED_POWER_SCALE) / group->sgp->power;
+ avg_sg_load = (avg_sg_load * SCHED_POWER_SCALE) / group->sgp->power;
if (local_group) {
this_load = avg_load;
- } else if (avg_load < min_load) {
- min_load = avg_load;
+ this_sg_load = avg_sg_load;
+ } else if (avg_sg_load < min_sg_load) {/* Decision changed to suit PJT's metric */
+ min_sg_load = avg_sg_load;
idlest = group;
}
} while (group = group->next, group != sd->groups);
- if (!idlest || 100*this_load < imbalance*min_load)
+ if (!idlest || 100*this_sg_load < imbalance*min_sg_load)
return NULL;
return idlest;
}
next prev parent reply other threads:[~2012-10-25 10:26 UTC|newest]
Thread overview: 44+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-10-25 10:24 [RFC PATCH 00/13] sched: Integrating Per-entity-load-tracking with the core scheduler Preeti U Murthy
2012-10-25 10:24 ` Preeti U Murthy
2012-10-25 10:24 ` [RFC PATCH 01/13] sched:Prevent movement of short running tasks during load balancing Preeti U Murthy
2012-10-25 10:24 ` Preeti U Murthy
2012-10-25 10:25 ` [RFC PATCH 02/13] sched:Pick the apt busy sched group " Preeti U Murthy
2012-10-25 10:25 ` Preeti U Murthy
2012-10-25 10:25 ` [RFC PATCH 03/13] sched:Decide whether there be transfer of loads based on the PJT's metric Preeti U Murthy
2012-10-25 10:25 ` Preeti U Murthy
2012-10-25 10:25 ` [RFC PATCH 04/13] sched:Decide group_imb using " Preeti U Murthy
2012-10-25 10:25 ` Preeti U Murthy
2012-10-25 10:25 ` [RFC PATCH 05/13] sched:Calculate imbalance " Preeti U Murthy
2012-10-25 10:25 ` Preeti U Murthy
2012-10-25 10:25 ` [RFC PATCH 06/13] sched: Changing find_busiest_queue to use " Preeti U Murthy
2012-10-25 10:25 ` Preeti U Murthy
2012-10-25 10:25 ` [RFC PATCH 07/13] sched: Change move_tasks " Preeti U Murthy
2012-10-25 10:25 ` Preeti U Murthy
2012-10-25 10:25 ` [RFC PATCH 08/13] sched: Some miscallaneous changes in load_balance Preeti U Murthy
2012-10-25 10:25 ` Preeti U Murthy
2012-10-25 10:25 ` [RFC PATCH 09/13] sched: Modify check_asym_packing to use PJT's metric Preeti U Murthy
2012-10-25 10:25 ` Preeti U Murthy
2012-10-25 10:26 ` [RFC PATCH 10/13] sched: Modify fix_small_imbalance " Preeti U Murthy
2012-10-25 10:26 ` Preeti U Murthy
2012-10-25 10:26 ` Preeti U Murthy [this message]
2012-10-25 10:26 ` [RFC PATCH 11/13] sched: Modify find_idlest_group " Preeti U Murthy
2012-10-25 10:26 ` [RFC PATCH 12/13] sched: Modify find_idlest_cpu " Preeti U Murthy
2012-10-25 10:26 ` Preeti U Murthy
2012-10-25 10:26 ` [RFC PATCH 13/13] sched: Modifying wake_affine " Preeti U Murthy
2012-10-25 10:26 ` Preeti U Murthy
2012-10-25 10:33 ` [RFC PATCH 00/13] sched: Integrating Per-entity-load-tracking with the core scheduler Preeti Murthy
2012-10-25 15:56 ` Peter Zijlstra
2012-10-25 15:56 ` Peter Zijlstra
2012-10-25 18:00 ` Preeti U Murthy
2012-10-25 18:00 ` Preeti U Murthy
2012-10-25 18:12 ` Preeti U Murthy
2012-10-25 18:12 ` Preeti U Murthy
2012-10-26 12:29 ` Peter Zijlstra
2012-10-26 12:29 ` Peter Zijlstra
2012-10-26 13:07 ` Ingo Molnar
2012-10-26 13:07 ` Ingo Molnar
2012-10-27 3:36 ` Preeti U Murthy
2012-10-27 3:36 ` Preeti U Murthy
2012-10-27 3:33 ` Preeti U Murthy
2012-10-27 3:33 ` Preeti U Murthy
2012-10-26 2:35 ` Preeti Murthy
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20121025102605.21022.5545.stgit@preeti.in.ibm.com \
--to=preeti@linux.vnet.ibm.com \
--cc=linux-arm-kernel@lists.infradead.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.