From: Srikar Dronamraju <srikar@linux.ibm.com>
To: linux-kernel@vger.kernel.org, linuxppc-dev@lists.ozlabs.org,
Peter Zijlstra <peterz@infradead.org>
Cc: Ben Segall <bsegall@google.com>,
Christophe Leroy <christophe.leroy@csgroup.eu>,
Dietmar Eggemann <dietmar.eggemann@arm.com>,
Ingo Molnar <mingo@kernel.org>,
Juri Lelli <juri.lelli@redhat.com>,
K Prateek Nayak <kprateek.nayak@amd.com>,
Madhavan Srinivasan <maddy@linux.ibm.com>,
Mel Gorman <mgorman@suse.de>,
Michael Ellerman <mpe@ellerman.id.au>,
Nicholas Piggin <npiggin@gmail.com>,
Shrikanth Hegde <sshegde@linux.ibm.com>,
Srikar Dronamraju <srikar@linux.ibm.com>,
Steven Rostedt <rostedt@goodmis.org>,
Swapnil Sapkal <swapnil.sapkal@amd.com>,
Thomas Huth <thuth@redhat.com>,
Valentin Schneider <vschneid@redhat.com>,
Vincent Guittot <vincent.guittot@linaro.org>,
virtualization@lists.linux.dev,
Yicong Yang <yangyicong@hisilicon.com>,
Ilya Leoshkevich <iii@linux.ibm.com>
Subject: [PATCH 01/17] sched/fair: Enable group_asym_packing in find_idlest_group
Date: Thu, 4 Dec 2025 23:23:49 +0530 [thread overview]
Message-ID: <20251204175405.1511340-2-srikar@linux.ibm.com> (raw)
In-Reply-To: <20251204175405.1511340-1-srikar@linux.ibm.com>
Current scheduler code doesn't handle SD_ASYM_PACKING in the
find_idlest_cpu path. On few architectures, like Powerpc, cache is at a
core. Moving threads across cores may end up in cache misses.
While asym_packing can be enabled above SMT level, enabling Asym packing
across cores could result in poorer performance due to cache misses.
However if the initial task placement via find_idlest_cpu does take
asym_packing into consideration, then scheduler can avoid asym_packing
migrations. This will result in lesser migrations and better packing and
better overall performance.
Previous version was posted at
https://lore.kernel.org/all/20231018155036.2314342-1-srikar@linux.vnet.ibm.com/t
Signed-off-by: Srikar Dronamraju <srikar@linux.ibm.com>
---
kernel/sched/fair.c | 33 ++++++++++++++++++++++++++++-----
1 file changed, 28 insertions(+), 5 deletions(-)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 5b752324270b..979c3e333fba 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -10664,11 +10664,13 @@ static int idle_cpu_without(int cpu, struct task_struct *p)
* @group: sched_group whose statistics are to be updated.
* @sgs: variable to hold the statistics for this group.
* @p: The task for which we look for the idlest group/CPU.
+ * @this_cpu: current cpu
*/
static inline void update_sg_wakeup_stats(struct sched_domain *sd,
struct sched_group *group,
struct sg_lb_stats *sgs,
- struct task_struct *p)
+ struct task_struct *p,
+ int asym_prefer_cpu)
{
int i, nr_running;
@@ -10705,6 +10707,12 @@ static inline void update_sg_wakeup_stats(struct sched_domain *sd,
}
+ if (asym_prefer_cpu != READ_ONCE(group->asym_prefer_cpu) &&
+ sched_asym(sd, READ_ONCE(group->asym_prefer_cpu),
+ READ_ONCE(asym_prefer_cpu))) {
+ sgs->group_asym_packing = 1;
+ }
+
sgs->group_capacity = group->sgc->capacity;
sgs->group_weight = group->group_weight;
@@ -10721,7 +10729,8 @@ static inline void update_sg_wakeup_stats(struct sched_domain *sd,
sgs->group_capacity;
}
-static bool update_pick_idlest(struct sched_group *idlest,
+static bool update_pick_idlest(struct sched_domain *sd,
+ struct sched_group *idlest,
struct sg_lb_stats *idlest_sgs,
struct sched_group *group,
struct sg_lb_stats *sgs)
@@ -10745,8 +10754,11 @@ static bool update_pick_idlest(struct sched_group *idlest,
return false;
break;
- case group_imbalanced:
case group_asym_packing:
+ return sched_asym(sd, READ_ONCE(group->asym_prefer_cpu),
+ READ_ONCE(idlest->asym_prefer_cpu));
+
+ case group_imbalanced:
case group_smt_balance:
/* Those types are not used in the slow wakeup path */
return false;
@@ -10790,6 +10802,7 @@ sched_balance_find_dst_group(struct sched_domain *sd, struct task_struct *p, int
.avg_load = UINT_MAX,
.group_type = group_overloaded,
};
+ int asym_prefer_cpu;
do {
int local_group;
@@ -10812,10 +10825,12 @@ sched_balance_find_dst_group(struct sched_domain *sd, struct task_struct *p, int
} else {
sgs = &tmp_sgs;
}
+ if (!local || local_group)
+ asym_prefer_cpu = READ_ONCE(group->asym_prefer_cpu);
- update_sg_wakeup_stats(sd, group, sgs, p);
+ update_sg_wakeup_stats(sd, group, sgs, p, asym_prefer_cpu);
- if (!local_group && update_pick_idlest(idlest, &idlest_sgs, group, sgs)) {
+ if (!local_group && update_pick_idlest(sd, idlest, &idlest_sgs, group, sgs)) {
idlest = group;
idlest_sgs = *sgs;
}
@@ -10845,6 +10860,14 @@ sched_balance_find_dst_group(struct sched_domain *sd, struct task_struct *p, int
if (local_sgs.group_type > idlest_sgs.group_type)
return idlest;
+ if (idlest_sgs.group_type == group_asym_packing) {
+ if (sched_asym(sd, READ_ONCE(idlest->asym_prefer_cpu),
+ READ_ONCE(local->asym_prefer_cpu))) {
+ return idlest;
+ }
+ return NULL;
+ }
+
switch (local_sgs.group_type) {
case group_overloaded:
case group_fully_busy:
--
2.43.7
next prev parent reply other threads:[~2025-12-04 17:55 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-12-04 17:53 [PATCH 00/17] Steal time based dynamic CPU resource management Srikar Dronamraju
2025-12-04 17:53 ` Srikar Dronamraju [this message]
2025-12-04 17:53 ` [PATCH 02/17] powerpc/lpar: Reorder steal accounting calculation Srikar Dronamraju
2025-12-04 17:53 ` [PATCH 03/17] pseries/lpar: Process steal metrics Srikar Dronamraju
2025-12-04 17:53 ` [PATCH 04/17] powerpc/smp: Add num_available_cores callback for smp_ops Srikar Dronamraju
2025-12-04 17:53 ` [PATCH 05/17] pseries/smp: Query and set entitlements Srikar Dronamraju
2025-12-04 17:53 ` [PATCH 06/17] powerpc/smp: Delay processing steal time at boot Srikar Dronamraju
2025-12-04 17:53 ` [PATCH 07/17] sched/core: Set balance_callback only if CPU is dying Srikar Dronamraju
2025-12-04 17:53 ` [PATCH 08/17] sched/core: Implement CPU soft offline/online Srikar Dronamraju
2025-12-05 16:03 ` Peter Zijlstra
2025-12-05 18:54 ` Srikar Dronamraju
2025-12-05 16:07 ` Peter Zijlstra
2025-12-05 18:57 ` Srikar Dronamraju
2025-12-04 17:53 ` [PATCH 09/17] powerpc/smp: Implement arch_scale_cpu_capacity for shared LPARs Srikar Dronamraju
2025-12-04 17:53 ` [PATCH 10/17] powerpc/smp: Define arch_update_cpu_topology " Srikar Dronamraju
2025-12-04 17:53 ` [PATCH 11/17] pseries/smp: Create soft offline infrastructure for Powerpc " Srikar Dronamraju
2025-12-04 17:54 ` [PATCH 12/17] pseries/smp: Trigger softoffline based on steal metrics Srikar Dronamraju
2025-12-04 17:54 ` [PATCH 13/17] pseries/smp: Account cores when triggering softoffline Srikar Dronamraju
2025-12-04 17:54 ` [PATCH 14/17] powerpc/smp: Assume preempt if CPU is inactive Srikar Dronamraju
2025-12-04 17:54 ` [PATCH 15/17] pseries/hotplug: Update available_cores on a dlpar event Srikar Dronamraju
2025-12-04 17:54 ` [PATCH 16/17] pseries/smp: Allow users to override steal thresholds Srikar Dronamraju
2025-12-04 17:54 ` [PATCH 17/17] pseries/lpar: Add debug interface to set steal interval Srikar Dronamraju
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=20251204175405.1511340-2-srikar@linux.ibm.com \
--to=srikar@linux.ibm.com \
--cc=bsegall@google.com \
--cc=christophe.leroy@csgroup.eu \
--cc=dietmar.eggemann@arm.com \
--cc=iii@linux.ibm.com \
--cc=juri.lelli@redhat.com \
--cc=kprateek.nayak@amd.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linuxppc-dev@lists.ozlabs.org \
--cc=maddy@linux.ibm.com \
--cc=mgorman@suse.de \
--cc=mingo@kernel.org \
--cc=mpe@ellerman.id.au \
--cc=npiggin@gmail.com \
--cc=peterz@infradead.org \
--cc=rostedt@goodmis.org \
--cc=sshegde@linux.ibm.com \
--cc=swapnil.sapkal@amd.com \
--cc=thuth@redhat.com \
--cc=vincent.guittot@linaro.org \
--cc=virtualization@lists.linux.dev \
--cc=vschneid@redhat.com \
--cc=yangyicong@hisilicon.com \
/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 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).