[PATCH v2] [tip: sched/core] sched: Move PLACE_LAG and RUN_TO_PARITY to sysctl

[Cristian Prundeanu <cpru@amazon.com>]

Replacing CFS with the EEVDF scheduler in kernel 6.6 introduced
significant performance degradation in multiple database-oriented
workloads. This degradation manifests in all kernel versions using EEVDF,
across multiple Linux distributions, hardware architectures (x86_64,
aarm64, amd64), and CPU generations.

Testing combinations of available scheduler features showed that the
largest improvement (short of disabling all EEVDF features) came from
disabling both PLACE_LAG and RUN_TO_PARITY.

Moving PLACE_LAG and RUN_TO_PARITY to sysctl will allow users to override
their default values and persist them with established mechanisms.

Link: https://lore.kernel.org/20241017052000.99200-1-cpru@amazon.com
Signed-off-by: Cristian Prundeanu <cpru@amazon.com>
---
v2: use latest sched/core; defer default value change to a follow-up patch

 include/linux/sched/sysctl.h |  8 ++++++++
 kernel/sched/core.c          | 13 +++++++++++++
 kernel/sched/fair.c          |  7 ++++---
 kernel/sched/features.h      | 10 ----------
 kernel/sysctl.c              | 20 ++++++++++++++++++++
 5 files changed, 45 insertions(+), 13 deletions(-)

diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h
index 5a64582b086b..a899398bc1c4 100644
--- a/include/linux/sched/sysctl.h
+++ b/include/linux/sched/sysctl.h
@@ -29,4 +29,12 @@ extern int sysctl_numa_balancing_mode;
 #define sysctl_numa_balancing_mode	0
 #endif
 
+#if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SYSCTL)
+extern unsigned int sysctl_sched_place_lag_enabled;
+extern unsigned int sysctl_sched_run_to_parity_enabled;
+#else
+#define sysctl_sched_place_lag_enabled 1
+#define sysctl_sched_run_to_parity_enabled 1
+#endif
+
 #endif /* _LINUX_SCHED_SYSCTL_H */
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 9142a0394d46..a379240628ea 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -134,6 +134,19 @@ const_debug unsigned int sysctl_sched_features =
 	0;
 #undef SCHED_FEAT
 
+#ifdef CONFIG_SYSCTL
+/*
+ * Using the avg_vruntime, do the right thing and preserve lag across
+ * sleep+wake cycles. EEVDF placement strategy #1, #2 if disabled.
+ */
+__read_mostly unsigned int sysctl_sched_place_lag_enabled = 1;
+/*
+ * Inhibit (wakeup) preemption until the current task has either matched the
+ * 0-lag point or until it has exhausted its slice.
+ */
+__read_mostly unsigned int sysctl_sched_run_to_parity_enabled = 1;
+#endif
+
 /*
  * Print a warning if need_resched is set for the given duration (if
  * LATENCY_WARN is enabled).
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 1e78caa21436..c87fd1accd54 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -923,7 +923,8 @@ static struct sched_entity *pick_eevdf(struct cfs_rq *cfs_rq)
 	 * Once selected, run a task until it either becomes non-eligible or
 	 * until it gets a new slice. See the HACK in set_next_entity().
 	 */
-	if (sched_feat(RUN_TO_PARITY) && curr && curr->vlag == curr->deadline)
+	if (sysctl_sched_run_to_parity_enabled && curr &&
+	    curr->vlag == curr->deadline)
 		return curr;
 
 	/* Pick the leftmost entity if it's eligible */
@@ -5199,7 +5200,7 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	 *
 	 * EEVDF: placement strategy #1 / #2
 	 */
-	if (sched_feat(PLACE_LAG) && cfs_rq->nr_queued && se->vlag) {
+	if (sysctl_sched_place_lag_enabled && cfs_rq->nr_queued && se->vlag) {
 		struct sched_entity *curr = cfs_rq->curr;
 		unsigned long load;
 
@@ -9327,7 +9328,7 @@ static inline int task_is_ineligible_on_dst_cpu(struct task_struct *p, int dest_
 #else
 	dst_cfs_rq = &cpu_rq(dest_cpu)->cfs;
 #endif
-	if (sched_feat(PLACE_LAG) && dst_cfs_rq->nr_queued &&
+	if (sysctl_sched_place_lag_enabled && dst_cfs_rq->nr_queued &&
 	    !entity_eligible(task_cfs_rq(p), &p->se))
 		return 1;
 
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index 3c12d9f93331..b98ec31ef2c4 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -1,10 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 
-/*
- * Using the avg_vruntime, do the right thing and preserve lag across
- * sleep+wake cycles. EEVDF placement strategy #1, #2 if disabled.
- */
-SCHED_FEAT(PLACE_LAG, true)
 /*
  * Give new tasks half a slice to ease into the competition.
  */
@@ -13,11 +8,6 @@ SCHED_FEAT(PLACE_DEADLINE_INITIAL, true)
  * Preserve relative virtual deadline on 'migration'.
  */
 SCHED_FEAT(PLACE_REL_DEADLINE, true)
-/*
- * Inhibit (wakeup) preemption until the current task has either matched the
- * 0-lag point or until is has exhausted it's slice.
- */
-SCHED_FEAT(RUN_TO_PARITY, true)
 /*
  * Allow wakeup of tasks with a shorter slice to cancel RUN_TO_PARITY for
  * current.
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 7ae7a4136855..11651d87f6d4 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -2019,6 +2019,26 @@ static struct ctl_table kern_table[] = {
 		.extra2		= SYSCTL_INT_MAX,
 	},
 #endif
+#ifdef CONFIG_SCHED_DEBUG
+	{
+		.procname	= "sched_place_lag_enabled",
+		.data		= &sysctl_sched_place_lag_enabled,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
+	},
+	{
+		.procname	= "sched_run_to_parity_enabled",
+		.data		= &sysctl_sched_run_to_parity_enabled,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
+	},
+#endif
 };
 
 static struct ctl_table vm_table[] = {

base-commit: 05dbaf8dd8bf537d4b4eb3115ab42a5fb40ff1f5
-- 
2.48.1