The find_busiest_queue() naming has two small quirks:

 - Scheduler functions that deal with runqueues usually have a rq_ prefix
   or _rq postfix, but this function has neither.

 - Plus the 'busiest' qualifier to this function was historically
   correct, but has become somewhat of a misnomer: in quite a few
   cases we will not pick the busiest runqueue - but the best
   (possible) runqueue we can balance tasks from. So name it a
   bit more neutrally, similar to the 'src/dst' nomenclature
   we are already using when moving tasks between runqueues.

To fix both quirks, rename it to find_src_rq().

Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Shrikanth Hegde <sshegde@linux.ibm.com>
Cc: Valentin Schneider <vschneid@redhat.com>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
---
 kernel/sched/fair.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 0d2753c50be9..e600cac7806d 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -10959,9 +10959,9 @@ static struct sched_group *find_busiest_group(struct lb_env *env)
 }
 
 /*
- * find_busiest_queue - find the busiest runqueue among the CPUs in the group.
+ * find_src_rq - find the busiest runqueue among the CPUs in the group.
  */
-static struct rq *find_busiest_queue(struct lb_env *env,
+static struct rq *find_src_rq(struct lb_env *env,
 				     struct sched_group *group)
 {
 	struct rq *busiest = NULL, *rq;
@@ -11280,7 +11280,7 @@ static int sched_balance_rq(int this_cpu, struct rq *this_rq,
 		goto out_balanced;
 	}
 
-	busiest = find_busiest_queue(&env, group);
+	busiest = find_src_rq(&env, group);
 	if (!busiest) {
 		schedstat_inc(sd->lb_nobusyq[idle]);
 		goto out_balanced;
-- 
2.40.1

The following commit has been merged into the sched/core branch of tip:

Commit-ID:     f1cd2e2e79d283e315356bd403c7f928e994f057
Gitweb:        https://git.kernel.org/tip/f1cd2e2e79d283e315356bd403c7f928e994f057
Author:        Ingo Molnar <mingo@kernel.org>
AuthorDate:    Mon, 23 Oct 2023 13:04:12 +02:00
Committer:     Ingo Molnar <mingo@kernel.org>
CommitterDate: Tue, 12 Mar 2024 12:00:00 +01:00

sched/balancing: Rename find_busiest_queue() => sched_balance_find_src_rq()

The find_busiest_queue() naming has two small quirks:

 - Scheduler functions that deal with runqueues usually have a rq_ prefix
   or _rq postfix, but this function has neither.

 - Plus the 'busiest' qualifier to this function was historically
   correct, but has become somewhat of a misnomer: in quite a few
   cases we will not pick the busiest runqueue - but the best
   (possible) runqueue we can balance tasks from. So name it a
   bit more neutrally, similar to the 'src/dst' nomenclature
   we are already using when moving tasks between runqueues.

To fix both quirks, and to standardize scheduler load-balancing
function names on the sched_balance_() prefix, rename the
function to sched_balance_find_src_rq().

Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Shrikanth Hegde <sshegde@linux.ibm.com>
Link: https://lore.kernel.org/r/20240308111819.1101550-7-mingo@kernel.org
---
 kernel/sched/fair.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 0d2753c..1cd9a18 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -10959,9 +10959,9 @@ out_balanced:
 }
 
 /*
- * find_busiest_queue - find the busiest runqueue among the CPUs in the group.
+ * sched_balance_find_src_rq - find the busiest runqueue among the CPUs in the group.
  */
-static struct rq *find_busiest_queue(struct lb_env *env,
+static struct rq *sched_balance_find_src_rq(struct lb_env *env,
 				     struct sched_group *group)
 {
 	struct rq *busiest = NULL, *rq;
@@ -11280,7 +11280,7 @@ redo:
 		goto out_balanced;
 	}
 
-	busiest = find_busiest_queue(&env, group);
+	busiest = sched_balance_find_src_rq(&env, group);
 	if (!busiest) {
 		schedstat_inc(sd->lb_nobusyq[idle]);
 		goto out_balanced;