FROMGIT: sched/deadline: Less agressive dl_server handling

Chris reported that commit 5f6bd380c7 ("sched/rt: Remove default
bandwidth control") caused a significant dip in his favourite
benchmark of the day. Simply disabling dl_server cured things.

His workload hammers the 0->1, 1->0 transitions, and the
dl_server_{start,stop}() overhead kills it -- fairly obviously a bad
idea in hind sight and all that.

Change things around to only disable the dl_server when there has not
been a fair task around for a whole period. Since the default period
is 1 second, this ensures the benchmark never trips this, overhead
gone.

Fixes: 557a6bfc66 ("sched/fair: Add trivial fair server")
Reported-by: Chris Mason <clm@meta.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
(cherry picked from commit 7bca60ce656978b01caafc4e2285272ae9631953
 https://git.kernel.org/pub/scm/linux/kernel/git/peterz/queue.git/commit/?h=sched/core)
Link: https://lore.kernel.org/all/20250520101727.507378961@infradead.org/
Tested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Change-Id: Iaa47846edcc4a06e87baf21fccfbd0cbdeaf2b7f
Bug: 410614532
Bug: 422165470
Signed-off-by: Shaleen Agrawal <quic_shalagra@quicinc.com>
[jstultz: Switched to FROMGIT]
Signed-off-by: John Stultz <jstultz@google.com>
This commit is contained in:
Peter Zijlstra
2025-05-20 11:19:30 +02:00
committed by John Stultz
parent 35c421e883
commit 738664c527
2 changed files with 28 additions and 4 deletions

View File

@@ -689,6 +689,7 @@ struct sched_dl_entity {
unsigned int dl_defer : 1;
unsigned int dl_defer_armed : 1;
unsigned int dl_defer_running : 1;
unsigned int dl_server_idle : 1;
/*
* Bandwidth enforcement timer. Each -deadline task has its

View File

@@ -1195,6 +1195,8 @@ static void __push_dl_task(struct rq *rq, struct rq_flags *rf)
/* a defer timer will not be reset if the runtime consumed was < dl_server_min_res */
static const u64 dl_server_min_res = 1 * NSEC_PER_MSEC;
static bool dl_server_stopped(struct sched_dl_entity *dl_se);
static enum hrtimer_restart dl_server_timer(struct hrtimer *timer, struct sched_dl_entity *dl_se)
{
struct rq *rq = rq_of_dl_se(dl_se);
@@ -1214,6 +1216,7 @@ static enum hrtimer_restart dl_server_timer(struct hrtimer *timer, struct sched_
if (!dl_se->server_has_tasks(dl_se)) {
replenish_dl_entity(dl_se);
dl_server_stopped(dl_se);
return HRTIMER_NORESTART;
}
@@ -1620,8 +1623,10 @@ void dl_server_update_idle_time(struct rq *rq, struct task_struct *p)
void dl_server_update(struct sched_dl_entity *dl_se, s64 delta_exec)
{
/* 0 runtime = fair server disabled */
if (dl_se->dl_runtime)
if (dl_se->dl_runtime) {
dl_se->dl_server_idle = 0;
update_curr_dl_se(dl_se->rq, dl_se, delta_exec);
}
}
void dl_server_start(struct sched_dl_entity *dl_se)
@@ -1644,7 +1649,7 @@ void dl_server_start(struct sched_dl_entity *dl_se)
setup_new_dl_entity(dl_se);
}
if (!dl_se->dl_runtime)
if (!dl_se->dl_runtime || dl_se->dl_server_active)
return;
dl_se->dl_server_active = 1;
@@ -1653,7 +1658,7 @@ void dl_server_start(struct sched_dl_entity *dl_se)
resched_curr(dl_se->rq);
}
void dl_server_stop(struct sched_dl_entity *dl_se)
static void __dl_server_stop(struct sched_dl_entity *dl_se)
{
if (!dl_se->dl_runtime)
return;
@@ -1665,6 +1670,24 @@ void dl_server_stop(struct sched_dl_entity *dl_se)
dl_se->dl_server_active = 0;
}
static bool dl_server_stopped(struct sched_dl_entity *dl_se)
{
if (!dl_se->dl_server_active)
return false;
if (dl_se->dl_server_idle) {
__dl_server_stop(dl_se);
return true;
}
dl_se->dl_server_idle = 1;
return false;
}
void dl_server_stop(struct sched_dl_entity *dl_se)
{
}
void dl_server_init(struct sched_dl_entity *dl_se, struct rq *rq,
dl_server_has_tasks_f has_tasks,
dl_server_pick_f pick_task)
@@ -2432,7 +2455,7 @@ again:
if (dl_server(dl_se)) {
p = dl_se->server_pick_task(dl_se);
if (!p) {
if (dl_server_active(dl_se)) {
if (!dl_server_stopped(dl_se)) {
dl_se->dl_yielded = 1;
update_curr_dl_se(rq, dl_se, 0);
}