From f23c042ce34ba265cf3129d530702b5d218e3f4b Mon Sep 17 00:00:00 2001 From: Daniel Bristot de Oliveira Date: Mon, 27 May 2024 14:06:47 +0200 Subject: sched/deadline: Comment sched_dl_entity::dl_server variable Add an explanation for the newly added variable. Fixes: 63ba8422f876 ("sched/deadline: Introduce deadline servers") Signed-off-by: Daniel Bristot de Oliveira Signed-off-by: Peter Zijlstra (Intel) Tested-by: Juri Lelli Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/147f7aa8cb8fd925f36aa8059af6a35aad08b45a.1716811044.git.bristot@kernel.org --- include/linux/sched.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index f8d150343d42..1c771ea4481d 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -639,6 +639,8 @@ struct sched_dl_entity { * * @dl_overrun tells if the task asked to be informed about runtime * overruns. + * + * @dl_server tells if this is a server entity. */ unsigned int dl_throttled : 1; unsigned int dl_yielded : 1; -- cgit v1.2.3 From a110a81c52a9de73e2e57e826dd3bf0fd4c22226 Mon Sep 17 00:00:00 2001 From: Daniel Bristot de Oliveira Date: Mon, 27 May 2024 14:06:51 +0200 Subject: sched/deadline: Deferrable dl server Among the motivations for the DL servers is the real-time throttling mechanism. This mechanism works by throttling the rt_rq after running for a long period without leaving space for fair tasks. The base dl server avoids this problem by boosting fair tasks instead of throttling the rt_rq. The point is that it boosts without waiting for potential starvation, causing some non-intuitive cases. For example, an IRQ dispatches two tasks on an idle system, a fair and an RT. The DL server will be activated, running the fair task before the RT one. This problem can be avoided by deferring the dl server activation. By setting the defer option, the dl_server will dispatch an SCHED_DEADLINE reservation with replenished runtime, but throttled. The dl_timer will be set for the defer time at (period - runtime) ns from start time. Thus boosting the fair rq at defer time. If the fair scheduler has the opportunity to run while waiting for defer time, the dl server runtime will be consumed. If the runtime is completely consumed before the defer time, the server will be replenished while still in a throttled state. Then, the dl_timer will be reset to the new defer time If the fair server reaches the defer time without consuming its runtime, the server will start running, following CBS rules (thus without breaking SCHED_DEADLINE). Then the server will continue the running state (without deferring) until it fair tasks are able to execute as regular fair scheduler (end of the starvation). Signed-off-by: Daniel Bristot de Oliveira Signed-off-by: Peter Zijlstra (Intel) Tested-by: Juri Lelli Link: https://lore.kernel.org/r/dd175943c72533cd9f0b87767c6499204879cc38.1716811044.git.bristot@kernel.org --- include/linux/sched.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 1c771ea4481d..4edd7e2096fb 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -641,12 +641,24 @@ struct sched_dl_entity { * overruns. * * @dl_server tells if this is a server entity. + * + * @dl_defer tells if this is a deferred or regular server. For + * now only defer server exists. + * + * @dl_defer_armed tells if the deferrable server is waiting + * for the replenishment timer to activate it. + * + * @dl_defer_running tells if the deferrable server is actually + * running, skipping the defer phase. */ unsigned int dl_throttled : 1; unsigned int dl_yielded : 1; unsigned int dl_non_contending : 1; unsigned int dl_overrun : 1; unsigned int dl_server : 1; + unsigned int dl_defer : 1; + unsigned int dl_defer_armed : 1; + unsigned int dl_defer_running : 1; /* * Bandwidth enforcement timer. Each -deadline task has its -- cgit v1.2.3 From c8a85394cfdb4696b4e2f8a0f3066a1c921af426 Mon Sep 17 00:00:00 2001 From: "Joel Fernandes (Google)" Date: Mon, 27 May 2024 14:06:54 +0200 Subject: sched/core: Fix picking of tasks for core scheduling with DL server * Use simple CFS pick_task for DL pick_task DL server's pick_task calls CFS's pick_next_task_fair(), this is wrong because core scheduling's pick_task only calls CFS's pick_task() for evaluation / checking of the CFS task (comparing across CPUs), not for actually affirmatively picking the next task. This causes RB tree corruption issues in CFS that were found by syzbot. * Make pick_task_fair clear DL server A DL task pick might set ->dl_server, but it is possible the task will never run (say the other HT has a stop task). If the CFS task is picked in the future directly (say without DL server), ->dl_server will be set. So clear it in pick_task_fair(). This fixes the KASAN issue reported by syzbot in set_next_entity(). (DL refactoring suggestions by Vineeth Pillai). Reported-by: Suleiman Souhlal Signed-off-by: "Joel Fernandes (Google)" Signed-off-by: Daniel Bristot de Oliveira Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Vineeth Pillai Tested-by: Juri Lelli Link: https://lore.kernel.org/r/b10489ab1f03d23e08e6097acea47442e7d6466f.1716811044.git.bristot@kernel.org --- include/linux/sched.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 4edd7e2096fb..2c1b4ee3234f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -686,7 +686,8 @@ struct sched_dl_entity { */ struct rq *rq; dl_server_has_tasks_f server_has_tasks; - dl_server_pick_f server_pick; + dl_server_pick_f server_pick_next; + dl_server_pick_f server_pick_task; #ifdef CONFIG_RT_MUTEXES /* -- cgit v1.2.3 From 130fd056dd82b02db9a661c013071af35309be1a Mon Sep 17 00:00:00 2001 From: Qais Yousef Date: Mon, 10 Jun 2024 20:20:16 +0100 Subject: sched/rt: Clean up usage of rt_task() rt_task() checks if a task has RT priority. But depends on your dictionary, this could mean it belongs to RT class, or is a 'realtime' task, which includes RT and DL classes. Since this has caused some confusion already on discussion [1], it seemed a clean up is due. I define the usage of rt_task() to be tasks that belong to RT class. Make sure that it returns true only for RT class and audit the users and replace the ones required the old behavior with the new realtime_task() which returns true for RT and DL classes. Introduce similar realtime_prio() to create similar distinction to rt_prio() and update the users that required the old behavior to use the new function. Move MAX_DL_PRIO to prio.h so it can be used in the new definitions. Document the functions to make it more obvious what is the difference between them. PI-boosted tasks is a factor that must be taken into account when choosing which function to use. Rename task_is_realtime() to realtime_task_policy() as the old name is confusing against the new realtime_task(). No functional changes were intended. [1] https://lore.kernel.org/lkml/20240506100509.GL40213@noisy.programming.kicks-ass.net/ Signed-off-by: Qais Yousef Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Phil Auld Reviewed-by: "Steven Rostedt (Google)" Reviewed-by: Sebastian Andrzej Siewior Link: https://lore.kernel.org/r/20240610192018.1567075-2-qyousef@layalina.io --- include/linux/ioprio.h | 2 +- include/linux/sched/deadline.h | 6 ++++-- include/linux/sched/prio.h | 1 + include/linux/sched/rt.h | 27 ++++++++++++++++++++++++++- 4 files changed, 32 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ioprio.h b/include/linux/ioprio.h index db1249cd9692..75859b78d540 100644 --- a/include/linux/ioprio.h +++ b/include/linux/ioprio.h @@ -40,7 +40,7 @@ static inline int task_nice_ioclass(struct task_struct *task) { if (task->policy == SCHED_IDLE) return IOPRIO_CLASS_IDLE; - else if (task_is_realtime(task)) + else if (realtime_task_policy(task)) return IOPRIO_CLASS_RT; else return IOPRIO_CLASS_BE; diff --git a/include/linux/sched/deadline.h b/include/linux/sched/deadline.h index df3aca89d4f5..5cb88b748ad6 100644 --- a/include/linux/sched/deadline.h +++ b/include/linux/sched/deadline.h @@ -10,8 +10,6 @@ #include -#define MAX_DL_PRIO 0 - static inline int dl_prio(int prio) { if (unlikely(prio < MAX_DL_PRIO)) @@ -19,6 +17,10 @@ static inline int dl_prio(int prio) return 0; } +/* + * Returns true if a task has a priority that belongs to DL class. PI-boosted + * tasks will return true. Use dl_policy() to ignore PI-boosted tasks. + */ static inline int dl_task(struct task_struct *p) { return dl_prio(p->prio); diff --git a/include/linux/sched/prio.h b/include/linux/sched/prio.h index ab83d85e1183..6ab43b4f72f9 100644 --- a/include/linux/sched/prio.h +++ b/include/linux/sched/prio.h @@ -14,6 +14,7 @@ */ #define MAX_RT_PRIO 100 +#define MAX_DL_PRIO 0 #define MAX_PRIO (MAX_RT_PRIO + NICE_WIDTH) #define DEFAULT_PRIO (MAX_RT_PRIO + NICE_WIDTH / 2) diff --git a/include/linux/sched/rt.h b/include/linux/sched/rt.h index b2b9e6eb9683..a055dd68a77c 100644 --- a/include/linux/sched/rt.h +++ b/include/linux/sched/rt.h @@ -7,18 +7,43 @@ struct task_struct; static inline int rt_prio(int prio) +{ + if (unlikely(prio < MAX_RT_PRIO && prio >= MAX_DL_PRIO)) + return 1; + return 0; +} + +static inline int realtime_prio(int prio) { if (unlikely(prio < MAX_RT_PRIO)) return 1; return 0; } +/* + * Returns true if a task has a priority that belongs to RT class. PI-boosted + * tasks will return true. Use rt_policy() to ignore PI-boosted tasks. + */ static inline int rt_task(struct task_struct *p) { return rt_prio(p->prio); } -static inline bool task_is_realtime(struct task_struct *tsk) +/* + * Returns true if a task has a priority that belongs to RT or DL classes. + * PI-boosted tasks will return true. Use realtime_task_policy() to ignore + * PI-boosted tasks. + */ +static inline int realtime_task(struct task_struct *p) +{ + return realtime_prio(p->prio); +} + +/* + * Returns true if a task has a policy that belongs to RT or DL classes. + * PI-boosted tasks will return false. + */ +static inline bool realtime_task_policy(struct task_struct *tsk) { int policy = tsk->policy; -- cgit v1.2.3 From b166af3db70fdcecf125662a2360471bb20be203 Mon Sep 17 00:00:00 2001 From: Qais Yousef Date: Mon, 10 Jun 2024 20:20:17 +0100 Subject: sched/rt, dl: Convert functions to return bool {rt, realtime, dl}_{task, prio}() functions' return value is actually a bool. Convert their return type to reflect that. Suggested-by: "Steven Rostedt (Google)" Signed-off-by: Qais Yousef Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Sebastian Andrzej Siewior Reviewed-by: "Steven Rostedt (Google)" Reviewed-by: Metin Kaya Link: https://lore.kernel.org/r/20240610192018.1567075-3-qyousef@layalina.io --- include/linux/sched/deadline.h | 8 +++----- include/linux/sched/rt.h | 16 ++++++---------- 2 files changed, 9 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/deadline.h b/include/linux/sched/deadline.h index 5cb88b748ad6..3a912ab42bb5 100644 --- a/include/linux/sched/deadline.h +++ b/include/linux/sched/deadline.h @@ -10,18 +10,16 @@ #include -static inline int dl_prio(int prio) +static inline bool dl_prio(int prio) { - if (unlikely(prio < MAX_DL_PRIO)) - return 1; - return 0; + return unlikely(prio < MAX_DL_PRIO); } /* * Returns true if a task has a priority that belongs to DL class. PI-boosted * tasks will return true. Use dl_policy() to ignore PI-boosted tasks. */ -static inline int dl_task(struct task_struct *p) +static inline bool dl_task(struct task_struct *p) { return dl_prio(p->prio); } diff --git a/include/linux/sched/rt.h b/include/linux/sched/rt.h index a055dd68a77c..91ef1ef2019f 100644 --- a/include/linux/sched/rt.h +++ b/include/linux/sched/rt.h @@ -6,25 +6,21 @@ struct task_struct; -static inline int rt_prio(int prio) +static inline bool rt_prio(int prio) { - if (unlikely(prio < MAX_RT_PRIO && prio >= MAX_DL_PRIO)) - return 1; - return 0; + return unlikely(prio < MAX_RT_PRIO && prio >= MAX_DL_PRIO); } -static inline int realtime_prio(int prio) +static inline bool realtime_prio(int prio) { - if (unlikely(prio < MAX_RT_PRIO)) - return 1; - return 0; + return unlikely(prio < MAX_RT_PRIO); } /* * Returns true if a task has a priority that belongs to RT class. PI-boosted * tasks will return true. Use rt_policy() to ignore PI-boosted tasks. */ -static inline int rt_task(struct task_struct *p) +static inline bool rt_task(struct task_struct *p) { return rt_prio(p->prio); } @@ -34,7 +30,7 @@ static inline int rt_task(struct task_struct *p) * PI-boosted tasks will return true. Use realtime_task_policy() to ignore * PI-boosted tasks. */ -static inline int realtime_task(struct task_struct *p) +static inline bool realtime_task(struct task_struct *p) { return realtime_prio(p->prio); } -- cgit v1.2.3 From ae04f69de0bef93c7086cf2983dbc8e8fd624ebe Mon Sep 17 00:00:00 2001 From: Qais Yousef Date: Mon, 10 Jun 2024 20:20:18 +0100 Subject: sched/rt: Rename realtime_{prio, task}() to rt_or_dl_{prio, task}() Some find the name realtime overloaded. Use rt_or_dl() as an alternative, hopefully better, name. Suggested-by: Daniel Bristot de Oliveira Signed-off-by: Qais Yousef Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20240610192018.1567075-4-qyousef@layalina.io --- include/linux/ioprio.h | 2 +- include/linux/sched/rt.h | 10 +++++----- 2 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ioprio.h b/include/linux/ioprio.h index 75859b78d540..b25377b6ea98 100644 --- a/include/linux/ioprio.h +++ b/include/linux/ioprio.h @@ -40,7 +40,7 @@ static inline int task_nice_ioclass(struct task_struct *task) { if (task->policy == SCHED_IDLE) return IOPRIO_CLASS_IDLE; - else if (realtime_task_policy(task)) + else if (rt_or_dl_task_policy(task)) return IOPRIO_CLASS_RT; else return IOPRIO_CLASS_BE; diff --git a/include/linux/sched/rt.h b/include/linux/sched/rt.h index 91ef1ef2019f..4e3338103654 100644 --- a/include/linux/sched/rt.h +++ b/include/linux/sched/rt.h @@ -11,7 +11,7 @@ static inline bool rt_prio(int prio) return unlikely(prio < MAX_RT_PRIO && prio >= MAX_DL_PRIO); } -static inline bool realtime_prio(int prio) +static inline bool rt_or_dl_prio(int prio) { return unlikely(prio < MAX_RT_PRIO); } @@ -27,19 +27,19 @@ static inline bool rt_task(struct task_struct *p) /* * Returns true if a task has a priority that belongs to RT or DL classes. - * PI-boosted tasks will return true. Use realtime_task_policy() to ignore + * PI-boosted tasks will return true. Use rt_or_dl_task_policy() to ignore * PI-boosted tasks. */ -static inline bool realtime_task(struct task_struct *p) +static inline bool rt_or_dl_task(struct task_struct *p) { - return realtime_prio(p->prio); + return rt_or_dl_prio(p->prio); } /* * Returns true if a task has a policy that belongs to RT or DL classes. * PI-boosted tasks will return false. */ -static inline bool realtime_task_policy(struct task_struct *tsk) +static inline bool rt_or_dl_task_policy(struct task_struct *tsk) { int policy = tsk->policy; -- cgit v1.2.3 From abc158c82ae555078aa5dd2d8407c3df0f868904 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 23 May 2024 10:55:59 +0200 Subject: sched: Prepare generic code for delayed dequeue While most of the delayed dequeue code can be done inside the sched_class itself, there is one location where we do not have an appropriate hook, namely ttwu_runnable(). Add an ENQUEUE_DELAYED call to the on_rq path to deal with waking delayed dequeue tasks. Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Valentin Schneider Tested-by: Valentin Schneider Link: https://lkml.kernel.org/r/20240727105029.200000445@infradead.org --- include/linux/sched.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 2c1b4ee3234f..f4a648e739e1 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -544,6 +544,7 @@ struct sched_entity { struct list_head group_node; unsigned int on_rq; + unsigned int sched_delayed; u64 exec_start; u64 sum_exec_runtime; -- cgit v1.2.3 From a1c446611e31ca5363d4db51e398271da1dce0af Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 1 Jul 2024 21:30:09 +0200 Subject: sched,freezer: Mark TASK_FROZEN special The special task states are those that do not suffer spurious wakeups, TASK_FROZEN is very much one of those, mark it as such. Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Valentin Schneider Tested-by: Valentin Schneider Link: https://lkml.kernel.org/r/20240727105029.998329901@infradead.org --- include/linux/sched.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index f4a648e739e1..8a3a389bd623 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -149,8 +149,9 @@ struct user_event_mm; * Special states are those that do not use the normal wait-loop pattern. See * the comment with set_special_state(). */ -#define is_special_task_state(state) \ - ((state) & (__TASK_STOPPED | __TASK_TRACED | TASK_PARKED | TASK_DEAD)) +#define is_special_task_state(state) \ + ((state) & (__TASK_STOPPED | __TASK_TRACED | TASK_PARKED | \ + TASK_DEAD | TASK_FROZEN)) #ifdef CONFIG_DEBUG_ATOMIC_SLEEP # define debug_normal_state_change(state_value) \ -- cgit v1.2.3 From 82e9d0456e06cebe2c89f3c73cdbc9e3805e9437 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 31 May 2024 15:49:40 +0200 Subject: sched/fair: Avoid re-setting virtual deadline on 'migrations' During OSPM24 Youssef noted that migrations are re-setting the virtual deadline. Notably everything that does a dequeue-enqueue, like setting nice, changing preferred numa-node, and a myriad of other random crap, will cause this to happen. This shouldn't be. Preserve the relative virtual deadline across such dequeue/enqueue cycles. Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Valentin Schneider Tested-by: Valentin Schneider Link: https://lkml.kernel.org/r/20240727105030.625119246@infradead.org --- include/linux/sched.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 8a3a389bd623..d25e1cfd5766 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -544,8 +544,10 @@ struct sched_entity { u64 min_vruntime; struct list_head group_node; - unsigned int on_rq; - unsigned int sched_delayed; + unsigned char on_rq; + unsigned char sched_delayed; + unsigned char rel_deadline; + /* hole */ u64 exec_start; u64 sum_exec_runtime; -- cgit v1.2.3 From 857b158dc5e81c6de795ef6be006eed146098fc6 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 22 May 2023 13:46:30 +0200 Subject: sched/eevdf: Use sched_attr::sched_runtime to set request/slice suggestion Allow applications to directly set a suggested request/slice length using sched_attr::sched_runtime. The implementation clamps the value to: 0.1[ms] <= slice <= 100[ms] which is 1/10 the size of HZ=1000 and 10 times the size of HZ=100. Applications should strive to use their periodic runtime at a high confidence interval (95%+) as the target slice. Using a smaller slice will introduce undue preemptions, while using a larger value will increase latency. For all the following examples assume a scheduling quantum of 8, and for consistency all examples have W=4: {A,B,C,D}(w=1,r=8): ABCD... +---+---+---+--- t=0, V=1.5 t=1, V=3.5 A |------< A |------< B |------< B |------< C |------< C |------< D |------< D |------< ---+*------+-------+--- ---+--*----+-------+--- t=2, V=5.5 t=3, V=7.5 A |------< A |------< B |------< B |------< C |------< C |------< D |------< D |------< ---+----*--+-------+--- ---+------*+-------+--- Note: 4 identical tasks in FIFO order ~~~ {A,B}(w=1,r=16) C(w=2,r=16) AACCBBCC... +---+---+---+--- t=0, V=1.25 t=2, V=5.25 A |--------------< A |--------------< B |--------------< B |--------------< C |------< C |------< ---+*------+-------+--- ---+----*--+-------+--- t=4, V=8.25 t=6, V=12.25 A |--------------< A |--------------< B |--------------< B |--------------< C |------< C |------< ---+-------*-------+--- ---+-------+---*---+--- Note: 1 heavy task -- because q=8, double r such that the deadline of the w=2 task doesn't go below q. Note: observe the full schedule becomes: W*max(r_i/w_i) = 4*2q = 8q in length. Note: the period of the heavy task is half the full period at: W*(r_i/w_i) = 4*(2q/2) = 4q ~~~ {A,C,D}(w=1,r=16) B(w=1,r=8): BAACCBDD... +---+---+---+--- t=0, V=1.5 t=1, V=3.5 A |--------------< A |---------------< B |------< B |------< C |--------------< C |--------------< D |--------------< D |--------------< ---+*------+-------+--- ---+--*----+-------+--- t=3, V=7.5 t=5, V=11.5 A |---------------< A |---------------< B |------< B |------< C |--------------< C |--------------< D |--------------< D |--------------< ---+------*+-------+--- ---+-------+--*----+--- t=6, V=13.5 A |---------------< B |------< C |--------------< D |--------------< ---+-------+----*--+--- Note: 1 short task -- again double r so that the deadline of the short task won't be below q. Made B short because its not the leftmost task, but is eligible with the 0,1,2,3 spread. Note: like with the heavy task, the period of the short task observes: W*(r_i/w_i) = 4*(1q/1) = 4q ~~~ A(w=1,r=16) B(w=1,r=8) C(w=2,r=16) BCCAABCC... +---+---+---+--- t=0, V=1.25 t=1, V=3.25 A |--------------< A |--------------< B |------< B |------< C |------< C |------< ---+*------+-------+--- ---+--*----+-------+--- t=3, V=7.25 t=5, V=11.25 A |--------------< A |--------------< B |------< B |------< C |------< C |------< ---+------*+-------+--- ---+-------+--*----+--- t=6, V=13.25 A |--------------< B |------< C |------< ---+-------+----*--+--- Note: 1 heavy and 1 short task -- combine them all. Note: both the short and heavy task end up with a period of 4q ~~~ A(w=1,r=16) B(w=2,r=16) C(w=1,r=8) BBCAABBC... +---+---+---+--- t=0, V=1 t=2, V=5 A |--------------< A |--------------< B |------< B |------< C |------< C |------< ---+*------+-------+--- ---+----*--+-------+--- t=3, V=7 t=5, V=11 A |--------------< A |--------------< B |------< B |------< C |------< C |------< ---+------*+-------+--- ---+-------+--*----+--- t=7, V=15 A |--------------< B |------< C |------< ---+-------+------*+--- Note: as before but permuted ~~~ From all this it can be deduced that, for the steady state: - the total period (P) of a schedule is: W*max(r_i/w_i) - the average period of a task is: W*(r_i/w_i) - each task obtains the fair share: w_i/W of each full period P Signed-off-by: Peter Zijlstra (Intel) Tested-by: Valentin Schneider Link: https://lkml.kernel.org/r/20240727105030.842834421@infradead.org --- include/linux/sched.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index d25e1cfd5766..89a3d8d94e96 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -547,6 +547,7 @@ struct sched_entity { unsigned char on_rq; unsigned char sched_delayed; unsigned char rel_deadline; + unsigned char custom_slice; /* hole */ u64 exec_start; -- cgit v1.2.3 From aef6987d89544d63a47753cf3741cabff0b5574c Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 20 Jun 2024 13:16:49 +0200 Subject: sched/eevdf: Propagate min_slice up the cgroup hierarchy In the absence of an explicit cgroup slice configureation, make mixed slice length work with cgroups by propagating the min_slice up the hierarchy. This ensures the cgroup entity gets timely service to service its entities that have this timing constraint set on them. Signed-off-by: Peter Zijlstra (Intel) Tested-by: Valentin Schneider Link: https://lkml.kernel.org/r/20240727105030.948188417@infradead.org --- include/linux/sched.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 89a3d8d94e96..3709dedbab59 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -542,6 +542,7 @@ struct sched_entity { struct rb_node run_node; u64 deadline; u64 min_vruntime; + u64 min_slice; struct list_head group_node; unsigned char on_rq; -- cgit v1.2.3 From 4686cc598f669dea1b50dde1568e6c65c355bc67 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 14 Aug 2024 00:25:51 +0200 Subject: sched: Clean up DL server vs core sched Abide by the simple rule: pick_next_task() := pick_task() + set_next_task(.first = true) This allows us to trivially get rid of server_pick_next() and things collapse nicely. Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20240813224015.837303391@infradead.org --- include/linux/sched.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 3709dedbab59..57cf27a3045c 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -692,7 +692,6 @@ struct sched_dl_entity { */ struct rq *rq; dl_server_has_tasks_f server_has_tasks; - dl_server_pick_f server_pick_next; dl_server_pick_f server_pick_task; #ifdef CONFIG_RT_MUTEXES -- cgit v1.2.3