Change from v11
-. Rebase onto the latest tip/sched/core
-. make the word 'cpu' in comments be upper case as Ingo did
in the commit 97fb7a0a89
-. Avoid a compile warning caused by mismatching bwt const and
non-const 'struct sched_domain' in find_cpu()
Change from v10
-. modify a comment a bit as Steven suggested
Change from v9
-. modify a comment a bit so to be more clear as Juri suggested
Change from v8
-. add suggested-by Peterz
-. add several comments
Change from v7
-. fix a trivial typo
-. modify commit messages to explain what it does more clearly
-. simplify code with an existing macro
Change from v6
-. add a comment about selection of fallback_cpu incase more than one exist
-. modify a comment explaining what we do wrt PREFER_SIBLING
Change from v5
-. exclude two patches already picked up by peterz
(sched/deadline: Make find_later_rq() choose a closer cpu in topology)
(sched/deadline: Change return value of cpudl_find())
-. apply what peterz fixed for 'prefer sibling', into deadline and rt
Change from v4
-. remove a patch that might cause huge lock contention
(by spin lock(&cpudl.lock) in a hot path of scheduler)
Change from v3
-. rename closest_cpu to best_cpu so that it align with rt
-. protect referring cpudl.elements with cpudl.lock
-. change return value of cpudl_find() to bool
Change from v2
-. add support for SD_PREFER_SIBLING
Change from v1
-. clean up the patch
Byungchul Park (2):
sched/deadline: Add support for SD_PREFER_SIBLING on find_later_rq()
sched/rt: Add support for SD_PREFER_SIBLING on find_lowest_rq()
kernel/sched/deadline.c | 80 ++++++++++++++++++++++++++++++++++++++++++++-----
kernel/sched/rt.c | 78 +++++++++++++++++++++++++++++++++++++++++++++--
2 files changed, 148 insertions(+), 10 deletions(-)
--
1.9.1
Hello Juri,
I've changed the code a little bit to avoid a compile warning caused by
'const' args of find_cpu(). Can I keep your Acked-by?
BEFORE:
static int find_cpu(const struct cpumask *mask,
const struct sched_domain *sd,
const struct sched_domain *prefer)
AFTER:
static int find_cpu(const struct cpumask *mask,
struct sched_domain *sd,
struct sched_domain *prefer)
(I temporarily removed the Acked-by you gave me.)
Acked-by: Juri Lelli <[email protected]>
-----8<-----
From 5a4753e8c15369420a16fa04026f74ae5c9d377c Mon Sep 17 00:00:00 2001
From: Byungchul Park <[email protected]>
Date: Mon, 4 Jun 2018 16:46:56 +0900
Subject: [RESEND PATCH v12 1/2] sched/deadline: Add support for SD_PREFER_SIBLING on
find_later_rq()
It would be better to try to check other siblings first if
SD_PREFER_SIBLING is flaged when pushing tasks - migration.
Suggested-by: Peter Zijlstra <[email protected]>
Signed-off-by: Byungchul Park <[email protected]>
---
kernel/sched/deadline.c | 80 ++++++++++++++++++++++++++++++++++++++++++++-----
1 file changed, 73 insertions(+), 7 deletions(-)
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 1356afd..6130d40 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1853,12 +1853,33 @@ static struct task_struct *pick_earliest_pushable_dl_task(struct rq *rq, int cpu
static DEFINE_PER_CPU(cpumask_var_t, local_cpu_mask_dl);
+/*
+ * Find the first CPU in: mask & sd & ~prefer
+ */
+static int find_cpu(const struct cpumask *mask,
+ struct sched_domain *sd,
+ struct sched_domain *prefer)
+{
+ int cpu;
+
+ for_each_cpu(cpu, mask) {
+ if (!cpumask_test_cpu(cpu, sched_domain_span(sd)))
+ continue;
+ if (prefer && cpumask_test_cpu(cpu, sched_domain_span(prefer)))
+ continue;
+ break;
+ }
+
+ return cpu;
+}
+
static int find_later_rq(struct task_struct *task)
{
- struct sched_domain *sd;
+ struct sched_domain *sd, *prefer = NULL;
struct cpumask *later_mask = this_cpu_cpumask_var_ptr(local_cpu_mask_dl);
int this_cpu = smp_processor_id();
int cpu = task_cpu(task);
+ int fallback_cpu = -1;
/* Make sure the mask is initialized first */
if (unlikely(!later_mask))
@@ -1910,15 +1931,37 @@ static int find_later_rq(struct task_struct *task)
return this_cpu;
}
- best_cpu = cpumask_first_and(later_mask,
- sched_domain_span(sd));
/*
- * Last chance: if a CPU being in both later_mask
- * and current sd span is valid, that becomes our
- * choice. Of course, the latest possible CPU is
- * already under consideration through later_mask.
+ * If a CPU exists that is in the later_mask and
+ * the current sd span, but not in the prefer sd
+ * span, then that becomes our choice.
+ *
+ * Of course, the latest possible CPU is already
+ * under consideration through later_mask.
*/
+ best_cpu = find_cpu(later_mask, sd, prefer);
+
if (best_cpu < nr_cpu_ids) {
+ /*
+ * If current domain is SD_PREFER_SIBLING
+ * flaged, we have to try to check other
+ * siblings first.
+ */
+ if (sd->flags & SD_PREFER_SIBLING) {
+ prefer = sd;
+
+ /*
+ * fallback_cpu should be one
+ * in the closest domain among
+ * SD_PREFER_SIBLING domains,
+ * in case that more than one
+ * SD_PREFER_SIBLING domains
+ * exist in the hierachy.
+ */
+ if (fallback_cpu == -1)
+ fallback_cpu = best_cpu;
+ continue;
+ }
rcu_read_unlock();
return best_cpu;
}
@@ -1927,6 +1970,29 @@ static int find_later_rq(struct task_struct *task)
rcu_read_unlock();
/*
+ * If fallback_cpu is valid, all our guesses failed *except* for
+ * SD_PREFER_SIBLING domain. Now, we can return the fallback CPU.
+ *
+ * XXX: Consider the following example, 4 cores SMT2 system:
+ *
+ * LLC [0 - 7]
+ * SMT [0 1][2 3][4 5][6 7]
+ * o x o x x x x x
+ *
+ * where 'o': occupied and 'x': empty.
+ *
+ * A wakeup on CPU0 will exclude CPU1 and choose CPU3, since
+ * CPU1 is in a SD_PREFER_SIBLING sd and CPU3 is not. However,
+ * in this case, CPU4 would have been a better choice, since
+ * CPU3 is a (SMT) thread of an already loaded core.
+ *
+ * Doing it 'right' is difficult and expensive. The current
+ * solution is an acceptable approximation.
+ */
+ if (fallback_cpu != -1)
+ return fallback_cpu;
+
+ /*
* At this point, all our guesses failed, we just return
* 'something', and let the caller sort the things out.
*/
--
1.9.1
Hello Steven,
I've changed the code a little bit to avoid a compile warning caused by
'const' args of find_cpu(). Can I keep your Reviewed-by?
BEFORE:
static int find_cpu(const struct cpumask *mask,
const struct sched_domain *sd,
const struct sched_domain *prefer)
AFTER:
static int find_cpu(const struct cpumask *mask,
struct sched_domain *sd,
struct sched_domain *prefer)
(I temporarily removed the Reviewed-by you gave me.)
Reviewed-by: Steven Rostedt (VMware) <[email protected]>
-----8<-----
From 205b197043085947ae30cd939bc12e436c328fe5 Mon Sep 17 00:00:00 2001
From: Byungchul Park <[email protected]>
Date: Mon, 4 Jun 2018 16:47:45 +0900
Subject: [RESEND PATCH v12 2/2] sched/rt: Add support for SD_PREFER_SIBLING on
find_lowest_rq()
It would be better to try to check other siblings first if
SD_PREFER_SIBLING is flaged when pushing tasks - migration.
Suggested-by: Peter Zijlstra <[email protected]>
Signed-off-by: Byungchul Park <[email protected]>
---
kernel/sched/rt.c | 78 ++++++++++++++++++++++++++++++++++++++++++++++++++++---
1 file changed, 75 insertions(+), 3 deletions(-)
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index ef3c4e6..b2aff1a 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1623,12 +1623,33 @@ static struct task_struct *pick_highest_pushable_task(struct rq *rq, int cpu)
static DEFINE_PER_CPU(cpumask_var_t, local_cpu_mask);
+/*
+ * Find the first CPU in: mask & sd & ~prefer
+ */
+static int find_cpu(const struct cpumask *mask,
+ struct sched_domain *sd,
+ struct sched_domain *prefer)
+{
+ int cpu;
+
+ for_each_cpu(cpu, mask) {
+ if (!cpumask_test_cpu(cpu, sched_domain_span(sd)))
+ continue;
+ if (prefer && cpumask_test_cpu(cpu, sched_domain_span(prefer)))
+ continue;
+ break;
+ }
+
+ return cpu;
+}
+
static int find_lowest_rq(struct task_struct *task)
{
- struct sched_domain *sd;
+ struct sched_domain *sd, *prefer = NULL;
struct cpumask *lowest_mask = this_cpu_cpumask_var_ptr(local_cpu_mask);
int this_cpu = smp_processor_id();
int cpu = task_cpu(task);
+ int fallback_cpu = -1;
/* Make sure the mask is initialized first */
if (unlikely(!lowest_mask))
@@ -1673,9 +1694,37 @@ static int find_lowest_rq(struct task_struct *task)
return this_cpu;
}
- best_cpu = cpumask_first_and(lowest_mask,
- sched_domain_span(sd));
+ /*
+ * If a CPU exists that is in the lowest_mask and
+ * the current sd span, but not in the prefer sd
+ * span, then that becomes our choice.
+ *
+ * Of course, the lowest possible CPU is already
+ * under consideration through lowest_mask.
+ */
+ best_cpu = find_cpu(lowest_mask, sd, prefer);
+
if (best_cpu < nr_cpu_ids) {
+ /*
+ * If current domain is SD_PREFER_SIBLING
+ * flaged, we have to try to check other
+ * siblings first.
+ */
+ if (sd->flags & SD_PREFER_SIBLING) {
+ prefer = sd;
+
+ /*
+ * fallback_cpu should be one
+ * in the closest domain among
+ * SD_PREFER_SIBLING domains,
+ * in case that more than one
+ * SD_PREFER_SIBLING domains
+ * exist in the hierachy.
+ */
+ if (fallback_cpu == -1)
+ fallback_cpu = best_cpu;
+ continue;
+ }
rcu_read_unlock();
return best_cpu;
}
@@ -1684,6 +1733,29 @@ static int find_lowest_rq(struct task_struct *task)
rcu_read_unlock();
/*
+ * If fallback_cpu is valid, all our guesses failed *except* for
+ * SD_PREFER_SIBLING domain. Now, we can return the fallback CPU.
+ *
+ * XXX: Consider the following example, 4 cores SMT2 system:
+ *
+ * LLC [0 - 7]
+ * SMT [0 1][2 3][4 5][6 7]
+ * o x o x x x x x
+ *
+ * where 'o': occupied and 'x': empty.
+ *
+ * A wakeup on CPU0 will exclude CPU1 and choose CPU3, since
+ * CPU1 is in a SD_PREFER_SIBLING sd and CPU3 is not. However,
+ * in this case, CPU4 would have been a better choice, since
+ * CPU3 is a (SMT) thread of an already loaded core.
+ *
+ * Doing it 'right' is difficult and expensive. The current
+ * solution is an acceptable approximation.
+ */
+ if (fallback_cpu != -1)
+ return fallback_cpu;
+
+ /*
* And finally, if there were no matches within the domains
* just give the caller *something* to work with from the compatible
* locations.
--
1.9.1
On Mon, 18 Jun 2018 13:58:08 +0900
Byungchul Park <[email protected]> wrote:
> Hello Juri,
>
> I've changed the code a little bit to avoid a compile warning caused by
> 'const' args of find_cpu(). Can I keep your Acked-by?
>
> BEFORE:
> static int find_cpu(const struct cpumask *mask,
> const struct sched_domain *sd,
> const struct sched_domain *prefer)
>
> AFTER:
> static int find_cpu(const struct cpumask *mask,
> struct sched_domain *sd,
> struct sched_domain *prefer)
>
Instead of doing that, why not fix sched_domain_span() to take a
constant. There's no reason that function should be modifying the
sched_domain.
-- Steve
> (I temporarily removed the Acked-by you gave me.)
> Acked-by: Juri Lelli <[email protected]>
>
> -----8<-----
> >From 5a4753e8c15369420a16fa04026f74ae5c9d377c Mon Sep 17 00:00:00 2001
> From: Byungchul Park <[email protected]>
> Date: Mon, 4 Jun 2018 16:46:56 +0900
> Subject: [RESEND PATCH v12 1/2] sched/deadline: Add support for SD_PREFER_SIBLING on
> find_later_rq()
>
> It would be better to try to check other siblings first if
> SD_PREFER_SIBLING is flaged when pushing tasks - migration.
>
> Suggested-by: Peter Zijlstra <[email protected]>
> Signed-off-by: Byungchul Park <[email protected]>
> ---
> kernel/sched/deadline.c | 80 ++++++++++++++++++++++++++++++++++++++++++++-----
> 1 file changed, 73 insertions(+), 7 deletions(-)
>
> diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
> index 1356afd..6130d40 100644
> --- a/kernel/sched/deadline.c
> +++ b/kernel/sched/deadline.c
> @@ -1853,12 +1853,33 @@ static struct task_struct *pick_earliest_pushable_dl_task(struct rq *rq, int cpu
>
> static DEFINE_PER_CPU(cpumask_var_t, local_cpu_mask_dl);
>
> +/*
> + * Find the first CPU in: mask & sd & ~prefer
> + */
> +static int find_cpu(const struct cpumask *mask,
> + struct sched_domain *sd,
> + struct sched_domain *prefer)
> +{
> + int cpu;
> +
> + for_each_cpu(cpu, mask) {
> + if (!cpumask_test_cpu(cpu, sched_domain_span(sd)))
> + continue;
> + if (prefer && cpumask_test_cpu(cpu, sched_domain_span(prefer)))
> + continue;
> + break;
> + }
> +
> + return cpu;
> +}
> +
>
On Mon, 18 Jun 2018 13:58:09 +0900
Byungchul Park <[email protected]> wrote:
> Hello Steven,
>
> I've changed the code a little bit to avoid a compile warning caused by
> 'const' args of find_cpu(). Can I keep your Reviewed-by?
>
> BEFORE:
> static int find_cpu(const struct cpumask *mask,
> const struct sched_domain *sd,
> const struct sched_domain *prefer)
>
> AFTER:
> static int find_cpu(const struct cpumask *mask,
> struct sched_domain *sd,
> struct sched_domain *prefer)
>
> (I temporarily removed the Reviewed-by you gave me.)
> Reviewed-by: Steven Rostedt (VMware) <[email protected]>
I would fix sched_domain_span() to take a constant and keep the
previous patch.
-- Steve
On Tue, Jun 19, 2018 at 6:42 AM, Steven Rostedt <[email protected]> wrote:
> On Mon, 18 Jun 2018 13:58:09 +0900
> Byungchul Park <[email protected]> wrote:
>
>> Hello Steven,
>>
>> I've changed the code a little bit to avoid a compile warning caused by
>> 'const' args of find_cpu(). Can I keep your Reviewed-by?
>>
>> BEFORE:
>> static int find_cpu(const struct cpumask *mask,
>> const struct sched_domain *sd,
>> const struct sched_domain *prefer)
>>
>> AFTER:
>> static int find_cpu(const struct cpumask *mask,
>> struct sched_domain *sd,
>> struct sched_domain *prefer)
>>
>> (I temporarily removed the Reviewed-by you gave me.)
>> Reviewed-by: Steven Rostedt (VMware) <[email protected]>
>
> I would fix sched_domain_span() to take a constant and keep the
> previous patch.
Right. I also considered it like you and asked it here:
https://lkml.org/lkml/2018/1/11/106
But I didn't get any answer so tried to keep sched_domain_span()
unchanged conservatively.
Peterz, what's your opinion?
>
> -- Steve
--
Thanks,
Byungchul
On Tue, Jun 19, 2018 at 02:16:36PM +0900, Byungchul Park wrote:
> On Tue, Jun 19, 2018 at 6:42 AM, Steven Rostedt <[email protected]> wrote:
> > On Mon, 18 Jun 2018 13:58:09 +0900
> > Byungchul Park <[email protected]> wrote:
> >
> >> Hello Steven,
> >>
> >> I've changed the code a little bit to avoid a compile warning caused by
> >> 'const' args of find_cpu(). Can I keep your Reviewed-by?
> >>
> >> BEFORE:
> >> static int find_cpu(const struct cpumask *mask,
> >> const struct sched_domain *sd,
> >> const struct sched_domain *prefer)
> >>
> >> AFTER:
> >> static int find_cpu(const struct cpumask *mask,
> >> struct sched_domain *sd,
> >> struct sched_domain *prefer)
> >>
> >> (I temporarily removed the Reviewed-by you gave me.)
> >> Reviewed-by: Steven Rostedt (VMware) <[email protected]>
> >
> > I would fix sched_domain_span() to take a constant and keep the
> > previous patch.
>
> Right. I also considered it like you and asked it here:
>
> https://lkml.org/lkml/2018/1/11/106
>
> But I didn't get any answer so tried to keep sched_domain_span()
> unchanged conservatively.
>
> Peterz, what's your opinion?
Peterz and Ingo,
I cannot progress forward without your opinion. Please your opinion.
> > -- Steve
>
> --
> Thanks,
> Byungchul
On Tue, Jun 19, 2018 at 02:16:36PM +0900, Byungchul Park wrote:
> On Tue, Jun 19, 2018 at 6:42 AM, Steven Rostedt <[email protected]> wrote:
> > On Mon, 18 Jun 2018 13:58:09 +0900
> > Byungchul Park <[email protected]> wrote:
> >
> >> Hello Steven,
> >>
> >> I've changed the code a little bit to avoid a compile warning caused by
> >> 'const' args of find_cpu(). Can I keep your Reviewed-by?
> >>
> >> BEFORE:
> >> static int find_cpu(const struct cpumask *mask,
> >> const struct sched_domain *sd,
> >> const struct sched_domain *prefer)
> >>
> >> AFTER:
> >> static int find_cpu(const struct cpumask *mask,
> >> struct sched_domain *sd,
> >> struct sched_domain *prefer)
> >>
> >> (I temporarily removed the Reviewed-by you gave me.)
> >> Reviewed-by: Steven Rostedt (VMware) <[email protected]>
> >
> > I would fix sched_domain_span() to take a constant and keep the
> > previous patch.
>
> Right. I also considered it like you and asked it here:
>
> https://lkml.org/lkml/2018/1/11/106
>
> But I didn't get any answer so tried to keep sched_domain_span()
> unchanged conservatively.
>
> Peterz, what's your opinion?
Maintainers, Peter and Ingo,
I believe it would be OK, even better to change sched_domain_span()
itself. But I wonder if you also think so, do you?
> >
> > -- Steve
>
> --
> Thanks,
> Byungchul