sched/deadline: fix dl bandwidth of root domain overflow after dl task dead
PATCH 1/1 sched/deadline: fix dl bandwidth of root domain overflow after dl task dead
The total used dl bandwidth of each root domain will be reset to 0 after cpu hotplug when rebuild sched domains, since the call path is:
_cpu_down
cpuset_cpu_inactive()
cpuset_update_active_cpus()
partition_sched_domains()
build_sched_domains()
init_rootdomain()
init_dl_bw() The bandwidth which dl task occupy will be released when dl task dead, it will be minus from total used dl bandwidth of its root domain, however, bandwidth overflow occurs since total used dl bandwidth is 0.
This patch fix it by attaching the bandwidth which dl task occupy to the new root domain when the task is migrating since cpu hotplug, and attach all the used dl bandwidth of dl tasks to the new root domain when sched domains are rebuild.
--- kernel/sched/core.c | 1 + kernel/sched/deadline.c | 25 +++++++++++++++++++++++++ kernel/sched/sched.h | 1 + 3 files changed, 27 insertions(+)
kernel/sched/core.c +1 -0
@@ -5586,6 +5586,7 @@ static void rq_attach_root(struct rq *rq, struct root_domain *rd) rq->rd = rd;cpumask_set_cpu (rq->cpu, rd->span); +attach_dl_bw (rq);if (cpumask_test_cpu (rq->cpu, cpu_active_mask))set_rq_online (rq);
kernel/sched/deadline.c +25 -0
@@ -224,6 +224,7 @@ static void dl_task_offline_migration(struct rq *rq, struct task_struct *p) {struct rq *later_rq =NULL ;bool fallback = false; +struct dl_bw *dl_b; later_rq =find_lock_later_rq (p, rq);
@@ -258,6 +259,11 @@ static void dl_task_offline_migration(struct rq *rq, struct task_struct *p)set_task_cpu (p, later_rq->cpu);activate_task (later_rq, p,ENQUEUE_REPLENISH ); + dl_b =dl_bw_of (later_rq->cpu); +raw_spin_lock (&dl_b->lock); +__dl_add (dl_b, p->dl.dl_bw); +raw_spin_unlock (&dl_b->lock); +if (!fallback)resched_curr (later_rq);
@@ -1776,6 +1782,25 @@ static void prio_changed_dl(struct rq *rq, struct task_struct *p,switched_to_dl (rq, p); } +void attach_dl_bw (struct rq *rq) +{ +struct rb_node *next_node = rq->dl.rb_leftmost; +struct sched_dl_entity *dl_se; +struct dl_bw *dl_b; + + dl_b =dl_bw_of (rq->cpu); +raw_spin_lock (&dl_b->lock); +next_node: +if (next_node) { + dl_se = rb_entry(next_node, struct sched_dl_entity, rb_node); +__dl_add (dl_b, dl_se->dl_bw); + next_node =rb_next (next_node); + + goto next_node; + } +raw_spin_unlock (&dl_b->lock); +} +const struct sched_class dl_sched_class = { .next = &rt_sched_class, .enqueue_task = enqueue_task_dl,
kernel/sched/sched.h +1 -0
@@ -1676,6 +1676,7 @@ extern void init_dl_rq(struct dl_rq *dl_rq);extern void cfs_bandwidth_usage_inc (void );extern void cfs_bandwidth_usage_dec (void ); +void attach_dl_bw (struct rq *rq);#ifdef CONFIG_NO_HZ_COMMON enum rq_nohz_flag_bits {
Signature · 1 line
1.9.1
Hi Wanpeng,
I finally got to review this, sorry about the huge delay.
Quoted 11 lines · Wanpeng Li
The total used dl bandwidth of each root domain will be reset to 0 after cpu hotplug when rebuild sched domains, since the call path is:
_cpu_down
cpuset_cpu_inactive()cpuset_update_active_cpus() partition_sched_domains() build_sched_domains() init_rootdomain() init_dl_bw()
Quoted 4 lines
The bandwidth which dl task occupy will be released when dl task dead, it will be minus from total used dl bandwidth of its root domain, however, bandwidth overflow occurs since total used dl bandwidth is 0.
Right, that's a bug.
Quoted 5 lines
This patch fix it by attaching the bandwidth which dl task occupy to the new root domain when the task is migrating since cpu hotplug, and attach all the used dl bandwidth of dl tasks to the new root domain when sched domains are rebuild.
But, I think this fix has still a couple of problems:
- what happens if a DL task is simply sleeping when domains are reconfigured?
- def_root_domain has now multiple accounting problems, as you do this thing even when a cpu is moved there in the cpuoff path
Also, runqueue (and throttling) information are dynamic, while we are trying to fix a static problem. It's probably not a good idea mixing them.
I'm not sure how (I need more time to think it through), but can we maybe fix this using cpuset information?
Thanks,
- Juri
Quoted 82 lines
Signed-off-by Wanpeng Li <[email protected]>--- kernel/sched/core.c | 1 + kernel/sched/deadline.c | 25 +++++++++++++++++++++++++ kernel/sched/sched.h | 1 + 3 files changed, 27 insertions(+)kernel/sched/core.c +1
-0@@ -5586,6 +5586,7 @@ static void rq_attach_root(struct rq *rq, struct root_domain *rd) rq->rd = rd;cpumask_set_cpu (rq->cpu, rd->span); +attach_dl_bw (rq);if (cpumask_test_cpu (rq->cpu, cpu_active_mask))set_rq_online (rq);kernel/sched/deadline.c +25
-0@@ -224,6 +224,7 @@ static void dl_task_offline_migration(struct rq *rq, struct task_struct *p) {struct rq *later_rq =NULL ;bool fallback = false; +struct dl_bw *dl_b; later_rq =find_lock_later_rq (p, rq);@@ -258,6 +259,11 @@ static void dl_task_offline_migration(struct rq *rq, struct task_struct *p)set_task_cpu (p, later_rq->cpu);activate_task (later_rq, p,ENQUEUE_REPLENISH ); + dl_b =dl_bw_of (later_rq->cpu); +raw_spin_lock (&dl_b->lock); +__dl_add (dl_b, p->dl.dl_bw); +raw_spin_unlock (&dl_b->lock); +if (!fallback)resched_curr (later_rq);@@ -1776,6 +1782,25 @@ static void prio_changed_dl(struct rq *rq, struct task_struct *p,switched_to_dl (rq, p); } +void attach_dl_bw (struct rq *rq) +{ +struct rb_node *next_node = rq->dl.rb_leftmost; +struct sched_dl_entity *dl_se; +struct dl_bw *dl_b; + + dl_b =dl_bw_of (rq->cpu); +raw_spin_lock (&dl_b->lock); +next_node: +if (next_node) { + dl_se = rb_entry(next_node, struct sched_dl_entity, rb_node); +__dl_add (dl_b, dl_se->dl_bw); + next_node =rb_next (next_node); + + goto next_node; + } +raw_spin_unlock (&dl_b->lock); +} +const struct sched_class dl_sched_class = { .next = &rt_sched_class, .enqueue_task = enqueue_task_dl,kernel/sched/sched.h +1
-0@@ -1676,6 +1676,7 @@ extern void init_dl_rq(struct dl_rq *dl_rq);extern void cfs_bandwidth_usage_inc (void );extern void cfs_bandwidth_usage_dec (void ); +void attach_dl_bw (struct rq *rq);#ifdef CONFIG_NO_HZ_COMMON enum rq_nohz_flag_bits {
A message that is not in the archive (sent off-list or not yet received): CANRm+Cy43icX8DsLQJCwy+hbOuUynK5MOMfrHj5YA19LK_HmdQ@mail.gmail.com
Quoted 2 lines · Wanpeng Li
Hi Juri,
Hi,
Quoted 44 lines
2015-05-06 16:14 GMT+08:00 Juri Lelli <[email protected] <mailto:[email protected]>>:
Hi Wanpeng,
I finally got to review this, sorry about the huge delay.
On 07/04/2015 04:36, Wanpeng Li wrote:
> The total used dl bandwidth of each root domain will be reset to 0 after > cpu hotplug when rebuild sched domains, since the call path is:
>
>_cpu_down
>cpuset_cpu_inactive()
>cpuset_update_active_cpus()
>partition_sched_domains()
>build_sched_domains()
>init_rootdomain()
>init_dl_bw()
>
> The bandwidth which dl task occupy will be released when dl task dead, > it will be minus from total used dl bandwidth of its root domain, > however, bandwidth overflow occurs since total used dl bandwidth is 0. >Right, that's a bug.
> This patch fix it by attaching the bandwidth which dl task occupy to > the new root domain when the task is migrating since cpu hotplug, and > attach all the used dl bandwidth of dl tasks to the new root domain > when sched domains are rebuild.
>But, I think this fix has still a couple of problems:
- what happens if a DL task is simply sleeping when domains are reconfigured?
-
def_root_domainhas now multiple accounting problems, as you do this thing even when a cpu is moved there in the cpuoff pathAlso, runqueue (and throttling) information are dynamic, while we are trying to fix a static problem. It's probably not a good idea mixing them.
Quoted 6 lines
I'm not sure how (I need more time to think it through), but can we maybe fix this using cpuset information?
Any ideas?
Yes, actually. I might have a different fix, but I'd like to play with it a bit more as it is a bit too intrusive. Let me see if I can come up with something that I can share.
Thanks,
- Juri
Quoted 106 lines
Regards,
Wanpeng LiThanks, - Juri > Signed-off-by: Wanpeng Li <[email protected] <mailto:[email protected]>> > --- > kernel/sched/core.c | 1 + > kernel/sched/deadline.c | 25 +++++++++++++++++++++++++ > kernel/sched/sched.h | 1 + > 3 files changed, 27 insertions(+) > > diff --git a/kernel/sched/core.c b/kernel/sched/core.c > index 28b0d75..c940999 100644 > --- a/kernel/sched/core.c > +++ b/kernel/sched/core.c > @@ -5586,6 +5586,7 @@ static void rq_attach_root(struct rq *rq, struct root_domain *rd) > rq->rd = rd; > > cpumask_set_cpu(rq->cpu, rd->span); > + attach_dl_bw(rq); > if (cpumask_test_cpu(rq->cpu, cpu_active_mask)) > set_rq_online(rq); > > diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c > index 5e95145..62680d7 100644 > --- a/kernel/sched/deadline.c > +++ b/kernel/sched/deadline.c > @@ -224,6 +224,7 @@ static void dl_task_offline_migration(struct rq *rq, struct task_struct *p) > { > struct rq *later_rq = NULL; > bool fallback = false; > + struct dl_bw *dl_b; > > later_rq = find_lock_later_rq(p, rq); > > @@ -258,6 +259,11 @@ static void dl_task_offline_migration(struct rq *rq, struct task_struct *p) > set_task_cpu(p, later_rq->cpu); > activate_task(later_rq, p, ENQUEUE_REPLENISH); > > + dl_b = dl_bw_of(later_rq->cpu); > + raw_spin_lock(&dl_b->lock); > + __dl_add(dl_b, p->dl.dl_bw); > + raw_spin_unlock(&dl_b->lock); > + > if (!fallback) > resched_curr(later_rq); > > @@ -1776,6 +1782,25 @@ static void prio_changed_dl(struct rq *rq, struct task_struct *p, > switched_to_dl(rq, p); > } > > +void attach_dl_bw(struct rq *rq) > +{ > + struct rb_node *next_node = rq->dl.rb_leftmost; > + struct sched_dl_entity *dl_se; > + struct dl_bw *dl_b; > + > + dl_b = dl_bw_of(rq->cpu); > + raw_spin_lock(&dl_b->lock); > +next_node: > + if (next_node) { > + dl_se = rb_entry(next_node, struct sched_dl_entity, rb_node); > + __dl_add(dl_b, dl_se->dl_bw); > + next_node = rb_next(next_node); > + > + goto next_node; > + } > + raw_spin_unlock(&dl_b->lock); > +} > + > const struct sched_class dl_sched_class = { > .next = &rt_sched_class, > .enqueue_task = enqueue_task_dl, > diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h > index e0e1299..a7b1a59 100644 > --- a/kernel/sched/sched.h > +++ b/kernel/sched/sched.h > @@ -1676,6 +1676,7 @@ extern void init_dl_rq(struct dl_rq *dl_rq); > > extern void cfs_bandwidth_usage_inc(void); > extern void cfs_bandwidth_usage_dec(void); > +void attach_dl_bw(struct rq *rq); > > #ifdef CONFIG_NO_HZ_COMMON > enum rq_nohz_flag_bits { > -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [email protected] <mailto:[email protected]> More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Quoted 53 lines · Juri Lelli
Quoted 2 lines · Wanpeng Li
Hi Juri,
Hi,
Quoted 48 lines
2015-05-06 16:14 GMT+08:00 Juri Lelli <[email protected] <mailto:[email protected]>>:
Hi Wanpeng,
I finally got to review this, sorry about the huge delay.
On 07/04/2015 04:36, Wanpeng Li wrote:
> The total used dl bandwidth of each root domain will be reset to 0 after > cpu hotplug when rebuild sched domains, since the call path is:
>
>_cpu_down
>cpuset_cpu_inactive()
>cpuset_update_active_cpus()
>partition_sched_domains()
>build_sched_domains()
>init_rootdomain()
>init_dl_bw()
>
> The bandwidth which dl task occupy will be released when dl task dead, > it will be minus from total used dl bandwidth of its root domain, > however, bandwidth overflow occurs since total used dl bandwidth is 0. >Right, that's a bug.
> This patch fix it by attaching the bandwidth which dl task occupy to > the new root domain when the task is migrating since cpu hotplug, and > attach all the used dl bandwidth of dl tasks to the new root domain > when sched domains are rebuild.
>But, I think this fix has still a couple of problems:
- what happens if a DL task is simply sleeping when domains are reconfigured?
-
def_root_domainhas now multiple accounting problems, as you do this thing even when a cpu is moved there in the cpuoff pathAlso, runqueue (and throttling) information are dynamic, while we are trying to fix a static problem. It's probably not a good idea mixing them.
I'm not sure how (I need more time to think it through), but can we maybe fix this using cpuset information?
Quoted 5 lines
Quoted 2 lines
Any ideas?
Yes, actually. I might have a different fix, but I'd like to play with it a bit more as it is a bit too intrusive. Let me see if I can come up with something that I can share.
Cool, looking forward for your patches. :)
Regards,
Wanpeng Li
Quoted 111 lines
Thanks,
- Juri
Quoted 106 lines
Regards,
Wanpeng LiThanks, - Juri > Signed-off-by: Wanpeng Li <[email protected] <mailto:[email protected]>> > --- > kernel/sched/core.c | 1 + > kernel/sched/deadline.c | 25 +++++++++++++++++++++++++ > kernel/sched/sched.h | 1 + > 3 files changed, 27 insertions(+) > > diff --git a/kernel/sched/core.c b/kernel/sched/core.c > index 28b0d75..c940999 100644 > --- a/kernel/sched/core.c > +++ b/kernel/sched/core.c > @@ -5586,6 +5586,7 @@ static void rq_attach_root(struct rq *rq, struct root_domain *rd) > rq->rd = rd; > > cpumask_set_cpu(rq->cpu, rd->span); > + attach_dl_bw(rq); > if (cpumask_test_cpu(rq->cpu, cpu_active_mask)) > set_rq_online(rq); > > diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c > index 5e95145..62680d7 100644 > --- a/kernel/sched/deadline.c > +++ b/kernel/sched/deadline.c > @@ -224,6 +224,7 @@ static void dl_task_offline_migration(struct rq *rq, struct task_struct *p) > { > struct rq *later_rq = NULL; > bool fallback = false; > + struct dl_bw *dl_b; > > later_rq = find_lock_later_rq(p, rq); > > @@ -258,6 +259,11 @@ static void dl_task_offline_migration(struct rq *rq, struct task_struct *p) > set_task_cpu(p, later_rq->cpu); > activate_task(later_rq, p, ENQUEUE_REPLENISH); > > + dl_b = dl_bw_of(later_rq->cpu); > + raw_spin_lock(&dl_b->lock); > + __dl_add(dl_b, p->dl.dl_bw); > + raw_spin_unlock(&dl_b->lock); > + > if (!fallback) > resched_curr(later_rq); > > @@ -1776,6 +1782,25 @@ static void prio_changed_dl(struct rq *rq, struct task_struct *p, > switched_to_dl(rq, p); > } > > +void attach_dl_bw(struct rq *rq) > +{ > + struct rb_node *next_node = rq->dl.rb_leftmost; > + struct sched_dl_entity *dl_se; > + struct dl_bw *dl_b; > + > + dl_b = dl_bw_of(rq->cpu); > + raw_spin_lock(&dl_b->lock); > +next_node: > + if (next_node) { > + dl_se = rb_entry(next_node, struct sched_dl_entity, rb_node); > + __dl_add(dl_b, dl_se->dl_bw); > + next_node = rb_next(next_node); > + > + goto next_node; > + } > + raw_spin_unlock(&dl_b->lock); > +} > + > const struct sched_class dl_sched_class = { > .next = &rt_sched_class, > .enqueue_task = enqueue_task_dl, > diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h > index e0e1299..a7b1a59 100644 > --- a/kernel/sched/sched.h > +++ b/kernel/sched/sched.h > @@ -1676,6 +1676,7 @@ extern void init_dl_rq(struct dl_rq *dl_rq); > > extern void cfs_bandwidth_usage_inc(void); > extern void cfs_bandwidth_usage_dec(void); > +void attach_dl_bw(struct rq *rq); > > #ifdef CONFIG_NO_HZ_COMMON > enum rq_nohz_flag_bits { > -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [email protected] <mailto:[email protected]> More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Quoted 53 lines · Juri Lelli
Quoted 2 lines · Wanpeng Li
Hi Juri,
Hi,
Quoted 48 lines
2015-05-06 16:14 GMT+08:00 Juri Lelli <[email protected] <mailto:[email protected]>>:
Hi Wanpeng,
I finally got to review this, sorry about the huge delay.
On 07/04/2015 04:36, Wanpeng Li wrote:
> The total used dl bandwidth of each root domain will be reset to 0 after > cpu hotplug when rebuild sched domains, since the call path is:
>
>_cpu_down
>cpuset_cpu_inactive()
>cpuset_update_active_cpus()
>partition_sched_domains()
>build_sched_domains()
>init_rootdomain()
>init_dl_bw()
>
> The bandwidth which dl task occupy will be released when dl task dead, > it will be minus from total used dl bandwidth of its root domain, > however, bandwidth overflow occurs since total used dl bandwidth is 0. >Right, that's a bug.
> This patch fix it by attaching the bandwidth which dl task occupy to > the new root domain when the task is migrating since cpu hotplug, and > attach all the used dl bandwidth of dl tasks to the new root domain > when sched domains are rebuild.
>But, I think this fix has still a couple of problems:
- what happens if a DL task is simply sleeping when domains are reconfigured?
-
def_root_domainhas now multiple accounting problems, as you do this thing even when a cpu is moved there in the cpuoff pathAlso, runqueue (and throttling) information are dynamic, while we are trying to fix a static problem. It's probably not a good idea mixing them.
I'm not sure how (I need more time to think it through), but can we maybe fix this using cpuset information?
Quoted 5 lines
Quoted 2 lines
Any ideas?
Yes, actually. I might have a different fix, but I'd like to play with it a bit more as it is a bit too intrusive. Let me see if I can come up with something that I can share.
Ping Peter, Juri, any detail ideas to help me post another version of my patch? ;-)
Regards,
Wanpeng Li
Quoted 111 lines
Thanks,
- Juri
Quoted 106 lines
Regards,
Wanpeng LiThanks, - Juri > Signed-off-by: Wanpeng Li <[email protected] <mailto:[email protected]>> > --- > kernel/sched/core.c | 1 + > kernel/sched/deadline.c | 25 +++++++++++++++++++++++++ > kernel/sched/sched.h | 1 + > 3 files changed, 27 insertions(+) > > diff --git a/kernel/sched/core.c b/kernel/sched/core.c > index 28b0d75..c940999 100644 > --- a/kernel/sched/core.c > +++ b/kernel/sched/core.c > @@ -5586,6 +5586,7 @@ static void rq_attach_root(struct rq *rq, struct root_domain *rd) > rq->rd = rd; > > cpumask_set_cpu(rq->cpu, rd->span); > + attach_dl_bw(rq); > if (cpumask_test_cpu(rq->cpu, cpu_active_mask)) > set_rq_online(rq); > > diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c > index 5e95145..62680d7 100644 > --- a/kernel/sched/deadline.c > +++ b/kernel/sched/deadline.c > @@ -224,6 +224,7 @@ static void dl_task_offline_migration(struct rq *rq, struct task_struct *p) > { > struct rq *later_rq = NULL; > bool fallback = false; > + struct dl_bw *dl_b; > > later_rq = find_lock_later_rq(p, rq); > > @@ -258,6 +259,11 @@ static void dl_task_offline_migration(struct rq *rq, struct task_struct *p) > set_task_cpu(p, later_rq->cpu); > activate_task(later_rq, p, ENQUEUE_REPLENISH); > > + dl_b = dl_bw_of(later_rq->cpu); > + raw_spin_lock(&dl_b->lock); > + __dl_add(dl_b, p->dl.dl_bw); > + raw_spin_unlock(&dl_b->lock); > + > if (!fallback) > resched_curr(later_rq); > > @@ -1776,6 +1782,25 @@ static void prio_changed_dl(struct rq *rq, struct task_struct *p, > switched_to_dl(rq, p); > } > > +void attach_dl_bw(struct rq *rq) > +{ > + struct rb_node *next_node = rq->dl.rb_leftmost; > + struct sched_dl_entity *dl_se; > + struct dl_bw *dl_b; > + > + dl_b = dl_bw_of(rq->cpu); > + raw_spin_lock(&dl_b->lock); > +next_node: > + if (next_node) { > + dl_se = rb_entry(next_node, struct sched_dl_entity, rb_node); > + __dl_add(dl_b, dl_se->dl_bw); > + next_node = rb_next(next_node); > + > + goto next_node; > + } > + raw_spin_unlock(&dl_b->lock); > +} > + > const struct sched_class dl_sched_class = { > .next = &rt_sched_class, > .enqueue_task = enqueue_task_dl, > diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h > index e0e1299..a7b1a59 100644 > --- a/kernel/sched/sched.h > +++ b/kernel/sched/sched.h > @@ -1676,6 +1676,7 @@ extern void init_dl_rq(struct dl_rq *dl_rq); > > extern void cfs_bandwidth_usage_inc(void); > extern void cfs_bandwidth_usage_dec(void); > +void attach_dl_bw(struct rq *rq); > > #ifdef CONFIG_NO_HZ_COMMON > enum rq_nohz_flag_bits { > -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [email protected] <mailto:[email protected]> More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Hi,
Quoted 54 lines · Wanpeng Li
Quoted 53 lines · Juri Lelli
Quoted 2 lines · Wanpeng Li
Hi Juri,
Hi,
Quoted 48 lines
2015-05-06 16:14 GMT+08:00 Juri Lelli <[email protected] <mailto:[email protected]>>:
Hi Wanpeng,
I finally got to review this, sorry about the huge delay.
On 07/04/2015 04:36, Wanpeng Li wrote:
> The total used dl bandwidth of each root domain will be reset to 0 after > cpu hotplug when rebuild sched domains, since the call path is:
>
>_cpu_down
>cpuset_cpu_inactive()
>cpuset_update_active_cpus()
>partition_sched_domains()
>build_sched_domains()
>init_rootdomain()
>init_dl_bw()
>
> The bandwidth which dl task occupy will be released when dl task dead, > it will be minus from total used dl bandwidth of its root domain, > however, bandwidth overflow occurs since total used dl bandwidth is 0. >Right, that's a bug.
> This patch fix it by attaching the bandwidth which dl task occupy to > the new root domain when the task is migrating since cpu hotplug, and > attach all the used dl bandwidth of dl tasks to the new root domain > when sched domains are rebuild.
>But, I think this fix has still a couple of problems:
- what happens if a DL task is simply sleeping when domains are reconfigured?
-
def_root_domainhas now multiple accounting problems, as you do this thing even when a cpu is moved there in the cpuoff pathAlso, runqueue (and throttling) information are dynamic, while we are trying to fix a static problem. It's probably not a good idea mixing them.
I'm not sure how (I need more time to think it through), but can we maybe fix this using cpuset information?
Quoted 9 lines
Quoted 5 lines
Quoted 2 lines
Any ideas?
Yes, actually. I might have a different fix, but I'd like to play with it a bit more as it is a bit too intrusive. Let me see if I can come up with something that I can share.
Ping Peter, Juri, any detail ideas to help me post another version of my patch? ;-)
Let me see if I'm able to post my version of the fix before end of this week ;).
Thanks!
- Juri
Quoted 115 lines
Regards,
Wanpeng LiQuoted 111 lines
Thanks,
- Juri
Quoted 106 lines
Regards,
Wanpeng LiThanks, - Juri > Signed-off-by: Wanpeng Li <[email protected] <mailto:[email protected]>> > --- > kernel/sched/core.c | 1 + > kernel/sched/deadline.c | 25 +++++++++++++++++++++++++ > kernel/sched/sched.h | 1 + > 3 files changed, 27 insertions(+) > > diff --git a/kernel/sched/core.c b/kernel/sched/core.c > index 28b0d75..c940999 100644 > --- a/kernel/sched/core.c > +++ b/kernel/sched/core.c > @@ -5586,6 +5586,7 @@ static void rq_attach_root(struct rq *rq, struct root_domain *rd) > rq->rd = rd; > > cpumask_set_cpu(rq->cpu, rd->span); > + attach_dl_bw(rq); > if (cpumask_test_cpu(rq->cpu, cpu_active_mask)) > set_rq_online(rq); > > diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c > index 5e95145..62680d7 100644 > --- a/kernel/sched/deadline.c > +++ b/kernel/sched/deadline.c > @@ -224,6 +224,7 @@ static void dl_task_offline_migration(struct rq *rq, struct task_struct *p) > { > struct rq *later_rq = NULL; > bool fallback = false; > + struct dl_bw *dl_b; > > later_rq = find_lock_later_rq(p, rq); > > @@ -258,6 +259,11 @@ static void dl_task_offline_migration(struct rq *rq, struct task_struct *p) > set_task_cpu(p, later_rq->cpu); > activate_task(later_rq, p, ENQUEUE_REPLENISH); > > + dl_b = dl_bw_of(later_rq->cpu); > + raw_spin_lock(&dl_b->lock); > + __dl_add(dl_b, p->dl.dl_bw); > + raw_spin_unlock(&dl_b->lock); > + > if (!fallback) > resched_curr(later_rq); > > @@ -1776,6 +1782,25 @@ static void prio_changed_dl(struct rq *rq, struct task_struct *p, > switched_to_dl(rq, p); > } > > +void attach_dl_bw(struct rq *rq) > +{ > + struct rb_node *next_node = rq->dl.rb_leftmost; > + struct sched_dl_entity *dl_se; > + struct dl_bw *dl_b; > + > + dl_b = dl_bw_of(rq->cpu); > + raw_spin_lock(&dl_b->lock); > +next_node: > + if (next_node) { > + dl_se = rb_entry(next_node, struct sched_dl_entity, rb_node); > + __dl_add(dl_b, dl_se->dl_bw); > + next_node = rb_next(next_node); > + > + goto next_node; > + } > + raw_spin_unlock(&dl_b->lock); > +} > + > const struct sched_class dl_sched_class = { > .next = &rt_sched_class, > .enqueue_task = enqueue_task_dl, > diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h > index e0e1299..a7b1a59 100644 > --- a/kernel/sched/sched.h > +++ b/kernel/sched/sched.h > @@ -1676,6 +1676,7 @@ extern void init_dl_rq(struct dl_rq *dl_rq); > > extern void cfs_bandwidth_usage_inc(void); > extern void cfs_bandwidth_usage_dec(void); > +void attach_dl_bw(struct rq *rq); > > #ifdef CONFIG_NO_HZ_COMMON > enum rq_nohz_flag_bits { > -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [email protected] <mailto:[email protected]> More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/