[PATCH 1/2] sched/deadline: don't need to check SD_BALANCE_FORK

[PATCH 1/2] sched/deadline: don't need to check SD_BALANCE_FORK

[Wanpeng Li]

There is no need to do balance during fork since SCHED_DEADLINE 
tasks can't fork. This patch avoid the SD_BALANCE_FORK check.

Signed-off-by: Wanpeng Li <wanpeng.li@linux.intel.com>
---
 kernel/sched/deadline.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index abfaf3d..f46b7f1 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -914,7 +914,7 @@ select_task_rq_dl(struct task_struct *p, int cpu, int sd_flag, int flags)
 	struct task_struct *curr;
 	struct rq *rq;
 
-	if (sd_flag != SD_BALANCE_WAKE && sd_flag != SD_BALANCE_FORK)
+	if (sd_flag != SD_BALANCE_WAKE)
 		goto out;
 
 	rq = cpu_rq(cpu);
-- 
1.9.1

[PATCH 2/2] sched/deadline: don't need to balance during wakeup if wakee is pinned

[Wanpeng Li]

Use nr_cpus_allowed to bail from select_task_rq() when only one cpu 
can be used, and saves some cycles for pinned tasks.

Signed-off-by: Wanpeng Li <wanpeng.li@linux.intel.com>
---
 kernel/sched/deadline.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index f46b7f1..5874bf8 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -914,6 +914,9 @@ select_task_rq_dl(struct task_struct *p, int cpu, int sd_flag, int flags)
 	struct task_struct *curr;
 	struct rq *rq;
 
+	if (p->nr_cpus_allowed == 1)
+		goto out;
+
 	if (sd_flag != SD_BALANCE_WAKE)
 		goto out;
 
-- 
1.9.1

Re: [PATCH 2/2] sched/deadline: don't need to balance during wakeup if wakee is pinned

[Wanpeng Li]

Cc Juri,

于 10/14/14, 10:22 AM, Wanpeng Li 写道:
> Use nr_cpus_allowed to bail from select_task_rq() when only one cpu 
> can be used, and saves some cycles for pinned tasks.
>
> Signed-off-by: Wanpeng Li <wanpeng.li@linux.intel.com>
> ---
>  kernel/sched/deadline.c | 3 +++
>  1 file changed, 3 insertions(+)
>
> diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
> index f46b7f1..5874bf8 100644
> --- a/kernel/sched/deadline.c
> +++ b/kernel/sched/deadline.c
> @@ -914,6 +914,9 @@ select_task_rq_dl(struct task_struct *p, int cpu, int sd_flag, int flags)
>  	struct task_struct *curr;
>  	struct rq *rq;
>  
> +	if (p->nr_cpus_allowed == 1)
> +		goto out;
> +
>  	if (sd_flag != SD_BALANCE_WAKE)
>  		goto out;
>  

Re: [PATCH 2/2] sched/deadline: don't need to balance during wakeup if wakee is pinned

[Juri Lelli]

Hi,

On 21/10/14 13:19, Wanpeng Li wrote:
> Cc Juri,
> 
> 于 10/14/14, 10:22 AM, Wanpeng Li 写道:
>> Use nr_cpus_allowed to bail from select_task_rq() when only one cpu 
>> can be used, and saves some cycles for pinned tasks.
>>
>> Signed-off-by: Wanpeng Li <wanpeng.li@linux.intel.com>
>> ---
>>  kernel/sched/deadline.c | 3 +++
>>  1 file changed, 3 insertions(+)
>>
>> diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
>> index f46b7f1..5874bf8 100644
>> --- a/kernel/sched/deadline.c
>> +++ b/kernel/sched/deadline.c
>> @@ -914,6 +914,9 @@ select_task_rq_dl(struct task_struct *p, int cpu, int sd_flag, int flags)
>>  	struct task_struct *curr;
>>  	struct rq *rq;
>>  
>> +	if (p->nr_cpus_allowed == 1)
>> +		goto out;
>> +
>>  	if (sd_flag != SD_BALANCE_WAKE)
>>  		goto out;
>> 

Apart from the encoding of the resend, it looks good, thanks!

Best,

- Juri

Re: [PATCH 2/2] sched/deadline: don't need to balance during wakeup if wakee is pinned

[Wanpeng Li]

Hi Juri,

于 10/21/14, 9:29 PM, Juri Lelli 写道:
> Hi,
>
> On 21/10/14 13:19, Wanpeng Li wrote:
>> Cc Juri,
>>
>> 于 10/14/14, 10:22 AM, Wanpeng Li 写道:
>>> Use nr_cpus_allowed to bail from select_task_rq() when only one cpu
>>> can be used, and saves some cycles for pinned tasks.
>>>
>>> Signed-off-by: Wanpeng Li <wanpeng.li@linux.intel.com>
>>> ---
>>>   kernel/sched/deadline.c | 3 +++
>>>   1 file changed, 3 insertions(+)
>>>
>>> diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
>>> index f46b7f1..5874bf8 100644
>>> --- a/kernel/sched/deadline.c
>>> +++ b/kernel/sched/deadline.c
>>> @@ -914,6 +914,9 @@ select_task_rq_dl(struct task_struct *p, int cpu, int sd_flag, int flags)
>>>   	struct task_struct *curr;
>>>   	struct rq *rq;
>>>   
>>> +	if (p->nr_cpus_allowed == 1)
>>> +		goto out;
>>> +
>>>   	if (sd_flag != SD_BALANCE_WAKE)
>>>   		goto out;
>>>
> Apart from the encoding of the resend, it looks good, thanks!

What's your meaning of resend? Do you mean this one?

https://lkml.org/lkml/2014/10/10/425

I'm afraid they are different patches.

Regards,
Wanpeng Li

>
> Best,
>
> - Juri
>

Re: [PATCH 2/2] sched/deadline: don't need to balance during wakeup if wakee is pinned

[Juri Lelli]

On 21/10/14 14:39, Wanpeng Li wrote:
> Hi Juri,
> 
> 于 10/21/14, 9:29 PM, Juri Lelli 写道:
>> Hi,
>>
>> On 21/10/14 13:19, Wanpeng Li wrote:
>>> Cc Juri,
>>>
>>> 于 10/14/14, 10:22 AM, Wanpeng Li 写道:
>>>> Use nr_cpus_allowed to bail from select_task_rq() when only one cpu
>>>> can be used, and saves some cycles for pinned tasks.
>>>>
>>>> Signed-off-by: Wanpeng Li <wanpeng.li@linux.intel.com>
>>>> ---
>>>>   kernel/sched/deadline.c | 3 +++
>>>>   1 file changed, 3 insertions(+)
>>>>
>>>> diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
>>>> index f46b7f1..5874bf8 100644
>>>> --- a/kernel/sched/deadline.c
>>>> +++ b/kernel/sched/deadline.c
>>>> @@ -914,6 +914,9 @@ select_task_rq_dl(struct task_struct *p, int cpu, int sd_flag, int flags)
>>>>   	struct task_struct *curr;
>>>>   	struct rq *rq;
>>>>   
>>>> +	if (p->nr_cpus_allowed == 1)
>>>> +		goto out;
>>>> +
>>>>   	if (sd_flag != SD_BALANCE_WAKE)
>>>>   		goto out;
>>>>
>> Apart from the encoding of the resend, it looks good, thanks!
> 
> What's your meaning of resend? Do you mean this one?

Nope. I just meant that I received your "Cc Juri" encoded as Chinese
Simplified. But, I guess the original lkml patch looks good. Sorry for
the confusion :).

Best,

- Juri

> 
> https://lkml.org/lkml/2014/10/10/425
> 
> I'm afraid they are different patches.
> 
> Regards,
> Wanpeng Li
> 
>>
>> Best,
>>
>> - Juri
>>
> 
> 

[tip:sched/core] sched/deadline: Don' t balance during wakeup if wakee is pinned

[tip-bot for Wanpeng Li]

Commit-ID:  f4e9d94a5bf60193d45f92b136e3d166be3ec8d5
Gitweb:     http://git.kernel.org/tip/f4e9d94a5bf60193d45f92b136e3d166be3ec8d5
Author:     Wanpeng Li <wanpeng.li@linux.intel.com>
AuthorDate: Tue, 14 Oct 2014 10:22:40 +0800
Committer:  Ingo Molnar <mingo@kernel.org>
CommitDate: Tue, 28 Oct 2014 10:48:02 +0100

sched/deadline: Don't balance during wakeup if wakee is pinned

Use nr_cpus_allowed to bail from select_task_rq() when only one cpu
can be used, and saves some cycles for pinned tasks.

Signed-off-by: Wanpeng Li <wanpeng.li@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1413253360-5318-2-git-send-email-wanpeng.li@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/deadline.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index fab3bf8..2e31a30 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -933,6 +933,9 @@ select_task_rq_dl(struct task_struct *p, int cpu, int sd_flag, int flags)
 	struct task_struct *curr;
 	struct rq *rq;
 
+	if (p->nr_cpus_allowed == 1)
+		goto out;
+
 	if (sd_flag != SD_BALANCE_WAKE)
 		goto out;
 

Re: [PATCH 1/2] sched/deadline: don't need to check SD_BALANCE_FORK

[Wanpeng Li]

Cc Juri,

于 10/14/14, 10:22 AM, Wanpeng Li 写道:
> There is no need to do balance during fork since SCHED_DEADLINE 
> tasks can't fork. This patch avoid the SD_BALANCE_FORK check.
>
> Signed-off-by: Wanpeng Li <wanpeng.li@linux.intel.com>
> ---
>  kernel/sched/deadline.c | 2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
> index abfaf3d..f46b7f1 100644
> --- a/kernel/sched/deadline.c
> +++ b/kernel/sched/deadline.c
> @@ -914,7 +914,7 @@ select_task_rq_dl(struct task_struct *p, int cpu, int sd_flag, int flags)
>  	struct task_struct *curr;
>  	struct rq *rq;
>  
> -	if (sd_flag != SD_BALANCE_WAKE && sd_flag != SD_BALANCE_FORK)
> +	if (sd_flag != SD_BALANCE_WAKE)
>  		goto out;
>  
>  	rq = cpu_rq(cpu);

Re: [PATCH 1/2] sched/deadline: don't need to check SD_BALANCE_FORK

[Juri Lelli]

Hi,

On 21/10/14 13:18, Wanpeng Li wrote:
> Cc Juri,
> 
> 于 10/14/14, 10:22 AM, Wanpeng Li 写道:
>> There is no need to do balance during fork since SCHED_DEADLINE 
>> tasks can't fork. This patch avoid the SD_BALANCE_FORK check.
>>
>> Signed-off-by: Wanpeng Li <wanpeng.li@linux.intel.com>
>> ---
>>  kernel/sched/deadline.c | 2 +-
>>  1 file changed, 1 insertion(+), 1 deletion(-)
>>
>> diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
>> index abfaf3d..f46b7f1 100644
>> --- a/kernel/sched/deadline.c
>> +++ b/kernel/sched/deadline.c
>> @@ -914,7 +914,7 @@ select_task_rq_dl(struct task_struct *p, int cpu, int sd_flag, int flags)
>>  	struct task_struct *curr;
>>  	struct rq *rq;
>>  
>> -	if (sd_flag != SD_BALANCE_WAKE && sd_flag != SD_BALANCE_FORK)
>> +	if (sd_flag != SD_BALANCE_WAKE)
>>  		goto out;
>>  
>>  	rq = cpu_rq(cpu);

Yes, makes sense.

Thanks,

- Juri

[tip:sched/core] sched/deadline: Don't check SD_BALANCE_FORK

[tip-bot for Wanpeng Li]

Commit-ID:  1d7e974cbf2fce2683f34ff33c173fd7ef5478c7
Gitweb:     http://git.kernel.org/tip/1d7e974cbf2fce2683f34ff33c173fd7ef5478c7
Author:     Wanpeng Li <wanpeng.li@linux.intel.com>
AuthorDate: Tue, 14 Oct 2014 10:22:39 +0800
Committer:  Ingo Molnar <mingo@kernel.org>
CommitDate: Tue, 28 Oct 2014 10:48:01 +0100

sched/deadline: Don't check SD_BALANCE_FORK

There is no need to do balance during fork since SCHED_DEADLINE
tasks can't fork. This patch avoid the SD_BALANCE_FORK check.

Signed-off-by: Wanpeng Li <wanpeng.li@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1413253360-5318-1-git-send-email-wanpeng.li@linux.intel.com
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/deadline.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 8aaa971..fab3bf8 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -933,7 +933,7 @@ select_task_rq_dl(struct task_struct *p, int cpu, int sd_flag, int flags)
 	struct task_struct *curr;
 	struct rq *rq;
 
-	if (sd_flag != SD_BALANCE_WAKE && sd_flag != SD_BALANCE_FORK)
+	if (sd_flag != SD_BALANCE_WAKE)
 		goto out;
 
 	rq = cpu_rq(cpu);