On 26 April 2013 12:30, Peter Zijlstra wrote:
> On Wed, Mar 27, 2013 at 12:00:40PM +0100, Vincent Guittot wrote:
>> On 27 March 2013 11:21, Preeti U Murthy wrote:
>> > Hi,
>> >
>> > On 03/26/2013 05:56 PM, Peter Zijlstra wrote:
>> >> On Fri, 2013-03-22 at 13:25 +0100, Vincent Guittot wrote:
>>
Hi Peter,
On 04/26/2013 03:48 PM, Peter Zijlstra wrote:
> On Wed, Mar 27, 2013 at 03:51:51PM +0530, Preeti U Murthy wrote:
>> Hi,
>>
>> On 03/26/2013 05:56 PM, Peter Zijlstra wrote:
>>> On Fri, 2013-03-22 at 13:25 +0100, Vincent Guittot wrote:
+static bool is_buddy_busy(int cpu)
+{
On Wed, Mar 27, 2013 at 12:00:40PM +0100, Vincent Guittot wrote:
> On 27 March 2013 11:21, Preeti U Murthy wrote:
> > Hi,
> >
> > On 03/26/2013 05:56 PM, Peter Zijlstra wrote:
> >> On Fri, 2013-03-22 at 13:25 +0100, Vincent Guittot wrote:
> >>> +static bool is_buddy_busy(int cpu)
> >>> +{
> >>> +
On Wed, Mar 27, 2013 at 03:51:51PM +0530, Preeti U Murthy wrote:
> Hi,
>
> On 03/26/2013 05:56 PM, Peter Zijlstra wrote:
> > On Fri, 2013-03-22 at 13:25 +0100, Vincent Guittot wrote:
> >> +static bool is_buddy_busy(int cpu)
> >> +{
> >> + struct rq *rq = cpu_rq(cpu);
> >> +
> >> + /*
On Wed, Mar 27, 2013 at 03:51:51PM +0530, Preeti U Murthy wrote:
Hi,
On 03/26/2013 05:56 PM, Peter Zijlstra wrote:
On Fri, 2013-03-22 at 13:25 +0100, Vincent Guittot wrote:
+static bool is_buddy_busy(int cpu)
+{
+ struct rq *rq = cpu_rq(cpu);
+
+ /*
+* A busy
On Wed, Mar 27, 2013 at 12:00:40PM +0100, Vincent Guittot wrote:
On 27 March 2013 11:21, Preeti U Murthy pre...@linux.vnet.ibm.com wrote:
Hi,
On 03/26/2013 05:56 PM, Peter Zijlstra wrote:
On Fri, 2013-03-22 at 13:25 +0100, Vincent Guittot wrote:
+static bool is_buddy_busy(int cpu)
+{
Hi Peter,
On 04/26/2013 03:48 PM, Peter Zijlstra wrote:
On Wed, Mar 27, 2013 at 03:51:51PM +0530, Preeti U Murthy wrote:
Hi,
On 03/26/2013 05:56 PM, Peter Zijlstra wrote:
On Fri, 2013-03-22 at 13:25 +0100, Vincent Guittot wrote:
+static bool is_buddy_busy(int cpu)
+{
+ struct rq *rq
On 26 April 2013 12:30, Peter Zijlstra pet...@infradead.org wrote:
On Wed, Mar 27, 2013 at 12:00:40PM +0100, Vincent Guittot wrote:
On 27 March 2013 11:21, Preeti U Murthy pre...@linux.vnet.ibm.com wrote:
Hi,
On 03/26/2013 05:56 PM, Peter Zijlstra wrote:
On Fri, 2013-03-22 at 13:25
On Wed, Mar 27, 2013 at 05:18:53PM +, Nicolas Pitre wrote:
> On Wed, 27 Mar 2013, Catalin Marinas wrote:
>
> > So if the above works, the scheduler guys can mandate that little CPUs
> > are always first and for ARM it would be a matter of getting the right
> > CPU topology in the DT
On Wed, 27 Mar 2013, Catalin Marinas wrote:
> So if the above works, the scheduler guys can mandate that little CPUs
> are always first and for ARM it would be a matter of getting the right
> CPU topology in the DT (independent of what hw vendors think of CPU
> topology) and booting Linux on CPU
On Wed, 27 Mar 2013, Vincent Guittot wrote:
> On 27 March 2013 09:46, Peter Zijlstra wrote:
> > On Tue, 2013-03-26 at 08:29 -0700, Arjan van de Ven wrote:
> >> > Isn't this basically related to picking the NO_HZ cpu; if the system
> >> > isn't fully symmetric with its power gates you want the
On 27 March 2013 11:21, Preeti U Murthy wrote:
> Hi,
>
> On 03/26/2013 05:56 PM, Peter Zijlstra wrote:
>> On Fri, 2013-03-22 at 13:25 +0100, Vincent Guittot wrote:
>>> +static bool is_buddy_busy(int cpu)
>>> +{
>>> + struct rq *rq = cpu_rq(cpu);
>>> +
>>> + /*
>>> +* A busy
Hi,
On 03/26/2013 05:56 PM, Peter Zijlstra wrote:
> On Fri, 2013-03-22 at 13:25 +0100, Vincent Guittot wrote:
>> +static bool is_buddy_busy(int cpu)
>> +{
>> + struct rq *rq = cpu_rq(cpu);
>> +
>> + /*
>> +* A busy buddy is a CPU with a high load or a small load with
>> a lot
On Wed, 2013-03-27 at 09:54 +0100, Vincent Guittot wrote:
> It's not mandatory to have little cores on low numbers even if it's
> advised
ARGH!
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at
On Tue, 2013-03-26 at 08:29 -0700, Arjan van de Ven wrote:
> > Isn't this basically related to picking the NO_HZ cpu; if the system
> > isn't fully symmetric with its power gates you want the NO_HZ cpu to be
> > the 'special' cpu. If it is symmetric we really don't care which core
> > is left
On 27 March 2013 09:46, Peter Zijlstra wrote:
> On Tue, 2013-03-26 at 08:29 -0700, Arjan van de Ven wrote:
>> > Isn't this basically related to picking the NO_HZ cpu; if the system
>> > isn't fully symmetric with its power gates you want the NO_HZ cpu to be
>> > the 'special' cpu. If it is
On Wed, 2013-03-27 at 12:48 +0800, Alex Shi wrote:
>
> Yes, the new forked runnable load was set as full utilisation in V5
> power aware scheduling. PJT, Mike and I both agree on this. PJT just
> discussion how to give the full load to new forked task. and we get
> agreement in my coming V6 power
On Wed, 2013-03-27 at 12:48 +0800, Alex Shi wrote:
Yes, the new forked runnable load was set as full utilisation in V5
power aware scheduling. PJT, Mike and I both agree on this. PJT just
discussion how to give the full load to new forked task. and we get
agreement in my coming V6 power
On 27 March 2013 09:46, Peter Zijlstra pet...@infradead.org wrote:
On Tue, 2013-03-26 at 08:29 -0700, Arjan van de Ven wrote:
Isn't this basically related to picking the NO_HZ cpu; if the system
isn't fully symmetric with its power gates you want the NO_HZ cpu to be
the 'special' cpu. If it
On Tue, 2013-03-26 at 08:29 -0700, Arjan van de Ven wrote:
Isn't this basically related to picking the NO_HZ cpu; if the system
isn't fully symmetric with its power gates you want the NO_HZ cpu to be
the 'special' cpu. If it is symmetric we really don't care which core
is left 'running'
On Wed, 2013-03-27 at 09:54 +0100, Vincent Guittot wrote:
It's not mandatory to have little cores on low numbers even if it's
advised
ARGH!
--
To unsubscribe from this list: send the line unsubscribe linux-kernel in
the body of a message to majord...@vger.kernel.org
More majordomo info at
Hi,
On 03/26/2013 05:56 PM, Peter Zijlstra wrote:
On Fri, 2013-03-22 at 13:25 +0100, Vincent Guittot wrote:
+static bool is_buddy_busy(int cpu)
+{
+ struct rq *rq = cpu_rq(cpu);
+
+ /*
+* A busy buddy is a CPU with a high load or a small load with
a lot of
+*
On 27 March 2013 11:21, Preeti U Murthy pre...@linux.vnet.ibm.com wrote:
Hi,
On 03/26/2013 05:56 PM, Peter Zijlstra wrote:
On Fri, 2013-03-22 at 13:25 +0100, Vincent Guittot wrote:
+static bool is_buddy_busy(int cpu)
+{
+ struct rq *rq = cpu_rq(cpu);
+
+ /*
+* A busy
On Wed, 27 Mar 2013, Vincent Guittot wrote:
On 27 March 2013 09:46, Peter Zijlstra pet...@infradead.org wrote:
On Tue, 2013-03-26 at 08:29 -0700, Arjan van de Ven wrote:
Isn't this basically related to picking the NO_HZ cpu; if the system
isn't fully symmetric with its power gates you
On Wed, 27 Mar 2013, Catalin Marinas wrote:
So if the above works, the scheduler guys can mandate that little CPUs
are always first and for ARM it would be a matter of getting the right
CPU topology in the DT (independent of what hw vendors think of CPU
topology) and booting Linux on CPU 4
On Wed, Mar 27, 2013 at 05:18:53PM +, Nicolas Pitre wrote:
On Wed, 27 Mar 2013, Catalin Marinas wrote:
So if the above works, the scheduler guys can mandate that little CPUs
are always first and for ARM it would be a matter of getting the right
CPU topology in the DT (independent of
On 03/27/2013 12:33 PM, Preeti U Murthy wrote:
> Hi Peter,
>
> On 03/26/2013 06:07 PM, Peter Zijlstra wrote:
>> On Fri, 2013-03-22 at 13:25 +0100, Vincent Guittot wrote:
>>> +static bool is_light_task(struct task_struct *p)
>>> +{
>>> + /* A light task runs less than 20% in average */
>>> +
Hi Peter,
On 03/26/2013 06:07 PM, Peter Zijlstra wrote:
> On Fri, 2013-03-22 at 13:25 +0100, Vincent Guittot wrote:
>> +static bool is_light_task(struct task_struct *p)
>> +{
>> + /* A light task runs less than 20% in average */
>> + return ((p->se.avg.runnable_avg_sum * 5) <
>> +
Isn't this basically related to picking the NO_HZ cpu; if the system
isn't fully symmetric with its power gates you want the NO_HZ cpu to be
the 'special' cpu. If it is symmetric we really don't care which core
is left 'running' and we can even select a new pack cpu from the idle
cores once the
On 26 March 2013 13:46, Peter Zijlstra wrote:
> On Fri, 2013-03-22 at 13:25 +0100, Vincent Guittot wrote:
>> During the creation of sched_domain, we define a pack buddy CPU for
>> each CPU
>> when one is available. We want to pack at all levels where a group of
>> CPU can
>> be power gated
On 26 March 2013 13:37, Peter Zijlstra wrote:
> On Fri, 2013-03-22 at 13:25 +0100, Vincent Guittot wrote:
>> +static bool is_light_task(struct task_struct *p)
>> +{
>> + /* A light task runs less than 20% in average */
>> + return ((p->se.avg.runnable_avg_sum * 5) <
>> +
On Fri, 2013-03-22 at 13:25 +0100, Vincent Guittot wrote:
> During the creation of sched_domain, we define a pack buddy CPU for
> each CPU
> when one is available. We want to pack at all levels where a group of
> CPU can
> be power gated independently from others.
> On a system that can't power
On Fri, 2013-03-22 at 13:25 +0100, Vincent Guittot wrote:
> +static bool is_light_task(struct task_struct *p)
> +{
> + /* A light task runs less than 20% in average */
> + return ((p->se.avg.runnable_avg_sum * 5) <
> + (p->se.avg.runnable_avg_period));
> +}
OK,
On Fri, 2013-03-22 at 13:25 +0100, Vincent Guittot wrote:
> +static bool is_buddy_busy(int cpu)
> +{
> + struct rq *rq = cpu_rq(cpu);
> +
> + /*
> +* A busy buddy is a CPU with a high load or a small load with
> a lot of
> +* running tasks.
> +*/
> +
On Fri, 2013-03-22 at 13:25 +0100, Vincent Guittot wrote:
+static bool is_buddy_busy(int cpu)
+{
+ struct rq *rq = cpu_rq(cpu);
+
+ /*
+* A busy buddy is a CPU with a high load or a small load with
a lot of
+* running tasks.
+*/
+ return
On Fri, 2013-03-22 at 13:25 +0100, Vincent Guittot wrote:
+static bool is_light_task(struct task_struct *p)
+{
+ /* A light task runs less than 20% in average */
+ return ((p-se.avg.runnable_avg_sum * 5)
+ (p-se.avg.runnable_avg_period));
+}
OK, so we
On Fri, 2013-03-22 at 13:25 +0100, Vincent Guittot wrote:
During the creation of sched_domain, we define a pack buddy CPU for
each CPU
when one is available. We want to pack at all levels where a group of
CPU can
be power gated independently from others.
On a system that can't power gate a
On 26 March 2013 13:37, Peter Zijlstra pet...@infradead.org wrote:
On Fri, 2013-03-22 at 13:25 +0100, Vincent Guittot wrote:
+static bool is_light_task(struct task_struct *p)
+{
+ /* A light task runs less than 20% in average */
+ return ((p-se.avg.runnable_avg_sum * 5)
+
On 26 March 2013 13:46, Peter Zijlstra pet...@infradead.org wrote:
On Fri, 2013-03-22 at 13:25 +0100, Vincent Guittot wrote:
During the creation of sched_domain, we define a pack buddy CPU for
each CPU
when one is available. We want to pack at all levels where a group of
CPU can
be power
Isn't this basically related to picking the NO_HZ cpu; if the system
isn't fully symmetric with its power gates you want the NO_HZ cpu to be
the 'special' cpu. If it is symmetric we really don't care which core
is left 'running' and we can even select a new pack cpu from the idle
cores once the
Hi Peter,
On 03/26/2013 06:07 PM, Peter Zijlstra wrote:
On Fri, 2013-03-22 at 13:25 +0100, Vincent Guittot wrote:
+static bool is_light_task(struct task_struct *p)
+{
+ /* A light task runs less than 20% in average */
+ return ((p-se.avg.runnable_avg_sum * 5)
+
On 03/27/2013 12:33 PM, Preeti U Murthy wrote:
Hi Peter,
On 03/26/2013 06:07 PM, Peter Zijlstra wrote:
On Fri, 2013-03-22 at 13:25 +0100, Vincent Guittot wrote:
+static bool is_light_task(struct task_struct *p)
+{
+ /* A light task runs less than 20% in average */
+ return
During the creation of sched_domain, we define a pack buddy CPU for each CPU
when one is available. We want to pack at all levels where a group of CPU can
be power gated independently from others.
On a system that can't power gate a group of CPUs independently, the flag is
set at all sched_domain
During the creation of sched_domain, we define a pack buddy CPU for each CPU
when one is available. We want to pack at all levels where a group of CPU can
be power gated independently from others.
On a system that can't power gate a group of CPUs independently, the flag is
set at all sched_domain
44 matches
Mail list logo
