On 21 September 2012 16:00, Marcin Juszkiewicz
wrote:
> W dniu 21.09.2012 22:24, Zach Pfeffer pisze:
>> On 21 September 2012 15:07, Mike Turquette wrote:
>
>>> https://github.com/omapconf/omapconf
>>
>> Is there an Android.mk? Looking at
>> https://github.com/omapconf/omapconf it says it works on
Just wanted to share this with everyone.
I've attached the "output" folder that the NI instrument creates for
each test session. In the results file you'll see a text doc called
results.txt that lists the comma delimited parameters that get
measured followed by the measurements themselves:
Curren
On Thursday, September 20, 2012, Daniel Lezcano wrote:
> The function __cpuidle_register_driver name is confusing because it
> suggests, conforming to the coding style of the kernel, it registers
> the driver without taking a lock. Actually, it just fill the different
> power field states with a de
On Thu, Sep 20, 2012 at 7:33 PM, Ash Charles wrote:
> Like Jeff mentioned, I also saw some illegal instructions on early
> linaro builds but didn't pursue it at the time. I just did a little
> digging online and there was some mention of ARM errata causing issues
> ( https://bugs.launchpad.net/ub
W dniu 21.09.2012 22:24, Zach Pfeffer pisze:
> On 21 September 2012 15:07, Mike Turquette wrote:
>> https://github.com/omapconf/omapconf
>
> Is there an Android.mk? Looking at
> https://github.com/omapconf/omapconf it says it works on Android, but
> I don't see an Android.mk to compile it with.
On 21 September 2012 15:07, Mike Turquette wrote:
> Hi all,
>
> Some of you may have heard of a tool we use inside TI for debugging on
> OMAP. It's a nice userspace tool which can inspect many aspects of
> hardware state called "omapconf". The tool has just been open sourced
> and can be found a
Hi all,
Some of you may have heard of a tool we use inside TI for debugging on
OMAP. It's a nice userspace tool which can inspect many aspects of
hardware state called "omapconf". The tool has just been open sourced
and can be found at:
https://github.com/omapconf/omapconf
Regards,
Mike
_
From: Morten Rasmussen
This patch adds load_avg_ratio to each task. The load_avg_ratio is a
variant of load_avg_contrib which is not scaled by the task priority. It
is calculated like this:
runnable_avg_sum * NICE_0_LOAD / (runnable_avg_period + 1).
Signed-off-by: Morten Rasmussen
---
include
From: Morten Rasmussen
This patch introduces the basic SCHED_HMP infrastructure. Each class of
cpus is represented by a hmp_domain and tasks will only be moved between
these domains when their load profiles suggest it is beneficial.
SCHED_HMP relies heavily on the task load-tracking introduced i
From: Morten Rasmussen
Introduces a priority threshold which prevents low priority task
from migrating to faster hmp_domains (cpus). This is useful for
user-space software which assigns lower task priority to background
task.
Signed-off-by: Morten Rasmussen
---
arch/arm/Kconfig| 13 +
From: Morten Rasmussen
We need a way to prevent tasks that are migrating up and down the
hmp_domains from migrating straight on through before the load has
adapted to the new compute capacity of the CPU on the new hmp_domain.
This patch adds a next up/down migration delay that prevents the task
f
From: Morten Rasmussen
Adds ftrace events for key variables related to the entity
load-tracking to help debugging scheduler behaviour. Allows tracing
of load contribution and runqueue residency ratio for both entities
and runqueues as well as entity CPU usage ratio.
Signed-off-by: Morten Rasmuss
From: Morten Rasmussen
Hi Paul, Paul, Peter, Suresh, linaro-sched-sig, and LKML,
As a follow-up on my Linux Plumbers Conference talk about my experiments with
scheduling on heterogeneous systems I'm posting a proof-of-concept patch set
with my modifications. The intention behind the modification
From: Morten Rasmussen
SCHED_HMP requires the different cpu types to be represented by an
ordered list of hmp_domains. Each hmp_domain represents all cpus of
a particular type using a cpumask.
The list is platform specific and therefore must be generated by
platform code by implementing arch_get
From: Morten Rasmussen
We can't rely on Kconfig options to set the fast and slow CPU lists for
HMP scheduling if we want a single kernel binary to support multiple
devices with different CPU topology. E.g. TC2 (ARM's Test-Chip-2
big.LITTLE system), Fast Models, or even non big.LITTLE devices.
Th
From: Morten Rasmussen
This patch introduces forced task migration for moving suitable
currently running tasks between hmp_domains. Task behaviour is likely
to change over time. Tasks running in a less capable hmp_domain may
change to become more demanding and should therefore be migrated up.
The
From: Morten Rasmussen
Adds ftrace event for tracing task migrations using HMP
optimized scheduling.
Signed-off-by: Morten Rasmussen
---
include/trace/events/sched.h | 28
kernel/sched/fair.c | 15 +++
2 files changed, 39 insertions(+), 4 d
From: Morten Rasmussen
Adds Kconfig entries to enable HMP scheduling on ARM platforms.
Currently, it disables CPU level sched_domain load-balacing in order
to simplify things. This needs fixing in a later revision. HMP
scheduling will do the load-balancing at this level instead.
Signed-off-by: M
Prepare devfreq core framework to support devices which
can idle. When device idleness is detected perhaps through
runtime-pm, need some mechanism to suspend devfreq load
monitoring and resume back when device is online. Present
code continues monitoring unless device is removed from
devfreq core.
This patchset updates devfreq core to add support for devices
which can idle. When device idleness is detected perhaps
through runtime-pm, need some mechanism to suspend devfreq
load monitoring and resume when device is back online.
patch 1 introduce core design changes - per device work, decouple
Add devfreq suspend/resume apis for devfreq users. This patch
supports suspend and resume of devfreq load monitoring, required
for devices which can idle.
Signed-off-by: Rajagopal Venkat
---
drivers/devfreq/devfreq.c | 28
drivers/devfreq/governor.h
Devfreq returns governor predicted frequency as current frequency
via sysfs interface. But device may not support all frequencies
that governor predicts. So add a callback in device profile to get
current freq from driver. Also add a new sysfs node to expose
governor predicted next target frequency
Like Jeff mentioned, I also saw some illegal instructions on early
linaro builds but didn't pursue it at the time. I just did a little
digging online and there was some mention of ARM errata causing issues
( https://bugs.launchpad.net/ubuntu/+source/fakeroot/+bug/495536)
Based on,
https://github.
On 21 September 2012 16:02, Zhang Rui wrote:
> On 五, 2012-09-21 at 15:50 +0800, Hongbo Zhang wrote:
>> On 21 September 2012 15:21, Zhang Rui wrote:
>> > On 五, 2012-09-21 at 14:57 +0800, zhanghongbo wrote:
>> >> From: "hongbo.zhang"
>> >>
>> >> This patch set contains two patches.
>> >>
>> >> [PA
On 五, 2012-09-21 at 15:50 +0800, Hongbo Zhang wrote:
> On 21 September 2012 15:21, Zhang Rui wrote:
> > On 五, 2012-09-21 at 14:57 +0800, zhanghongbo wrote:
> >> From: "hongbo.zhang"
> >>
> >> This patch set contains two patches.
> >>
> >> [PATCH 1/2]
> >> A new interface is introduced to deactive
On 21 September 2012 15:21, Zhang Rui wrote:
> On 五, 2012-09-21 at 14:57 +0800, zhanghongbo wrote:
>> From: "hongbo.zhang"
>>
>> This patch set contains two patches.
>>
>> [PATCH 1/2]
>> A new interface is introduced to deactive all the referenced cooling devices
>> when thermal zone is disabled.
On 五, 2012-09-21 at 14:57 +0800, zhanghongbo wrote:
> From: "hongbo.zhang"
>
> This patch set contains two patches.
>
> [PATCH 1/2]
> A new interface is introduced to deactive all the referenced cooling devices
> when thermal zone is disabled.
we can not deactive a cooling device directly.
we s
27 matches
Mail list logo