On 13 February 2013 21:03, Paul Turner wrote:
> On Tue, Feb 12, 2013 at 5:19 AM, Vincent Guittot
> wrote:
>> need_active_balance uses env->src_cpu which is set only if there is more
>> than 1 task on the run queue.
>> We must set the src_cpu field unconditionnally
>> otherwise the test "env->src_
On 13 February 2013 21:02, Damien Wyart wrote:
>> Bingo, that was the problem in my setup: as the patch was applied
>> through a script with others, I had missed the error message about the
>> conflict (I have also another conflict which can be safely ignored so
>> the new one did not catch my eye
On Tue, Feb 12, 2013 at 5:19 AM, Vincent Guittot
wrote:
> need_active_balance uses env->src_cpu which is set only if there is more
> than 1 task on the run queue.
> We must set the src_cpu field unconditionnally
> otherwise the test "env->src_cpu > env->dst_cpu" will always fail if there is
> only
> Bingo, that was the problem in my setup: as the patch was applied
> through a script with others, I had missed the error message about the
> conflict (I have also another conflict which can be safely ignored so
> the new one did not catch my eye)... So the patch was only
> half-applied, and the f
* Vincent Guittot [2013-02-13 18:49]:
> I have look into Frederic's tree but i didn't find any reason that
> could explain your problem. May be Frederic will have some ideas
> I have also tested his branch with and without my patch and both
> kernel are booting (on an ARM platform without using th
On 13 February 2013 15:28, Vincent Guittot wrote:
> On 13 February 2013 15:08, Damien Wyart wrote:
>> * Vincent Guittot [2013-02-13 13:08]:
>>> Damien,
>>> Regarding your sched_domain config and especially the flags field, you
>>> should not be impacted by my patch because
>>> - need_active_bala
On 13 February 2013 15:08, Damien Wyart wrote:
> * Vincent Guittot [2013-02-13 13:08]:
>> Damien,
>> Regarding your sched_domain config and especially the flags field, you
>> should not be impacted by my patch because
>> - need_active_balance is the only new place that use env->src_cpu in
>> the
* Vincent Guittot [2013-02-13 13:08]:
> Damien,
> Regarding your sched_domain config and especially the flags field, you
> should not be impacted by my patch because
> - need_active_balance is the only new place that use env->src_cpu in
> the load_balance function
> - and your machine will never t
Damien,
Regarding your sched_domain config and especially the flags field, you
should not be impacted by my patch because
- need_active_balance is the only new place that use env->src_cpu in
the load_balance function
- and your machine will never test the condition: "env->src_cpu >
env->dst_cpu" i
Hi Damien,
Thanks for the test and the feedback.
Could you send me the sched_domain configuration of your machine with
the kernel that boots on your machine ?
It's available in /proc/sys/kernel/sched_domain/cpu*/
This should not have any impact on your machine but it looks like it have one.
Rega
Hi,
I tested this on top of 3.8-rc7 and this made the machine (x86_64, Core
i7 920) unable to boot (very early as nothing at all is displayed on
screen). Nothing in the kernel log (after booting with a working
kernel).
Double-checked by just backing out only this patch and this made the
machine b
need_active_balance uses env->src_cpu which is set only if there is more
than 1 task on the run queue. We must set the src_cpu field unconditionnally
otherwise the test "env->src_cpu > env->dst_cpu" will always fail if there is
only 1 task on the run queue
Signed-off-by: Vincent Guittot
---
kern
12 matches
Mail list logo
