Re: [PATCH 07/10] nohz: Enforce timekeeping on CPU 0

2014-07-30 Thread Frederic Weisbecker
On Tue, Jul 29, 2014 at 02:12:37PM +0200, Peter Zijlstra wrote: > On Mon, Jul 28, 2014 at 07:37:33PM +0200, Frederic Weisbecker wrote: > > The timekeeper gets initialized to the value of the CPU where the > > first clockevent device is setup. This works well because the timekeeper > > can be any on

Re: [PATCH 07/10] nohz: Enforce timekeeping on CPU 0

2014-07-29 Thread Peter Zijlstra
On Mon, Jul 28, 2014 at 07:37:33PM +0200, Frederic Weisbecker wrote: > The timekeeper gets initialized to the value of the CPU where the > first clockevent device is setup. This works well because the timekeeper > can be any online CPU in most configs. > > Full dynticks has its own requirement tho

[PATCH 07/10] nohz: Enforce timekeeping on CPU 0

2014-07-28 Thread Frederic Weisbecker
The timekeeper gets initialized to the value of the CPU where the first clockevent device is setup. This works well because the timekeeper can be any online CPU in most configs. Full dynticks has its own requirement though and needs the timekeeper to always be 0. And this requirement seem to accom

Re: [PATCH 07/10] nohz: Enforce timekeeping on CPU 0

2014-07-19 Thread Frederic Weisbecker
On Sat, Jul 19, 2014 at 01:31:25PM -0400, Nicolas Pitre wrote: > On Sat, 19 Jul 2014, Frederic Weisbecker wrote: > > > The timekeeper gets initialized to the value of the CPU where the > > first clockevent device is setup. This works well because the timekeeper > > can be any online CPU in most co

Re: [PATCH 07/10] nohz: Enforce timekeeping on CPU 0

2014-07-19 Thread Peter Zijlstra
On Sat, Jul 19, 2014 at 02:46:56PM -0400, Nicolas Pitre wrote: > People think all sorts of things. And it becomes very irritating when > thoughtful assumptions get burned into ROM for example. We should be > able to do better in the kernel. Agreed. There used to be an x86 subarch where the boo

Re: [PATCH 07/10] nohz: Enforce timekeeping on CPU 0

2014-07-19 Thread Nicolas Pitre
On Sat, 19 Jul 2014, Peter Zijlstra wrote: > On Sat, Jul 19, 2014 at 01:31:25PM -0400, Nicolas Pitre wrote: > > On Sat, 19 Jul 2014, Frederic Weisbecker wrote: > > > > > The timekeeper gets initialized to the value of the CPU where the > > > first clockevent device is setup. This works well becau

Re: [PATCH 07/10] nohz: Enforce timekeeping on CPU 0

2014-07-19 Thread Peter Zijlstra
On Sat, Jul 19, 2014 at 01:31:25PM -0400, Nicolas Pitre wrote: > On Sat, 19 Jul 2014, Frederic Weisbecker wrote: > > > The timekeeper gets initialized to the value of the CPU where the > > first clockevent device is setup. This works well because the timekeeper > > can be any online CPU in most co

Re: [PATCH 07/10] nohz: Enforce timekeeping on CPU 0

2014-07-19 Thread Nicolas Pitre
On Sat, 19 Jul 2014, Frederic Weisbecker wrote: > The timekeeper gets initialized to the value of the CPU where the > first clockevent device is setup. This works well because the timekeeper > can be any online CPU in most configs. > > Full dynticks has its own requirement though and needs the ti

[PATCH 07/10] nohz: Enforce timekeeping on CPU 0

2014-07-18 Thread Frederic Weisbecker
The timekeeper gets initialized to the value of the CPU where the first clockevent device is setup. This works well because the timekeeper can be any online CPU in most configs. Full dynticks has its own requirement though and needs the timekeeper to always be 0. And this requirement seem to accom