Messages in this thread | | | Subject | Re: [PATCH 8/8] intel_idle: create a native cpuidle driver for select intel processors | From | Chase Douglas <> | Date | Fri, 28 May 2010 11:09:40 -0400 |
| |
On Fri, 2010-05-28 at 00:16 -0400, Len Brown wrote: > > I see that you have updated this code in your tree to disable C4 and C6 > > on atom. This has piqued my curiosity. I've now seen 2 atom netbooks > > from different OEMs that hide C4 when you plug the power in. After the > > first machine I thought, "must be a BIOS/ACPI bug," but now I'm > > beginning to wonder if there's some issue with atom C4 states? That's > > beside the fact that I've not seen C6 on either machine at all. Do you > > have any insight? > > The reasoning behind ACPI taking deep C-states away > when on AC is the assumption that users on AC > care more about low latency and high performance > than they care about power savings, heat, and noise.
Maybe they forgot that a netbook is still a *lap*top when they did this, cause I can't keep mine on my lap when it's plugged in :). The CPU idles at 60 centigrade when powered on, and drops to a manageable 30-ish centigrade when running on battery.
> So my intent is to give Linux control over this decision, > via PM_QOS or otherwise. At the moment C4 is commented out > because when i first tested it failed the lapic timer workaround.
I am looking forward to testing out these changes on my netbook once this issue get sorted out!
-- Chase
| |