Re: [PATCH] Dynamic tick for x86 version 050610-1
* Benjamin Herrenschmidt <[EMAIL PROTECTED]> [050719 06:55]: > On Tue, 2005-07-19 at 14:51 +0800, [EMAIL PROTECTED] wrote: > > On Sat, Jun 18, 2005 at 04:30:32PM +1000, Benjamin Herrenschmidt wrote: > > > > > > > I'm try to port it powerpc, Here is a patch. > > > > > > > > Port Dynamic Tick Timer to new platform is easy. :) > > > > 1) Find the reprogram timer interface. > > > > 2) do a hook in the idle function. > > > > > > > > That worked on my PowerBookG4 12'. > > > > > > Did you get a measurable gain on power consumption ? > > > > > > Last time I toyed with this, I didn't. > > > > Today I do a measurable about it. > > > > First I using 2.6.12 without dynamic enable and unplug the AC power, > > I check the /proc/pmu/battery_0, like this. > > -- > > flags : 0011 > > charge : 907 > > max_charge : 2863 > > current: -987 > > voltage: 10950 > > time rem. : 3600 > > -- > > I only intresting with current, that show the system power load. > > > > When I enable dynamic, The current can low at -900. > > The numbers are repeatable ? I mean, if you actually let it settle down > in both cases ? Also, you should be careful about "parasites" in the > measurement, like pbbuttons dimming the backlight, the hard disk going > to sleep etc... > > >From your numbers you get something like 10% improvement, which isn't > too bad. Just quick update here, I'm back from vacation and will try to post updated dyn-tick patch soon with the PPC patch integrated. Tony - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: [PATCH] Dynamic tick for x86 version 050610-1
* Benjamin Herrenschmidt [EMAIL PROTECTED] [050719 06:55]: On Tue, 2005-07-19 at 14:51 +0800, [EMAIL PROTECTED] wrote: On Sat, Jun 18, 2005 at 04:30:32PM +1000, Benjamin Herrenschmidt wrote: I'm try to port it powerpc, Here is a patch. Port Dynamic Tick Timer to new platform is easy. :) 1) Find the reprogram timer interface. 2) do a hook in the idle function. That worked on my PowerBookG4 12'. Did you get a measurable gain on power consumption ? Last time I toyed with this, I didn't. Today I do a measurable about it. First I using 2.6.12 without dynamic enable and unplug the AC power, I check the /proc/pmu/battery_0, like this. -- flags : 0011 charge : 907 max_charge : 2863 current: -987 voltage: 10950 time rem. : 3600 -- I only intresting with current, that show the system power load. When I enable dynamic, The current can low at -900. The numbers are repeatable ? I mean, if you actually let it settle down in both cases ? Also, you should be careful about parasites in the measurement, like pbbuttons dimming the backlight, the hard disk going to sleep etc... From your numbers you get something like 10% improvement, which isn't too bad. Just quick update here, I'm back from vacation and will try to post updated dyn-tick patch soon with the PPC patch integrated. Tony - To unsubscribe from this list: send the line unsubscribe linux-kernel in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: [PATCH] Dynamic tick for x86 version 050610-1
On Tue, 2005-07-19 at 14:51 +0800, [EMAIL PROTECTED] wrote: > On Sat, Jun 18, 2005 at 04:30:32PM +1000, Benjamin Herrenschmidt wrote: > > > > > I'm try to port it powerpc, Here is a patch. > > > > > > Port Dynamic Tick Timer to new platform is easy. :) > > > 1) Find the reprogram timer interface. > > > 2) do a hook in the idle function. > > > > > > That worked on my PowerBookG4 12'. > > > > Did you get a measurable gain on power consumption ? > > > > Last time I toyed with this, I didn't. > > Today I do a measurable about it. > > First I using 2.6.12 without dynamic enable and unplug the AC power, > I check the /proc/pmu/battery_0, like this. > -- > flags : 0011 > charge : 907 > max_charge : 2863 > current: -987 > voltage: 10950 > time rem. : 3600 > -- > I only intresting with current, that show the system power load. > > When I enable dynamic, The current can low at -900. The numbers are repeatable ? I mean, if you actually let it settle down in both cases ? Also, you should be careful about "parasites" in the measurement, like pbbuttons dimming the backlight, the hard disk going to sleep etc... >From your numbers you get something like 10% improvement, which isn't too bad. Ben. - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: [PATCH] Dynamic tick for x86 version 050610-1
On Sat, Jun 18, 2005 at 04:30:32PM +1000, Benjamin Herrenschmidt wrote: > > > I'm try to port it powerpc, Here is a patch. > > > > Port Dynamic Tick Timer to new platform is easy. :) > > 1) Find the reprogram timer interface. > > 2) do a hook in the idle function. > > > > That worked on my PowerBookG4 12'. > > Did you get a measurable gain on power consumption ? > > Last time I toyed with this, I didn't. Today I do a measurable about it. First I using 2.6.12 without dynamic enable and unplug the AC power, I check the /proc/pmu/battery_0, like this. -- flags : 0011 charge : 907 max_charge : 2863 current: -987 voltage: 10950 time rem. : 3600 -- I only intresting with current, that show the system power load. When I enable dynamic, The current can low at -900. So, It works. :> 2.6.12 + suspend2 + ck3 + dynamic http://soulinfo.com/~hugang/kernel/linux-2.6.12/ -- Hu Gang .-.Steve /v\ // \\ /( )\ GPG Key ID ^^-^^ http://soulinfo.com/~hugang/hugang.asc - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: [PATCH] Dynamic tick for x86 version 050610-1
On Sat, Jun 18, 2005 at 04:30:32PM +1000, Benjamin Herrenschmidt wrote: I'm try to port it powerpc, Here is a patch. Port Dynamic Tick Timer to new platform is easy. :) 1) Find the reprogram timer interface. 2) do a hook in the idle function. That worked on my PowerBookG4 12'. Did you get a measurable gain on power consumption ? Last time I toyed with this, I didn't. Today I do a measurable about it. First I using 2.6.12 without dynamic enable and unplug the AC power, I check the /proc/pmu/battery_0, like this. -- flags : 0011 charge : 907 max_charge : 2863 current: -987 voltage: 10950 time rem. : 3600 -- I only intresting with current, that show the system power load. When I enable dynamic, The current can low at -900. So, It works. : 2.6.12 + suspend2 + ck3 + dynamic http://soulinfo.com/~hugang/kernel/linux-2.6.12/ -- Hu Gang .-.Steve /v\ // \\ /( )\ GPG Key ID ^^-^^ http://soulinfo.com/~hugang/hugang.asc - To unsubscribe from this list: send the line unsubscribe linux-kernel in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: [PATCH] Dynamic tick for x86 version 050610-1
On Tue, 2005-07-19 at 14:51 +0800, [EMAIL PROTECTED] wrote: On Sat, Jun 18, 2005 at 04:30:32PM +1000, Benjamin Herrenschmidt wrote: I'm try to port it powerpc, Here is a patch. Port Dynamic Tick Timer to new platform is easy. :) 1) Find the reprogram timer interface. 2) do a hook in the idle function. That worked on my PowerBookG4 12'. Did you get a measurable gain on power consumption ? Last time I toyed with this, I didn't. Today I do a measurable about it. First I using 2.6.12 without dynamic enable and unplug the AC power, I check the /proc/pmu/battery_0, like this. -- flags : 0011 charge : 907 max_charge : 2863 current: -987 voltage: 10950 time rem. : 3600 -- I only intresting with current, that show the system power load. When I enable dynamic, The current can low at -900. The numbers are repeatable ? I mean, if you actually let it settle down in both cases ? Also, you should be careful about parasites in the measurement, like pbbuttons dimming the backlight, the hard disk going to sleep etc... From your numbers you get something like 10% improvement, which isn't too bad. Ben. - To unsubscribe from this list: send the line unsubscribe linux-kernel in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
