Re: [PATCH 6/6] sched: final power vs capacity cleanup
On Thu, 15 May 2014, Nicolas Pitre wrote: > On Thu, 15 May 2014, Peter Zijlstra wrote: > > > On Wed, May 14, 2014 at 04:57:10PM -0400, Nicolas Pitre wrote: > > > It is better not to think about compute capacity as being equivalent to > > > "CPU power". The upcoming "power aware" scheduler may create confusion > > > with the notion of energy consumption if "power" is used too liberally. > > > > > > This contains the architecture visible changes. Incidentally, only ARM > > > takes advantage of the available pow^H^H^Hcapacity scaling hooks and > > > therefore those changes outside kernel/sched/ are confined to one ARM > > > specific file. The default arch_scale_smt_power() hook is not overridden > > > by anyone. > > > > > > Replacements are as follows: > > > > > > arch_scale_freq_power --> arch_scale_freq_capacity > > > arch_scale_smt_power --> arch_scale_smt_capacity > > > SCHED_POWER_SCALE --> SCHED_CAPA_SCALE > > > SCHED_POWER_SHIFT --> SCHED_POWER_SHIFT > > > > The patch seems to actually make that CAPA_SHIFT > > Huh... right, of course. > > > > The local usage of "power" in arch/arm/kernel/topology.c is also changed > > > to "capacity" as appropriate. > > > > For some reason every time I read: 'capa' I think of some south American > > monster -- http://en.wikipedia.org/wiki/Chupacabra, I'm not at all sure > > why my brain links them. > > :-) > > capa != paca > > I chose that not to make this much longer than "POWER", and since there > are already "LOAD" related constants, I thought there was some symetry > to another 4-letter identifier. Do you have other suggestions? I understand that Vincent is inclined to rebase his future work on top of this renaming. Should I repost or you're happy to fix the commit log manually? Any other concerns I should address? Nicolas -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: [PATCH 6/6] sched: final power vs capacity cleanup
On Thu, 15 May 2014, Peter Zijlstra wrote: > On Wed, May 14, 2014 at 04:57:10PM -0400, Nicolas Pitre wrote: > > It is better not to think about compute capacity as being equivalent to > > "CPU power". The upcoming "power aware" scheduler may create confusion > > with the notion of energy consumption if "power" is used too liberally. > > > > This contains the architecture visible changes. Incidentally, only ARM > > takes advantage of the available pow^H^H^Hcapacity scaling hooks and > > therefore those changes outside kernel/sched/ are confined to one ARM > > specific file. The default arch_scale_smt_power() hook is not overridden > > by anyone. > > > > Replacements are as follows: > > > > arch_scale_freq_power --> arch_scale_freq_capacity > > arch_scale_smt_power --> arch_scale_smt_capacity > > SCHED_POWER_SCALE --> SCHED_CAPA_SCALE > > SCHED_POWER_SHIFT --> SCHED_POWER_SHIFT > > The patch seems to actually make that CAPA_SHIFT Huh... right, of course. > > The local usage of "power" in arch/arm/kernel/topology.c is also changed > > to "capacity" as appropriate. > > For some reason every time I read: 'capa' I think of some south American > monster -- http://en.wikipedia.org/wiki/Chupacabra, I'm not at all sure > why my brain links them. :-) capa != paca I chose that not to make this much longer than "POWER", and since there are already "LOAD" related constants, I thought there was some symetry to another 4-letter identifier. Do you have other suggestions? Nicolas -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: [PATCH 6/6] sched: final power vs capacity cleanup
On Wed, May 14, 2014 at 04:57:10PM -0400, Nicolas Pitre wrote: > It is better not to think about compute capacity as being equivalent to > "CPU power". The upcoming "power aware" scheduler may create confusion > with the notion of energy consumption if "power" is used too liberally. > > This contains the architecture visible changes. Incidentally, only ARM > takes advantage of the available pow^H^H^Hcapacity scaling hooks and > therefore those changes outside kernel/sched/ are confined to one ARM > specific file. The default arch_scale_smt_power() hook is not overridden > by anyone. > > Replacements are as follows: > > arch_scale_freq_power --> arch_scale_freq_capacity > arch_scale_smt_power --> arch_scale_smt_capacity > SCHED_POWER_SCALE --> SCHED_CAPA_SCALE > SCHED_POWER_SHIFT --> SCHED_POWER_SHIFT The patch seems to actually make that CAPA_SHIFT > The local usage of "power" in arch/arm/kernel/topology.c is also changed > to "capacity" as appropriate. For some reason every time I read: 'capa' I think of some south American monster -- http://en.wikipedia.org/wiki/Chupacabra, I'm not at all sure why my brain links them. But yes, once we kill the capacity stuff we have now with some utilization bound, capacity becomes uniquely the compute capacity. pgpdAUkFIyTwx.pgp Description: PGP signature