Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1307522

Re: [RFC PATCH 2/2] sched: idle: IRQ based next prediction for idle period

Show all headers | View raw

On Tue, 12 Jan 2016, Daniel Lezcano wrote:
> On 01/12/2016 03:26 PM, Thomas Gleixner wrote:
> > You better implement the switching part in the cpuidle core first, i.e.
> > proper
> > callbacks when a governor is switched in/out. Then make use of this
> > switcheroo
> > right away. Doing it the other way round is just wrong.
> 
> The problem is this code is not another governor but a 'predictor' where the
> scheduler will use the information to ask the cpuidle to go to a specific idle
> state without going through the governor code, so into the governor's
> callbacks. It is on top of cpuidle. The scheduler will become the governor.
> 
> The current straightforward code, does the switch in the cpu_idle_loop
> idle_task's function:
> 
> [ ... ]
> 
> if (cpu_idle_force_poll || tick_check_broadcast_expired())
> 	cpu_idle_poll();
> else {
> 	if (sched_idle_enabled()) {
> 		int latency = pm_qos_request(PM_QOS_CPU_DMA_LATENCY);
> 		s64 duration = sched_idle_next_wakeup();
> 		sched_idle(duration, latency);
> 	} else {
> 		cpuidle_idle_call();
> 	}
> }
> 
> Due to the complexity of the code, this first step introduce a mechanism to
> predict the next event and re-use it trivially in the idle task.

This looks really wrong. Why on earth don't you implement a proper governor
and just get rid of this extra hackery?

Thanks,

	tglx

Back to linux.kernel | Previous | Next — Previous in thread | Next in thread | Find similar | Unroll thread

Thread

[RFC PATCH 2/2] sched: idle: IRQ based next prediction for idle period Daniel Lezcano <daniel.lezcano@linaro.org> - 2016-01-06 16:30 +0100
  Re: [RFC PATCH 2/2] sched: idle: IRQ based next prediction for idle  period Nicolas Pitre <nicolas.pitre@linaro.org> - 2016-01-06 18:50 +0100
    Re: [RFC PATCH 2/2] sched: idle: IRQ based next prediction for idle  period Daniel Lezcano <daniel.lezcano@linaro.org> - 2016-01-07 16:50 +0100
      Re: [RFC PATCH 2/2] sched: idle: IRQ based next prediction for idle  period Nicolas Pitre <nicolas.pitre@linaro.org> - 2016-01-12 20:30 +0100
    Re: [RFC PATCH 2/2] sched: idle: IRQ based next prediction for idle  period Daniel Lezcano <daniel.lezcano@linaro.org> - 2016-01-10 23:40 +0100
      Re: [RFC PATCH 2/2] sched: idle: IRQ based next prediction for idle  period Nicolas Pitre <nicolas.pitre@linaro.org> - 2016-01-10 23:50 +0100
        Re: [RFC PATCH 2/2] sched: idle: IRQ based next prediction for idle  period Daniel Lezcano <daniel.lezcano@linaro.org> - 2016-01-11 00:00 +0100
          Re: [RFC PATCH 2/2] sched: idle: IRQ based next prediction for idle  period Nicolas Pitre <nicolas.pitre@linaro.org> - 2016-01-11 00:20 +0100
  Re: [RFC PATCH 2/2] sched: idle: IRQ based next prediction for idle  period Thomas Gleixner <tglx@linutronix.de> - 2016-01-08 16:50 +0100
    Re: [RFC PATCH 2/2] sched: idle: IRQ based next prediction for idle  period Daniel Lezcano <daniel.lezcano@linaro.org> - 2016-01-12 13:50 +0100
      Re: [RFC PATCH 2/2] sched: idle: IRQ based next prediction for idle  period Thomas Gleixner <tglx@linutronix.de> - 2016-01-12 14:50 +0100
        Re: [RFC PATCH 2/2] sched: idle: IRQ based next prediction for idle  period Daniel Lezcano <daniel.lezcano@linaro.org> - 2016-01-12 15:20 +0100
          Re: [RFC PATCH 2/2] sched: idle: IRQ based next prediction for idle  period Thomas Gleixner <tglx@linutronix.de> - 2016-01-12 15:30 +0100
            Re: [RFC PATCH 2/2] sched: idle: IRQ based next prediction for idle  period Daniel Lezcano <daniel.lezcano@linaro.org> - 2016-01-12 16:00 +0100
              Re: [RFC PATCH 2/2] sched: idle: IRQ based next prediction for idle  period Thomas Gleixner <tglx@linutronix.de> - 2016-01-12 16:20 +0100
                Re: [RFC PATCH 2/2] sched: idle: IRQ based next prediction for idle  period Daniel Lezcano <daniel.lezcano@linaro.org> - 2016-01-12 17:10 +0100
                Re: [RFC PATCH 2/2] sched: idle: IRQ based next prediction for idle  period Thomas Gleixner <tglx@linutronix.de> - 2016-01-13 10:20 +0100

csiph-web