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

Groups > linux.kernel > #1313461

Re: [RFC V2 2/2] sched: idle: IRQ based next prediction for idle period

From Peter Zijlstra <peterz@infradead.org>
Newsgroups linux.kernel
Subject Re: [RFC V2 2/2] sched: idle: IRQ based next prediction for idle period
Date 2016-01-20 20:40 +0100
Message-ID <qT6LL-2E2-3@gated-at.bofh.it> (permalink)
References <qT3ux-vq-3@gated-at.bofh.it> <qT3ux-vq-1@gated-at.bofh.it>
Organization linux.* mail to news gateway

Show all headers | View raw

On Wed, Jan 20, 2016 at 05:00:33PM +0100, Daniel Lezcano wrote:
> +		variance = stats_variance(&w->stats, mean);
> +		/*
> +		 * We want to check the last interval is:
> +		 *
> +		 *  mean - stddev < interval < mean + stddev
> +		 *
> +		 * That simplifies to:
> +		 *
> +		 * -stddev < interval - mean < stddev
> +		 *
> +		 * abs(interval - mean) < stddev
> +		 *
> +		 * The standard deviation is the sqrt of the variance:
> +		 *
> +		 * abs(interval - mean) < sqrt(variance)
> +		 *
> +		 * and we want to prevent to do an sqrt, so we square
> +		 * the equation:
> +		 *
> +		 * (interval - mean)^2 < variance
> +		 *
> +		 * So if the latest value of the stats complies with
> +		 * this condition, then the wakeup source is
> +		 * considered predictable and can be used to predict
> +		 * the next event.
> +		 */
> +		interval = w->stats.values[w->stats.w_ptr];
> +		if ((u64)((interval - mean) * (interval - mean)) > variance)
> +			continue;
> +

Cute :-)

You could consider putting a simple 3 point median filter in front of
stat_add() to get rid of the worst input noise.

(I know, improving all this was a point for later)

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

Thread

Re: [RFC PATCH 2/2] sched: idle: IRQ based next prediction for idle  period Daniel Lezcano <daniel.lezcano@linaro.org> - 2016-01-18 14:30 +0100
  Re: [RFC PATCH 2/2] sched: idle: IRQ based next prediction for idle  period Thomas Gleixner <tglx@linutronix.de> - 2016-01-20 16:50 +0100
    [RFC V2 2/2] sched: idle: IRQ based next prediction for idle period Daniel Lezcano <daniel.lezcano@linaro.org> - 2016-01-20 17:10 +0100
      Re: [RFC V2 2/2] sched: idle: IRQ based next prediction for idle  period Nicolas Pitre <nicolas.pitre@linaro.org> - 2016-01-20 18:50 +0100
        Re: [RFC V2 2/2] sched: idle: IRQ based next prediction for idle  period Peter Zijlstra <peterz@infradead.org> - 2016-01-20 19:50 +0100
        Re: [RFC V2 2/2] sched: idle: IRQ based next prediction for idle  period Daniel Lezcano <daniel.lezcano@linaro.org> - 2016-01-21 11:10 +0100
      Re: [RFC V2 2/2] sched: idle: IRQ based next prediction for idle  period Peter Zijlstra <peterz@infradead.org> - 2016-01-20 20:10 +0100
        Re: [RFC V2 2/2] sched: idle: IRQ based next prediction for idle  period Nicolas Pitre <nicolas.pitre@linaro.org> - 2016-01-20 20:20 +0100
          Re: [RFC V2 2/2] sched: idle: IRQ based next prediction for idle  period Peter Zijlstra <peterz@infradead.org> - 2016-01-20 20:40 +0100
      Re: [RFC V2 2/2] sched: idle: IRQ based next prediction for idle  period Peter Zijlstra <peterz@infradead.org> - 2016-01-20 20:40 +0100
      Re: [RFC V2 2/2] sched: idle: IRQ based next prediction for idle  period Peter Zijlstra <peterz@infradead.org> - 2016-01-20 20:50 +0100
        Re: [RFC V2 2/2] sched: idle: IRQ based next prediction for idle  period Nicolas Pitre <nicolas.pitre@linaro.org> - 2016-01-20 21:00 +0100
          Re: [RFC V2 2/2] sched: idle: IRQ based next prediction for idle  period Peter Zijlstra <peterz@infradead.org> - 2016-01-20 21:30 +0100
      Re: [RFC V2 2/2] sched: idle: IRQ based next prediction for idle  period Thomas Gleixner <tglx@linutronix.de> - 2016-01-20 21:00 +0100
        Re: [RFC V2 2/2] sched: idle: IRQ based next prediction for idle  period Daniel Lezcano <daniel.lezcano@linaro.org> - 2016-01-21 15:00 +0100
          Re: [RFC V2 2/2] sched: idle: IRQ based next prediction for idle  period Thomas Gleixner <tglx@linutronix.de> - 2016-01-21 15:20 +0100
    [RFC V2 0/2] IRQ based next prediction Daniel Lezcano <daniel.lezcano@linaro.org> - 2016-01-20 17:10 +0100
    [RFC V2 2/2] sched: idle: IRQ based next prediction for idle period Daniel Lezcano <daniel.lezcano@linaro.org> - 2016-01-20 17:10 +0100
      Re: [RFC V2 2/2] sched: idle: IRQ based next prediction for idle  period Nicolas Pitre <nicolas.pitre@linaro.org> - 2016-01-20 21:20 +0100
        Re: [RFC V2 2/2] sched: idle: IRQ based next prediction for idle  period Daniel Lezcano <daniel.lezcano@linaro.org> - 2016-01-21 14:10 +0100
    [RFC V2 0/2] IRQ based next prediction Daniel Lezcano <daniel.lezcano@linaro.org> - 2016-01-20 17:10 +0100
      [RFC V2 1/2] irq: Add a framework to measure interrupt timings Daniel Lezcano <daniel.lezcano@linaro.org> - 2016-01-20 17:10 +0100
        Re: [RFC V2 1/2] irq: Add a framework to measure interrupt timings Thomas Gleixner <tglx@linutronix.de> - 2016-01-20 19:00 +0100
          Re: [RFC V2 1/2] irq: Add a framework to measure interrupt timings Daniel Lezcano <daniel.lezcano@linaro.org> - 2016-01-21 10:30 +0100
            Re: [RFC V2 1/2] irq: Add a framework to measure interrupt timings Thomas Gleixner <tglx@linutronix.de> - 2016-01-21 11:30 +0100
        Re: [RFC V2 1/2] irq: Add a framework to measure interrupt timings Peter Zijlstra <peterz@infradead.org> - 2016-01-20 20:10 +0100
          Re: [RFC V2 1/2] irq: Add a framework to measure interrupt timings Thomas Gleixner <tglx@linutronix.de> - 2016-01-20 21:00 +0100
            Re: [RFC V2 1/2] irq: Add a framework to measure interrupt timings Nicolas Pitre <nicolas.pitre@linaro.org> - 2016-01-20 21:10 +0100
            Re: [RFC V2 1/2] irq: Add a framework to measure interrupt timings Peter Zijlstra <peterz@infradead.org> - 2016-01-20 21:30 +0100
              Re: [RFC V2 1/2] irq: Add a framework to measure interrupt timings Thomas Gleixner <tglx@linutronix.de> - 2016-01-20 21:30 +0100
            Re: [RFC V2 1/2] irq: Add a framework to measure interrupt timings Daniel Lezcano <daniel.lezcano@linaro.org> - 2016-01-21 11:00 +0100
              Re: [RFC V2 1/2] irq: Add a framework to measure interrupt timings Peter Zijlstra <peterz@infradead.org> - 2016-01-21 11:10 +0100
                Re: [RFC V2 1/2] irq: Add a framework to measure interrupt timings Daniel Lezcano <daniel.lezcano@linaro.org> - 2016-01-21 13:40 +0100
                Re: [RFC V2 1/2] irq: Add a framework to measure interrupt timings Thomas Gleixner <tglx@linutronix.de> - 2016-01-21 21:30 +0100
              Re: [RFC V2 1/2] irq: Add a framework to measure interrupt timings Thomas Gleixner <tglx@linutronix.de> - 2016-01-21 15:00 +0100
                Re: [RFC V2 1/2] irq: Add a framework to measure interrupt timings Daniel Lezcano <daniel.lezcano@linaro.org> - 2016-01-21 15:20 +0100
                Re: [RFC V2 1/2] irq: Add a framework to measure interrupt timings Thomas Gleixner <tglx@linutronix.de> - 2016-01-21 20:00 +0100
                Re: [RFC V2 1/2] irq: Add a framework to measure interrupt timings Peter Zijlstra <peterz@infradead.org> - 2016-01-22 11:20 +0100
          Re: [RFC V2 1/2] irq: Add a framework to measure interrupt timings Daniel Lezcano <daniel.lezcano@linaro.org> - 2016-01-21 10:30 +0100
        Re: [RFC V2 1/2] irq: Add a framework to measure interrupt timings Peter Zijlstra <peterz@infradead.org> - 2016-01-20 20:30 +0100
          Re: [RFC V2 1/2] irq: Add a framework to measure interrupt timings Daniel Lezcano <daniel.lezcano@linaro.org> - 2016-01-21 11:00 +0100
      [RFC V2 1/2] irq: Add a framework to measure interrupt timings Daniel Lezcano <daniel.lezcano@linaro.org> - 2016-01-20 17:10 +0100

csiph-web