Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]
Groups > linux.kernel > #1314066
| From | Daniel Lezcano <daniel.lezcano@linaro.org> |
|---|---|
| Newsgroups | linux.kernel |
| Subject | Re: [RFC V2 2/2] sched: idle: IRQ based next prediction for idle period |
| Date | 2016-01-21 11:10 +0100 |
| Message-ID | <qTklI-3M2-5@gated-at.bofh.it> (permalink) |
| References | <qT3bb-7a-5@gated-at.bofh.it> <qT3ux-vq-3@gated-at.bofh.it> <qT3ux-vq-1@gated-at.bofh.it> <qT53j-1s5-3@gated-at.bofh.it> |
| Organization | linux.* mail to news gateway |
Hi Nico,
On 01/20/2016 06:46 PM, Nicolas Pitre wrote:
> On Wed, 20 Jan 2016, Daniel Lezcano wrote:
>
>> Many IRQs are quiet most of the time, or they tend to come in bursts of
>> fairly equal time intervals within each burst. It is therefore possible
>> to detect those IRQs with stable intervals and guestimate when the next
>> IRQ event is most likely to happen.
>>
>> Examples of such IRQs may include audio related IRQs where the FIFO size
>> and/or DMA descriptor size with the sample rate create stable intervals,
>> block devices during large data transfers, etc. Even network streaming
>> of multimedia content creates patterns of periodic network interface IRQs
>> in some cases.
>>
>> This patch adds code to track the mean interval and variance for each IRQ
>> over a window of time intervals between IRQ events. Those statistics can
>> be used to assist cpuidle in selecting the most appropriate sleep state
>> by predicting the most likely time for the next interrupt.
>>
>> Because the stats are gathered in interrupt context, the core computation
>> is as light as possible.
>>
>> Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
>> ---
[ ... ]
>> +struct stats {
>> + u64 sum; /* sum of values */
>> + u32 values[STATS_NR_VALUES]; /* array of values */
>> + unsigned char w_ptr; /* current window pointer */
>
> Why did you change this from an unsigned int?
>
> This won't provide any memory space saving given that the structure has
> to be padded up to the next 64-bit boundary.
Ok, I will change it back to unsigned int.
[ ... ]
>> + for (i = 0; i < STATS_NR_VALUES; i++) {
>> + s64 diff = s->values[i] - mean;
>> + variance += (u64)diff * diff;
>> + }
>
> This is completely wrong. Even more wrong than it used to be. I must
> have expressed myself badly about this last time.
>
> To avoid any confusion, here's what the code should be:
>
> int i;
> u64 variance = 0;
>
> for (i = 0; i < STATS_NR_VALUES; i++) {
> s32 diff = s->values[i] - mean;
> variance += (s64)diff * diff;
> }
>
> [...]
Aah, ok :)
[ ... ]
>> + if (diff > (1 << 20)) {
>
> You could use the USEC_PER_SEC constant here. It is already widely used
> and would make the code even more obvious.
Indeed.
[ ... ]
>> + /*
>> + * There is no point attempting predictions on interrupts more
>> + * than 1 second apart. This has no benefit for sleep state
>> + * selection and increases the risk of overflowing our variance
>> + * computation. Reset all stats in that case.
>> + */
>
> This comment is wrong. It is relevant in sched_irq_timing_handler() but
> not here. Instead this should be something like:
>
> /*
> * This interrupt last triggered more than a second ago.
> * It is definitely not predictable for our purpose anymore.
> */
Ok.
[ ... ]
>> + interval = w->stats.values[w->stats.w_ptr];
>> + if ((u64)((interval - mean) * (interval - mean)) > variance)
>
> s/u64/s64/ please.
Noted.
Thanks Nico for the review.
-- Daniel
--
<http://www.linaro.org/> Linaro.org │ Open source software for ARM SoCs
Follow Linaro: <http://www.facebook.com/pages/Linaro> Facebook |
<http://twitter.com/#!/linaroorg> Twitter |
<http://www.linaro.org/linaro-blog/> Blog
Back to linux.kernel | Previous | Next — Previous in thread | Next in thread | Find similar | Unroll 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