Exploring the link between C-states and latency

[nomaddroid]

Do you have problems with latency/performance by disabling them in power plan? Or just when you disable them in BIOS?
Does your CPU support C1E? If you don't have an option to disable it in BIOS you can do it with ThrottleStop.
What kind of latency values are you talking about and how did you measure them? Or is it more a visual/feeling thing?
As system related measurements in microseconds, this is mine and it's fine:

Code: Select all

--------------------------
DPC Info
--------------------------
CPU 0 Usage,      CPU 1 Usage,      CPU 2 Usage,      CPU 3 Usage, 
usec      %,      usec      %,      usec      %,      usec      %, Module
5015   0.00,      1485   0.00,       546   0.00,       162   0.00, ntoskrnl.exe

Total = 2537 for module ntoskrnl.exe
Elapsed Time, >        0 usecs AND <=        1 usecs,    423, or  16.67%
Elapsed Time, >        1 usecs AND <=        2 usecs,    384, or  15.14%
Elapsed Time, >        2 usecs AND <=        4 usecs,   1332, or  52.50%
Elapsed Time, >        4 usecs AND <=        8 usecs,     93, or   3.67%
Elapsed Time, >        8 usecs AND <=       16 usecs,    297, or  11.71%

I haven't measured any latencies but only mentioned about them theoritically. But the input drift or delay, and the jitter that I mentioned in the post, it was more of a feeling thing, which I am personally sure that the difference is there by toggling C-states. As for what C-states are supported, as per HWiNFO, C0, C1, and C6 are supported. Laptop's BIOS doesn't allow C-states to be viewed or modified.

[MatrixQW]

I believe you. Some things might not be reflected in numbers but still have an effect.
Check out this topic and fine app:
Should you be worried about 1, 5, or 10 ms of input lag? Use Latency Split Test (LST) and find out!

[nomaddroid]

I believe you. Some things might not be reflected in numbers but still have an effect.
Check out this topic and fine app:
Should you be worried about 1, 5, or 10 ms of input lag? Use Latency Split Test (LST) and find out!

Thanks for sharing. I gave it a try and guessed 12 out of 16 correctly for 1 ms vs 4 ms test.

[nomaddroid]

I believe you. Some things might not be reflected in numbers but still have an effect.
Check out this topic and fine app:
Should you be worried about 1, 5, or 10 ms of input lag? Use Latency Split Test (LST) and find out!

Thanks for sharing. I gave it a try and guessed 12 out of 16 correctly for 1 ms vs 4 ms test.

Took the test again as per the guide. Based on the hardware that I use, 8 ms seem to draw the line between placebo and observable. Anything below that, not so much I guess.

[Vocaleyes]

Genuine question.

While this latency measuring tool is amazing in itself, would the issue not then be that running this test on a system with inconsistent input and visual latency issues make the test itself null and void until it’s taken on a machine without those issues?

[RealNC]

Genuine question.

While this latency measuring tool is amazing in itself, would the issue not then be that running this test on a system with inconsistent input and visual latency issues make the test itself null and void until it’s taken on a machine without those issues?

It would still be inconsistent, but with the increased latency you add being consistent. So if the results are noisy, they would be noisy with a consistent offset.

[Vocaleyes]

Genuine question.

While this latency measuring tool is amazing in itself, would the issue not then be that running this test on a system with inconsistent input and visual latency issues make the test itself null and void until it’s taken on a machine without those issues?

It would still be inconsistent, but with the increased latency you add being consistent. So if the results are noisy, they would be noisy with a consistent offset.

Ok sweet, so in that situation it would be better to run the test a few more times than on a normally functioning device to find the mean I guess, as to reduce the sporadic results from potential graphical inconsistencies.

[nomaddroid]

Genuine question.

While this latency measuring tool is amazing in itself, would the issue not then be that running this test on a system with inconsistent input and visual latency issues make the test itself null and void until it’s taken on a machine without those issues?

I am thinking that this test benchmarks the users who are supposedly noticing latency issues with their own systems that they use daily, so that they could at least get a quick grasp on the numbers, and maybe an affirmation on whether what they are noticing is placebo or not. The latency numbers displayed could obviously be approximation (simulated latency from engine) since they vary depending on the hardware.

Though, for my issue, while this was informational to understand from how many milliseconds I began to notice the blatant change in the input latency, it still couldn't pinpoint or portray the issue I mentioned in the post since the software itself also affected. Simply put, the mouse movements doesn't feel right, in desktop mode or games. This feeling existed before I even started to tinker with C-states and similar. Eventually, after careful examination (not mathematically), I learnt that C-states play a role.

[MatrixQW]

I believe you. Some things might not be reflected in numbers but still have an effect.
Check out this topic and fine app:
Should you be worried about 1, 5, or 10 ms of input lag? Use Latency Split Test (LST) and find out!

Thanks for sharing. I gave it a try and guessed 12 out of 16 correctly for 1 ms vs 4 ms test.

Took the test again as per the guide. Based on the hardware that I use, 8 ms seem to draw the line between placebo and observable. Anything below that, not so much I guess.

You are getting very low fps, therefore making it impossible to test really low values.
However everyone has their limit of perception and you seem to have found yours.

[MatrixQW]

Genuine question.

While this latency measuring tool is amazing in itself, would the issue not then be that running this test on a system with inconsistent input and visual latency issues make the test itself null and void until it’s taken on a machine without those issues?

I am thinking that this test benchmarks the users who are supposedly noticing latency issues with their own systems that they use daily, so that they could at least get a quick grasp on the numbers, and maybe an affirmation on whether what they are noticing is placebo or not. The latency numbers displayed could obviously be approximation (simulated latency from engine) since they vary depending on the hardware.

Though, for my issue, while this was informational to understand from how many milliseconds I began to notice the blatant change in the input latency, it still couldn't pinpoint or portray the issue I mentioned in the post since the software itself also affected. Simply put, the mouse movements doesn't feel right, in desktop mode or games. This feeling existed before I even started to tinker with C-states and similar. Eventually, after careful examination (not mathematically), I learnt that C-states play a role.

The purpose of LST is not about discovering latency issues in your system but your own limit of perceiving it.
When I did it, it was very clear to me what limit was easy for me to feel and what was hard but still consistently perceivable.
But let's take C-States as an example. If a PC runs this test at 1000 fps with C-States disabled and the user determines his threshold is 5ms consistent by running several tests and after enabling C-States he starts to notice issues and his results drop to 8ms you could clearly assume it causes latency.

This website used to have useful posts and information about monitors but it got flooded with EMI posts.
After Chief disallowed them, "Input lag Fix" topics started to appear with placebo solutions or wrong information that just give a poor image to BlurBusters in my opinion.
I don't doubt there are a few or some users with genuine latency issues but some people claim that one setting in Windows, monitor or whatever causes latency when in reality does nothing.
Without mentioning names, there is one user that sees/feels latency in almost every hardware/software setting. Don't go this path.
I'm pretty sure if these same people do this LST test on a PC without issues they can't even make it below 6ms, while they are claiming things that are below 1ms, in microseconds, or have no effect at all.