How to optimize Windows 10 for Low Input Lag?

Everything about latency. Tips, testing methods, mouse lag, display lag, game engine lag, network lag, whole input lag chain, VSYNC OFF vs VSYNC ON, and more! Input Lag Articles on Blur Busters.
howiec
Posts: 183
Joined: 17 Jun 2014, 15:36

Re: How to optimize Windows 10 for Low Input Lag?

Post by howiec » 01 Nov 2020, 10:55

ffs_ wrote:
01 Nov 2020, 07:20
That's all great, but how it will help when you're playing the game, or you just enjoy your "low latency" on the desktop? :)
... I don't know how to be any clearer. Maybe I have to break it down into even simpler words but I feel like I'm repeating myself...

Idle latency is an indicator of how quickly your system can react to an input and then handle it. So it can certainly correlate to the total input lag chain duration (input-to-photon) with certain assumptions. If your absolute lowest Interrupt-to-Process latency is say 500us, then that's literally the lowest possible value for your input lag (which is certainly going to be higher if you're talking about game + GPU + display processing).

Measuring latency during gaming simply adds to the above mentioned "quickest, baseline latency" by generating competing interrupts, DPCs, and other processing, so of course you'll see higher latency.

How you interpret this value is completely up to you and I don't see a clear and standardized way to normalize that value across different systems/platforms with different loads and settings.

This has been quoted many times by others:
"Note: it is recommended to close all other running programs before running the interrupt to user process latency test, or before interpreting the value that it reports. This test simulates the workings of a real-time audio process. Unlike other tests that LatencyMon performs, it does not make sense to run this test while an audio program is active. "
https://www.resplendence.com/latencymon ... pt2process

However, I disagree when they say it makes zero sense because a latency value during load could be used in a DOE style approach for general comparisons with plenty of caution.
ffs_ wrote:
01 Nov 2020, 07:20
howiec wrote:
01 Nov 2020, 05:40
A system under load should have even higher input lag
And again, input-lag or latency? :)
Both unless, as I mentioned, you eliminate contention and have plenty of resources (e.g. dedicated cores).
ffs_ wrote:
01 Nov 2020, 07:20
howiec wrote:
01 Nov 2020, 05:40
HPET overhead applies to both idle and load, and hence can increase latency in both cases as well, thus affecting input lag. Whether or not you notice it and/or prefer it on/off in your games or programs is a different thing.

If you are so adamant that HPET:On + useplatformclock:true does not increase input lag at all, simply put it to the test for your case.
Either use an LDAT if you have access to one, reflex analyzer, or very high FPS capture with all the correct camera settings like how Chief does it.
I don't have access to anything of those. You can post your LatencyMon results (idle and in-game) so we could compare numbers and see how "bad" HPET is. I posted my LatencyMon results above and I think they're far from bad despite using HPET.
Then you simply can't measure it. From above explanations, it should be clear that comparing load latency across 2 different platforms with different loads doesn't make sense. Also, what you should be comparing is input-lag, since that is the end goal (aside from a preferred mouse sensitivity/feel).

Analogy: If you ask someone to compare AC cooled temperatures inside 2 different homes (different location, volume, insulation, weather, people, appliances, HVAC, etc.) during different "loads" (1 house with an active fireplace and 3 refrigerators running max vs the other with none, etc.), what exactly can you surmise from the different temperatures?
ffs_ wrote:
01 Nov 2020, 07:20
howiec wrote:
01 Nov 2020, 05:40
Why are we still talking about this?
I gave general advice because HPET has increased overhead by design.
Then you mentioned your Ryzen system.
Then I mentioned Intel to be clear that I haven't tested Ryzen firsthand.
Then you said that's why you mentioned Ryzen.

We're saying the same thing: We're on different platforms...

Yes, I can say a word because simply looking at the actual HPET architecture vs TSC, it's obvious that it's slower/more costly to access.
The performance loss may not be as bad on a newer Ryzen vs current Intel systems but it still cannot be as "fast" as TSC.

There are various test and supporting data out there. Heck, even the Linux kernel code bashes HPET to some degree for various related and unrelated reasons.
https://github.com/torvalds/linux/blob/ ... nel/hpet.c
That's all cool and you can bash HPET as much as you want or "prove" how "bad" it is compared to TSC or other timer(s), but the thing is I didn't say HPET is generally better or faster or gives less ISR/DPC latency than TSC or other timer(s), I only said it gives better mouse input (better input-lag) on my system even if it costs a bit of performance and ISR/DPC latency. I'm aware that in theory TSC should be better, and I can even tell you a secret: I have HPET disabled in BIOS on my old Intel PC because it gives me better results in both latency and input-lag, but for some reason on my Ryzen PC it's vice versa. ¯\_(ツ)_/¯
And that's the point. You haven't even measured the input-lag. The mouse sensitivity/feel that you experience does not necessarily mean you have lower input lag. It is just different.
Last edited by howiec on 01 Nov 2020, 11:16, edited 1 time in total.

ffs_
Posts: 47
Joined: 24 Jul 2020, 00:57

Re: How to optimize Windows 10 for Low Input Lag?

Post by ffs_ » 01 Nov 2020, 11:11

You haven't measured input-lag neither...

I'd like to see the difference in input-lag between 30 us and 300 us, it's 10x difference in latency, but I think the difference in input-lag will be negligible. So in my opinion there is no point to wank on good DPC/ISR numbers when we talk about input-lag, unless you have severe problems with your system and your ISR/DPC spikes are very high. But if you made measurements and have something to show, please do it.
howiec wrote:
01 Nov 2020, 10:55
The mouse sensitivity/feel that you experience does not necessarily mean you have lower input lag. It is just different.
I'm fully aware that input-lag and mouse movement feel (or sensitivity) are different things.

howiec
Posts: 183
Joined: 17 Jun 2014, 15:36

Re: How to optimize Windows 10 for Low Input Lag?

Post by howiec » 01 Nov 2020, 11:31

ffs_ wrote:
01 Nov 2020, 11:11
You haven't measured input-lag neither...

I'd like to see the difference in input-lag between 30 us and 300 us, it's 10x difference in latency, but I think the difference in input-lag will be negligible. So in my opinion there is no point to wank on good DPC/ISR numbers when we talk about input-lag, unless you have severe problems with your system and your ISR/DPC spikes are very high. But if you made measurements and have something to show, please do it.
howiec wrote:
01 Nov 2020, 10:55
The mouse sensitivity/feel that you experience does not necessarily mean you have lower input lag. It is just different.
I'm fully aware that input-lag and mouse movement feel (or sensitivity) are different things.
??? Assuming best case scenario, the input-lag difference is 270us...

I don't think anyone said you must have X latency to have low input lag of value Y.

I would certainly measure input-to-photon lag on my system if I could. It would be a good study. Until I have the tools for sub-millisecond accuracy and precision, it'll have to wait.

1000WATT
Posts: 391
Joined: 22 Jul 2018, 05:44

Re: How to optimize Windows 10 for Low Input Lag?

Post by 1000WATT » 01 Nov 2020, 12:05

ffs_ wrote:
31 Oct 2020, 05:50
1000WATT wrote:
30 Oct 2020, 08:35
If you change xhci. the keyboard will not work in bios but will work in win. Reset BIOS will help.
I managed to turn off "USB legacy support" and "XHCI legacy support" and everything worked in full UEFI mode, but I didn't notice any benefits, so it wasn't worth experimenting with these options.
:lol: My post has nothing to do with your configuration on "amd".
ffs_ wrote:
01 Nov 2020, 11:11
You haven't measured input-lag neither...

I'd like to see the difference in input-lag between 30 us and 300 us, it's 10x difference in latency, but I think the difference in input-lag will be negligible.
Yes, the input delay on the same system will be negligible. But bursts of frame time can be observed with eyes without software monitoring. And on a system with +270 at the moment of the frame burst, your mouse will stick.

But none of this matters. In any case, you need to use what you like best. ;)
I often do not clearly state my thoughts. google translate is far from perfect. And in addition to the translator, I myself am mistaken. Do not take me seriously.

ffs_
Posts: 47
Joined: 24 Jul 2020, 00:57

Re: How to optimize Windows 10 for Low Input Lag?

Post by ffs_ » 01 Nov 2020, 12:08

howiec wrote:
01 Nov 2020, 10:55
From above explanations, it should be clear that comparing load latency across 2 different platforms with different loads doesn't make sense.
No problem, I measured it on my PC without "useplatformclock true" tweak.

Idle: https://i.imgur.com/Pd4a15W.png
In-game: https://i.imgur.com/cnk7dut.png

I'd say results are more or less the same as before.
howiec wrote:
01 Nov 2020, 10:55
Also, what you should be comparing is input-lag, since that is the end goal
That's exactly my point.
howiec wrote:
01 Nov 2020, 11:31
??? Assuming best case scenario, the input-lag difference is 270us...
So, negligible.
1000WATT wrote:
01 Nov 2020, 12:05
:lol: My post has nothing to do with your configuration on "amd".
:lol: My post has nothing to do with AMD or Intel as well.
1000WATT wrote:
01 Nov 2020, 12:05
Yes, the input delay on the same system will be negligible. But bursts of frame time can be observed with eyes without software monitoring. And on a system with +270 at the moment of the frame burst, your mouse will stick.
With "+270" or with 300?

Because 200-300 us is probably typical ISR/DPC while playing the game. And people who don't bother to optimize their system probably get even more (500-700 us or so).
Last edited by ffs_ on 01 Nov 2020, 12:13, edited 1 time in total.

1000WATT
Posts: 391
Joined: 22 Jul 2018, 05:44

Re: How to optimize Windows 10 for Low Input Lag?

Post by 1000WATT » 01 Nov 2020, 12:13

Several years ago I used the freesync + mbr hack. And so that the monitor does not flicker from the backlight flashes. I had to lick the system. And the lower the value in latencymon, the less often these annoying outbreaks occurred.
Oh there were times) https://youtu.be/zi1lgBcnZzg
I often do not clearly state my thoughts. google translate is far from perfect. And in addition to the translator, I myself am mistaken. Do not take me seriously.

ffs_
Posts: 47
Joined: 24 Jul 2020, 00:57

Re: How to optimize Windows 10 for Low Input Lag?

Post by ffs_ » 01 Nov 2020, 12:20

I don't use Freesync/G-sync/V-sync or any other "sync", hence your example doesn't say much to me tbh.

What game is this btw?

1000WATT
Posts: 391
Joined: 22 Jul 2018, 05:44

Re: How to optimize Windows 10 for Low Input Lag?

Post by 1000WATT » 01 Nov 2020, 12:37

league of legends
The freesync + mbr example is more suitable for people who know what I'm talking about. For example those who used gsync + ulmb. And these people are well aware of the shortcomings of this bundle. This is a great indicator of volatile input. It doesn't matter which synchronization methods you use. At the moment of the frame spike, the input from the manipulators is interrupted.
I often do not clearly state my thoughts. google translate is far from perfect. And in addition to the translator, I myself am mistaken. Do not take me seriously.

User avatar
Chief Blur Buster
Site Admin
Posts: 11647
Joined: 05 Dec 2013, 15:44
Location: Toronto / Hamilton, Ontario, Canada
Contact:

Re: How to optimize Windows 10 for Low Input Lag?

Post by Chief Blur Buster » 01 Nov 2020, 13:46

reply wrote:
...HPET...
Easy on HPET arguments / bashing.

The moral of the story is that HPET is not a one-size-fixes-all. There are pros/cons of HPET. Respect the pros/cons. It helps some, not others. It is a double edged sword with two very sharp edges -- and sometimes it's also additionally hanging like a Sword of Damocles above a floor that will explode if you don't catch the sword with your bare hands first. Both user POV and developer POV. Due to that, HPET subtopic is so vast, deserves its very own separate thread, to prevent distracting from more obvious lower-lying-apple optimizations.

Carry on, preferably away from the HPET powderkeg (for now...); back away slowly. ;)

Now pouring a barrel of Kerosene fuel into this fire (look! A nice roaring bonfire!):
ffs_ wrote:
01 Nov 2020, 07:20
Because 200-300 us is probably typical ISR/DPC while playing the game. And people who don't bother to optimize their system probably get even more (500-700 us or so).
The Blur Busters Vicious Cycle Effect is colliding hard with these ISR times, making this a potential new entrant to The Amazing Human Visible Feats Of The Millisecond.

A 0.5ms gametme-vs-photontime error is human visible nowadays under extreme-clear display conditions (2 pixels of stutter at 4000 pixels/second on a true realworld 0.5ms-MPRT strobed 4K display, especially with a >2000Hz pollrate mouse). When display motionblur (MPRT, and not GtG) in milliseconds is less than ISR times, then Houston We Have a Problem when jitter noise goes above human visibility noisefloor due to retina-resolutions and retina-refreshrates.

Not everyone is running display configurations that will make ISR stutter visible, but we're already getting into the territory with cherrypicked displays, in a cherrypicked game, configured to cherrypicked settings, if mouse is not the weak link, if display is not the weak link, if the game is not the weak link. And assumes that really bad DPC/ISR impacts the gametime:photontime relativity by jittering gametimes (frametimes) towards/away from refreshtimes.
Head of Blur Busters - BlurBusters.com | TestUFO.com | Follow @BlurBusters on Twitter

Image
Forum Rules wrote:  1. Rule #1: Be Nice. This is published forum rule #1. Even To Newbies & People You Disagree With!
  2. Please report rule violations If you see a post that violates forum rules, then report the post.
  3. ALWAYS respect indie testers here. See how indies are bootstrapping Blur Busters research!

howiec
Posts: 183
Joined: 17 Jun 2014, 15:36

Re: How to optimize Windows 10 for Low Input Lag?

Post by howiec » 01 Nov 2020, 20:47

ffs_ wrote:
01 Nov 2020, 12:08
howiec wrote:
01 Nov 2020, 10:55
From above explanations, it should be clear that comparing load latency across 2 different platforms with different loads doesn't make sense.
No problem, I measured it on my PC without "useplatformclock true" tweak.

Idle: https://i.imgur.com/Pd4a15W.png
In-game: https://i.imgur.com/cnk7dut.png

I'd say results are more or less the same as before.
howiec wrote:
01 Nov 2020, 10:55
Also, what you should be comparing is input-lag, since that is the end goal
That's exactly my point.
So don't ask to compare load latency across 2 completely different systems, environments, and loads... The only practical thing you can conclude is that we both don't have extremely large latency spikes during load, somewhat alluding to no seriously "broken" drivers.

You can ask to compare input-to-photon lag across any system.
It also makes sense to compare idle latency across different systems.
ffs_ wrote:
01 Nov 2020, 12:08
howiec wrote:
01 Nov 2020, 11:31
??? Assuming best case scenario, the input-lag difference is 270us...
So, negligible.
I would never say that's negligible. That's the best case scenario when in reality it is only a general indicator. There can be completely different underlying causes of increased latency which can lead to both minor or major cascade effects.

Post Reply