flood's input lag measurements

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.
spacediver
Posts: 505
Joined: 18 Dec 2013, 23:51

Re: flood's input lag measurements

Post by spacediver » 25 Sep 2014, 20:21

what software is that? I'm curious to measure my own mouse.

flood
Posts: 929
Joined: 21 Dec 2013, 01:25

Re: flood's input lag measurements

Post by flood » 25 Sep 2014, 20:22

MouseTester

you can dig around for it on overclock.net or just download it (and a bunch of other stuff) from here: https://docs.google.com/spreadsheets/d/ ... 2034443442

spacediver
Posts: 505
Joined: 18 Dec 2013, 23:51

Re: flood's input lag measurements

Post by spacediver » 25 Sep 2014, 21:00

cheers

Q83Ia7ta
Posts: 761
Joined: 18 Dec 2013, 09:29

Re: flood's input lag measurements

Post by Q83Ia7ta » 26 Sep 2014, 21:11

flood wrote:think step function vs a blurred step function.

when i hit the mouse by colliding another mouse onto it, the speed goes from 0 m/s to 0.5 m/s or so within a millisecond. the sensor should capture this behavior as a sudden change

actual plots from mousetester (ignore solid line)
g100s:
http://i.imgur.com/YWf113k.png
m100:
http://i.imgur.com/L2QSh6i.png

i suspect it's because the m100 has a power-saving standby mode when its not moving. (the led starts to blink)
Isn't that difference goes from polling rate of 500Hz (g100s) and 125Hz (m100)?
btw m100 has hardware acceleration (mouse pointer acceleration of motion).

flood
Posts: 929
Joined: 21 Dec 2013, 01:25

Re: flood's input lag measurements

Post by flood » 26 Sep 2014, 22:14

no look at the pictures

the g100s has only one point before the velocity drops down
the m100 has 5 AND it's 125hz so it took 40ms to respond.................

i'm guessing it's related to the m100's power saving mode which strobes the led when the mouse isn't moving.

flood
Posts: 929
Joined: 21 Dec 2013, 01:25

Re: flood's input lag measurements

Post by flood » 28 Sep 2014, 01:18

more csgo measurements
same settings but varying fps_max
no cap (~900fps stable): 5 6 5 6 5
500: 5 4 5 7 4
250: 7 5 5 7 7
125: 8 8 6 5 10 8 8 5 11 11

flood
Posts: 929
Joined: 21 Dec 2013, 01:25

Re: flood's input lag measurements

Post by flood » 28 Sep 2014, 01:46

what happens when the framerate is actually low instead of just being capped low?

i changed the map to cs_insertion which is a more graphically intensive map. the fps for these were all 300 +- 20

9 11 12 12 11 9 11 9 12 13

this matches with what i expect:

input lag = base input lag + frame render time + X

base input lag would be the input lag with infinite framerate
X is a random variable between 0 and the "time between frame"

fps_max reduces the time between frames, but doesn't affect the render time. that's why the fps_max measurements were sometimes very low, even at fps_max 125.

flood
Posts: 929
Joined: 21 Dec 2013, 01:25

Re: flood's input lag measurements

Post by flood » 28 Sep 2014, 02:00

csgo antialiasing off:
in simple map
fps ~1050

7 measurements: 7 6 5 5 4 6 6

no traditional aa, fxaa enabled:
fps~950
3 measurements: 4 6 5

16xQ CSAA, fxaa disabled
fps~850
1 measurement: 5


too lazy to do more for antialiasing. i think it's safe to conclude that antialiasing does not affect input lag in csgo, apart from increasing the rendering time.

flood
Posts: 929
Joined: 21 Dec 2013, 01:25

Re: flood's input lag measurements

Post by flood » 28 Sep 2014, 02:20

back to 4x msaa

multicore rendering on:
fps ~900
4 4 5 4 8 8 5 5 6 5

i have no idea what to make of this. those 8's may be from the g100s sensor malfunctioning/skipping :P i got excited after seeing the string of 4's and smacked the mouse really hard for the next two measurements.


csgo settings maxed out: (high/veryhigh, 8xMSAA,14xAF,no fxaa no vsync no motionblur)
3 measurements: 7 4 6

csgo, my default settings, rawinput off
3 measurements: 5 5 6

spacediver
Posts: 505
Joined: 18 Dec 2013, 23:51

Re: flood's input lag measurements

Post by spacediver » 28 Sep 2014, 02:47

just so i'm following on one of your lines of thought:

assuming equal base input lag, over many measurements one would expect the same distribution of input lag in both these situations:

1) artificially capping a game at 125 fps (when uncapped it could do 1000000 fps)
2) a game that can only render at 125 fps even when uncapped

correct?

Post Reply