Comparing bare-bones Win7 vs 10 install

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.
MT_
Posts: 113
Joined: 17 Jan 2017, 15:39

Re: Comparing bare-bones Win7 vs 10 install

Post by MT_ » 07 Feb 2019, 14:29

MatrixQW wrote:
Chief Blur Buster wrote:If anyone is willing to do these kinds of tests in such depth, I'm interested in poring over those charts.
I would if i had the tools.
'I fast reaction' could volunteer, he seems to have it all covered. If he is willing of course.
I think QuakeWorld can be a good game to make these tests. It has a bultin server so ping is 0. And you can create the environment you need with this game.
MT_ wrote:One relief of that aspect is the fact that the OS is mostly closed source, and only a limited amount of 'tweaking' can be done on it!
Most things people change just affect cpu overhead and the impact is minimal, only too much of it can cause a spike wich will be noticeable, i really doubt it can increase input lag.
You shouldn't need to touch system timers for example. Windows decides wich one to use based on the hardware you have.
'I fast reaction' recommends to disable HPET in Bios but then enables it in the system. Makes no sense.
Last time i checked, Windows used HPET+TSC at boot and then only TSC in the system. So you don't need to disable it in BIOS and shouldn't enable it in the OS as the only timer.
Games/applications that use QueryPerformanceCounter could get reduced performance if HPET is enabled in the OS.
MT_ wrote:Well, after months I give up. I'm gonna stick W7 and pray one day W10 will mature enough (And find damn solution for forced windowed vsync, another reason to avoid the OS imho for older games like CSGO)
Why don't you play true fullscreen?
Doesn't the input lag come from that windowed mode?
Seems there are alot of CSGO players. Do they play in W7 too?
I didnt mean the difference in fps would noticably or at all affect input lag, I mean the fact that two OS behave differently in multipe aspects could indicate much has changed under the hood, it could be anything at this point. In my book there is an 'optimized' path from peripheral input to display output, and an 'unoptimized' path which feels what W10 currently is. Call it input to pixel precision?

I play exclusive full screen, always. I ment that Windows 10 has forced DWM V-sync, and in any case 1 frame of delay when using Gsync (full) windowed.

Major flaw in W10 imho, as games like CSGO and a few others run horrible in full screen (Alt tab can easily take 10 seconds). The main game I play (MWO) in full screen literally go nuts if I alt-tab in specific scenarios, although works perfect otherwise. (Both actual game flaws, not OS/Hw specific).

(Full)windowed without DWM In W7 is still a very good option for high FPS games like CSGO, not to much for low fps games as tearing would become annoying, hence why full screen + G-sync is mostly the best option in general.

But taking all that out of the equation, the fact that there is no way in W10 to avoid that 1 frame of delay, is in my book an inherit flaw of the OS.

The recent 'Full screen optimization' is still in very early development and seems more of a dirty fix to keep then from finding a 'proper' solution.

As for competitive CSGO players? No clue, that info seems almost impossible to find. Keep in mind that Esport players are often sponsored, and its a 'tight' little crew thats probably incredibly hard to get in as a lone player.

They use mice by brands that they get sponsored by, even if they don't personally prefer said mice and could probably play better with their own prefered peripherals.

Do they use W7 or 10? Who knows. Pretty sure on Esport tournaments they use pre-build/configured PC's all setup by the organizers themselves, to prevent any unfair advantage.

One should not compare Esports to home-competitive level play, nor compare twitch shooters vs trackers and other type of games when it comes to input lag, as the difference in types of games greatly affect the threshold on when different types of input lag is felt.

I feel we're going off topic here though, but this had to be said.
LTSC 21H2 Post-install Script
https://github.com/Marctraider/LiveScript-LTSC-21H2

System: MSI Z390 MEG Ace - 2080 Super (300W mod) - 9900K 5GHz Fixed Core (De-lid) - 32GB DDR3-3733-CL18 - Xonar Essence STX II

User avatar
jorimt
Posts: 2481
Joined: 04 Nov 2016, 10:44
Location: USA

Re: Comparing bare-bones Win7 vs 10 install

Post by jorimt » 07 Feb 2019, 15:24

MT_ wrote:I ment that Windows 10 has forced DWM V-sync, and in any case 1 frame of delay when using Gsync (full) windowed.
FYI, my tests have shown that DWM may indeed not introduce 1 frame of lag in borderless or windowed mode with G-SYNC active:
https://www.blurbusters.com/gsync/gsync ... ttings/10/

Image

Image

As far as I'm aware, G-SYNC overrides the DWM by forcing a different flip mode when the window is focused/active, thus the usual DWM triple buffer/1 frame added by composition shouldn't apply.
(jorimt: /jor-uhm-tee/)
Author: Blur Busters "G-SYNC 101" Series

Displays: ASUS PG27AQN, LG 48CX VR: Beyond, Quest 3, Reverb G2, Index OS: Windows 11 Pro Case: Fractal Design Torrent PSU: Seasonic PRIME TX-1000 MB: ASUS Z790 Hero CPU: Intel i9-13900k w/Noctua NH-U12A GPU: GIGABYTE RTX 4090 GAMING OC RAM: 32GB G.SKILL Trident Z5 DDR5 6400MHz CL32 SSDs: 2TB WD_BLACK SN850 (OS), 4TB WD_BLACK SN850X (Games) Keyboards: Wooting 60HE, Logitech G915 TKL Mice: Razer Viper Mini SE, Razer Viper 8kHz Sound: Creative Sound Blaster Katana V2 (speakers/amp/DAC), AFUL Performer 8 (IEMs)

MT_
Posts: 113
Joined: 17 Jan 2017, 15:39

Re: Comparing bare-bones Win7 vs 10 install

Post by MT_ » 12 Apr 2019, 15:20

jorimt wrote:
MT_ wrote:I ment that Windows 10 has forced DWM V-sync, and in any case 1 frame of delay when using Gsync (full) windowed.
FYI, my tests have shown that DWM may indeed not introduce 1 frame of lag in borderless or windowed mode with G-SYNC active:
https://www.blurbusters.com/gsync/gsync ... ttings/10/

Image

Image

As far as I'm aware, G-SYNC overrides the DWM by forcing a different flip mode when the window is focused/active, thus the usual DWM triple buffer/1 frame added by composition shouldn't apply.
This applies to 7, 10? (And which builds, if it matters?)

Thx.
LTSC 21H2 Post-install Script
https://github.com/Marctraider/LiveScript-LTSC-21H2

System: MSI Z390 MEG Ace - 2080 Super (300W mod) - 9900K 5GHz Fixed Core (De-lid) - 32GB DDR3-3733-CL18 - Xonar Essence STX II

User avatar
jorimt
Posts: 2481
Joined: 04 Nov 2016, 10:44
Location: USA

Re: Comparing bare-bones Win7 vs 10 install

Post by jorimt » 12 Apr 2019, 15:49

MT_ wrote:This applies to 7, 10? (And which builds, if it matters?)
Can't guarantee it for 7 (tested on Windows 10 only), but knowing what I do, I'm pretty sure the OS version/build shouldn't matter here; if G-SYNC borderless/windowed mode bypasses Aero/DWM composition by forcing an alt flip mode at the GPU driver-level, then there isn't going to be the usual 1 frame of lag added over exclusive fullscreen, which is what my existing tests showed.
(jorimt: /jor-uhm-tee/)
Author: Blur Busters "G-SYNC 101" Series

Displays: ASUS PG27AQN, LG 48CX VR: Beyond, Quest 3, Reverb G2, Index OS: Windows 11 Pro Case: Fractal Design Torrent PSU: Seasonic PRIME TX-1000 MB: ASUS Z790 Hero CPU: Intel i9-13900k w/Noctua NH-U12A GPU: GIGABYTE RTX 4090 GAMING OC RAM: 32GB G.SKILL Trident Z5 DDR5 6400MHz CL32 SSDs: 2TB WD_BLACK SN850 (OS), 4TB WD_BLACK SN850X (Games) Keyboards: Wooting 60HE, Logitech G915 TKL Mice: Razer Viper Mini SE, Razer Viper 8kHz Sound: Creative Sound Blaster Katana V2 (speakers/amp/DAC), AFUL Performer 8 (IEMs)

MT_
Posts: 113
Joined: 17 Jan 2017, 15:39

Re: Comparing bare-bones Win7 vs 10 install

Post by MT_ » 21 May 2019, 12:58

jorimt wrote:
MT_ wrote:This applies to 7, 10? (And which builds, if it matters?)
Can't guarantee it for 7 (tested on Windows 10 only), but knowing what I do, I'm pretty sure the OS version/build shouldn't matter here; if G-SYNC borderless/windowed mode bypasses Aero/DWM composition by forcing an alt flip mode at the GPU driver-level, then there isn't going to be the usual 1 frame of lag added over exclusive fullscreen, which is what my existing tests showed.
I have not been able to replicate DWM bypassing with G-sync windowed in any full screen windowed or windowed game, other than the new 'Full Screen optimization' functionality whearas the game has to be put into full screen exclusive mode for it to work.

Neither 1607 nor 1809, tested various Nvidia drivers from over the years.

Other than the 'Full screen optimization' feature, there's no way in hell I can introduce tearing in any game/driver/W10 version combo which would indicate DWM is still active.

Further evidence of this would be the horrible framepacing (occasional frame skips) with G-sync windowed compared to exclusive full screen.

So perhaps its bypassing that 1 frame latency but it seems something still forces vsync. I guess thats where the confusion lies on my end ;)

I've seen sporadic people post about having tearing in actual WINDOWED mode in Creator's but I'm not sure how to replicate that. That would be amazing.

Perhaps this stuff needs some additional clarification on the article? Like it bypasses that extra 1 frame of latency, but DWM still applies somehow and apparently interacts with G-sync in some way. It still feels like a hackjob to me and less smooth than FSE.
LTSC 21H2 Post-install Script
https://github.com/Marctraider/LiveScript-LTSC-21H2

System: MSI Z390 MEG Ace - 2080 Super (300W mod) - 9900K 5GHz Fixed Core (De-lid) - 32GB DDR3-3733-CL18 - Xonar Essence STX II

User avatar
jorimt
Posts: 2481
Joined: 04 Nov 2016, 10:44
Location: USA

Re: Comparing bare-bones Win7 vs 10 install

Post by jorimt » 21 May 2019, 14:27

MT_ wrote:I have not been able to replicate DWM bypassing with G-sync windowed
I never said G-SYNC bypasses the DWM itself, I said it appears to bypass the DWM's composition/flip mode when the game window (either in windowed or borderless) is focused on, which is what causes the additional 1 frame of lag without G-SYNC; DWM is still active with borderless/windowed G-SYNC as far as I'm aware.

I wasn't able to make it tear (e.g. disable DWM w/G-SYNC) during my original testing either, which is something I already noted in the article, by the way:
https://www.blurbusters.com/gsync/gsync ... ttings/10/
all combinations of NVCP and in-game V-SYNC, as well as the Windows 10 “Game Mode” and “fullscreen optimization” settings were tested to see if DWM could be disabled, and tearing could be introduced; it could not be, so Game Mode and fullscreen optimizations were disabled once again, and NVCP V-SYNC was re-enabled across scenarios for consistency’s sake.
(jorimt: /jor-uhm-tee/)
Author: Blur Busters "G-SYNC 101" Series

Displays: ASUS PG27AQN, LG 48CX VR: Beyond, Quest 3, Reverb G2, Index OS: Windows 11 Pro Case: Fractal Design Torrent PSU: Seasonic PRIME TX-1000 MB: ASUS Z790 Hero CPU: Intel i9-13900k w/Noctua NH-U12A GPU: GIGABYTE RTX 4090 GAMING OC RAM: 32GB G.SKILL Trident Z5 DDR5 6400MHz CL32 SSDs: 2TB WD_BLACK SN850 (OS), 4TB WD_BLACK SN850X (Games) Keyboards: Wooting 60HE, Logitech G915 TKL Mice: Razer Viper Mini SE, Razer Viper 8kHz Sound: Creative Sound Blaster Katana V2 (speakers/amp/DAC), AFUL Performer 8 (IEMs)

bbluster
Posts: 4
Joined: 24 May 2019, 10:23

Re: Comparing bare-bones Win7 vs 10 install

Post by bbluster » 11 Jun 2019, 14:39

Are you using a custom version of Windows 7 or have you removed certain features with tools, how slim is it?

Post Reply