NV DB Vsync + RTSS limit

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.
User avatar
RealNC
Site Admin
Posts: 3741
Joined: 24 Dec 2013, 18:32
Contact:

Re: NV DB Vsync + RTSS limit

Post by RealNC » 18 Feb 2017, 11:54

knypol wrote:How can i limit with decimal precission? I just downloaded RTSS and I can only increase/decrease by 1.
http://forums.blurbusters.com/viewtopic ... 215#p23315
SteamGitHubStack Overflow
The views and opinions expressed in my posts are my own and do not necessarily reflect the official policy or position of Blur Busters.

knypol
Posts: 76
Joined: 18 Aug 2016, 03:40

Re: NV DB Vsync + RTSS limit

Post by knypol » 18 Feb 2017, 12:18

THX

knypol
Posts: 76
Joined: 18 Aug 2016, 03:40

Re: NV DB Vsync + RTSS limit

Post by knypol » 19 Feb 2017, 08:45

Any1 actually tested that RTSS (-0.1 fps) + VCP VSYNC ON with max prerendered 1 has less input lag than alone NVCP VSYNC ON with max prerendered 1? Doesn't RTSS adds some input lag?

Sparky
Posts: 682
Joined: 15 Jan 2014, 02:29

Re: NV DB Vsync + RTSS limit

Post by Sparky » 19 Feb 2017, 10:09

knypol wrote:Any1 actually tested that RTSS (-0.1 fps) + VCP VSYNC ON with max prerendered 1 has less input lag than alone NVCP VSYNC ON with max prerendered 1? Doesn't RTSS adds some input lag?
I haven't tested NVCP specifically, because I have an AMD video card, but RTSS added 1 frame of lag over an in-game cap, while plain v-sync adds much more.
Here are some numbers(CS:GO, 85.2hz refresh rate):

nocap vsync on: 65.7ms
nocap vsync on flip queue 1: 56.3ms
nocap vsync off: 7.3ms

RTSS 85 vsync on: 31.8ms
RTSS 85 vsync off: 24.5ms

fps_max 85 vsync on: 21.0ms
fps_max 85 vsync off: 14.0ms

Here's a graph with some more stuff on it: https://docs.google.com/spreadsheets/d/ ... nteractive

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

Re: NV DB Vsync + RTSS limit

Post by Chief Blur Buster » 19 Feb 2017, 12:52

knypol wrote:Any1 actually tested that RTSS (-0.1 fps) + VCP VSYNC ON with max prerendered 1 has less input lag than alone NVCP VSYNC ON with max prerendered 1? Doesn't RTSS adds some input lag?
RTSS doesn't necessarily add input lag per se, it's highly dependant on how the game engine interacts with the frame capping software.

RTSS will usually have less VSYNC ON input lag than uncapped, but an in-game capper (e.g. CS:GO) may do a better job. But not all games have a proper frame rate capping feature.
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!

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

Re: NV DB Vsync + RTSS limit

Post by Chief Blur Buster » 19 Feb 2017, 12:55

Sparky wrote:
knypol wrote:Any1 actually tested that RTSS (-0.1 fps) + VCP VSYNC ON with max prerendered 1 has less input lag than alone NVCP VSYNC ON with max prerendered 1? Doesn't RTSS adds some input lag?
I haven't tested NVCP specifically, because I have an AMD video card, but RTSS added 1 frame of lag over an in-game cap, while plain v-sync adds much more.
Here are some numbers(CS:GO, 85.2hz refresh rate):

nocap vsync on: 65.7ms
nocap vsync on flip queue 1: 56.3ms
nocap vsync off: 7.3ms

RTSS 85 vsync on: 31.8ms
RTSS 85 vsync off: 24.5ms

fps_max 85 vsync on: 21.0ms
fps_max 85 vsync off: 14.0ms

Here's a graph with some more stuff on it: https://docs.google.com/spreadsheets/d/ ... nteractive
Observations:
--> Looks like RTSS greatly reduces VSYNC ON input lag compared to uncapped VSYNC ON.
--> Looks like RTSS slightly increases VSYNC OFF input lag compared to uncapped VSYNC OFF.
--> In-game frame rate capping can do a better job than RTSS. But not all games have in-game frame-rate capping.

Still, this is fantastic -- VSYNC ON 65.7m -> VSYNC ON 21ms.
That's eliminating almost 75% of your VSYNC ON input lag!

It is pretty consistent with rough basic rules of thumb (at least for your particular system)
--> For lowest input lag during VSYNC OFF, you want uncapped (or a very high framerate cap, like fps_max 500)
--> For lowest input lag during VSYNC ON, you want to frame-rate cap with in-game capping, and if game doesn't have capping support, then RTSS can help here.

Also, are you using large vertical totals for your video signal?
The use of large vertical totals also reduces VSYNC ON input lag (for both strobed and non-strobed modes).
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!

User avatar
Arulan
Posts: 7
Joined: 22 Jul 2014, 12:01

Re: NV DB Vsync + RTSS limit

Post by Arulan » 19 Feb 2017, 15:56

Thanks for the excellent replies. There is a lot of good information here.
Chief Blur Buster wrote: It is pretty consistent with rough basic rules of thumb (at least for your particular system)
--> For lowest input lag during VSYNC OFF, you want uncapped (or a very high framerate cap, like fps_max 500)
--> For lowest input lag during VSYNC ON, you want to frame-rate cap with in-game capping, and if game doesn't have capping support, then RTSS can help here.
Is the general consensus still that in-game capping, while producing a lower input latency, doesn't produce as consistent frame delivery as RTSS?

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

Re: NV DB Vsync + RTSS limit

Post by Chief Blur Buster » 19 Feb 2017, 21:05

Arulan wrote:Is the general consensus still that in-game capping, while producing a lower input latency, doesn't produce as consistent frame delivery as RTSS?
This can be true. Frame consistency can be quite the issue. If you use single-card operation and turn off multi-core rendering, then frame consistency is much better. However, some RTSS setups appears to have better frame consistency (several of you are doing a good job benchmarking this). Regardless, I think lots of improvement can be made with either in-game frame capping and/or RTSS.
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!

Sparky
Posts: 682
Joined: 15 Jan 2014, 02:29

Re: NV DB Vsync + RTSS limit

Post by Sparky » 19 Feb 2017, 21:20

Chief Blur Buster wrote:
Also, are you using large vertical totals for your video signal?
The use of large vertical totals also reduces VSYNC ON input lag (for both strobed and non-strobed modes).
Those were CRT based tests, I haven't done any testing with modified signal timing. As for high vertical totals impacting latency, I suppose that would depend on when exactly the video card does the buffer flip, hopefully in the front porch. If it does it at the start of the back porch then high vertical totals would actually increase lag. Either way, it won't be a big impact, about half a refresh interval if you can double the normal pixel clock. Still really interesting, sounds like a big benefit to pulsed backlights.

Sparky
Posts: 682
Joined: 15 Jan 2014, 02:29

Re: NV DB Vsync + RTSS limit

Post by Sparky » 19 Feb 2017, 21:41

Arulan wrote:Thanks for the excellent replies. There is a lot of good information here.
Chief Blur Buster wrote: It is pretty consistent with rough basic rules of thumb (at least for your particular system)
--> For lowest input lag during VSYNC OFF, you want uncapped (or a very high framerate cap, like fps_max 500)
--> For lowest input lag during VSYNC ON, you want to frame-rate cap with in-game capping, and if game doesn't have capping support, then RTSS can help here.
Is the general consensus still that in-game capping, while producing a lower input latency, doesn't produce as consistent frame delivery as RTSS?
Well, There is an extra frame of buffering, so it will smooth out hitches caused by the CPU taking longer than expected on a frame, but there will still be an artifact where things move faster than normal then slower than normal as the CPU catches up to the slack introduced by the stall.

In terms of latency, the main problem with frame limiters and vsync is that while the latency is reasonably low, it's less consistent, Say uncapped vsync is 55ms plus or minus 5ms, (100fps 100hz), capped vsync might be 20ms plus or minus 10ms at say 99.999fps 100hz, because frame completion is no longer phase locked to frames being displayed. To get low and consistent latency you need either super high refresh rates or a variable refresh rate display. Or just use vsync off I guess.

Post Reply