I'm not getting huge variation in Ashley 's demo (It's around what — got), how exactly is that demo trying to throttle? If it's just spawning a lot of objects with Sine motion, it's probably CPU lag more than GPU lag.

I'm pretty sure fillrate is the limitation that tends to cause these huge inconsistencies, since reducing the window size *always* helps with it.

Of course it's possible, you'll just need to be a bit clever. It depends a lot on your backgrounds, any parallax, etc.

OK, back to the original issue - as a refresher, basically we've noticed that some lag is worse than other lag.

I've done some datalogging in three settings: CPU lag in the lag demo already provided, GPU lag in the same demo, and my game Airscape: The Fall of Gravity. At 30fps, here's what I noticed purely based on 'feel':

CPU lag: Felt perfectly fine, exactly what 30fps should be.

GPU lag: definite weirdness

Airscape: Absolutely horrible to control, nightmarish. Felt more like 5fps than 30fps.

Here are the dt logs I've made: [dt logged every tick]

CPU lag: very little deviation between dt

GPU lag: a fair bit of deviation between dt

Airscape: a LOT of deviation between dt

Ashley hopefully you can do something with this. There's definitely evidence here that something's wrong.

Everyone else, I've attached an updated lag test that you can use to test on your own machines. Bonus points for attaching to your games ( Aurel I'm looking at you )

No, collision would be one of your issues.

It's potentially possible in a very limited sense with the Canvas plugin but honestly C2 isn't your best option for vector stuff like this.

Ashley fair enough, but it will probably need fine-tuning.

— Did you try my demo with GPU lag?

Ashley I agree 45fps is too high a benchmark, however, as this thread has brought up, 45fps is not the same in all circumstances. Spikes, unevenness etc are the main issue. If we were able to make 30fps consistent it would be perfectly fine.

I can't propose new values for the dt caps, but I'd love to be able to play around with lower caps. 0.0167 is the ideal value, so it would be great to be able to cap it at, say, 0.02. The fact is, some games (including mine and Aurel's) have enough fast motion that it becomes problematic to remain framerate-independent at high dt values. Slowing down the game might actually be better.

Ashley I agree with you, and I'm sure most games are fine with low FPS in this regard. HOWEVER, small lag spikes are common and these play havoc with dt - whenever there's a lag spike, dt is set to its lowest value and objects teleport everywhere.

Ashley

1) GPU blacklisting is definitely not the problem. I've checked this, I'm on a new laptop with the latest drivers, and I've tried the test both on the GPU and the integrated graphics.

2) I had a look at the other browsers and the lag difference doesn't seem to be there at least on my PC. So it's a Chrome/NW problem?

3) What would C2's profiler say that would be useful? It doesn't measure GPU at all, just CPU?

I don't think anyone would propose artificially throttling FPS like that - you're making it sound like HTML5 is permanently locked to 60fps? I don't remember reading it anywhere but I guess it could be true.

The issue brought up by Aurel is a good one and I'd urge you to take a look at allowing us to cap dt at a lower value to prevent collision issues. This isn't directly related to the issue in this thread but does play off it.

Those who tested with no results - you have to wait a few seconds for the lag to kick in. Change the loop iterations if it doesn't kick in fast enough.

OK, so I've gone and created a test project using Arima's suggestion.

Initially I just did the collision check method as Arima said, but when I tested it I noticed that at 30fps the game was pretty much fine.

So, I tried creating lag by a different method (rendering lots of 1% opacity rectangles) and immediately the difference was super obvious. There's significant input delay when the lag is on the GPU side.

Can anyone confirm? (Capx attached)

Ashley reckon we could get a comment on this? Is this something fixable?