I've attached screenshots from Firefox (the one with lots of small stutter), and a screenshot from Microsoft Edge (with hardly any stutter.) Why is there such a difference between both of these browsers? I also tested on Chrome, and it has same results as Edge (I'm guessing because they are both on Chromium?)
[Moderator edit -- added image zoom links]
FireFox - download/file.php?id=1724
Chrome - download/file.php?id=1723
Weird Firefox stutter compared to none in Chrome/Edge
Weird Firefox stutter compared to none in Chrome/Edge
- Attachments
-
- firefox.PNG (16.94 KiB) Viewed 7633 times
-
- edge and chrome.PNG (12.2 KiB) Viewed 7633 times
- Chief Blur Buster
- Site Admin
- Posts: 11680
- Joined: 05 Dec 2013, 15:44
- Location: Toronto / Hamilton, Ontario, Canada
- Contact:
Re: Weird Firefox stutter compared to none in Chrome/Edge
They have to do with the differences between the JavaScript performance.now() API which is essentially a floating point (microsecond quality) timestamp.
Unfortunately, Meltdown/Spectre hacks made it necessary for some browser vendors to add intentional random() fuzz to this timestamp. Ideally it should be based on RTDSC or QueryPerformanceCounter() but the precision is often intentionally fuzzed by the browser vendors to make it harder for hackers to detect temporal fingerprints from your system (leakage of information from nanosecond/microsecond jitter).
Also, sometimes Chromium is worse, if you use battery management mode on an older laptop, it often falls to the same millisecond-precision!
Unfortunately, Meltdown/Spectre hacks made it necessary for some browser vendors to add intentional random() fuzz to this timestamp. Ideally it should be based on RTDSC or QueryPerformanceCounter() but the precision is often intentionally fuzzed by the browser vendors to make it harder for hackers to detect temporal fingerprints from your system (leakage of information from nanosecond/microsecond jitter).
Also, sometimes Chromium is worse, if you use battery management mode on an older laptop, it often falls to the same millisecond-precision!
Head of Blur Busters - BlurBusters.com | TestUFO.com | Follow @BlurBusters on Twitter
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!
Re: Weird Firefox stutter compared to none in Chrome/Edge
So this is expected and intended behavior? What does this mean for playing games or watching videos within the Firefox browser. Will it affect quality or performance in any regard?Chief Blur Buster wrote: ↑05 Aug 2021, 02:01They have to do with the differences between the [which is essentially a floating point (microsecond quality) timestamp.
Unfortunately, Meltdown/Spectre hacks made it necessary for some browser vendors to add intentional random() fuzz to this timestamp. Ideally it should be based on RTDSC or QueryPerformanceCounter() but the precision is often intentionally fuzzed by the browser vendors to make it harder for hackers to detect temporal fingerprints from your system (leakage of information from nanosecond/microsecond jitter).
Also, sometimes Chromium is worse, if you use battery management mode on an older laptop, it often falls to the same millisecond-precision!
- Chief Blur Buster
- Site Admin
- Posts: 11680
- Joined: 05 Dec 2013, 15:44
- Location: Toronto / Hamilton, Ontario, Canada
- Contact:
Re: Weird Firefox stutter compared to none in Chrome/Edge
Yes. Browser developer differences.
Not really.
Frame rates (24fps = 41.6ms) and refresh cycles (60Hz = 16.7ms and 240Hz = 4.17ms) are so low granularity that these tiny 0.1ms or 1ms noise won't interfere with browser-based games or browser-based video.
And if you mean games in Steam, they are not web browsers, so not applicable...
This stuff is only a problem if you're getting red colored spikes like these at www.testufo.com/animation-time-graph that looks like interference by background processes even though you freshly rebooted the computer and only opened one browser tab directly to Animation Time Graph.
In all cases, this is almost always caused by processing spikes (CPU or GPU), one person traced it to MalwareBytes. Another person traced it to CPU-hungry RGB keyboard software.
It's surprisingly how sensitive TestUFO is to detecting background CPU spikes. Those kind of spikes can interfere with game stutters too.
Head of Blur Busters - BlurBusters.com | TestUFO.com | Follow @BlurBusters on Twitter
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!