| Summary: | Empire Total War - Graphical Corruption | ||
|---|---|---|---|
| Product: | Mesa | Reporter: | andrew.m.mcmahon |
| Component: | Drivers/Gallium/radeonsi | Assignee: | Default DRI bug account <dri-devel> |
| Status: | RESOLVED FIXED | QA Contact: | Default DRI bug account <dri-devel> |
| Severity: | normal | ||
| Priority: | medium | ||
| Version: | git | ||
| Hardware: | x86-64 (AMD64) | ||
| OS: | Linux (All) | ||
| Whiteboard: | |||
| i915 platform: | i915 features: | ||
| Bug Depends on: | |||
| Bug Blocks: | 77449 | ||
| Attachments: |
glxinfo | grep strings
steam system info Xorg log Xorg log dmesg -w mesa-git glxinfo |
||
|
Description
andrew.m.mcmahon
2019-01-12 15:04:58 UTC
Created attachment 143079 [details]
steam system info
Created attachment 143084 [details]
Xorg log
Created attachment 143085 [details]
Xorg log
Created attachment 143086 [details]
dmesg -w
I've used apitrace (DEBUGGER="apitrace32 trace" steam steam://rungameid/10500) to capture some trace files. I'm able to replay them using apitrace replay [file] so I hope others are too. I've uploaded a 7z archive containing a "bugged" trace and a "workaround" trace with their corresponding terminal output: https://drive.google.com/file/d/1BAQFnrJqujU7dYGQTfheABTRjj-_a8Ys/view?usp=sharing By complete coincidence the archive happens to be 666MB. The bugged trace is several gigabytes in size whilst the workaround is a mere 90MB so there must be something funny happening there... One last comment before I leave it to the experts. Another bug report with Unity 18.04: https://steamcommunity.com/app/10500/discussions/0/3441214221460524307/ If anyone wants to go above and beyond the call of duty then I've uploaded some traces for Medieval 2 here: https://drive.google.com/open?id=17LUb2EsS3oqYjEyZ-yxIB_C_DBnS0Wz8 I've used the same trick of disabling/enabling PBO surfaces. Finally what exactly are PBO surfaces? Do I need them? What's the penalty for not using them? The game seems to trace faster with them off than on. Are the Linux ports by Feral a bit wonky and/or prone to strange behaviour - or are they generally decent? Created attachment 143088 [details]
mesa-git glxinfo
As a last ditch effort I thought I'd try the latest mesa/llvm that are provided by [llvm-git] and [mesa-git] unofficial repo's.
Unfortunately the issue still occurs.
My system has changed somewhat since writing this bug report. As all Feral games on STEAM officially support either STEAMOS or Ubuntu; I thought I'd check out xubuntu 18.04 LTS - specifically: https://pastebin.com/f8cTGLSY The same glitch appears with the current Mesa drivers provided by the distribution (18.2.8) But using oibaf's ppa: https://launchpad.net/~oibaf/+archive/ubuntu/graphics-drivers Mesa related packages are updated to: Mesa 19.1.0-devel (git-54522d0 2019-03-06 bionic-oibaf-ppa) And I can no longer reproduce the issue! https://i.imgur.com/VhIylSp.jpg As I've made no other changes other than switching Mesa packages I can only assume that this has been fixed by an update/commit recently. Many thanks to everyone who works on Mesa. In just a few years (since I last tried Debian) my R9 285 has gone from having no support whatever in Linux to being very capable indeed to the point where I no longer require Windows: https://imgur.com/a/keUM4VS https://imgur.com/a/awddkUg |
Use of freedesktop.org services, including Bugzilla, is subject to our Code of Conduct. How we collect and use information is described in our Privacy Policy.
