Beanstalk Longshot test farm
Menu

#1458 fix(vk): the swapchain's image is waited for on the CPU, so a window behind another one no longer stops the GPU's work

by HumanBean closed Open on Forgejo

Commit

Head
da29a64
Base
main c14641a
Approval
approved HumanBean, · reviewed

Plan (gpt-6.1-terra)

Compare fullscreen frame pacing and pictures on Windows AMD RDNA 4

In plain words

On Windows with an AMD proprietary driver and an RDNA 4-class GPU, this plan compares main and the branch in Hyrule Field for about 15 minutes. It tests fullscreen frame generation at 2x and 4x with V-Sync Auto and On, using frametime as a pacing proxy and comparing pictures. A crash, GPU-hang log, significant p99 frametime regression, or picture mismatch fails the plan. The farm cannot put a browser over the game or start it behind another window, so the requested hidden-window reproduction, recovery, and launcher-start checks remain untested.

Asked for

on Windows with an AMD GPU on AMD's own driver (RDNA 4 like an RX 9070 XT if there is one, else RDNA 3), this branch against main, fullscreen, V-Sync Auto: 1. Frame generation 2x, play in Hyrule Field, then put a browser window over the game for 30 s and bring the game back; do it 4 times. Expected on this branch: no "FATAL: the GPU hung", the picture comes back each time (the log may say "the window's image was not given back in 250 ms" then "was given back"). On main it is expected to end with the GPU hang within about 30 s. 2. Start the game from the launcher with frame generation 4x and another window in front of it at the start, and let it run through the intro. Expected: no GPU hang on this branch. 3. With the game in front, frame generation 2x and 4x, V-Sync Auto and V-Sync On: compare frame pacing with main (the frame interpolation lines, or PresentMon). Expected: no worse than main.

Raw plan 101 lines Download plan.json

  "pass" 
    "crash" false
    "screenshot" 
      "max_diff" 0.05
    
    "frametime_p99_ms" 
      "max_delta_pct" 15
    
    "log_forbidden_hits" 
      "max" 0
    
  
  "probe" 
    
      "kind" "crash"
    
    
      "kind" "frametime"
    
    
      "kind" "log_match"
      "expected" 
      "forbidden" 
        "FATAL: the GPU hung"
      
    
  
  "matrix" 
    "vsync" 
      0
      1
    
    "frame_generation" 
      2
      4
    
  
  "schema" 4
  "target" 
    
      "gpu" 
        "rx 9*"
      
      "name" "windows+amd-proprietary+gpu-rx-9*"
      "tags" 
        "windows"
        "amd-proprietary"
      
      "max_reports" 2
      "min_reports" 1
    
  
  "summary" "Compare fullscreen frame pacing and pictures on Windows AMD RDNA 4"
  "baseline" 
    "ref" "main"
  
  "scenario" 
    
      "env" 
      "name" "field-pacing"
      "runs" 2
      "step" 
        
          "do" "teleport"
          "to" "HyruleField_Child"
        
        
          "do" "wait"
          "map" "HyruleField_Child"
          "event" "map"
          "timeout_s" 60
        
        
          "x" 0.0
          "y" 1.0
          "do" "stick"
          "stick" "L"
          "frames" 180
        
        
          "do" "measure"
          "name" "field"
          "warmup_s" 10
          "duration_s" 30
        
        
          "do" "shot"
          "name" "field"
          "upload" false
          "compare" "baseline"
        
      
      "start" "new"
      "matrix" true
      "settings" 
        "fullscreen" 1
      
    
  

Targets

TargetTierReportsStatus
windows+amd-proprietary+gpu-rx-9* GPU "rx 9*"reviewed HumanBean 1 1/1 fail

Reports

ReportCommitTargetTesterResultWhen
rp_c64831cd35a6deaeda29a64windows+amd-proprietary+gpu-rx-9* Razytos/agent-d8f902fail

Jobs

JobCommitTargetStateTesterStartedAttemptsEstimateNote
jb_5805488f3a600a3b logda29a64windows+amd-proprietary+gpu-rx-9* done runRazytos/agent-d8f9021
jb_a41644ac03f2d2d5 logda29a64windows+amd-proprietary+gpu-rx-9* cancelled—1 the PR was closed