1. Verbose live progress during SAT tests (CPU, Memory, Storage, AMD GPU)

- New tui/sat_progress.go: polls {DefaultSATBaseDir}/{prefix}-*/verbose.log every 300ms and parses completed/in-progress steps
  - Busy screen now shows each step as PASS  lscpu (234ms) / FAIL  stress-ng (60.0s) / ...   sensors-after instead of just "Working..."

  2. Test results shown on screen (instead of just "Archive written to /path")
  - RunCPUAcceptancePackResult, RunMemoryAcceptancePackResult, RunStorageAcceptancePackResult, RunAMDAcceptancePackResult now read summary.txt from the run directory and return a formatted per-step result:
  Run: 2025-03-25T10:00:00Z

  PASS  lscpu
  PASS  sensors-before
  FAIL  stress-ng
  PASS  sensors-after

  Overall: FAILED  (ok=3  failed=1)

  3. AMD GPU SAT with auto-detection
  - platform.System.DetectGPUVendor(): checks /dev/nvidia0 → "nvidia", /dev/kfd → "amd"
  - platform.System.RunAMDAcceptancePack(): runs rocm-smi, rocm-smi --showallinfo, dmidecode
  - GPU SAT (G key / GPU row enter) automatically routes to AMD or NVIDIA based on detected vendor
  - "Run All" also auto-detects vendor

  4. Panel detail view
  - GPU detail now shows the most recent (NVIDIA or AMD) SAT result, whichever is newer
  - All SAT detail views use the same human-readable formatSATDetail format
This commit is contained in:
Mikhail Chusavitin
2026-03-25 17:54:27 +03:00
parent adcc147b32
commit 0c16616cc9
9 changed files with 300 additions and 57 deletions

View File

@@ -22,6 +22,56 @@ type NvidiaGPU struct {
MemoryMB int
}
// AMDGPUInfo holds basic info about an AMD GPU from rocm-smi.
type AMDGPUInfo struct {
Index int
Name string
}
// DetectGPUVendor returns "nvidia" if /dev/nvidia0 exists, "amd" if /dev/kfd exists, or "" otherwise.
func (s *System) DetectGPUVendor() string {
if _, err := os.Stat("/dev/nvidia0"); err == nil {
return "nvidia"
}
if _, err := os.Stat("/dev/kfd"); err == nil {
return "amd"
}
return ""
}
// ListAMDGPUs returns AMD GPUs visible to rocm-smi.
func (s *System) ListAMDGPUs() ([]AMDGPUInfo, error) {
out, err := exec.Command("rocm-smi", "--showproductname", "--csv").Output()
if err != nil {
return nil, fmt.Errorf("rocm-smi: %w", err)
}
var gpus []AMDGPUInfo
for _, line := range strings.Split(strings.TrimSpace(string(out)), "\n") {
line = strings.TrimSpace(line)
if line == "" || strings.HasPrefix(strings.ToLower(line), "device") {
continue
}
parts := strings.SplitN(line, ",", 2)
name := ""
if len(parts) >= 2 {
name = strings.TrimSpace(parts[1])
}
idx := len(gpus)
gpus = append(gpus, AMDGPUInfo{Index: idx, Name: name})
}
return gpus, nil
}
// RunAMDAcceptancePack runs an AMD GPU diagnostic pack using rocm-smi.
func (s *System) RunAMDAcceptancePack(baseDir string) (string, error) {
return runAcceptancePack(baseDir, "gpu-amd", []satJob{
{name: "01-rocm-smi.log", cmd: []string{"rocm-smi"}},
{name: "02-rocm-smi-showallinfo.log", cmd: []string{"rocm-smi", "--showallinfo"}},
{name: "03-dmidecode-baseboard.log", cmd: []string{"dmidecode", "-t", "baseboard"}},
{name: "04-dmidecode-system.log", cmd: []string{"dmidecode", "-t", "system"}},
})
}
// ListNvidiaGPUs returns GPUs visible to nvidia-smi.
func (s *System) ListNvidiaGPUs() ([]NvidiaGPU, error) {
out, err := exec.Command("nvidia-smi",