reanimator/bee
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 1 Wiki Activity

feat(dcgm): add NVIDIA DCGM diagnostics, fix KVM console

Browse Source 
- Add 9002-nvidia-dcgm.hook.chroot: installs datacenter-gpu-manager
  from NVIDIA apt repo during live-build
- Enable nvidia-dcgm.service in chroot setup hook
- Replace bee-gpu-stress with dcgmi diag (levels 1-4) in NVIDIA SAT
- TUI: replace GPU checkbox + duration UI with DCGM level selection
- Remove console=tty2 from boot params: KVM/VGA now shows tty1
  where bee-tui runs, fixing unresponsive console

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Michael Chus
2026-03-26 23:08:12 +03:00
parent 967455194c
commit eea98e6d76
12 changed files with 121 additions and 170 deletions
Download Patch File Download Diff File Expand all files Collapse all files

31
audit/internal/tui/screen_health_check.go
View File

@@ -33,8 +33,6 @@ const (
hcCurTotal = 9
)
// hcModeDurations maps mode index (0=Quick,1=Standard,2=Express) to GPU stress seconds.
var hcModeDurations = [3]int{600, 3600, 28800}
// hcCPUDurations maps mode index to CPU stress-ng seconds.
var hcCPUDurations = [3]int{60, 300, 900}
@@ -232,7 +230,6 @@ func (m model) hcRunAll() (tea.Model, tea.Cmd) {
}
func (m model) executeRunAll() (tea.Model, tea.Cmd) {
durationSec := hcModeDurations[m.hcMode]
durationIdx := m.hcMode
sel := m.hcSel
app := m.app
@@ -250,28 +247,14 @@ func (m model) executeRunAll() (tea.Model, tea.Cmd) {
}
parts = append(parts, "=== GPU (AMD) ===\n"+body)
} else {
gpus, err := app.ListNvidiaGPUs()
if err != nil || len(gpus) == 0 {
parts = append(parts, "=== GPU ===\nNo NVIDIA GPUs detected or driver not loaded.")
} else {
var indices []int
sizeMB := 0
for _, g := range gpus {
indices = append(indices, g.Index)
if sizeMB == 0 || g.MemoryMB < sizeMB {
sizeMB = g.MemoryMB
}
}
if sizeMB == 0 {
sizeMB = 64
}
r, err := app.RunNvidiaAcceptancePackWithOptions(context.Background(), "", durationSec, sizeMB, indices)
body := r.Body
if err != nil {
body += "\nERROR: " + err.Error()
}
parts = append(parts, "=== GPU ===\n"+body)
// Map hcMode (0=Quick,1=Standard,2=Express) to DCGM level (1,2,3)
diagLevel := durationIdx + 1
r, err := app.RunNvidiaAcceptancePackWithOptions(context.Background(), "", diagLevel, nil)
body := r.Body
if err != nil {
body += "\nERROR: " + err.Error()
}
parts = append(parts, "=== GPU (DCGM) ===\n"+body)
}
}
if sel[hcMemory] {