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

- 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>
2026-03-26 23:08:12 +03:00
parent 967455194c
commit eea98e6d76
12 changed files with 121 additions and 170 deletions
--- a/audit/internal/tui/screen_nvidia_sat.go
+++ b/audit/internal/tui/screen_nvidia_sat.go
@@ -5,61 +5,33 @@ import (
 	"fmt"
 	"strings"

-	"bee/audit/internal/platform"
-
 	tea "github.com/charmbracelet/bubbletea"
 )

-var nvidiaDurationOptions = []struct {
+var nvidiaDCGMOptions = []struct {
 	label   string
-	seconds int
+	level   int
+	note    string
 }{
-	{"10 minutes", 600},
-	{"1 hour", 3600},
-	{"8 hours", 28800},
-	{"24 hours", 86400},
+	{"Level 1 — Quick", 1, "~1 min, configuration check"},
+	{"Level 2 — Medium", 2, "~2 min, memory test"},
+	{"Level 3 — Targeted stress", 3, "~10 min, SM + memory + PCIe [recommended]"},
+	{"Level 4 — Extended stress", 4, "~30 min, extended burn-in"},
 }

-// enterNvidiaSATSetup resets the setup screen and starts loading GPU list.
+// enterNvidiaSATSetup resets and shows the DCGM level selection screen.
 func (m model) enterNvidiaSATSetup() (tea.Model, tea.Cmd) {
 	m.screen = screenNvidiaSATSetup
-	m.nvidiaGPUs = nil
-	m.nvidiaGPUSel = nil
-	m.nvidiaDurIdx = 0
-	m.nvidiaSATCursor = 0
-	m.busy = true
-	m.busyTitle = "NVIDIA SAT"
-	return m, func() tea.Msg {
-		gpus, err := m.app.ListNvidiaGPUs()
-		return nvidiaGPUsMsg{gpus: gpus, err: err}
-	}
-}
-
-// handleNvidiaGPUsMsg processes the GPU list response.
-func (m model) handleNvidiaGPUsMsg(msg nvidiaGPUsMsg) (tea.Model, tea.Cmd) {
+	m.nvidiaDurIdx = 2 // default: Level 3
+	m.nvidiaSATCursor = 2
 	m.busy = false
-	m.busyTitle = ""
-	if msg.err != nil {
-		m.title = "NVIDIA SAT"
-		m.body = fmt.Sprintf("Failed to list GPUs: %v", msg.err)
-		m.prevScreen = screenHealthCheck
-		m.screen = screenOutput
-		return m, nil
-	}
-	m.nvidiaGPUs = msg.gpus
-	m.nvidiaGPUSel = make([]bool, len(msg.gpus))
-	for i := range m.nvidiaGPUSel {
-		m.nvidiaGPUSel[i] = true // all selected by default
-	}
-	m.nvidiaSATCursor = 0
 	return m, nil
 }

-// updateNvidiaSATSetup handles keys on the setup screen.
+// updateNvidiaSATSetup handles keys on the DCGM setup screen.
 func (m model) updateNvidiaSATSetup(msg tea.KeyMsg) (tea.Model, tea.Cmd) {
-	numDur := len(nvidiaDurationOptions)
-	numGPU := len(m.nvidiaGPUs)
-	totalItems := numDur + numGPU + 2 // +2: Start, Cancel
+	numOpts := len(nvidiaDCGMOptions)
+	totalItems := numOpts + 2 // +2: Start, Cancel
 	switch msg.String() {
 	case "up", "k":
 		if m.nvidiaSATCursor > 0 {
@@ -69,23 +41,12 @@ func (m model) updateNvidiaSATSetup(msg tea.KeyMsg) (tea.Model, tea.Cmd) {
 		if m.nvidiaSATCursor < totalItems-1 {
 			m.nvidiaSATCursor++
 		}
-	case " ":
-		switch {
-		case m.nvidiaSATCursor < numDur:
-			m.nvidiaDurIdx = m.nvidiaSATCursor
-		case m.nvidiaSATCursor < numDur+numGPU:
-			i := m.nvidiaSATCursor - numDur
-			m.nvidiaGPUSel[i] = !m.nvidiaGPUSel[i]
-		}
-	case "enter":
-		startIdx := numDur + numGPU
+	case " ", "enter":
+		startIdx := numOpts
 		cancelIdx := startIdx + 1
 		switch {
-		case m.nvidiaSATCursor < numDur:
+		case m.nvidiaSATCursor < numOpts:
 			m.nvidiaDurIdx = m.nvidiaSATCursor
-		case m.nvidiaSATCursor < startIdx:
-			i := m.nvidiaSATCursor - numDur
-			m.nvidiaGPUSel[i] = !m.nvidiaGPUSel[i]
 		case m.nvidiaSATCursor == startIdx:
 			return m.startNvidiaSAT()
 		case m.nvidiaSATCursor == cancelIdx:
@@ -101,34 +62,9 @@ func (m model) updateNvidiaSATSetup(msg tea.KeyMsg) (tea.Model, tea.Cmd) {
 	return m, nil
 }

-// startNvidiaSAT launches the NVIDIA acceptance pack.
+// startNvidiaSAT launches the DCGM diagnostic.
 func (m model) startNvidiaSAT() (tea.Model, tea.Cmd) {
-	var selectedGPUs []platform.NvidiaGPU
-	for i, sel := range m.nvidiaGPUSel {
-		if sel {
-			selectedGPUs = append(selectedGPUs, m.nvidiaGPUs[i])
-		}
-	}
-	if len(selectedGPUs) == 0 {
-		selectedGPUs = m.nvidiaGPUs // fallback: use all if none explicitly selected
-	}
-
-	sizeMB := 0
-	for _, g := range selectedGPUs {
-		if sizeMB == 0 || g.MemoryMB < sizeMB {
-			sizeMB = g.MemoryMB
-		}
-	}
-	if sizeMB == 0 {
-		sizeMB = 64
-	}
-
-	var gpuIndices []int
-	for _, g := range selectedGPUs {
-		gpuIndices = append(gpuIndices, g.Index)
-	}
-
-	durationSec := nvidiaDurationOptions[m.nvidiaDurIdx].seconds
+	diagLevel := nvidiaDCGMOptions[m.nvidiaDurIdx].level

 	ctx, cancel := context.WithCancel(context.Background())
 	m.nvidiaSATCancel = cancel
@@ -137,7 +73,7 @@ func (m model) startNvidiaSAT() (tea.Model, tea.Cmd) {
 	m.nvidiaSATCursor = 0

 	satCmd := func() tea.Msg {
-		result, err := m.app.RunNvidiaAcceptancePackWithOptions(ctx, "", durationSec, sizeMB, gpuIndices)
+		result, err := m.app.RunNvidiaAcceptancePackWithOptions(ctx, "", diagLevel, nil)
 		return nvidiaSATDoneMsg{title: result.Title, body: result.Body, err: err}
 	}

@@ -161,13 +97,13 @@ func (m model) updateNvidiaSATRunning(msg tea.KeyMsg) (tea.Model, tea.Cmd) {
 	return m, nil
 }

-// renderNvidiaSATSetup renders the setup screen.
+// renderNvidiaSATSetup renders the DCGM level selection screen.
 func renderNvidiaSATSetup(m model) string {
 	var b strings.Builder
-	fmt.Fprintln(&b, "NVIDIA SAT")
+	fmt.Fprintln(&b, "NVIDIA Diagnostics (DCGM)")
 	fmt.Fprintln(&b)
-	fmt.Fprintln(&b, "Duration:")
-	for i, opt := range nvidiaDurationOptions {
+	fmt.Fprintln(&b, "Diagnostic level:")
+	for i, opt := range nvidiaDCGMOptions {
 		radio := "( )"
 		if i == m.nvidiaDurIdx {
 			radio = "(*)"
@@ -176,27 +112,10 @@ func renderNvidiaSATSetup(m model) string {
 		if m.nvidiaSATCursor == i {
 			prefix = "> "
 		}
-		fmt.Fprintf(&b, "%s%s %s\n", prefix, radio, opt.label)
+		fmt.Fprintf(&b, "%s%s %s  (%s)\n", prefix, radio, opt.label, opt.note)
 	}
 	fmt.Fprintln(&b)
-	if len(m.nvidiaGPUs) == 0 {
-		fmt.Fprintln(&b, "GPUs: (none detected)")
-	} else {
-		fmt.Fprintln(&b, "GPUs:")
-		for i, gpu := range m.nvidiaGPUs {
-			check := "[ ]"
-			if m.nvidiaGPUSel[i] {
-				check = "[x]"
-			}
-			prefix := "  "
-			if m.nvidiaSATCursor == len(nvidiaDurationOptions)+i {
-				prefix = "> "
-			}
-			fmt.Fprintf(&b, "%s%s %d: %s (%d MB)\n", prefix, check, gpu.Index, gpu.Name, gpu.MemoryMB)
-		}
-	}
-	fmt.Fprintln(&b)
-	startIdx := len(nvidiaDurationOptions) + len(m.nvidiaGPUs)
+	startIdx := len(nvidiaDCGMOptions)
 	startPfx := "  "
 	cancelPfx := "  "
 	if m.nvidiaSATCursor == startIdx {
@@ -208,11 +127,11 @@ func renderNvidiaSATSetup(m model) string {
 	fmt.Fprintf(&b, "%sStart\n", startPfx)
 	fmt.Fprintf(&b, "%sCancel\n", cancelPfx)
 	fmt.Fprintln(&b)
-	b.WriteString("[↑/↓] move  [space] toggle  [enter] select  [esc] cancel\n")
+	b.WriteString("[↑/↓] move  [space/enter] select  [esc] cancel\n")
 	return b.String()
 }

 // renderNvidiaSATRunning renders the running screen.
 func renderNvidiaSATRunning() string {
-	return "NVIDIA SAT\n\nTest is running...\n\n[a] Abort test  [ctrl+c] quit\n"
+	return "NVIDIA Diagnostics (DCGM)\n\nTest is running...\n\n[a] Abort test  [ctrl+c] quit\n"
 }