Add real-data duration estimates to validate tab profiles

- Add SATEstimated* constants to sat.go derived from _v8 production logs,
  with a rule to recalculate them whenever the script changes
- Extend validateInventory with NvidiaGPUCount to make estimates GPU-aware
- Update all validate card duration strings: CPU, memory, storage, NVIDIA GPU,
  targeted stress/power, pulse test, NCCL, nvbandwidth
- Fix nvbandwidth description ("intended to stay short" → actual ~45 min)
- Top-level profile labels show computed total including GPU count

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

audit/internal/platform/install_to_ram.go

@@ -140,26 +140,56 @@ func (s *System) RunInstallToRAM(ctx context.Context, logFunc func(string)) (ret
 	}
 
 	squashfsFiles, err := filepath.Glob("/run/live/medium/live/*.squashfs")
-	if err != nil || len(squashfsFiles) == 0 {
-		return fmt.Errorf("no squashfs files found in /run/live/medium/live/")
-	}
-
-	free := freeMemBytes()
-	var needed int64
-	for _, sf := range squashfsFiles {
-		fi, err2 := os.Stat(sf)
-		if err2 != nil {
-			return fmt.Errorf("stat %s: %v", sf, err2)
-		}
-		needed += fi.Size()
-	}
-	const headroom = 256 * 1024 * 1024
-	if free > 0 && needed+headroom > free {
-		return fmt.Errorf("insufficient RAM: need %s, available %s",
-			humanBytes(needed+headroom), humanBytes(free))
-	}
+	sourceAvailable := err == nil && len(squashfsFiles) > 0
 
 	dstDir := installToRAMDir
+
+	// If the source medium is unavailable, check whether a previous run already
+	// produced a complete copy in RAM. If so, skip the copy phase and proceed
+	// directly to the loop-rebind / bind-mount steps.
+	if !sourceAvailable {
+		copiedFiles, _ := filepath.Glob(filepath.Join(dstDir, "*.squashfs"))
+		if len(copiedFiles) > 0 {
+			log("Source medium not available, but a previous RAM copy was found — resuming from existing copy.")
+			// Proceed to rebind with the already-copied files.
+			for _, dst := range copiedFiles {
+				base := filepath.Base(dst)
+				// Re-associate the loop device that was originally backed by the
+				// source file (now gone); find it by the old source path pattern.
+				srcGuess := "/run/live/medium/live/" + base
+				loopDev, lerr := findLoopForFile(srcGuess)
+				if lerr != nil {
+					log(fmt.Sprintf("Loop device for %s not found (%v) — skipping re-association.", base, lerr))
+					continue
+				}
+				if rerr := reassociateLoopDevice(loopDev, dst); rerr != nil {
+					log(fmt.Sprintf("Warning: could not re-associate %s → %s: %v", loopDev, dst, rerr))
+				} else {
+					log(fmt.Sprintf("Loop device %s now backed by RAM copy.", loopDev))
+				}
+			}
+			goto bindMedium
+		}
+		return fmt.Errorf("no squashfs files found in /run/live/medium/live/ and no prior RAM copy in %s — reconnect the installation medium and retry", dstDir)
+	}
+
+	{
+		free := freeMemBytes()
+		var needed int64
+		for _, sf := range squashfsFiles {
+			fi, err2 := os.Stat(sf)
+			if err2 != nil {
+				return fmt.Errorf("stat %s: %v", sf, err2)
+			}
+			needed += fi.Size()
+		}
+		const headroom = 256 * 1024 * 1024
+		if free > 0 && needed+headroom > free {
+			return fmt.Errorf("insufficient RAM: need %s, available %s",
+				humanBytes(needed+headroom), humanBytes(free))
+		}
+	}
+
 	if state.CopyPresent {
 		log("Removing stale partial RAM copy before retry...")
 	}
@@ -199,6 +229,7 @@ func (s *System) RunInstallToRAM(ctx context.Context, logFunc func(string)) (ret
 		}
 	}
 
+bindMedium:
 	log("Copying remaining medium files...")
 	if err := cpDir(ctx, "/run/live/medium", dstDir, log); err != nil {
 		log(fmt.Sprintf("Warning: partial copy: %v", err))

audit/internal/platform/live_metrics.go

@@ -18,11 +18,19 @@ type LiveMetricSample struct {
 	Fans       []FanReading   `json:"fans"`
 	Temps      []TempReading  `json:"temps"`
 	PowerW     float64        `json:"power_w"`
+	PSUs       []PSUReading   `json:"psus,omitempty"`
 	CPULoadPct float64        `json:"cpu_load_pct"`
 	MemLoadPct float64        `json:"mem_load_pct"`
 	GPUs       []GPUMetricRow `json:"gpus"`
 }
 
+// PSUReading is a per-slot power supply input power reading.
+type PSUReading struct {
+	Slot   int     `json:"slot"`
+	Name   string  `json:"name"`
+	PowerW float64 `json:"power_w"`
+}
+
 // TempReading is a named temperature sensor value.
 type TempReading struct {
 	Name    string  `json:"name"`
@@ -57,6 +65,9 @@ func SampleLiveMetrics() LiveMetricSample {
 	// System power — returns 0 if unavailable
 	s.PowerW = sampleSystemPower()
 
+	// Per-PSU power — populated when IPMI SDR has Power Supply entities with Watt readings
+	s.PSUs = samplePSUPower()
+
 	// CPU load — from /proc/stat
 	s.CPULoadPct = sampleCPULoadPct()
 
@@ -326,3 +337,65 @@ func compactAmbientTempName(chip, name string) string {
 	}
 	return chip + " / " + name
 }
+
+// samplePSUPower reads per-PSU input power via IPMI SDR.
+// It parses `ipmitool sdr elist full` output looking for Power Supply entity
+// sensors (entity ID "10.N") that report a value in Watts.
+// Returns nil when IPMI is unavailable or no PSU Watt sensors exist.
+func samplePSUPower() []PSUReading {
+	out, err := exec.Command("ipmitool", "sdr", "elist", "full").Output()
+	if err != nil || len(out) == 0 {
+		return nil
+	}
+	// map slot → reading (keep highest-watt value per slot in case of duplicates)
+	type entry struct {
+		name   string
+		powerW float64
+	}
+	bySlot := map[int]entry{}
+	for _, line := range strings.Split(string(out), "\n") {
+		parts := strings.Split(line, "|")
+		if len(parts) < 5 {
+			continue
+		}
+		entityID := strings.TrimSpace(parts[3]) // e.g. "10.1"
+		if !strings.HasPrefix(entityID, "10.") {
+			continue // not a Power Supply entity
+		}
+		slotStr := strings.TrimPrefix(entityID, "10.")
+		slot, err := strconv.Atoi(slotStr)
+		if err != nil {
+			continue
+		}
+		valueField := strings.TrimSpace(parts[4]) // e.g. "740.00 Watts"
+		if !strings.Contains(strings.ToLower(valueField), "watts") {
+			continue
+		}
+		valueFields := strings.Fields(valueField)
+		if len(valueFields) < 2 {
+			continue
+		}
+		w, err := strconv.ParseFloat(valueFields[0], 64)
+		if err != nil || w <= 0 {
+			continue
+		}
+		sensorName := strings.TrimSpace(parts[0])
+		if existing, ok := bySlot[slot]; !ok || w > existing.powerW {
+			bySlot[slot] = entry{name: sensorName, powerW: w}
+		}
+	}
+	if len(bySlot) == 0 {
+		return nil
+	}
+	slots := make([]int, 0, len(bySlot))
+	for s := range bySlot {
+		slots = append(slots, s)
+	}
+	sort.Ints(slots)
+	psus := make([]PSUReading, 0, len(slots))
+	for _, s := range slots {
+		e := bySlot[s]
+		psus = append(psus, PSUReading{Slot: s, Name: e.name, PowerW: e.powerW})
+	}
+	return psus
+}

audit/internal/platform/sat.go

@@ -20,6 +20,54 @@ import (
 	"time"
 )
 
+// Estimated wall-clock durations for each SAT/validate test, derived from real
+// production logs in _benchmark/_v8/.
+//
+// Rule: whenever the commands, timeout parameters, or number of sub-jobs inside
+// the corresponding Run*Pack function change, re-measure the wall-clock duration
+// from actual task logs and update the matching constant here.
+//
+// Sources:
+//   - SATEstimatedCPUValidateSec:                 xFusion v8.6 — 62 s
+//   - SATEstimatedMemoryValidateSec:               xFusion v8.6 — 68 s
+//   - SATEstimatedNvidiaGPUValidatePerGPUSec:      xFusion v8.6/v8.22 — 77–87 s/GPU
+//   - SATEstimatedNvidiaGPUStressPerGPUSec:        xFusion v8.6/v8.22 — 444–448 s/GPU
+//   - SATEstimatedNvidiaTargetedStressPerGPUSec:   xFusion v8.6/v8.22 — 347–348 s/GPU (300 s default + overhead)
+//   - SATEstimatedNvidiaTargetedPowerPerGPUSec:    MSI v8.22 / xFusion v8.6 — 346–351 s/GPU
+//   - SATEstimatedNvidiaPulseTestSec:              xFusion v8.6 — 4 926 s / 8 GPU (all simultaneous)
+//   - SATEstimatedNvidiaInterconnectSec:           xFusion v8.6/v8.22 — 210–384 s / 8 GPU (all simultaneous)
+//   - SATEstimatedNvidiaBandwidthSec:              xFusion v8.6/v8.22 — 2 664–2 688 s / 8 GPU (all simultaneous)
+const (
+	// CPU stress: stress-ng 60 s + lscpu/sensors overhead.
+	SATEstimatedCPUValidateSec = 65
+	// CPU stress: stress-ng 1800 s (stress mode default).
+	SATEstimatedCPUStressSec = 1800
+
+	// RAM: memtester 256 MB / 1 pass.
+	SATEstimatedMemoryValidateSec = 70
+	// RAM: memtester 512 MB / 1 pass (extrapolated from validate timing, linear with size).
+	SATEstimatedMemoryStressSec = 140
+
+	// NVIDIA dcgmi diag Level 2 (medium), per GPU, sequential.
+	SATEstimatedNvidiaGPUValidatePerGPUSec = 85
+	// NVIDIA dcgmi diag Level 3 (targeted stress), per GPU, sequential.
+	SATEstimatedNvidiaGPUStressPerGPUSec = 450
+
+	// NVIDIA dcgmi targeted_stress 300 s + overhead, per GPU, sequential.
+	SATEstimatedNvidiaTargetedStressPerGPUSec = 350
+	// NVIDIA dcgmi targeted_power 300 s + overhead, per GPU, sequential.
+	SATEstimatedNvidiaTargetedPowerPerGPUSec = 350
+
+	// NVIDIA dcgmi pulse_test, all GPUs simultaneously (not per-GPU).
+	SATEstimatedNvidiaPulseTestSec = 5000
+
+	// NCCL all_reduce_perf, all GPUs simultaneously.
+	SATEstimatedNvidiaInterconnectSec = 300
+	// nvbandwidth, all GPUs simultaneously. Tool runs all built-in tests
+	// without a user-configurable time limit; duration is determined by nvbandwidth itself.
+	SATEstimatedNvidiaBandwidthSec = 2700
+)
+
 var (
 	satExecCommand  = exec.Command
 	satLookPath     = exec.LookPath

audit/internal/webui/charts_svg.go

@@ -462,6 +462,127 @@ func synthesizeChartTimes(times []time.Time, count int) []time.Time {
 	return out
 }
 
+// renderStackedMetricChartSVG renders a stacked area chart where each dataset
+// is visually "stacked" on top of the previous one. Intended for multi-PSU
+// power charts where the filled area of each PSU shows its individual
+// contribution and the total height equals the combined draw.
+func renderStackedMetricChartSVG(title string, labels []string, times []time.Time, datasets [][]float64, names []string, yMax *float64, canvasHeight int, timeline []chartTimelineSegment) ([]byte, error) {
+	pointCount := len(labels)
+	if len(times) > pointCount {
+		pointCount = len(times)
+	}
+	if pointCount == 0 {
+		pointCount = 1
+		labels = []string{""}
+		times = []time.Time{{}}
+	}
+	if len(labels) < pointCount {
+		padded := make([]string, pointCount)
+		copy(padded, labels)
+		labels = padded
+	}
+	if len(times) < pointCount {
+		times = synthesizeChartTimes(times, pointCount)
+	}
+	for i := range datasets {
+		if len(datasets[i]) == 0 {
+			datasets[i] = make([]float64, pointCount)
+		}
+	}
+
+	times, datasets = downsampleTimeSeries(times, datasets, 1400)
+	pointCount = len(times)
+
+	// Build cumulative sums per time point.
+	cumulative := make([][]float64, len(datasets)+1)
+	for i := range cumulative {
+		cumulative[i] = make([]float64, pointCount)
+	}
+	for i, ds := range datasets {
+		for j, v := range ds {
+			cumulative[i+1][j] = cumulative[i][j] + v
+		}
+	}
+
+	// Scale is based on the total (top cumulative row).
+	total := cumulative[len(cumulative)-1]
+	yMin := floatPtr(0)
+	if yMax == nil {
+		yMax = autoMax120(total)
+	}
+	scale := singleAxisChartScale([][]float64{total}, yMin, yMax)
+
+	legendItems := make([]metricChartSeries, len(datasets))
+	for i, name := range names {
+		color := metricChartPalette[i%len(metricChartPalette)]
+		legendItems[i] = metricChartSeries{Name: name, Color: color, Values: datasets[i]}
+	}
+
+	// Stats label from totals.
+	statsLabel := chartStatsLabel([][]float64{total})
+
+	layout := singleAxisChartLayout(canvasHeight, len(legendItems))
+	start, end := chartTimeBounds(times)
+
+	var b strings.Builder
+	writeSVGOpen(&b, layout.Width, layout.Height)
+	writeChartFrame(&b, title, statsLabel, layout.Width, layout.Height)
+	writeTimelineIdleSpans(&b, layout, start, end, timeline)
+	writeVerticalGrid(&b, layout, times, pointCount, 8)
+	writeHorizontalGrid(&b, layout, scale)
+	writeTimelineBoundaries(&b, layout, start, end, timeline)
+	writePlotBorder(&b, layout)
+	writeSingleAxisY(&b, layout, scale)
+	writeXAxisLabels(&b, layout, times, labels, start, end, 8)
+
+	// Draw stacked areas from top to bottom so lower layers are visible.
+	for i := len(datasets) - 1; i >= 0; i-- {
+		writeStackedArea(&b, layout, times, start, end, cumulative[i], cumulative[i+1], scale, legendItems[i].Color)
+	}
+	// Draw border polylines on top.
+	for i := len(datasets) - 1; i >= 0; i-- {
+		writeSeriesPolyline(&b, layout, times, start, end, cumulative[i+1], scale, legendItems[i].Color)
+	}
+
+	writeLegend(&b, layout, legendItems)
+	writeSVGClose(&b)
+	return []byte(b.String()), nil
+}
+
+// writeStackedArea draws a filled polygon between two cumulative value arrays
+// (baseline and top), using the given color at 55% opacity.
+func writeStackedArea(b *strings.Builder, layout chartLayout, times []time.Time, start, end time.Time, baseline, top []float64, scale chartScale, color string) {
+	n := len(top)
+	if n == 0 {
+		return
+	}
+	if len(baseline) < n {
+		baseline = make([]float64, n)
+	}
+
+	// Forward path along top values, then backward along baseline values.
+	var points strings.Builder
+	for i := 0; i < n; i++ {
+		x := chartXForTime(chartPointTime(times, i), start, end, layout.PlotLeft, layout.PlotRight)
+		y := chartYForValue(valueClamp(top[i], scale), scale, layout.PlotTop, layout.PlotBottom)
+		if i > 0 {
+			points.WriteByte(' ')
+		}
+		points.WriteString(strconv.FormatFloat(x, 'f', 1, 64))
+		points.WriteByte(',')
+		points.WriteString(strconv.FormatFloat(y, 'f', 1, 64))
+	}
+	for i := n - 1; i >= 0; i-- {
+		x := chartXForTime(chartPointTime(times, i), start, end, layout.PlotLeft, layout.PlotRight)
+		y := chartYForValue(valueClamp(baseline[i], scale), scale, layout.PlotTop, layout.PlotBottom)
+		points.WriteByte(' ')
+		points.WriteString(strconv.FormatFloat(x, 'f', 1, 64))
+		points.WriteByte(',')
+		points.WriteString(strconv.FormatFloat(y, 'f', 1, 64))
+	}
+	fmt.Fprintf(b, `<polygon points="%s" fill="%s" fill-opacity="0.55" stroke="none"/>`+"\n", points.String(), color)
+}
+
 func writeSVGOpen(b *strings.Builder, width, height int) {
 	fmt.Fprintf(b, `<svg xmlns="http://www.w3.org/2000/svg" width="%d" height="%d" viewBox="0 0 %d %d">`+"\n", width, height, width, height)
 }

audit/internal/webui/pages.go

@@ -1378,15 +1378,64 @@ setInterval(loadMetricsLayout, 5000);
 // ── Validate (Acceptance Tests) ───────────────────────────────────────────────
 
 type validateInventory struct {
-	CPU     string
-	Memory  string
-	Storage string
-	NVIDIA  string
-	AMD     string
+	CPU           string
+	Memory        string
+	Storage       string
+	NVIDIA        string
+	AMD           string
+	NvidiaGPUCount int
+	AMDGPUCount    int
+}
+
+// validateFmtDur formats a duration in seconds as a human-readable "~N min" or "~N s" string.
+func validateFmtDur(secs int) string {
+	if secs < 120 {
+		return fmt.Sprintf("~%d s", secs)
+	}
+	mins := (secs + 29) / 60
+	return fmt.Sprintf("~%d min", mins)
+}
+
+// validateTotalValidateSec returns the estimated wall-clock duration of
+// "Validate one by one" in Validate mode for n NVIDIA GPUs.
+func validateTotalValidateSec(n int) int {
+	if n < 0 {
+		n = 0
+	}
+	total := platform.SATEstimatedCPUValidateSec +
+		platform.SATEstimatedMemoryValidateSec +
+		n*platform.SATEstimatedNvidiaGPUValidatePerGPUSec +
+		platform.SATEstimatedNvidiaInterconnectSec +
+		platform.SATEstimatedNvidiaBandwidthSec
+	return total
+}
+
+// validateTotalStressSec returns the estimated wall-clock duration of
+// "Validate one by one" in Stress mode for n NVIDIA GPUs.
+func validateTotalStressSec(n int) int {
+	if n < 0 {
+		n = 0
+	}
+	total := platform.SATEstimatedCPUStressSec +
+		platform.SATEstimatedMemoryStressSec +
+		n*platform.SATEstimatedNvidiaGPUStressPerGPUSec +
+		n*platform.SATEstimatedNvidiaTargetedStressPerGPUSec +
+		n*platform.SATEstimatedNvidiaTargetedPowerPerGPUSec +
+		platform.SATEstimatedNvidiaPulseTestSec +
+		platform.SATEstimatedNvidiaInterconnectSec +
+		platform.SATEstimatedNvidiaBandwidthSec
+	return total
 }
 
 func renderValidate(opts HandlerOptions) string {
 	inv := loadValidateInventory(opts)
+	n := inv.NvidiaGPUCount
+	validateTotalStr := validateFmtDur(validateTotalValidateSec(n))
+	stressTotalStr := validateFmtDur(validateTotalStressSec(n))
+	gpuNote := ""
+	if n > 0 {
+		gpuNote = fmt.Sprintf(" (%d GPU)", n)
+	}
 	return `<div class="alert alert-info" style="margin-bottom:16px"><strong>Non-destructive:</strong> Validate tests collect diagnostics only. They do not write to disks, do not run sustained load, and do not increment hardware wear counters.</div>
 <p style="color:var(--muted);font-size:13px;margin-bottom:16px">Tasks continue in the background — view progress in <a href="/tasks">Tasks</a>.</p>
 
@@ -1396,10 +1445,10 @@ func renderValidate(opts HandlerOptions) string {
 	    <div class="validate-profile-col">
 	      <div class="form-row" style="margin:12px 0 0"><label>Mode</label></div>
 	      <label class="cb-row"><input type="radio" name="sat-mode" id="sat-mode-validate" value="validate" checked onchange="satModeChanged()"><span>Validate — quick non-destructive check</span></label>
-	      <label class="cb-row"><input type="radio" name="sat-mode" id="sat-mode-stress" value="stress" onchange="satModeChanged()"><span>Stress — thorough load test (~30–60 min)</span></label>
+	      <label class="cb-row"><input type="radio" name="sat-mode" id="sat-mode-stress" value="stress" onchange="satModeChanged()"><span>Stress — thorough load test (` + stressTotalStr + gpuNote + `)</span></label>
 	    </div>
 	    <div class="validate-profile-col validate-profile-action">
-	      <p style="color:var(--muted);font-size:12px;margin:0 0 10px">Runs validate modules sequentially with the selected cycle count and mode. Validate is quick (~5–15 min total); Stress is thorough (~30–60 min total).</p>
+	      <p style="color:var(--muted);font-size:12px;margin:0 0 10px">Runs validate modules sequentially. Validate: ` + validateTotalStr + gpuNote + `; Stress: ` + stressTotalStr + gpuNote + `. Estimates are based on real log data and scale with GPU count.</p>
 	      <button type="button" class="btn btn-primary" onclick="runAllSAT()">Validate one by one</button>
 	      <div style="margin-top:12px">
 	        <span id="sat-all-status" style="font-size:12px;color:var(--muted)"></span>
@@ -1413,19 +1462,19 @@ func renderValidate(opts HandlerOptions) string {
 		inv.CPU,
 		`Collects CPU inventory and temperatures, then runs a bounded CPU stress pass.`,
 		`<code>lscpu</code>, <code>sensors</code>, <code>stress-ng</code>`,
-		`60s in Validate, 30 min in Stress.`,
+		validateFmtDur(platform.SATEstimatedCPUValidateSec)+` in Validate (stress-ng 60 s). `+validateFmtDur(platform.SATEstimatedCPUStressSec)+` in Stress (stress-ng 30 min).`,
 	)) +
 		renderSATCard("memory", "Memory", "runSAT('memory')", "", renderValidateCardBody(
 			inv.Memory,
 			`Runs a RAM validation pass and records memory state around the test.`,
 			`<code>free</code>, <code>memtester</code>`,
-			`256 MB / 1 pass in Validate, 512 MB / 1 pass in Stress.`,
+			validateFmtDur(platform.SATEstimatedMemoryValidateSec)+` in Validate (256 MB × 1 pass). `+validateFmtDur(platform.SATEstimatedMemoryStressSec)+` in Stress (512 MB × 1 pass).`,
 		)) +
 		renderSATCard("storage", "Storage", "runSAT('storage')", "", renderValidateCardBody(
 			inv.Storage,
 			`Scans all storage devices and runs the matching health or self-test path for each device type.`,
 			`<code>lsblk</code>; NVMe: <code>nvme</code>; SATA/SAS: <code>smartctl</code>`,
-			`Short self-test in Validate, extended self-test in Stress.`,
+			`Seconds in Validate (NVMe: instant device query; SATA/SAS: short self-test). Up to ~1 h per device in Stress (extended self-test, device-dependent).`,
 		)) +
 		`</div>
 <div style="height:1px;background:var(--border);margin:16px 0"></div>
@@ -1450,14 +1499,33 @@ func renderValidate(opts HandlerOptions) string {
 		inv.NVIDIA,
 		`Runs NVIDIA diagnostics and board inventory checks.`,
 		`<code>nvidia-smi</code>, <code>dmidecode</code>, <code>dcgmi diag</code>`,
-		`Level 2 in Validate, Level 3 in Stress. Runs one GPU at a time on the selected NVIDIA GPUs.`,
+		func() string {
+			perV := platform.SATEstimatedNvidiaGPUValidatePerGPUSec
+			perS := platform.SATEstimatedNvidiaGPUStressPerGPUSec
+			if n > 0 {
+				return fmt.Sprintf("Validate: %s/GPU × %d = %s (Level 2, sequential). Stress: %s/GPU × %d = %s (Level 3, sequential).",
+					validateFmtDur(perV), n, validateFmtDur(perV*n),
+					validateFmtDur(perS), n, validateFmtDur(perS*n))
+			}
+			return fmt.Sprintf("Validate: %s/GPU (Level 2, sequential). Stress: %s/GPU (Level 3, sequential).",
+				validateFmtDur(perV), validateFmtDur(perS))
+		}(),
 	)) +
 		`<div id="sat-card-nvidia-targeted-stress">` +
 		renderSATCard("nvidia-targeted-stress", "NVIDIA GPU Targeted Stress", "runNvidiaValidateSet('nvidia-targeted-stress')", "", renderValidateCardBody(
 			inv.NVIDIA,
 			`Runs a controlled NVIDIA DCGM load to check stability under moderate stress.`,
 			`<code>dcgmi diag targeted_stress</code>`,
-			`Skipped in Validate mode. Runs after dcgmi diag in Stress mode. Runs one GPU at a time on the selected NVIDIA GPUs.<p id="sat-ts-mode-hint" style="color:var(--warn-fg);font-size:12px;margin:8px 0 0">Only runs in Stress mode. Switch mode above to enable in Run All.</p>`,
+			func() string {
+				per := platform.SATEstimatedNvidiaTargetedStressPerGPUSec
+				s := "Skipped in Validate. "
+				if n > 0 {
+					s += fmt.Sprintf("Stress: %s/GPU × %d = %s sequential.", validateFmtDur(per), n, validateFmtDur(per*n))
+				} else {
+					s += fmt.Sprintf("Stress: %s/GPU sequential.", validateFmtDur(per))
+				}
+				return s + `<p id="sat-ts-mode-hint" style="color:var(--warn-fg);font-size:12px;margin:8px 0 0">Only runs in Stress mode. Switch mode above to enable in Run All.</p>`
+			}(),
 		)) +
 		`</div>` +
 		`<div id="sat-card-nvidia-targeted-power">` +
@@ -1465,7 +1533,16 @@ func renderValidate(opts HandlerOptions) string {
 			inv.NVIDIA,
 			`Checks that the GPU can sustain its declared power delivery envelope. Pass/fail determined by DCGM.`,
 			`<code>dcgmi diag targeted_power</code>`,
-			`Skipped in Validate mode. Runs in Stress mode only. Runs one GPU at a time.<p id="sat-tp-mode-hint" style="color:var(--warn-fg);font-size:12px;margin:8px 0 0">Only runs in Stress mode. Switch mode above to enable in Run All.</p>`,
+			func() string {
+				per := platform.SATEstimatedNvidiaTargetedPowerPerGPUSec
+				s := "Skipped in Validate. "
+				if n > 0 {
+					s += fmt.Sprintf("Stress: %s/GPU × %d = %s sequential.", validateFmtDur(per), n, validateFmtDur(per*n))
+				} else {
+					s += fmt.Sprintf("Stress: %s/GPU sequential.", validateFmtDur(per))
+				}
+				return s + `<p id="sat-tp-mode-hint" style="color:var(--warn-fg);font-size:12px;margin:8px 0 0">Only runs in Stress mode. Switch mode above to enable in Run All.</p>`
+			}(),
 		)) +
 		`</div>` +
 		`<div id="sat-card-nvidia-pulse">` +
@@ -1473,7 +1550,7 @@ func renderValidate(opts HandlerOptions) string {
 			inv.NVIDIA,
 			`Tests power supply transient response by pulsing all GPUs simultaneously between idle and full load. Synchronous pulses across all GPUs create worst-case PSU load spikes — running per-GPU would miss PSU-level failures.`,
 			`<code>dcgmi diag pulse_test</code>`,
-			`Skipped in Validate mode. Runs in Stress mode only. Runs all selected GPUs simultaneously — synchronous pulsing is required to stress the PSU.<p id="sat-pt-mode-hint" style="color:var(--warn-fg);font-size:12px;margin:8px 0 0">Only runs in Stress mode. Switch mode above to enable in Run All.</p>`,
+			`Skipped in Validate. Stress: `+validateFmtDur(platform.SATEstimatedNvidiaPulseTestSec)+` (all GPUs simultaneously; measured on 8-GPU system).`+`<p id="sat-pt-mode-hint" style="color:var(--warn-fg);font-size:12px;margin:8px 0 0">Only runs in Stress mode. Switch mode above to enable in Run All.</p>`,
 		)) +
 		`</div>` +
 		`<div id="sat-card-nvidia-interconnect">` +
@@ -1481,7 +1558,7 @@ func renderValidate(opts HandlerOptions) string {
 			inv.NVIDIA,
 			`Verifies NVLink/NVSwitch fabric bandwidth using NCCL all_reduce_perf across all selected GPUs. Pass/fail based on achieved bandwidth vs. theoretical.`,
 			`<code>all_reduce_perf</code> (NCCL tests)`,
-			`Runs in Validate and Stress. Uses all selected GPUs simultaneously (requires ≥2) and is kept short so it fits the Validate flow.`,
+			`Validate and Stress: `+validateFmtDur(platform.SATEstimatedNvidiaInterconnectSec)+` (all GPUs simultaneously, requires ≥2).`,
 		)) +
 		`</div>` +
 		`<div id="sat-card-nvidia-bandwidth">` +
@@ -1489,7 +1566,7 @@ func renderValidate(opts HandlerOptions) string {
 			inv.NVIDIA,
 			`Validates GPU memory copy and peer-to-peer bandwidth paths using NVBandwidth.`,
 			`<code>nvbandwidth</code>`,
-			`Runs in Validate and Stress across all selected GPUs simultaneously. Intended to stay short enough for Validate.`,
+			`Validate and Stress: `+validateFmtDur(platform.SATEstimatedNvidiaBandwidthSec)+` (all GPUs simultaneously; nvbandwidth runs all built-in tests without a time limit — duration set by the tool).`,
 		)) +
 		`</div>` +
 		`</div>
@@ -1922,6 +1999,8 @@ func loadValidateInventory(opts HandlerOptions) validateInventory {
 	out.Storage = formatValidateDeviceSummary(storageTotal, storageCounts, "device")
 	out.NVIDIA = formatValidateDeviceSummary(nvidiaTotal, nvidiaCounts, "GPU")
 	out.AMD = formatValidateDeviceSummary(amdTotal, amdCounts, "GPU")
+	out.NvidiaGPUCount = nvidiaTotal
+	out.AMDGPUCount = amdTotal
 	return out
 }
 

audit/internal/webui/server.go

@@ -575,12 +575,14 @@ func (h *handler) handleMetricsChartSVG(w http.ResponseWriter, r *http.Request)
 	}
 	timeline := metricsTimelineSegments(samples, time.Now())
 	if idx, sub, ok := parseGPUChartPath(path); ok && sub == "overview" {
-		buf, ok, err := renderGPUOverviewChartSVG(idx, samples, timeline)
+		var overviewOk bool
+		var buf []byte
+		buf, overviewOk, err = renderGPUOverviewChartSVG(idx, samples, timeline)
 		if err != nil {
 			http.Error(w, err.Error(), http.StatusInternalServerError)
 			return
 		}
-		if !ok {
+		if !overviewOk {
 			http.Error(w, "metrics history unavailable", http.StatusServiceUnavailable)
 			return
 		}
@@ -589,23 +591,37 @@ func (h *handler) handleMetricsChartSVG(w http.ResponseWriter, r *http.Request)
 		_, _ = w.Write(buf)
 		return
 	}
-	datasets, names, labels, title, yMin, yMax, ok := chartDataFromSamples(path, samples)
+	datasets, names, labels, title, yMin, yMax, stacked, ok := chartDataFromSamples(path, samples)
 	if !ok {
 		http.Error(w, "metrics history unavailable", http.StatusServiceUnavailable)
 		return
 	}
 
-	buf, err := renderMetricChartSVG(
-		title,
-		labels,
-		sampleTimes(samples),
-		datasets,
-		names,
-		yMin,
-		yMax,
-		chartCanvasHeightForPath(path, len(names)),
-		timeline,
-	)
+	var buf []byte
+	if stacked {
+		buf, err = renderStackedMetricChartSVG(
+			title,
+			labels,
+			sampleTimes(samples),
+			datasets,
+			names,
+			yMax,
+			chartCanvasHeightForPath(path, len(names)),
+			timeline,
+		)
+	} else {
+		buf, err = renderMetricChartSVG(
+			title,
+			labels,
+			sampleTimes(samples),
+			datasets,
+			names,
+			yMin,
+			yMax,
+			chartCanvasHeightForPath(path, len(names)),
+			timeline,
+		)
+	}
 	if err != nil {
 		http.Error(w, err.Error(), http.StatusInternalServerError)
 		return
@@ -615,12 +631,8 @@ func (h *handler) handleMetricsChartSVG(w http.ResponseWriter, r *http.Request)
 	_, _ = w.Write(buf)
 }
 
-func chartDataFromSamples(path string, samples []platform.LiveMetricSample) ([][]float64, []string, []string, string, *float64, *float64, bool) {
-	var datasets [][]float64
-	var names []string
-	var title string
-	var yMin, yMax *float64
-	labels := sampleTimeLabels(samples)
+func chartDataFromSamples(path string, samples []platform.LiveMetricSample) (datasets [][]float64, names []string, labels []string, title string, yMin, yMax *float64, stacked bool, ok bool) {
+	labels = sampleTimeLabels(samples)
 
 	switch {
 	case path == "server-load":
@@ -656,15 +668,41 @@ func chartDataFromSamples(path string, samples []platform.LiveMetricSample) ([][
 
 	case path == "server-power":
 		title = "System Power"
-		power := make([]float64, len(samples))
-		for i, s := range samples {
-			power[i] = s.PowerW
+		// Use per-PSU stacked chart when PSU SDR data is available.
+		// Collect the union of PSU slots seen across all samples.
+		psuSlots := psuSlotsFromSamples(samples)
+		if len(psuSlots) > 1 {
+			// Build one dataset per PSU slot.
+			psuDatasets := make([][]float64, len(psuSlots))
+			psuNames := make([]string, len(psuSlots))
+			for si, slot := range psuSlots {
+				ds := make([]float64, len(samples))
+				for i, s := range samples {
+					for _, psu := range s.PSUs {
+						if psu.Slot == slot {
+							ds[i] = psu.PowerW
+							break
+						}
+					}
+				}
+				psuDatasets[si] = normalizePowerSeries(ds)
+				psuNames[si] = fmt.Sprintf("PSU %d", slot)
+			}
+			datasets = psuDatasets
+			names = psuNames
+			stacked = true
+			yMax = autoMax120(psuStackedTotal(psuDatasets))
+		} else {
+			power := make([]float64, len(samples))
+			for i, s := range samples {
+				power[i] = s.PowerW
+			}
+			power = normalizePowerSeries(power)
+			datasets = [][]float64{power}
+			names = []string{"Power W"}
+			yMin = floatPtr(0)
+			yMax = autoMax120(power)
 		}
-		power = normalizePowerSeries(power)
-		datasets = [][]float64{power}
-		names = []string{"Power W"}
-		yMin = floatPtr(0)
-		yMax = autoMax120(power)
 
 	case path == "server-fans":
 		title = "Fan RPM"
@@ -707,7 +745,7 @@ func chartDataFromSamples(path string, samples []platform.LiveMetricSample) ([][
 	case strings.HasPrefix(path, "gpu/"):
 		idx, sub, ok := parseGPUChartPath(path)
 		if !ok {
-			return nil, nil, nil, "", nil, nil, false
+			return nil, nil, nil, "", nil, nil, false, false
 		}
 		switch sub {
 		case "load":
@@ -715,7 +753,7 @@ func chartDataFromSamples(path string, samples []platform.LiveMetricSample) ([][
 			util := gpuDatasetByIndex(samples, idx, func(g platform.GPUMetricRow) float64 { return g.UsagePct })
 			mem := gpuDatasetByIndex(samples, idx, func(g platform.GPUMetricRow) float64 { return g.MemUsagePct })
 			if util == nil && mem == nil {
-				return nil, nil, nil, "", nil, nil, false
+				return nil, nil, nil, "", nil, nil, false, false
 			}
 			datasets = [][]float64{coalesceDataset(util, len(samples)), coalesceDataset(mem, len(samples))}
 			names = []string{"Load %", "Mem %"}
@@ -725,7 +763,7 @@ func chartDataFromSamples(path string, samples []platform.LiveMetricSample) ([][
 			title = gpuDisplayLabel(idx) + " Temperature"
 			temp := gpuDatasetByIndex(samples, idx, func(g platform.GPUMetricRow) float64 { return g.TempC })
 			if temp == nil {
-				return nil, nil, nil, "", nil, nil, false
+				return nil, nil, nil, "", nil, nil, false, false
 			}
 			datasets = [][]float64{temp}
 			names = []string{"Temp °C"}
@@ -735,7 +773,7 @@ func chartDataFromSamples(path string, samples []platform.LiveMetricSample) ([][
 			title = gpuDisplayLabel(idx) + " Core Clock"
 			clock := gpuDatasetByIndex(samples, idx, func(g platform.GPUMetricRow) float64 { return g.ClockMHz })
 			if clock == nil {
-				return nil, nil, nil, "", nil, nil, false
+				return nil, nil, nil, "", nil, nil, false, false
 			}
 			datasets = [][]float64{clock}
 			names = []string{"Core Clock MHz"}
@@ -744,7 +782,7 @@ func chartDataFromSamples(path string, samples []platform.LiveMetricSample) ([][
 			title = gpuDisplayLabel(idx) + " Memory Clock"
 			clock := gpuDatasetByIndex(samples, idx, func(g platform.GPUMetricRow) float64 { return g.MemClockMHz })
 			if clock == nil {
-				return nil, nil, nil, "", nil, nil, false
+				return nil, nil, nil, "", nil, nil, false, false
 			}
 			datasets = [][]float64{clock}
 			names = []string{"Memory Clock MHz"}
@@ -753,7 +791,7 @@ func chartDataFromSamples(path string, samples []platform.LiveMetricSample) ([][
 			title = gpuDisplayLabel(idx) + " Power"
 			power := gpuDatasetByIndex(samples, idx, func(g platform.GPUMetricRow) float64 { return g.PowerW })
 			if power == nil {
-				return nil, nil, nil, "", nil, nil, false
+				return nil, nil, nil, "", nil, nil, false, false
 			}
 			datasets = [][]float64{power}
 			names = []string{"Power W"}
@@ -761,10 +799,10 @@ func chartDataFromSamples(path string, samples []platform.LiveMetricSample) ([][
 		}
 
 	default:
-		return nil, nil, nil, "", nil, nil, false
+		return nil, nil, nil, "", nil, nil, false, false
 	}
 
-	return datasets, names, labels, title, yMin, yMax, len(datasets) > 0
+	return datasets, names, labels, title, yMin, yMax, stacked, len(datasets) > 0
 }
 
 func parseGPUChartPath(path string) (idx int, sub string, ok bool) {
@@ -930,6 +968,37 @@ func normalizePowerSeries(ds []float64) []float64 {
 	return out
 }
 
+// psuSlotsFromSamples returns the sorted list of PSU slot numbers seen across samples.
+func psuSlotsFromSamples(samples []platform.LiveMetricSample) []int {
+	seen := map[int]struct{}{}
+	for _, s := range samples {
+		for _, p := range s.PSUs {
+			seen[p.Slot] = struct{}{}
+		}
+	}
+	slots := make([]int, 0, len(seen))
+	for s := range seen {
+		slots = append(slots, s)
+	}
+	sort.Ints(slots)
+	return slots
+}
+
+// psuStackedTotal returns the point-by-point sum of all PSU datasets (for scale calculation).
+func psuStackedTotal(datasets [][]float64) []float64 {
+	if len(datasets) == 0 {
+		return nil
+	}
+	n := len(datasets[0])
+	total := make([]float64, n)
+	for _, ds := range datasets {
+		for i, v := range ds {
+			total[i] += v
+		}
+	}
+	return total
+}
+
 func normalizeFanSeries(ds []float64) []float64 {
 	if len(ds) == 0 {
 		return nil

audit/internal/webui/server_test.go

@@ -120,7 +120,7 @@ func TestChartDataFromSamplesUsesFullHistory(t *testing.T) {
 		},
 	}
 
-	datasets, names, labels, title, _, _, ok := chartDataFromSamples("gpu-all-power", samples)
+	datasets, names, labels, title, _, _, _, ok := chartDataFromSamples("gpu-all-power", samples)
 	if !ok {
 		t.Fatal("chartDataFromSamples returned ok=false")
 	}
@@ -164,7 +164,7 @@ func TestChartDataFromSamplesKeepsStableGPUSeriesOrder(t *testing.T) {
 		},
 	}
 
-	datasets, names, _, title, _, _, ok := chartDataFromSamples("gpu-all-power", samples)
+	datasets, names, _, title, _, _, _, ok := chartDataFromSamples("gpu-all-power", samples)
 	if !ok {
 		t.Fatal("chartDataFromSamples returned ok=false")
 	}
@@ -209,7 +209,7 @@ func TestChartDataFromSamplesIncludesGPUClockCharts(t *testing.T) {
 		},
 	}
 
-	datasets, names, _, title, _, _, ok := chartDataFromSamples("gpu-all-clock", samples)
+	datasets, names, _, title, _, _, _, ok := chartDataFromSamples("gpu-all-clock", samples)
 	if !ok {
 		t.Fatal("gpu-all-clock returned ok=false")
 	}
@@ -754,9 +754,9 @@ func TestValidatePageRendersNvidiaFabricCardsInValidateMode(t *testing.T) {
 	body := rec.Body.String()
 	for _, needle := range []string{
 		`NVIDIA Interconnect (NCCL)`,
-		`Runs in Validate and Stress.`,
+		`Validate and Stress:`,
 		`NVIDIA Bandwidth (NVBandwidth)`,
-		`Intended to stay short enough for Validate.`,
+		`nvbandwidth runs all built-in tests without a time limit`,
 	} {
 		if !strings.Contains(body, needle) {
 			t.Fatalf("validate page missing %q: %s", needle, body)

audit/internal/webui/task_report.go

@@ -171,21 +171,17 @@ func renderTaskChartSVG(path string, samples []platform.LiveMetricSample, timeli
 		}
 		return gpuDisplayLabel(idx) + " Overview", buf, true
 	}
-	datasets, names, labels, title, yMin, yMax, ok := chartDataFromSamples(path, samples)
+	datasets, names, labels, title, yMin, yMax, stacked, ok := chartDataFromSamples(path, samples)
 	if !ok {
 		return "", nil, false
 	}
-	buf, err := renderMetricChartSVG(
-		title,
-		labels,
-		sampleTimes(samples),
-		datasets,
-		names,
-		yMin,
-		yMax,
-		chartCanvasHeightForPath(path, len(names)),
-		timeline,
-	)
+	var buf []byte
+	var err error
+	if stacked {
+		buf, err = renderStackedMetricChartSVG(title, labels, sampleTimes(samples), datasets, names, yMax, chartCanvasHeightForPath(path, len(names)), timeline)
+	} else {
+		buf, err = renderMetricChartSVG(title, labels, sampleTimes(samples), datasets, names, yMin, yMax, chartCanvasHeightForPath(path, len(names)), timeline)
+	}
 	if err != nil {
 		return "", nil, false
 	}

audit/internal/webui/tasks.go

@@ -613,8 +613,9 @@ func (q *taskQueue) runTask(t *Task, j *jobState, ctx context.Context) {
 	}
 	a := q.opts.App
 
+	recovered := len(j.lines) > 0
 	j.append(fmt.Sprintf("Starting %s...", t.Name))
-	if len(j.lines) > 0 {
+	if recovered {
 		j.append(fmt.Sprintf("Recovered after bee-web restart at %s", time.Now().UTC().Format(time.RFC3339)))
 	}
 

bible-local/docs/iso-build-rules.md

@@ -15,6 +15,41 @@ This applies to:
 - `iso/builder/config/package-lists/*.list.chroot`
 - Any package referenced in bootloader configs, hooks, or overlay scripts
 
+## Bootloader sync rule
+
+The ISO has two independent bootloader configs that must be kept in sync manually:
+
+| File | Used by |
+|------|---------|
+| `config/bootloaders/grub-efi/grub.cfg` | UEFI (all modern servers) |
+| `config/bootloaders/isolinux/live.cfg.in` | CSM / legacy BIOS (syslinux) |
+
+live-build does NOT derive one from the other. Any new boot entry, kernel parameter
+change, or new mode added to one file must be manually mirrored in the other.
+
+**Canonical entry list** (both files must have all of these):
+
+| Label | Key params |
+|-------|-----------|
+| normal (default) | `nomodeset bee.nvidia.mode=normal` + full param set |
+| load to RAM | `toram nomodeset bee.nvidia.mode=normal` + full param set |
+| GSP=off | `nomodeset bee.nvidia.mode=gsp-off` + full param set |
+| KMS | no `nomodeset`, `bee.nvidia.mode=normal` + full param set |
+| KMS + GSP=off | no `nomodeset`, `bee.nvidia.mode=gsp-off` + full param set |
+| fail-safe | `nomodeset bee.nvidia.mode=gsp-off noapic noapm nodma nomce nolapic nosmp` |
+
+**Full standard param set** (append after `@APPEND_LIVE@` / `nomodeset` flags):
+```
+net.ifnames=0 biosdevname=0 mitigations=off transparent_hugepage=always
+numa_balancing=disable pcie_aspm=off intel_idle.max_cstate=1 processor.max_cstate=1
+nowatchdog nosoftlockup
+```
+(fail-safe is the exception — it deliberately uses minimal params.)
+
+**Historical note:** `grub-pc/` was mistakenly used instead of `grub-efi/` until v8.25.
+live-build reads `config/bootloaders/grub-efi/` for UEFI because the build is
+configured with `--bootloaders "grub-efi,syslinux"`. Directory `grub-pc` is ignored.
+
 ## Memtest rule
 
 Do not assume live-build's built-in memtest integration is sufficient for `bee`.

iso/builder/config/bootloaders/grub-efi/grub.cfg

@@ -16,6 +16,11 @@ menuentry "EASY-BEE" {
 }
 
 submenu "EASY-BEE (advanced options) -->" {
+    menuentry "EASY-BEE — load to RAM (toram)" {
+        linux   @KERNEL_LIVE@ @APPEND_LIVE@ toram nomodeset bee.nvidia.mode=normal net.ifnames=0 biosdevname=0 mitigations=off transparent_hugepage=always numa_balancing=disable pcie_aspm=off intel_idle.max_cstate=1 processor.max_cstate=1 nowatchdog nosoftlockup
+        initrd  @INITRD_LIVE@
+    }
+
     menuentry "EASY-BEE — GSP=off" {
         linux   @KERNEL_LIVE@ @APPEND_LIVE@ nomodeset bee.nvidia.mode=gsp-off net.ifnames=0 biosdevname=0 mitigations=off transparent_hugepage=always numa_balancing=disable pcie_aspm=off intel_idle.max_cstate=1 processor.max_cstate=1 nowatchdog nosoftlockup
         initrd  @INITRD_LIVE@
@@ -26,6 +31,11 @@ submenu "EASY-BEE (advanced options) -->" {
         initrd  @INITRD_LIVE@
     }
 
+    menuentry "EASY-BEE — KMS + GSP=off" {
+        linux   @KERNEL_LIVE@ @APPEND_LIVE@ bee.nvidia.mode=gsp-off net.ifnames=0 biosdevname=0 mitigations=off transparent_hugepage=always numa_balancing=disable pcie_aspm=off intel_idle.max_cstate=1 processor.max_cstate=1 nowatchdog nosoftlockup
+        initrd  @INITRD_LIVE@
+    }
+
     menuentry "EASY-BEE — fail-safe" {
         linux   @KERNEL_LIVE@ @APPEND_LIVE@ nomodeset bee.nvidia.mode=gsp-off noapic noapm nodma nomce nolapic nosmp vga=normal net.ifnames=0 biosdevname=0
         initrd  @INITRD_LIVE@

iso/builder/config/bootloaders/isolinux/live.cfg.in

@@ -3,37 +3,37 @@ label live-@FLAVOUR@-normal
     menu default
     linux @LINUX@
     initrd @INITRD@
-    append @APPEND_LIVE@ bee.nvidia.mode=normal pcie_aspm=off intel_idle.max_cstate=1 processor.max_cstate=1
-
-label live-@FLAVOUR@-kms
-    menu label EASY-BEE (^graphics/KMS)
-    linux @LINUX@
-    initrd @INITRD@
-    append @APPEND_LIVE@ bee.display=kms bee.nvidia.mode=normal pcie_aspm=off intel_idle.max_cstate=1 processor.max_cstate=1
+    append @APPEND_LIVE@ nomodeset bee.nvidia.mode=normal net.ifnames=0 biosdevname=0 mitigations=off transparent_hugepage=always numa_balancing=disable pcie_aspm=off intel_idle.max_cstate=1 processor.max_cstate=1 nowatchdog nosoftlockup
 
 label live-@FLAVOUR@-toram
     menu label EASY-BEE (^load to RAM)
     linux @LINUX@
     initrd @INITRD@
-    append @APPEND_LIVE@ toram bee.nvidia.mode=normal pcie_aspm=off intel_idle.max_cstate=1 processor.max_cstate=1
+    append @APPEND_LIVE@ toram nomodeset bee.nvidia.mode=normal net.ifnames=0 biosdevname=0 mitigations=off transparent_hugepage=always numa_balancing=disable pcie_aspm=off intel_idle.max_cstate=1 processor.max_cstate=1 nowatchdog nosoftlockup
 
 label live-@FLAVOUR@-gsp-off
     menu label EASY-BEE (^NVIDIA GSP=off)
     linux @LINUX@
     initrd @INITRD@
-    append @APPEND_LIVE@ nomodeset bee.nvidia.mode=gsp-off pcie_aspm=off intel_idle.max_cstate=1 processor.max_cstate=1
+    append @APPEND_LIVE@ nomodeset bee.nvidia.mode=gsp-off net.ifnames=0 biosdevname=0 mitigations=off transparent_hugepage=always numa_balancing=disable pcie_aspm=off intel_idle.max_cstate=1 processor.max_cstate=1 nowatchdog nosoftlockup
 
-label live-@FLAVOUR@-kms-gsp-off
-    menu label EASY-BEE (g^raphics/KMS, GSP=off)
+label live-@FLAVOUR@-kms
+    menu label EASY-BEE (^KMS, no nomodeset)
     linux @LINUX@
     initrd @INITRD@
-    append @APPEND_LIVE@ bee.display=kms bee.nvidia.mode=gsp-off pcie_aspm=off intel_idle.max_cstate=1 processor.max_cstate=1
+    append @APPEND_LIVE@ bee.nvidia.mode=normal net.ifnames=0 biosdevname=0 mitigations=off transparent_hugepage=always numa_balancing=disable pcie_aspm=off intel_idle.max_cstate=1 processor.max_cstate=1 nowatchdog nosoftlockup
+
+label live-@FLAVOUR@-kms-gsp-off
+    menu label EASY-BEE (KMS, ^GSP=off)
+    linux @LINUX@
+    initrd @INITRD@
+    append @APPEND_LIVE@ bee.nvidia.mode=gsp-off net.ifnames=0 biosdevname=0 mitigations=off transparent_hugepage=always numa_balancing=disable pcie_aspm=off intel_idle.max_cstate=1 processor.max_cstate=1 nowatchdog nosoftlockup
 
 label live-@FLAVOUR@-failsafe
     menu label EASY-BEE (^fail-safe)
     linux @LINUX@
     initrd @INITRD@
-    append @APPEND_LIVE@ bee.nvidia.mode=gsp-off memtest noapic noapm nodma nomce nolapic nosmp vga=normal
+    append @APPEND_LIVE@ nomodeset bee.nvidia.mode=gsp-off noapic noapm nodma nomce nolapic nosmp vga=normal net.ifnames=0 biosdevname=0
 
 label memtest
     menu label ^Memory Test (memtest86+)

iso/builder/config/hooks/normal/9000-bee-setup.hook.chroot

@@ -63,8 +63,10 @@ chmod +x /usr/local/bin/bee-sshsetup   2>/dev/null || true
 chmod +x /usr/local/bin/bee-smoketest  2>/dev/null || true
 chmod +x /usr/local/bin/bee            2>/dev/null || true
 chmod +x /usr/local/bin/bee-log-run    2>/dev/null || true
-chmod +x /usr/local/bin/bee-selfheal      2>/dev/null || true
-chmod +x /usr/local/bin/bee-boot-status  2>/dev/null || true
+chmod +x /usr/local/bin/bee-selfheal        2>/dev/null || true
+chmod +x /usr/local/bin/bee-boot-status    2>/dev/null || true
+chmod +x /usr/local/bin/bee-install        2>/dev/null || true
+chmod +x /usr/local/bin/bee-remount-medium 2>/dev/null || true
 if [ "$GPU_VENDOR" = "nvidia" ]; then
     chmod +x /usr/local/bin/bee-nvidia-load 2>/dev/null || true
     chmod +x /usr/local/bin/bee-gpu-burn 2>/dev/null || true

iso/builder/config/hooks/normal/9011-toram-rsync.hook.chroot

@@ -0,0 +1,46 @@
+#!/bin/sh
+# 9011-toram-rsync.hook.chroot
+#
+# Adds rsync to the initramfs so that live-boot's toram code takes the
+# rsync --progress path instead of the silent "cp -a" fallback.
+#
+# live-boot's 9990-toram-todisk.sh already contains:
+#   if [ -x /bin/rsync ]; then
+#       rsync -a --progress ... 1>/dev/console
+#   else
+#       cp -a ...   # no output
+#   fi
+#
+# We install an initramfs-tools hook that calls copy_exec /usr/bin/rsync,
+# which copies the binary + all shared-library dependencies into the initrd.
+
+set -e
+
+HOOK_DIR="/etc/initramfs-tools/hooks"
+HOOK="${HOOK_DIR}/bee-rsync"
+
+mkdir -p "${HOOK_DIR}"
+
+cat > "${HOOK}" << 'EOF'
+#!/bin/sh
+# initramfs hook: include rsync for live-boot toram progress output
+PREREQ=""
+prereqs() { echo "$PREREQ"; }
+case "$1" in prereqs) prereqs; exit 0 ;; esac
+
+. /usr/share/initramfs-tools/hook-functions
+
+if [ -x /usr/bin/rsync ]; then
+    copy_exec /usr/bin/rsync /bin
+fi
+EOF
+
+chmod +x "${HOOK}"
+
+echo "9011-toram-rsync: installed initramfs hook at ${HOOK}"
+
+# Rebuild initramfs so the hook takes effect in the ISO's initrd.img
+KVER=$(ls /lib/modules | sort -V | tail -1)
+echo "9011-toram-rsync: rebuilding initramfs for kernel ${KVER}"
+update-initramfs -u -k "${KVER}"
+echo "9011-toram-rsync: done"

iso/builder/config/package-lists/bee.list.chroot

@@ -3,6 +3,7 @@ dmidecode
 smartmontools
 nvme-cli
 pciutils
+rsync
 ipmitool
 util-linux
 e2fsprogs

iso/overlay/usr/local/bin/bee-install

@@ -65,6 +65,9 @@ done
 SQUASHFS="/run/live/medium/live/filesystem.squashfs"
 if [ ! -f "$SQUASHFS" ]; then
     echo "ERROR: squashfs not found at $SQUASHFS" >&2
+    echo "  The live medium may have been disconnected." >&2
+    echo "  Reconnect the disc and run:  bee-remount-medium --wait" >&2
+    echo "  Then re-run bee-install." >&2
     exit 1
 fi
 
@@ -162,10 +165,59 @@ log "  Mounted."
 log "--- Step 5/7: Unpacking filesystem (this takes 10-20 minutes) ---"
 log "  Source: $SQUASHFS"
 log "  Target: $MOUNT_ROOT"
-unsquashfs -f -d "$MOUNT_ROOT" "$SQUASHFS" 2>&1 | \
-    grep -E '^\[|^inod|^created|^extract' | \
-    while read -r line; do log "  $line"; done || true
-log "  Unpack complete."
+
+# unsquashfs does not support resume, so retry the entire unpack step if the
+# source medium disappears mid-copy (e.g. CD physically disconnected).
+UNPACK_ATTEMPTS=0
+UNPACK_MAX=5
+while true; do
+    UNPACK_ATTEMPTS=$(( UNPACK_ATTEMPTS + 1 ))
+    if [ "$UNPACK_ATTEMPTS" -gt "$UNPACK_MAX" ]; then
+        die "Unpack failed $UNPACK_MAX times — giving up. Check the disc and logs."
+    fi
+    [ "$UNPACK_ATTEMPTS" -gt 1 ] && log "  Retry attempt $UNPACK_ATTEMPTS / $UNPACK_MAX ..."
+
+    # Re-check squashfs is reachable before each attempt
+    if [ ! -f "$SQUASHFS" ]; then
+        log "  SOURCE LOST: $SQUASHFS not found."
+        log "  Reconnect the disc and run 'bee-remount-medium --wait' in another terminal,"
+        log "  then press Enter here to retry."
+        read -r _
+        continue
+    fi
+
+    # wipe partial unpack so unsquashfs starts clean
+    if [ "$UNPACK_ATTEMPTS" -gt 1 ]; then
+        log "  Cleaning partial unpack from $MOUNT_ROOT ..."
+        # keep the mount point itself but remove its contents
+        find "$MOUNT_ROOT" -mindepth 1 -maxdepth 1 -exec rm -rf {} + 2>/dev/null || true
+    fi
+
+    UNPACK_OK=0
+    unsquashfs -f -d "$MOUNT_ROOT" "$SQUASHFS" 2>&1 | \
+        grep -E '^\[|^inod|^created|^extract|^ERROR|failed' | \
+        while IFS= read -r line; do log "  $line"; done || UNPACK_OK=$?
+
+    # Check squashfs is still reachable (gone = disc pulled during copy)
+    if [ ! -f "$SQUASHFS" ]; then
+        log "  WARNING: source medium lost during unpack — will retry after remount."
+        log "  Run 'bee-remount-medium --wait' in another terminal, then press Enter."
+        read -r _
+        continue
+    fi
+
+    # Verify the unpack produced a usable root (presence of /etc is a basic check)
+    if [ -d "${MOUNT_ROOT}/etc" ]; then
+        log "  Unpack complete."
+        break
+    else
+        log "  WARNING: unpack produced no /etc — squashfs may be corrupt or incomplete."
+        if [ "$UNPACK_ATTEMPTS" -lt "$UNPACK_MAX" ]; then
+            log "  Retrying in 5 s ..."
+            sleep 5
+        fi
+    fi
+done
 
 # ------------------------------------------------------------------
 log "--- Step 6/7: Configuring installed system ---"

iso/overlay/usr/local/bin/bee-remount-medium

@@ -0,0 +1,100 @@
+#!/bin/bash
+# bee-remount-medium — find and remount the live ISO medium to /run/live/medium
+#
+# Run this after reconnecting the ISO source disc (USB/CD) if the live medium
+# was lost and /run/live/medium/live/filesystem.squashfs is missing.
+#
+# Usage: bee-remount-medium [--wait]
+#   --wait  keep retrying every 5 seconds until the medium is found (useful
+#           while physically reconnecting the device)
+
+set -euo pipefail
+
+MEDIUM_DIR="/run/live/medium"
+SQUASHFS_REL="live/filesystem.squashfs"
+WAIT_MODE=0
+
+for arg in "$@"; do
+    case "$arg" in
+        --wait|-w) WAIT_MODE=1 ;;
+        --help|-h)
+            echo "Usage: bee-remount-medium [--wait]"
+            echo "  Finds and remounts the live ISO medium to $MEDIUM_DIR"
+            echo "  --wait  retry every 5 s until a medium with squashfs is found"
+            exit 0 ;;
+    esac
+done
+
+log() { echo "[$(date +%H:%M:%S)] $*"; }
+die() { log "ERROR: $*" >&2; exit 1; }
+
+# Return all candidate block devices (optical + removable USB mass storage)
+find_candidates() {
+    # CD/DVD drives
+    for dev in /dev/sr* /dev/scd*; do
+        [ -b "$dev" ] && echo "$dev"
+    done
+    # USB/removable disks and partitions
+    for dev in /dev/sd* /dev/vd*; do
+        [ -b "$dev" ] || continue
+        # Only whole disks or partitions — skip the same device we are running from
+        local removable
+        local base
+        base=$(basename "$dev")
+        removable=$(cat "/sys/block/${base%%[0-9]*}/removable" 2>/dev/null || echo 0)
+        [ "$removable" = "1" ] && echo "$dev"
+    done
+}
+
+# Try to mount $1 to $MEDIUM_DIR and check for squashfs
+try_mount() {
+    local dev="$1"
+    local tmpdir
+    tmpdir=$(mktemp -d /tmp/bee-probe-XXXXXX)
+    if mount -o ro "$dev" "$tmpdir" 2>/dev/null; then
+        if [ -f "${tmpdir}/${SQUASHFS_REL}" ]; then
+            # Unmount probe mount and mount properly onto live path
+            umount "$tmpdir" 2>/dev/null || true
+            rmdir "$tmpdir"  2>/dev/null || true
+            # Unmount whatever is currently on MEDIUM_DIR (may be empty/stale)
+            umount "$MEDIUM_DIR" 2>/dev/null || true
+            mkdir -p "$MEDIUM_DIR"
+            if mount -o ro "$dev" "$MEDIUM_DIR"; then
+                log "Mounted $dev on $MEDIUM_DIR"
+                return 0
+            else
+                log "Mount of $dev on $MEDIUM_DIR failed"
+                return 1
+            fi
+        fi
+        umount "$tmpdir" 2>/dev/null || true
+    fi
+    rmdir "$tmpdir" 2>/dev/null || true
+    return 1
+}
+
+attempt() {
+    log "Scanning for ISO medium..."
+    for dev in $(find_candidates); do
+        log "  Trying $dev ..."
+        if try_mount "$dev"; then
+            local sq="${MEDIUM_DIR}/${SQUASHFS_REL}"
+            log "SUCCESS: squashfs available at $sq ($(du -sh "$sq" | cut -f1))"
+            return 0
+        fi
+    done
+    return 1
+}
+
+if [ "$WAIT_MODE" = "1" ]; then
+    log "Waiting for live medium (press Ctrl+C to abort)..."
+    while true; do
+        if attempt; then
+            exit 0
+        fi
+        log "  Not found — retrying in 5 s (reconnect the disc now)"
+        sleep 5
+    done
+else
+    attempt || die "No ISO medium with ${SQUASHFS_REL} found. Reconnect the disc and re-run, or use --wait."
+fi