Files
bee/audit/internal/app/app.go

1253 lines
38 KiB
Go

package app
import (
"context"
"encoding/json"
"fmt"
"log/slog"
"os"
"path/filepath"
"sort"
"strconv"
"strings"
"time"
"bee/audit/internal/collector"
"bee/audit/internal/platform"
"bee/audit/internal/runtimeenv"
"bee/audit/internal/schema"
)
var (
DefaultExportDir = "/appdata/bee/export"
DefaultAuditJSONPath = DefaultExportDir + "/bee-audit.json"
DefaultAuditLogPath = DefaultExportDir + "/bee-audit.log"
DefaultWebLogPath = DefaultExportDir + "/bee-web.log"
DefaultNetworkLogPath = DefaultExportDir + "/bee-network.log"
DefaultNvidiaLogPath = DefaultExportDir + "/bee-nvidia.log"
DefaultSSHLogPath = DefaultExportDir + "/bee-sshsetup.log"
DefaultRuntimeJSONPath = DefaultExportDir + "/runtime-health.json"
DefaultRuntimeLogPath = DefaultExportDir + "/runtime-health.log"
DefaultTechDumpDir = DefaultExportDir + "/techdump"
DefaultSATBaseDir = DefaultExportDir + "/bee-sat"
DefaultBenchmarkBaseDir = DefaultExportDir + "/bee-benchmark"
)
type App struct {
network networkManager
services serviceManager
exports exportManager
tools toolManager
sat satRunner
runtime runtimeChecker
installer installer
// StatusDB is the unified component health store (nil if unavailable).
StatusDB *ComponentStatusDB
}
type ActionResult struct {
Title string
Body string
}
type networkManager interface {
ListInterfaces() ([]platform.InterfaceInfo, error)
DefaultRoute() string
DHCPOne(iface string) (string, error)
DHCPAll() (string, error)
SetStaticIPv4(cfg platform.StaticIPv4Config) (string, error)
SetInterfaceState(iface string, up bool) error
GetInterfaceState(iface string) (bool, error)
CaptureNetworkSnapshot() (platform.NetworkSnapshot, error)
RestoreNetworkSnapshot(snapshot platform.NetworkSnapshot) error
}
type serviceManager interface {
ListBeeServices() ([]string, error)
ServiceState(name string) string
ServiceStatus(name string) (string, error)
ServiceDo(name string, action platform.ServiceAction) (string, error)
}
type exportManager interface {
ListRemovableTargets() ([]platform.RemovableTarget, error)
ExportFileToTarget(src string, target platform.RemovableTarget) (string, error)
}
type toolManager interface {
TailFile(path string, lines int) string
CheckTools(names []string) []platform.ToolStatus
}
type installer interface {
ListInstallDisks() ([]platform.InstallDisk, error)
InstallToDisk(ctx context.Context, device string, logFile string) error
IsLiveMediaInRAM() bool
LiveBootSource() platform.LiveBootSource
RunInstallToRAM(ctx context.Context, logFunc func(string)) error
}
type GPUPresenceResult struct {
Nvidia bool
AMD bool
}
func (a *App) DetectGPUPresence() GPUPresenceResult {
vendor := a.sat.DetectGPUVendor()
return GPUPresenceResult{
Nvidia: vendor == "nvidia",
AMD: vendor == "amd",
}
}
func (a *App) IsLiveMediaInRAM() bool {
return a.installer.IsLiveMediaInRAM()
}
func (a *App) LiveBootSource() platform.LiveBootSource {
return a.installer.LiveBootSource()
}
func (a *App) RunInstallToRAM(ctx context.Context, logFunc func(string)) error {
return a.installer.RunInstallToRAM(ctx, logFunc)
}
type satRunner interface {
RunNvidiaAcceptancePack(baseDir string, logFunc func(string)) (string, error)
RunNvidiaAcceptancePackWithOptions(ctx context.Context, baseDir string, diagLevel int, gpuIndices []int, logFunc func(string)) (string, error)
RunNvidiaBenchmark(ctx context.Context, baseDir string, opts platform.NvidiaBenchmarkOptions, logFunc func(string)) (string, error)
RunNvidiaStressPack(ctx context.Context, baseDir string, opts platform.NvidiaStressOptions, logFunc func(string)) (string, error)
RunMemoryAcceptancePack(ctx context.Context, baseDir string, logFunc func(string)) (string, error)
RunStorageAcceptancePack(ctx context.Context, baseDir string, logFunc func(string)) (string, error)
RunCPUAcceptancePack(ctx context.Context, baseDir string, durationSec int, logFunc func(string)) (string, error)
ListNvidiaGPUs() ([]platform.NvidiaGPU, error)
DetectGPUVendor() string
ListAMDGPUs() ([]platform.AMDGPUInfo, error)
RunAMDAcceptancePack(ctx context.Context, baseDir string, logFunc func(string)) (string, error)
RunAMDMemIntegrityPack(ctx context.Context, baseDir string, logFunc func(string)) (string, error)
RunAMDMemBandwidthPack(ctx context.Context, baseDir string, logFunc func(string)) (string, error)
RunAMDStressPack(ctx context.Context, baseDir string, durationSec int, logFunc func(string)) (string, error)
RunMemoryStressPack(ctx context.Context, baseDir string, durationSec int, logFunc func(string)) (string, error)
RunSATStressPack(ctx context.Context, baseDir string, durationSec int, logFunc func(string)) (string, error)
RunFanStressTest(ctx context.Context, baseDir string, opts platform.FanStressOptions) (string, error)
RunPlatformStress(ctx context.Context, baseDir string, opts platform.PlatformStressOptions, logFunc func(string)) (string, error)
RunNCCLTests(ctx context.Context, baseDir string, logFunc func(string)) (string, error)
}
type runtimeChecker interface {
CollectRuntimeHealth(exportDir string) (schema.RuntimeHealth, error)
CaptureTechnicalDump(baseDir string) error
}
func New(platform *platform.System) *App {
a := &App{
network: platform,
services: platform,
exports: platform,
tools: platform,
sat: platform,
runtime: platform,
installer: platform,
}
if db, err := OpenComponentStatusDB(DefaultExportDir + "/component-status.json"); err == nil {
a.StatusDB = db
}
return a
}
// ApplySATOverlay parses a raw audit JSON, overlays the latest SAT results,
// and returns the updated JSON. Used by the web UI to serve always-fresh status.
func ApplySATOverlay(auditJSON []byte) ([]byte, error) {
snap, err := readAuditSnapshot(auditJSON)
if err != nil {
return nil, err
}
applyLatestSATStatuses(&snap.Hardware, DefaultSATBaseDir, nil)
return json.MarshalIndent(snap, "", " ")
}
func readAuditSnapshot(auditJSON []byte) (schema.HardwareIngestRequest, error) {
var snap schema.HardwareIngestRequest
if err := json.Unmarshal(auditJSON, &snap); err != nil {
return schema.HardwareIngestRequest{}, err
}
collector.NormalizeSnapshot(&snap.Hardware, snap.CollectedAt)
return snap, nil
}
func (a *App) RunAudit(runtimeMode runtimeenv.Mode, output string) (string, error) {
if runtimeMode == runtimeenv.ModeLiveCD {
if err := a.runtime.CaptureTechnicalDump(DefaultTechDumpDir); err != nil {
slog.Warn("capture technical dump", "err", err)
}
}
result := collector.Run(runtimeMode)
applyLatestSATStatuses(&result.Hardware, DefaultSATBaseDir, a.StatusDB)
if health, err := ReadRuntimeHealth(DefaultRuntimeJSONPath); err == nil {
result.Runtime = &health
}
data, err := json.MarshalIndent(result, "", " ")
if err != nil {
return "", err
}
switch {
case output == "stdout":
_, err := os.Stdout.Write(append(data, '\n'))
return "stdout", err
case strings.HasPrefix(output, "file:"):
path := strings.TrimPrefix(output, "file:")
if err := atomicWriteFile(path, append(data, '\n'), 0644); err != nil {
return "", err
}
return path, nil
default:
return "", fmt.Errorf("unknown output destination %q — use stdout or file:<path>", output)
}
}
func (a *App) RunRuntimePreflight(output string) (string, error) {
health, err := a.runtime.CollectRuntimeHealth(DefaultExportDir)
if err != nil {
return "", err
}
data, err := json.MarshalIndent(health, "", " ")
if err != nil {
return "", err
}
switch {
case output == "stdout":
_, err := os.Stdout.Write(append(data, '\n'))
return "stdout", err
case strings.HasPrefix(output, "file:"):
path := strings.TrimPrefix(output, "file:")
if err := atomicWriteFile(path, append(data, '\n'), 0644); err != nil {
return "", err
}
return path, nil
default:
return "", fmt.Errorf("unknown output destination %q — use stdout or file:<path>", output)
}
}
func (a *App) RunRuntimePreflightResult() (ActionResult, error) {
path, err := a.RunRuntimePreflight("file:" + DefaultRuntimeJSONPath)
body := "Runtime preflight completed."
if path != "" {
body = "Runtime health written to " + path
}
return ActionResult{Title: "Run self-check", Body: body}, err
}
func (a *App) RuntimeHealthResult() ActionResult {
health, err := ReadRuntimeHealth(DefaultRuntimeJSONPath)
if err != nil {
return ActionResult{Title: "Runtime issues", Body: "No runtime health found."}
}
driverLabel := "Driver ready"
accelLabel := "CUDA ready"
switch a.sat.DetectGPUVendor() {
case "amd":
driverLabel = "AMDGPU ready"
accelLabel = "ROCm SMI ready"
case "nvidia":
driverLabel = "NVIDIA ready"
}
var body strings.Builder
fmt.Fprintf(&body, "Status: %s\n", firstNonEmpty(health.Status, "UNKNOWN"))
fmt.Fprintf(&body, "Export dir: %s\n", firstNonEmpty(health.ExportDir, DefaultExportDir))
fmt.Fprintf(&body, "%s: %t\n", driverLabel, health.DriverReady)
fmt.Fprintf(&body, "%s: %t\n", accelLabel, health.CUDAReady)
fmt.Fprintf(&body, "Network: %s", firstNonEmpty(health.NetworkStatus, "UNKNOWN"))
if len(health.Issues) > 0 {
body.WriteString("\n\nIssues:\n")
for _, issue := range health.Issues {
fmt.Fprintf(&body, "- %s: %s\n", issue.Code, issue.Description)
}
}
return ActionResult{Title: "Runtime issues", Body: strings.TrimSpace(body.String())}
}
func (a *App) RunAuditNow(runtimeMode runtimeenv.Mode) (ActionResult, error) {
path, err := a.RunAudit(runtimeMode, "file:"+DefaultAuditJSONPath)
body := "Audit completed."
if path != "" {
body = "Audit output: " + path
}
return ActionResult{Title: "Run audit", Body: body}, err
}
func (a *App) RunAuditToDefaultFile(runtimeMode runtimeenv.Mode) (string, error) {
return a.RunAudit(runtimeMode, "file:"+DefaultAuditJSONPath)
}
func (a *App) ExportLatestAudit(target platform.RemovableTarget) (string, error) {
if _, err := os.Stat(DefaultAuditJSONPath); err != nil {
return "", err
}
filename := fmt.Sprintf("audit-%s-%s.json", sanitizeFilename(hostnameOr("unknown")), time.Now().UTC().Format("20060102-150405"))
tmpPath := filepath.Join(os.TempDir(), filename)
data, err := os.ReadFile(DefaultAuditJSONPath)
if err != nil {
return "", err
}
if normalized, normErr := ApplySATOverlay(data); normErr == nil {
data = normalized
}
if err := os.WriteFile(tmpPath, data, 0644); err != nil {
return "", err
}
defer os.Remove(tmpPath)
return a.exports.ExportFileToTarget(tmpPath, target)
}
func (a *App) ExportLatestAuditResult(target platform.RemovableTarget) (ActionResult, error) {
path, err := a.ExportLatestAudit(target)
body := "Audit export failed."
if err == nil {
body = "Audit exported."
}
if err == nil && path != "" {
body = "Audit exported to " + path
}
return ActionResult{Title: "Export audit", Body: body}, err
}
func (a *App) ExportSupportBundle(target platform.RemovableTarget) (string, error) {
archive, err := BuildSupportBundle(DefaultExportDir)
if err != nil {
return "", err
}
defer os.Remove(archive)
return a.exports.ExportFileToTarget(archive, target)
}
func (a *App) ExportSupportBundleResult(target platform.RemovableTarget) (ActionResult, error) {
path, err := a.ExportSupportBundle(target)
body := "Support bundle export failed."
if err == nil {
body = "Support bundle exported. USB target unmounted and safe to remove."
}
if err == nil && path != "" {
body = "Support bundle exported to " + path + ".\n\nUSB target unmounted and safe to remove."
}
return ActionResult{Title: "Export support bundle", Body: body}, err
}
func (a *App) ListInterfaces() ([]platform.InterfaceInfo, error) {
return a.network.ListInterfaces()
}
func (a *App) DefaultRoute() string {
return a.network.DefaultRoute()
}
func (a *App) DHCPOne(iface string) (string, error) {
return a.network.DHCPOne(iface)
}
func (a *App) DHCPOneResult(iface string) (ActionResult, error) {
body, err := a.network.DHCPOne(iface)
return ActionResult{Title: "DHCP: " + iface, Body: bodyOr(body, "DHCP completed.")}, err
}
func (a *App) DHCPAll() (string, error) {
return a.network.DHCPAll()
}
func (a *App) DHCPAllResult() (ActionResult, error) {
body, err := a.network.DHCPAll()
return ActionResult{Title: "DHCP: all interfaces", Body: bodyOr(body, "DHCP completed.")}, err
}
func (a *App) SetStaticIPv4(cfg platform.StaticIPv4Config) (string, error) {
return a.network.SetStaticIPv4(cfg)
}
func (a *App) SetInterfaceState(iface string, up bool) error {
return a.network.SetInterfaceState(iface, up)
}
func (a *App) GetInterfaceState(iface string) (bool, error) {
return a.network.GetInterfaceState(iface)
}
func (a *App) CaptureNetworkSnapshot() (platform.NetworkSnapshot, error) {
return a.network.CaptureNetworkSnapshot()
}
func (a *App) RestoreNetworkSnapshot(snapshot platform.NetworkSnapshot) error {
return a.network.RestoreNetworkSnapshot(snapshot)
}
func (a *App) SetStaticIPv4Result(cfg platform.StaticIPv4Config) (ActionResult, error) {
body, err := a.network.SetStaticIPv4(cfg)
return ActionResult{Title: "Static IPv4: " + cfg.Interface, Body: bodyOr(body, "Static IPv4 updated.")}, err
}
func (a *App) NetworkStatus() (ActionResult, error) {
ifaces, err := a.network.ListInterfaces()
if err != nil {
return ActionResult{Title: "Network status"}, err
}
if len(ifaces) == 0 {
return ActionResult{Title: "Network status", Body: "No physical interfaces found."}, nil
}
var body strings.Builder
for _, iface := range ifaces {
ipv4 := "(no IPv4)"
if len(iface.IPv4) > 0 {
ipv4 = strings.Join(iface.IPv4, ", ")
}
fmt.Fprintf(&body, "- %s: state=%s ip=%s\n", iface.Name, iface.State, ipv4)
}
if gw := a.network.DefaultRoute(); gw != "" {
fmt.Fprintf(&body, "\nDefault route: %s\n", gw)
}
return ActionResult{Title: "Network status", Body: strings.TrimSpace(body.String())}, nil
}
func (a *App) DefaultStaticIPv4FormFields(iface string) []string {
return []string{
"",
"24",
strings.TrimSpace(a.network.DefaultRoute()),
"77.88.8.8 77.88.8.1 1.1.1.1 8.8.8.8",
}
}
func (a *App) ParseStaticIPv4Config(iface string, fields []string) platform.StaticIPv4Config {
get := func(index int) string {
if index >= 0 && index < len(fields) {
return strings.TrimSpace(fields[index])
}
return ""
}
return platform.StaticIPv4Config{
Interface: iface,
Address: get(0),
Prefix: get(1),
Gateway: get(2),
DNS: strings.Fields(get(3)),
}
}
func (a *App) ListBeeServices() ([]string, error) {
return a.services.ListBeeServices()
}
func (a *App) ServiceState(name string) string {
return a.services.ServiceState(name)
}
func (a *App) ServiceStatus(name string) (string, error) {
return a.services.ServiceStatus(name)
}
func (a *App) ServiceStatusResult(name string) (ActionResult, error) {
body, err := a.services.ServiceStatus(name)
return ActionResult{Title: "service status: " + name, Body: bodyOr(body, "No status output.")}, err
}
func (a *App) ServiceDo(name string, action platform.ServiceAction) (string, error) {
return a.services.ServiceDo(name, action)
}
func (a *App) ServiceActionResult(name string, action platform.ServiceAction) (ActionResult, error) {
body, err := a.services.ServiceDo(name, action)
return ActionResult{Title: "service " + string(action) + ": " + name, Body: bodyOr(body, "Action completed.")}, err
}
func (a *App) ListRemovableTargets() ([]platform.RemovableTarget, error) {
return a.exports.ListRemovableTargets()
}
func (a *App) TailFile(path string, lines int) string {
return a.tools.TailFile(path, lines)
}
func (a *App) CheckTools(names []string) []platform.ToolStatus {
return a.tools.CheckTools(names)
}
func (a *App) ToolCheckResult(names []string) ActionResult {
if len(names) == 0 {
return ActionResult{Title: "Required tools", Body: "No tools checked."}
}
var body strings.Builder
for _, tool := range a.tools.CheckTools(names) {
status := "MISSING"
if tool.OK {
status = "OK (" + tool.Path + ")"
}
fmt.Fprintf(&body, "- %s: %s\n", tool.Name, status)
}
return ActionResult{Title: "Required tools", Body: strings.TrimSpace(body.String())}
}
func (a *App) AuditLogTailResult() ActionResult {
logTail := strings.TrimSpace(a.tools.TailFile(DefaultAuditLogPath, 40))
jsonTail := strings.TrimSpace(a.tools.TailFile(DefaultAuditJSONPath, 20))
body := strings.TrimSpace(logTail + "\n\n" + jsonTail)
if body == "" {
body = "No audit logs found."
}
return ActionResult{Title: "Audit log tail", Body: body}
}
func (a *App) RunNvidiaAcceptancePack(baseDir string, logFunc func(string)) (string, error) {
if strings.TrimSpace(baseDir) == "" {
baseDir = DefaultSATBaseDir
}
return a.sat.RunNvidiaAcceptancePack(baseDir, logFunc)
}
func (a *App) RunNvidiaAcceptancePackResult(baseDir string) (ActionResult, error) {
path, err := a.RunNvidiaAcceptancePack(baseDir, nil)
body := "Archive written."
if path != "" {
body = "Archive written to " + path
}
return ActionResult{Title: "NVIDIA SAT", Body: body}, err
}
func (a *App) ListNvidiaGPUs() ([]platform.NvidiaGPU, error) {
return a.sat.ListNvidiaGPUs()
}
func (a *App) RunNvidiaAcceptancePackWithOptions(ctx context.Context, baseDir string, diagLevel int, gpuIndices []int, logFunc func(string)) (ActionResult, error) {
if strings.TrimSpace(baseDir) == "" {
baseDir = DefaultSATBaseDir
}
path, err := a.sat.RunNvidiaAcceptancePackWithOptions(ctx, baseDir, diagLevel, gpuIndices, logFunc)
body := "Archive written."
if path != "" {
body = "Archive written to " + path
}
return ActionResult{Title: "NVIDIA DCGM", Body: body}, err
}
func (a *App) RunNvidiaStressPack(baseDir string, opts platform.NvidiaStressOptions, logFunc func(string)) (string, error) {
return a.RunNvidiaStressPackCtx(context.Background(), baseDir, opts, logFunc)
}
func (a *App) RunNvidiaBenchmark(baseDir string, opts platform.NvidiaBenchmarkOptions, logFunc func(string)) (string, error) {
return a.RunNvidiaBenchmarkCtx(context.Background(), baseDir, opts, logFunc)
}
func (a *App) RunNvidiaBenchmarkCtx(ctx context.Context, baseDir string, opts platform.NvidiaBenchmarkOptions, logFunc func(string)) (string, error) {
if strings.TrimSpace(baseDir) == "" {
baseDir = DefaultBenchmarkBaseDir
}
return a.sat.RunNvidiaBenchmark(ctx, baseDir, opts, logFunc)
}
func (a *App) RunNvidiaStressPackCtx(ctx context.Context, baseDir string, opts platform.NvidiaStressOptions, logFunc func(string)) (string, error) {
if strings.TrimSpace(baseDir) == "" {
baseDir = DefaultSATBaseDir
}
return a.sat.RunNvidiaStressPack(ctx, baseDir, opts, logFunc)
}
func (a *App) RunMemoryAcceptancePack(baseDir string, logFunc func(string)) (string, error) {
return a.RunMemoryAcceptancePackCtx(context.Background(), baseDir, logFunc)
}
func (a *App) RunMemoryAcceptancePackCtx(ctx context.Context, baseDir string, logFunc func(string)) (string, error) {
if strings.TrimSpace(baseDir) == "" {
baseDir = DefaultSATBaseDir
}
return a.sat.RunMemoryAcceptancePack(ctx, baseDir, logFunc)
}
func (a *App) RunMemoryAcceptancePackResult(baseDir string) (ActionResult, error) {
path, err := a.RunMemoryAcceptancePack(baseDir, nil)
return ActionResult{Title: "Memory SAT", Body: satResultBody(path)}, err
}
func (a *App) RunCPUAcceptancePack(baseDir string, durationSec int, logFunc func(string)) (string, error) {
return a.RunCPUAcceptancePackCtx(context.Background(), baseDir, durationSec, logFunc)
}
func (a *App) RunCPUAcceptancePackCtx(ctx context.Context, baseDir string, durationSec int, logFunc func(string)) (string, error) {
if strings.TrimSpace(baseDir) == "" {
baseDir = DefaultSATBaseDir
}
return a.sat.RunCPUAcceptancePack(ctx, baseDir, durationSec, logFunc)
}
func (a *App) RunCPUAcceptancePackResult(baseDir string, durationSec int) (ActionResult, error) {
path, err := a.RunCPUAcceptancePack(baseDir, durationSec, nil)
return ActionResult{Title: "CPU SAT", Body: satResultBody(path)}, err
}
func (a *App) RunStorageAcceptancePack(baseDir string, logFunc func(string)) (string, error) {
return a.RunStorageAcceptancePackCtx(context.Background(), baseDir, logFunc)
}
func (a *App) RunStorageAcceptancePackCtx(ctx context.Context, baseDir string, logFunc func(string)) (string, error) {
if strings.TrimSpace(baseDir) == "" {
baseDir = DefaultSATBaseDir
}
return a.sat.RunStorageAcceptancePack(ctx, baseDir, logFunc)
}
func (a *App) RunStorageAcceptancePackResult(baseDir string) (ActionResult, error) {
path, err := a.RunStorageAcceptancePack(baseDir, nil)
return ActionResult{Title: "Storage SAT", Body: satResultBody(path)}, err
}
func (a *App) DetectGPUVendor() string {
return a.sat.DetectGPUVendor()
}
func (a *App) ListAMDGPUs() ([]platform.AMDGPUInfo, error) {
return a.sat.ListAMDGPUs()
}
func (a *App) RunAMDAcceptancePack(baseDir string, logFunc func(string)) (string, error) {
return a.RunAMDAcceptancePackCtx(context.Background(), baseDir, logFunc)
}
func (a *App) RunAMDAcceptancePackCtx(ctx context.Context, baseDir string, logFunc func(string)) (string, error) {
if strings.TrimSpace(baseDir) == "" {
baseDir = DefaultSATBaseDir
}
return a.sat.RunAMDAcceptancePack(ctx, baseDir, logFunc)
}
func (a *App) RunAMDAcceptancePackResult(baseDir string) (ActionResult, error) {
path, err := a.RunAMDAcceptancePack(baseDir, nil)
return ActionResult{Title: "AMD GPU SAT", Body: satResultBody(path)}, err
}
func (a *App) RunAMDMemIntegrityPackCtx(ctx context.Context, baseDir string, logFunc func(string)) (string, error) {
if strings.TrimSpace(baseDir) == "" {
baseDir = DefaultSATBaseDir
}
return a.sat.RunAMDMemIntegrityPack(ctx, baseDir, logFunc)
}
func (a *App) RunAMDMemBandwidthPackCtx(ctx context.Context, baseDir string, logFunc func(string)) (string, error) {
if strings.TrimSpace(baseDir) == "" {
baseDir = DefaultSATBaseDir
}
return a.sat.RunAMDMemBandwidthPack(ctx, baseDir, logFunc)
}
func (a *App) RunMemoryStressPack(baseDir string, durationSec int, logFunc func(string)) (string, error) {
return a.RunMemoryStressPackCtx(context.Background(), baseDir, durationSec, logFunc)
}
func (a *App) RunSATStressPack(baseDir string, durationSec int, logFunc func(string)) (string, error) {
return a.RunSATStressPackCtx(context.Background(), baseDir, durationSec, logFunc)
}
func (a *App) RunAMDStressPack(baseDir string, durationSec int, logFunc func(string)) (string, error) {
return a.RunAMDStressPackCtx(context.Background(), baseDir, durationSec, logFunc)
}
func (a *App) RunMemoryStressPackCtx(ctx context.Context, baseDir string, durationSec int, logFunc func(string)) (string, error) {
return a.sat.RunMemoryStressPack(ctx, baseDir, durationSec, logFunc)
}
func (a *App) RunSATStressPackCtx(ctx context.Context, baseDir string, durationSec int, logFunc func(string)) (string, error) {
return a.sat.RunSATStressPack(ctx, baseDir, durationSec, logFunc)
}
func (a *App) RunAMDStressPackCtx(ctx context.Context, baseDir string, durationSec int, logFunc func(string)) (string, error) {
if strings.TrimSpace(baseDir) == "" {
baseDir = DefaultSATBaseDir
}
return a.sat.RunAMDStressPack(ctx, baseDir, durationSec, logFunc)
}
func (a *App) RunFanStressTest(ctx context.Context, baseDir string, opts platform.FanStressOptions) (string, error) {
if strings.TrimSpace(baseDir) == "" {
baseDir = DefaultSATBaseDir
}
return a.sat.RunFanStressTest(ctx, baseDir, opts)
}
func (a *App) RunPlatformStress(ctx context.Context, baseDir string, opts platform.PlatformStressOptions, logFunc func(string)) (string, error) {
if strings.TrimSpace(baseDir) == "" {
baseDir = DefaultSATBaseDir
}
return a.sat.RunPlatformStress(ctx, baseDir, opts, logFunc)
}
func (a *App) RunNCCLTestsResult(ctx context.Context) (ActionResult, error) {
path, err := a.sat.RunNCCLTests(ctx, DefaultSATBaseDir, nil)
body := "Results: " + path
if err != nil && err != context.Canceled {
body += "\nERROR: " + err.Error()
}
return ActionResult{Title: "NCCL bandwidth test", Body: body}, err
}
func (a *App) RunFanStressTestResult(ctx context.Context, opts platform.FanStressOptions) (ActionResult, error) {
path, err := a.RunFanStressTest(ctx, "", opts)
body := formatFanStressResult(path)
if err != nil && err != context.Canceled {
body += "\nERROR: " + err.Error()
}
return ActionResult{Title: "GPU Platform Stress Test", Body: body}, err
}
// formatFanStressResult formats the summary.txt from a fan-stress run, including
// the per-step pass/fail display and the analysis section (throttling, max temps, fan response).
func formatFanStressResult(archivePath string) string {
if archivePath == "" {
return "No output produced."
}
runDir := strings.TrimSuffix(archivePath, ".tar.gz")
raw, err := os.ReadFile(filepath.Join(runDir, "summary.txt"))
if err != nil {
return "Archive written to " + archivePath
}
content := strings.TrimSpace(string(raw))
kv := parseKeyValueSummary(content)
var b strings.Builder
b.WriteString(formatSATDetail(content))
// Append analysis section.
var analysis []string
if v, ok := kv["throttling_detected"]; ok {
label := "NO"
if v == "true" {
label = "YES ← throttling detected during load"
}
analysis = append(analysis, "Throttling: "+label)
}
if v, ok := kv["max_gpu_temp_c"]; ok && v != "0.0" {
analysis = append(analysis, "Max GPU temp: "+v+"°C")
}
if v, ok := kv["max_cpu_temp_c"]; ok && v != "0.0" {
analysis = append(analysis, "Max CPU temp: "+v+"°C")
}
if v, ok := kv["fan_response_sec"]; ok && v != "N/A" && v != "-1.0" {
analysis = append(analysis, "Fan response: "+v+"s")
}
if len(analysis) > 0 {
b.WriteString("\n\n=== Analysis ===\n")
for _, line := range analysis {
b.WriteString(line + "\n")
}
}
return strings.TrimSpace(b.String())
}
// satResultBody reads summary.txt from the SAT run directory (archive path without .tar.gz)
// and returns a formatted human-readable result. Falls back to a plain message if unreadable.
func satResultBody(archivePath string) string {
if archivePath == "" {
return "No output produced."
}
runDir := strings.TrimSuffix(archivePath, ".tar.gz")
raw, err := os.ReadFile(filepath.Join(runDir, "summary.txt"))
if err != nil {
return "Archive written to " + archivePath
}
return formatSATDetail(strings.TrimSpace(string(raw)))
}
func (a *App) HealthSummaryResult() ActionResult {
raw, err := os.ReadFile(DefaultAuditJSONPath)
if err != nil {
return ActionResult{Title: "Health summary", Body: "No audit JSON found."}
}
var snapshot schema.HardwareIngestRequest
if err := json.Unmarshal(raw, &snapshot); err != nil {
return ActionResult{Title: "Health summary", Body: "Audit JSON is unreadable."}
}
collector.NormalizeSnapshot(&snapshot.Hardware, snapshot.CollectedAt)
summary := collector.BuildHealthSummary(snapshot.Hardware)
var body strings.Builder
status := summary.Status
if status == "" {
status = "Unknown"
}
fmt.Fprintf(&body, "Overall: %s\n", status)
fmt.Fprintf(&body, "Storage: warn=%d fail=%d\n", summary.StorageWarn, summary.StorageFail)
fmt.Fprintf(&body, "PCIe: warn=%d fail=%d\n", summary.PCIeWarn, summary.PCIeFail)
fmt.Fprintf(&body, "PSU: warn=%d fail=%d\n", summary.PSUWarn, summary.PSUFail)
fmt.Fprintf(&body, "Memory: warn=%d fail=%d\n", summary.MemoryWarn, summary.MemoryFail)
for _, item := range latestSATSummaries() {
fmt.Fprintf(&body, "\n\n%s", item)
}
if len(summary.Failures) > 0 {
fmt.Fprintf(&body, "\n\nFailures:\n- %s", strings.Join(summary.Failures, "\n- "))
}
if len(summary.Warnings) > 0 {
fmt.Fprintf(&body, "\n\nWarnings:\n- %s", strings.Join(summary.Warnings, "\n- "))
}
return ActionResult{Title: "Health summary", Body: strings.TrimSpace(body.String())}
}
func (a *App) MainBanner() string {
raw, err := os.ReadFile(DefaultAuditJSONPath)
if err != nil {
return ""
}
var snapshot schema.HardwareIngestRequest
if err := json.Unmarshal(raw, &snapshot); err != nil {
return ""
}
collector.NormalizeSnapshot(&snapshot.Hardware, snapshot.CollectedAt)
var lines []string
if system := formatSystemLine(snapshot.Hardware.Board); system != "" {
lines = append(lines, system)
}
if cpu := formatCPULine(snapshot.Hardware.CPUs); cpu != "" {
lines = append(lines, cpu)
}
if memory := formatMemoryLine(snapshot.Hardware.Memory); memory != "" {
lines = append(lines, memory)
}
if storage := formatStorageLine(snapshot.Hardware.Storage); storage != "" {
lines = append(lines, storage)
}
if gpu := formatGPULine(snapshot.Hardware.PCIeDevices); gpu != "" {
lines = append(lines, gpu)
}
if ip := formatIPLine(a.network.ListInterfaces); ip != "" {
lines = append(lines, ip)
}
return strings.TrimSpace(strings.Join(lines, "\n"))
}
func (a *App) FormatToolStatuses(statuses []platform.ToolStatus) string {
var body strings.Builder
for _, tool := range statuses {
status := "MISSING"
if tool.OK {
status = "OK (" + tool.Path + ")"
}
fmt.Fprintf(&body, "- %s: %s\n", tool.Name, status)
}
return strings.TrimSpace(body.String())
}
func (a *App) ParsePrefix(raw string, fallback int) int {
value, err := strconv.Atoi(strings.TrimSpace(raw))
if err != nil || value <= 0 {
return fallback
}
return value
}
func hostnameOr(fallback string) string {
hn, err := os.Hostname()
if err != nil || strings.TrimSpace(hn) == "" {
return fallback
}
return hn
}
func sanitizeFilename(v string) string {
var out []rune
for _, r := range v {
switch {
case r >= 'a' && r <= 'z', r >= 'A' && r <= 'Z', r >= '0' && r <= '9', r == '-', r == '_', r == '.':
out = append(out, r)
default:
out = append(out, '-')
}
}
if len(out) == 0 {
return "unknown"
}
return string(out)
}
func bodyOr(body, fallback string) string {
body = strings.TrimSpace(body)
if body == "" {
return fallback
}
return body
}
func ReadRuntimeHealth(path string) (schema.RuntimeHealth, error) {
raw, err := os.ReadFile(path)
if err != nil {
return schema.RuntimeHealth{}, err
}
var health schema.RuntimeHealth
if err := json.Unmarshal(raw, &health); err != nil {
return schema.RuntimeHealth{}, err
}
return health, nil
}
func latestSATSummaries() []string {
patterns := []struct {
label string
prefix string
}{
{label: "NVIDIA SAT", prefix: "gpu-nvidia-"},
{label: "Memory SAT", prefix: "memory-"},
{label: "Storage SAT", prefix: "storage-"},
{label: "CPU SAT", prefix: "cpu-"},
}
var out []string
for _, item := range patterns {
matches, err := filepath.Glob(filepath.Join(DefaultSATBaseDir, item.prefix+"*/summary.txt"))
if err != nil || len(matches) == 0 {
continue
}
sort.Strings(matches)
raw, err := os.ReadFile(matches[len(matches)-1])
if err != nil {
continue
}
out = append(out, formatSATSummary(item.label, string(raw)))
}
return out
}
func formatSATSummary(label, raw string) string {
values := parseKeyValueSummary(raw)
var body strings.Builder
fmt.Fprintf(&body, "%s:", label)
if overall := firstNonEmpty(values["overall_status"], "UNKNOWN"); overall != "" {
fmt.Fprintf(&body, " %s", overall)
}
if ok := firstNonEmpty(values["job_ok"], "0"); ok != "" {
fmt.Fprintf(&body, " ok=%s", ok)
}
if failed := firstNonEmpty(values["job_failed"], "0"); failed != "" {
fmt.Fprintf(&body, " failed=%s", failed)
}
if unsupported := firstNonEmpty(values["job_unsupported"], "0"); unsupported != "" && unsupported != "0" {
fmt.Fprintf(&body, " unsupported=%s", unsupported)
}
if devices := strings.TrimSpace(values["devices"]); devices != "" {
fmt.Fprintf(&body, "\nDevices: %s", devices)
}
return body.String()
}
func formatSystemLine(board schema.HardwareBoard) string {
model := strings.TrimSpace(strings.Join([]string{
trimPtr(board.Manufacturer),
trimPtr(board.ProductName),
}, " "))
serial := strings.TrimSpace(board.SerialNumber)
switch {
case model != "" && serial != "":
return fmt.Sprintf("System: %s | S/N %s", model, serial)
case model != "":
return "System: " + model
case serial != "":
return "System S/N: " + serial
default:
return ""
}
}
func formatCPULine(cpus []schema.HardwareCPU) string {
if len(cpus) == 0 {
return ""
}
modelCounts := map[string]int{}
unknown := 0
for _, cpu := range cpus {
model := trimPtr(cpu.Model)
if model == "" {
unknown++
continue
}
modelCounts[model]++
}
if len(modelCounts) == 1 && unknown == 0 {
for model, count := range modelCounts {
return fmt.Sprintf("CPU: %d x %s", count, model)
}
}
parts := make([]string, 0, len(modelCounts)+1)
if len(modelCounts) > 0 {
keys := make([]string, 0, len(modelCounts))
for key := range modelCounts {
keys = append(keys, key)
}
sort.Strings(keys)
for _, key := range keys {
parts = append(parts, fmt.Sprintf("%d x %s", modelCounts[key], key))
}
}
if unknown > 0 {
parts = append(parts, fmt.Sprintf("%d x unknown", unknown))
}
return "CPU: " + strings.Join(parts, ", ")
}
func formatMemoryLine(dimms []schema.HardwareMemory) string {
totalMB := 0
present := 0
types := map[string]struct{}{}
for _, dimm := range dimms {
if dimm.Present != nil && !*dimm.Present {
continue
}
if dimm.SizeMB == nil || *dimm.SizeMB <= 0 {
continue
}
present++
totalMB += *dimm.SizeMB
if value := trimPtr(dimm.Type); value != "" {
types[value] = struct{}{}
}
}
if totalMB == 0 {
return ""
}
typeText := joinSortedKeys(types)
line := fmt.Sprintf("Memory: %s", humanizeMB(totalMB))
if typeText != "" {
line += " " + typeText
}
if present > 0 {
line += fmt.Sprintf(" (%d DIMMs)", present)
}
return line
}
func formatStorageLine(disks []schema.HardwareStorage) string {
count := 0
totalGB := 0
for _, disk := range disks {
if disk.Present != nil && !*disk.Present {
continue
}
count++
if disk.SizeGB != nil && *disk.SizeGB > 0 {
totalGB += *disk.SizeGB
}
}
if count == 0 {
return ""
}
line := fmt.Sprintf("Storage: %d drives", count)
if totalGB > 0 {
line += fmt.Sprintf(" / %s", humanizeGB(totalGB))
}
return line
}
func formatGPULine(devices []schema.HardwarePCIeDevice) string {
gpus := map[string]int{}
for _, dev := range devices {
if !isGPUDevice(dev) {
continue
}
name := firstNonEmpty(trimPtr(dev.Model), trimPtr(dev.Manufacturer), "unknown")
gpus[name]++
}
if len(gpus) == 0 {
return ""
}
keys := make([]string, 0, len(gpus))
for key := range gpus {
keys = append(keys, key)
}
sort.Strings(keys)
parts := make([]string, 0, len(keys))
for _, key := range keys {
parts = append(parts, fmt.Sprintf("%d x %s", gpus[key], key))
}
return "GPU: " + strings.Join(parts, ", ")
}
func formatIPLine(list func() ([]platform.InterfaceInfo, error)) string {
if list == nil {
return ""
}
ifaces, err := list()
if err != nil {
return ""
}
seen := map[string]struct{}{}
var ips []string
for _, iface := range ifaces {
for _, ip := range iface.IPv4 {
ip = strings.TrimSpace(ip)
if ip == "" {
continue
}
if _, ok := seen[ip]; ok {
continue
}
seen[ip] = struct{}{}
ips = append(ips, ip)
}
}
if len(ips) == 0 {
return ""
}
sort.Strings(ips)
return "IP: " + strings.Join(ips, ", ")
}
func isGPUDevice(dev schema.HardwarePCIeDevice) bool {
class := trimPtr(dev.DeviceClass)
model := strings.ToLower(trimPtr(dev.Model))
vendor := strings.ToLower(trimPtr(dev.Manufacturer))
// Exclude ASPEED (BMC VGA adapter, not a compute GPU)
if strings.Contains(vendor, "aspeed") || strings.Contains(model, "aspeed") {
return false
}
// AMD Instinct / Radeon compute GPUs have class ProcessingAccelerator or DisplayController.
// Do NOT match by AMD vendor alone — chipset/CPU PCIe devices share that vendor.
return class == "VideoController" ||
class == "DisplayController" ||
class == "ProcessingAccelerator" ||
strings.Contains(model, "nvidia") ||
strings.Contains(vendor, "nvidia")
}
func trimPtr(value *string) string {
if value == nil {
return ""
}
return strings.TrimSpace(*value)
}
func joinSortedKeys(values map[string]struct{}) string {
if len(values) == 0 {
return ""
}
keys := make([]string, 0, len(values))
for key := range values {
keys = append(keys, key)
}
sort.Strings(keys)
return strings.Join(keys, "/")
}
func humanizeMB(totalMB int) string {
if totalMB <= 0 {
return ""
}
gb := float64(totalMB) / 1024.0
if gb >= 1024.0 {
tb := gb / 1024.0
return fmt.Sprintf("%.1f TB", tb)
}
if gb == float64(int64(gb)) {
return fmt.Sprintf("%.0f GB", gb)
}
return fmt.Sprintf("%.1f GB", gb)
}
func humanizeGB(totalGB int) string {
if totalGB <= 0 {
return ""
}
tb := float64(totalGB) / 1024.0
if tb >= 1.0 {
return fmt.Sprintf("%.1f TB", tb)
}
return fmt.Sprintf("%d GB", totalGB)
}
func parseKeyValueSummary(raw string) map[string]string {
out := map[string]string{}
for _, line := range strings.Split(raw, "\n") {
line = strings.TrimSpace(line)
if line == "" {
continue
}
key, value, ok := strings.Cut(line, "=")
if !ok {
continue
}
out[strings.TrimSpace(key)] = strings.TrimSpace(value)
}
return out
}
func firstNonEmpty(values ...string) string {
for _, value := range values {
value = strings.TrimSpace(value)
if value != "" {
return value
}
}
return ""
}
func (a *App) ListInstallDisks() ([]platform.InstallDisk, error) {
return a.installer.ListInstallDisks()
}
func (a *App) InstallToDisk(ctx context.Context, device string, logFile string) error {
return a.installer.InstallToDisk(ctx, device, logFile)
}
func formatSATDetail(raw string) string {
var b strings.Builder
kv := parseKeyValueSummary(raw)
if t, ok := kv["run_at_utc"]; ok {
fmt.Fprintf(&b, "Run: %s\n\n", t)
}
lines := strings.Split(raw, "\n")
var stepKeys []string
seenStep := map[string]bool{}
for _, line := range lines {
if idx := strings.Index(line, "_status="); idx >= 0 {
key := line[:idx]
if !seenStep[key] && key != "overall" {
seenStep[key] = true
stepKeys = append(stepKeys, key)
}
}
}
for _, key := range stepKeys {
status := kv[key+"_status"]
display := cleanSummaryKey(key)
switch status {
case "OK":
fmt.Fprintf(&b, "PASS %s\n", display)
case "FAILED":
fmt.Fprintf(&b, "FAIL %s\n", display)
case "UNSUPPORTED":
fmt.Fprintf(&b, "SKIP %s\n", display)
default:
fmt.Fprintf(&b, "? %s\n", display)
}
}
if overall, ok := kv["overall_status"]; ok {
ok2 := kv["job_ok"]
failed := kv["job_failed"]
fmt.Fprintf(&b, "\nOverall: %s (ok=%s failed=%s)", overall, ok2, failed)
}
return strings.TrimSpace(b.String())
}
func cleanSummaryKey(key string) string {
idx := strings.Index(key, "-")
if idx <= 0 {
return key
}
prefix := key[:idx]
for _, c := range prefix {
if c < '0' || c > '9' {
return key
}
}
return key[idx+1:]
}