feat: task queue, UI overhaul, burn tests, install-to-RAM
- Task queue: all SAT/audit jobs enqueue and run one-at-a-time; tasks persist past page navigation; new Tasks page with cancel/priority/log stream - UI: consolidate nav (Validate, Burn, Tasks, Tools); Audit becomes modal; Dashboard hardware summary badges + split metrics charts (load/temp/power); Tools page consolidates network, services, install, support bundle - AMD GPU: acceptance test and stress burn cards; GPU presence API greys out irrelevant SAT cards automatically - Burn tests: Memory Stress (stress-ng --vm), SAT Stress (stressapptest) - Install to RAM: copies squashfs to /dev/shm, re-associates loop devices via LOOP_CHANGE_FD ioctl so live media can be ejected - Charts: relative time axis (0 = now, negative left) - memtester: LimitMEMLOCK=infinity in bee-web.service; empty output → UNSUPPORTED - SAT overlay applied dynamically on every /audit.json serve - MIME panic guard for LiveCD ramdisk I/O errors - ISO: add memtest86+, stressapptest packages; memtest86+ GRUB entry; disable screensaver/DPMS in bee-openbox-session - Unknown SAT status severity = 1 (does not override OK) Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
@@ -53,6 +53,8 @@ type networkManager interface {
|
||||
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)
|
||||
}
|
||||
|
||||
type serviceManager interface {
|
||||
@@ -75,20 +77,46 @@ type toolManager interface {
|
||||
type installer interface {
|
||||
ListInstallDisks() ([]platform.InstallDisk, error)
|
||||
InstallToDisk(ctx context.Context, device string, logFile string) error
|
||||
IsLiveMediaInRAM() bool
|
||||
RunInstallToRAM(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) RunInstallToRAM(logFunc func(string)) error {
|
||||
return a.installer.RunInstallToRAM(logFunc)
|
||||
}
|
||||
|
||||
type satRunner interface {
|
||||
RunNvidiaAcceptancePack(baseDir string) (string, error)
|
||||
RunNvidiaAcceptancePackWithOptions(ctx context.Context, baseDir string, diagLevel int, gpuIndices []int) (string, error)
|
||||
RunMemoryAcceptancePack(baseDir string) (string, error)
|
||||
RunStorageAcceptancePack(baseDir string) (string, error)
|
||||
RunCPUAcceptancePack(baseDir string, durationSec int) (string, error)
|
||||
RunNvidiaAcceptancePack(baseDir string, logFunc func(string)) (string, error)
|
||||
RunNvidiaAcceptancePackWithOptions(ctx context.Context, baseDir string, diagLevel int, gpuIndices []int, logFunc func(string)) (string, error)
|
||||
RunMemoryAcceptancePack(baseDir string, logFunc func(string)) (string, error)
|
||||
RunStorageAcceptancePack(baseDir string, logFunc func(string)) (string, error)
|
||||
RunCPUAcceptancePack(baseDir string, durationSec int, logFunc func(string)) (string, error)
|
||||
ListNvidiaGPUs() ([]platform.NvidiaGPU, error)
|
||||
DetectGPUVendor() string
|
||||
ListAMDGPUs() ([]platform.AMDGPUInfo, error)
|
||||
RunAMDAcceptancePack(baseDir string) (string, error)
|
||||
RunAMDAcceptancePack(baseDir string, logFunc func(string)) (string, error)
|
||||
RunAMDStressPack(baseDir string, logFunc func(string)) (string, error)
|
||||
RunMemoryStressPack(baseDir string, logFunc func(string)) (string, error)
|
||||
RunSATStressPack(baseDir string, logFunc func(string)) (string, error)
|
||||
RunFanStressTest(ctx context.Context, baseDir string, opts platform.FanStressOptions) (string, error)
|
||||
RunNCCLTests(ctx context.Context, baseDir string) (string, error)
|
||||
RunNCCLTests(ctx context.Context, baseDir string, logFunc func(string)) (string, error)
|
||||
}
|
||||
|
||||
type runtimeChecker interface {
|
||||
@@ -108,6 +136,17 @@ func New(platform *platform.System) *App {
|
||||
}
|
||||
}
|
||||
|
||||
// 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) {
|
||||
var snap schema.HardwareIngestRequest
|
||||
if err := json.Unmarshal(auditJSON, &snap); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
applyLatestSATStatuses(&snap.Hardware, DefaultSATBaseDir)
|
||||
return json.MarshalIndent(snap, "", " ")
|
||||
}
|
||||
|
||||
func (a *App) RunAudit(runtimeMode runtimeenv.Mode, output string) (string, error) {
|
||||
if runtimeMode == runtimeenv.ModeLiveCD {
|
||||
if err := a.runtime.CaptureTechnicalDump(DefaultTechDumpDir); err != nil {
|
||||
@@ -301,6 +340,14 @@ 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) 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
|
||||
@@ -416,15 +463,15 @@ func (a *App) AuditLogTailResult() ActionResult {
|
||||
return ActionResult{Title: "Audit log tail", Body: body}
|
||||
}
|
||||
|
||||
func (a *App) RunNvidiaAcceptancePack(baseDir string) (string, error) {
|
||||
func (a *App) RunNvidiaAcceptancePack(baseDir string, logFunc func(string)) (string, error) {
|
||||
if strings.TrimSpace(baseDir) == "" {
|
||||
baseDir = DefaultSATBaseDir
|
||||
}
|
||||
return a.sat.RunNvidiaAcceptancePack(baseDir)
|
||||
return a.sat.RunNvidiaAcceptancePack(baseDir, logFunc)
|
||||
}
|
||||
|
||||
func (a *App) RunNvidiaAcceptancePackResult(baseDir string) (ActionResult, error) {
|
||||
path, err := a.RunNvidiaAcceptancePack(baseDir)
|
||||
path, err := a.RunNvidiaAcceptancePack(baseDir, nil)
|
||||
body := "Archive written."
|
||||
if path != "" {
|
||||
body = "Archive written to " + path
|
||||
@@ -436,11 +483,11 @@ func (a *App) ListNvidiaGPUs() ([]platform.NvidiaGPU, error) {
|
||||
return a.sat.ListNvidiaGPUs()
|
||||
}
|
||||
|
||||
func (a *App) RunNvidiaAcceptancePackWithOptions(ctx context.Context, baseDir string, diagLevel int, gpuIndices []int) (ActionResult, error) {
|
||||
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)
|
||||
path, err := a.sat.RunNvidiaAcceptancePackWithOptions(ctx, baseDir, diagLevel, gpuIndices, logFunc)
|
||||
body := "Archive written."
|
||||
if path != "" {
|
||||
body = "Archive written to " + path
|
||||
@@ -448,39 +495,39 @@ func (a *App) RunNvidiaAcceptancePackWithOptions(ctx context.Context, baseDir st
|
||||
return ActionResult{Title: "NVIDIA DCGM", Body: body}, err
|
||||
}
|
||||
|
||||
func (a *App) RunMemoryAcceptancePack(baseDir string) (string, error) {
|
||||
func (a *App) RunMemoryAcceptancePack(baseDir string, logFunc func(string)) (string, error) {
|
||||
if strings.TrimSpace(baseDir) == "" {
|
||||
baseDir = DefaultSATBaseDir
|
||||
}
|
||||
return a.sat.RunMemoryAcceptancePack(baseDir)
|
||||
return a.sat.RunMemoryAcceptancePack(baseDir, logFunc)
|
||||
}
|
||||
|
||||
func (a *App) RunMemoryAcceptancePackResult(baseDir string) (ActionResult, error) {
|
||||
path, err := a.RunMemoryAcceptancePack(baseDir)
|
||||
path, err := a.RunMemoryAcceptancePack(baseDir, nil)
|
||||
return ActionResult{Title: "Memory SAT", Body: satResultBody(path)}, err
|
||||
}
|
||||
|
||||
func (a *App) RunCPUAcceptancePack(baseDir string, durationSec int) (string, error) {
|
||||
func (a *App) RunCPUAcceptancePack(baseDir string, durationSec int, logFunc func(string)) (string, error) {
|
||||
if strings.TrimSpace(baseDir) == "" {
|
||||
baseDir = DefaultSATBaseDir
|
||||
}
|
||||
return a.sat.RunCPUAcceptancePack(baseDir, durationSec)
|
||||
return a.sat.RunCPUAcceptancePack(baseDir, durationSec, logFunc)
|
||||
}
|
||||
|
||||
func (a *App) RunCPUAcceptancePackResult(baseDir string, durationSec int) (ActionResult, error) {
|
||||
path, err := a.RunCPUAcceptancePack(baseDir, durationSec)
|
||||
path, err := a.RunCPUAcceptancePack(baseDir, durationSec, nil)
|
||||
return ActionResult{Title: "CPU SAT", Body: satResultBody(path)}, err
|
||||
}
|
||||
|
||||
func (a *App) RunStorageAcceptancePack(baseDir string) (string, error) {
|
||||
func (a *App) RunStorageAcceptancePack(baseDir string, logFunc func(string)) (string, error) {
|
||||
if strings.TrimSpace(baseDir) == "" {
|
||||
baseDir = DefaultSATBaseDir
|
||||
}
|
||||
return a.sat.RunStorageAcceptancePack(baseDir)
|
||||
return a.sat.RunStorageAcceptancePack(baseDir, logFunc)
|
||||
}
|
||||
|
||||
func (a *App) RunStorageAcceptancePackResult(baseDir string) (ActionResult, error) {
|
||||
path, err := a.RunStorageAcceptancePack(baseDir)
|
||||
path, err := a.RunStorageAcceptancePack(baseDir, nil)
|
||||
return ActionResult{Title: "Storage SAT", Body: satResultBody(path)}, err
|
||||
}
|
||||
|
||||
@@ -492,18 +539,33 @@ func (a *App) ListAMDGPUs() ([]platform.AMDGPUInfo, error) {
|
||||
return a.sat.ListAMDGPUs()
|
||||
}
|
||||
|
||||
func (a *App) RunAMDAcceptancePack(baseDir string) (string, error) {
|
||||
func (a *App) RunAMDAcceptancePack(baseDir string, logFunc func(string)) (string, error) {
|
||||
if strings.TrimSpace(baseDir) == "" {
|
||||
baseDir = DefaultSATBaseDir
|
||||
}
|
||||
return a.sat.RunAMDAcceptancePack(baseDir)
|
||||
return a.sat.RunAMDAcceptancePack(baseDir, logFunc)
|
||||
}
|
||||
|
||||
func (a *App) RunAMDAcceptancePackResult(baseDir string) (ActionResult, error) {
|
||||
path, err := a.RunAMDAcceptancePack(baseDir)
|
||||
path, err := a.RunAMDAcceptancePack(baseDir, nil)
|
||||
return ActionResult{Title: "AMD GPU SAT", Body: satResultBody(path)}, err
|
||||
}
|
||||
|
||||
func (a *App) RunMemoryStressPack(baseDir string, logFunc func(string)) (string, error) {
|
||||
return a.sat.RunMemoryStressPack(baseDir, logFunc)
|
||||
}
|
||||
|
||||
func (a *App) RunSATStressPack(baseDir string, logFunc func(string)) (string, error) {
|
||||
return a.sat.RunSATStressPack(baseDir, logFunc)
|
||||
}
|
||||
|
||||
func (a *App) RunAMDStressPack(baseDir string, logFunc func(string)) (string, error) {
|
||||
if strings.TrimSpace(baseDir) == "" {
|
||||
baseDir = DefaultSATBaseDir
|
||||
}
|
||||
return a.sat.RunAMDStressPack(baseDir, logFunc)
|
||||
}
|
||||
|
||||
func (a *App) RunFanStressTest(ctx context.Context, baseDir string, opts platform.FanStressOptions) (string, error) {
|
||||
if strings.TrimSpace(baseDir) == "" {
|
||||
baseDir = DefaultSATBaseDir
|
||||
@@ -512,7 +574,7 @@ func (a *App) RunFanStressTest(ctx context.Context, baseDir string, opts platfor
|
||||
}
|
||||
|
||||
func (a *App) RunNCCLTestsResult(ctx context.Context) (ActionResult, error) {
|
||||
path, err := a.sat.RunNCCLTests(ctx, DefaultSATBaseDir)
|
||||
path, err := a.sat.RunNCCLTests(ctx, DefaultSATBaseDir, nil)
|
||||
body := "Results: " + path
|
||||
if err != nil && err != context.Canceled {
|
||||
body += "\nERROR: " + err.Error()
|
||||
|
||||
@@ -43,6 +43,9 @@ func (f fakeNetwork) SetStaticIPv4(cfg platform.StaticIPv4Config) (string, error
|
||||
return f.setStaticIPv4Fn(cfg)
|
||||
}
|
||||
|
||||
func (f fakeNetwork) SetInterfaceState(_ string, _ bool) error { return nil }
|
||||
func (f fakeNetwork) GetInterfaceState(_ string) (bool, error) { return true, nil }
|
||||
|
||||
type fakeServices struct {
|
||||
serviceStatusFn func(string) (string, error)
|
||||
serviceDoFn func(string, platform.ServiceAction) (string, error)
|
||||
@@ -123,11 +126,11 @@ type fakeSAT struct {
|
||||
listNvidiaGPUsFn func() ([]platform.NvidiaGPU, error)
|
||||
}
|
||||
|
||||
func (f fakeSAT) RunNvidiaAcceptancePack(baseDir string) (string, error) {
|
||||
func (f fakeSAT) RunNvidiaAcceptancePack(baseDir string, _ func(string)) (string, error) {
|
||||
return f.runNvidiaFn(baseDir)
|
||||
}
|
||||
|
||||
func (f fakeSAT) RunNvidiaAcceptancePackWithOptions(_ context.Context, baseDir string, _ int, _ []int) (string, error) {
|
||||
func (f fakeSAT) RunNvidiaAcceptancePackWithOptions(_ context.Context, baseDir string, _ int, _ []int, _ func(string)) (string, error) {
|
||||
return f.runNvidiaFn(baseDir)
|
||||
}
|
||||
|
||||
@@ -138,15 +141,15 @@ func (f fakeSAT) ListNvidiaGPUs() ([]platform.NvidiaGPU, error) {
|
||||
return nil, nil
|
||||
}
|
||||
|
||||
func (f fakeSAT) RunMemoryAcceptancePack(baseDir string) (string, error) {
|
||||
func (f fakeSAT) RunMemoryAcceptancePack(baseDir string, _ func(string)) (string, error) {
|
||||
return f.runMemoryFn(baseDir)
|
||||
}
|
||||
|
||||
func (f fakeSAT) RunStorageAcceptancePack(baseDir string) (string, error) {
|
||||
func (f fakeSAT) RunStorageAcceptancePack(baseDir string, _ func(string)) (string, error) {
|
||||
return f.runStorageFn(baseDir)
|
||||
}
|
||||
|
||||
func (f fakeSAT) RunCPUAcceptancePack(baseDir string, durationSec int) (string, error) {
|
||||
func (f fakeSAT) RunCPUAcceptancePack(baseDir string, durationSec int, _ func(string)) (string, error) {
|
||||
if f.runCPUFn != nil {
|
||||
return f.runCPUFn(baseDir, durationSec)
|
||||
}
|
||||
@@ -167,18 +170,22 @@ func (f fakeSAT) ListAMDGPUs() ([]platform.AMDGPUInfo, error) {
|
||||
return nil, nil
|
||||
}
|
||||
|
||||
func (f fakeSAT) RunAMDAcceptancePack(baseDir string) (string, error) {
|
||||
func (f fakeSAT) RunAMDAcceptancePack(baseDir string, _ func(string)) (string, error) {
|
||||
if f.runAMDPackFn != nil {
|
||||
return f.runAMDPackFn(baseDir)
|
||||
}
|
||||
return "", nil
|
||||
}
|
||||
|
||||
func (f fakeSAT) RunAMDStressPack(_ string, _ func(string)) (string, error) { return "", nil }
|
||||
func (f fakeSAT) RunMemoryStressPack(_ string, _ func(string)) (string, error) { return "", nil }
|
||||
func (f fakeSAT) RunSATStressPack(_ string, _ func(string)) (string, error) { return "", nil }
|
||||
|
||||
func (f fakeSAT) RunFanStressTest(_ context.Context, _ string, _ platform.FanStressOptions) (string, error) {
|
||||
return "", nil
|
||||
}
|
||||
|
||||
func (f fakeSAT) RunNCCLTests(_ context.Context, _ string) (string, error) {
|
||||
func (f fakeSAT) RunNCCLTests(_ context.Context, _ string, _ func(string)) (string, error) {
|
||||
return "", nil
|
||||
}
|
||||
|
||||
@@ -574,13 +581,13 @@ func TestRunSATDefaultsToExportDir(t *testing.T) {
|
||||
},
|
||||
}
|
||||
|
||||
if _, err := a.RunNvidiaAcceptancePack(""); err != nil {
|
||||
if _, err := a.RunNvidiaAcceptancePack("", nil); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if _, err := a.RunMemoryAcceptancePack(""); err != nil {
|
||||
if _, err := a.RunMemoryAcceptancePack("", nil); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if _, err := a.RunStorageAcceptancePack(""); err != nil {
|
||||
if _, err := a.RunStorageAcceptancePack("", nil); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -141,9 +141,11 @@ func satSummaryStatus(summary satSummary, label string) (string, string, bool) {
|
||||
func satKeyStatus(rawStatus, label string) (string, string, bool) {
|
||||
switch strings.ToUpper(strings.TrimSpace(rawStatus)) {
|
||||
case "OK":
|
||||
return "OK", label + " passed", true
|
||||
// No error description on success — error_description is for problems only.
|
||||
return "OK", "", true
|
||||
case "PARTIAL", "UNSUPPORTED", "CANCELED", "CANCELLED":
|
||||
return "Warning", label + " incomplete", true
|
||||
// Tool couldn't run or test was incomplete — we can't assert hardware health.
|
||||
return "Unknown", "", true
|
||||
case "FAILED":
|
||||
return "Critical", label + " failed", true
|
||||
default:
|
||||
@@ -180,6 +182,8 @@ func statusSeverity(status string) int {
|
||||
return 2
|
||||
case "OK":
|
||||
return 1
|
||||
case "Unknown":
|
||||
return 1 // same as OK — does not override OK from another source
|
||||
default:
|
||||
return 0
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user