feat(watchdog): hardware error monitor + unified component status store
- Add platform/error_patterns.go: pluggable table of kernel log patterns (NVIDIA/GPU, PCIe AER, storage I/O, MCE, EDAC) — extend by adding one struct - Add app/component_status_db.go: persistent JSON store (component-status.json) keyed by "pcie:BDF", "storage:dev", "cpu:all", "memory:all"; OK never downgrades Warning or Critical - Add webui/kmsg_watcher.go: goroutine reads /dev/kmsg during SAT tasks, writes Warning to DB for matched hardware errors - Fix task status: overall_status=FAILED in summary.txt now marks task failed - Audit routine overlays component DB statuses into bee-audit.json on every read Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
@@ -9,7 +9,7 @@ import (
|
||||
"bee/audit/internal/schema"
|
||||
)
|
||||
|
||||
func applyLatestSATStatuses(snap *schema.HardwareSnapshot, baseDir string) {
|
||||
func applyLatestSATStatuses(snap *schema.HardwareSnapshot, baseDir string, db *ComponentStatusDB) {
|
||||
if snap == nil || strings.TrimSpace(baseDir) == "" {
|
||||
return
|
||||
}
|
||||
@@ -28,6 +28,8 @@ func applyLatestSATStatuses(snap *schema.HardwareSnapshot, baseDir string) {
|
||||
if summary, ok := loadLatestSATSummary(baseDir, "storage-"); ok {
|
||||
applyStorageSAT(snap.Storage, summary)
|
||||
}
|
||||
// Apply unified component status DB — overlaid last so it can only upgrade severity.
|
||||
applyComponentStatusDB(snap, db)
|
||||
}
|
||||
|
||||
type satSummary struct {
|
||||
@@ -206,6 +208,86 @@ func matchesGPUVendor(dev schema.HardwarePCIeDevice, vendor string) bool {
|
||||
}
|
||||
}
|
||||
|
||||
func applyComponentStatusDB(snap *schema.HardwareSnapshot, db *ComponentStatusDB) {
|
||||
if snap == nil || db == nil {
|
||||
return
|
||||
}
|
||||
for _, rec := range db.All() {
|
||||
key := rec.ComponentKey
|
||||
status := dbStatusToSATStatus(rec.Status)
|
||||
if status == "" {
|
||||
continue
|
||||
}
|
||||
detail := rec.ErrorSummary
|
||||
ts := rec.LastChangedAt.UTC().Format("2006-01-02T15:04:05Z")
|
||||
|
||||
switch {
|
||||
case strings.HasPrefix(key, "pcie:"):
|
||||
bdf := strings.TrimPrefix(key, "pcie:")
|
||||
bdf = strings.TrimPrefix(bdf, "gpu:") // strip sub-type if present
|
||||
// bdf may be empty (e.g. "pcie:gpu:nvidia") — skip BDF matching
|
||||
if sanitizeBDFForLookup(bdf) == "" {
|
||||
break
|
||||
}
|
||||
normalized := sanitizeBDFForLookup(bdf)
|
||||
for i := range snap.PCIeDevices {
|
||||
if snap.PCIeDevices[i].BDF == nil {
|
||||
continue
|
||||
}
|
||||
if sanitizeBDFForLookup(*snap.PCIeDevices[i].BDF) == normalized {
|
||||
mergeComponentStatus(&snap.PCIeDevices[i].HardwareComponentStatus, ts, status, detail)
|
||||
}
|
||||
}
|
||||
case strings.HasPrefix(key, "storage:"):
|
||||
devName := strings.TrimPrefix(key, "storage:")
|
||||
if devName == "all" {
|
||||
for i := range snap.Storage {
|
||||
mergeComponentStatus(&snap.Storage[i].HardwareComponentStatus, ts, status, detail)
|
||||
}
|
||||
} else {
|
||||
for i := range snap.Storage {
|
||||
linuxDev, _ := snap.Storage[i].Telemetry["linux_device"].(string)
|
||||
if filepath.Base(strings.TrimSpace(linuxDev)) == devName {
|
||||
mergeComponentStatus(&snap.Storage[i].HardwareComponentStatus, ts, status, detail)
|
||||
}
|
||||
}
|
||||
}
|
||||
case strings.HasPrefix(key, "memory:"):
|
||||
for i := range snap.Memory {
|
||||
mergeComponentStatus(&snap.Memory[i].HardwareComponentStatus, ts, status, detail)
|
||||
}
|
||||
case strings.HasPrefix(key, "cpu:"):
|
||||
for i := range snap.CPUs {
|
||||
mergeComponentStatus(&snap.CPUs[i].HardwareComponentStatus, ts, status, detail)
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// dbStatusToSATStatus converts ComponentStatusDB status strings to the format
|
||||
// expected by mergeComponentStatus (which uses "OK", "Warning", "Critical", "Unknown").
|
||||
func dbStatusToSATStatus(s string) string {
|
||||
switch strings.TrimSpace(s) {
|
||||
case "OK", "Warning", "Critical", "Unknown":
|
||||
return s
|
||||
default:
|
||||
return ""
|
||||
}
|
||||
}
|
||||
|
||||
// sanitizeBDFForLookup normalises a PCIe BDF address to a canonical lower-case form
|
||||
// suitable for comparison. "c8:00.0" → "0000:c8:00.0"; already-full BDFs are left as-is.
|
||||
func sanitizeBDFForLookup(bdf string) string {
|
||||
bdf = strings.ToLower(strings.TrimSpace(bdf))
|
||||
if bdf == "" || bdf == "gpu" || strings.ContainsAny(bdf, " \t") {
|
||||
return ""
|
||||
}
|
||||
if strings.Count(bdf, ":") == 1 {
|
||||
bdf = "0000:" + bdf
|
||||
}
|
||||
return bdf
|
||||
}
|
||||
|
||||
func ptrString(v *string) string {
|
||||
if v == nil {
|
||||
return ""
|
||||
|
||||
Reference in New Issue
Block a user