Redesign dashboard: split Runtime Health and Hardware Summary

- Runtime Health now shows only LiveCD system status (services, tools,
  drivers, network, CUDA/ROCm) — hardware component rows removed
- Hardware Summary now shows server components with readable descriptions
  (model, count×size) and component-status.json health badges
- Add Network Adapters row to Hardware Summary
- SFP module static info (vendor, PN, SN, connector, type, wavelength)
  now collected via ethtool -m regardless of carrier state
- PSU statuses from IPMI audit written to component-status.json so PSU
  badge shows actual status after first audit instead of UNKNOWN

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
2026-04-09 23:41:23 +03:00
parent c1690a084b
commit 05241f2e0e
7 changed files with 386 additions and 110 deletions

View File

@@ -190,6 +190,7 @@ func (a *App) RunAudit(runtimeMode runtimeenv.Mode, output string) (string, erro
}
result := collector.Run(runtimeMode)
applyLatestSATStatuses(&result.Hardware, DefaultSATBaseDir, a.StatusDB)
writePSUStatusesToDB(a.StatusDB, result.Hardware.PowerSupplies)
if health, err := ReadRuntimeHealth(DefaultRuntimeJSONPath); err == nil {
result.Runtime = &health
}
@@ -926,6 +927,41 @@ func bodyOr(body, fallback string) string {
return body
}
// writePSUStatusesToDB records PSU statuses collected during audit into the
// component-status DB so they are visible in the Hardware Summary card.
// PSU status is sourced from IPMI (ipmitool fru + sdr) during audit.
func writePSUStatusesToDB(db *ComponentStatusDB, psus []schema.HardwarePowerSupply) {
if db == nil || len(psus) == 0 {
return
}
const source = "audit:ipmi"
worstStatus := "OK"
for _, psu := range psus {
if psu.Status == nil {
continue
}
slot := "?"
if psu.Slot != nil {
slot = *psu.Slot
}
st := *psu.Status
detail := ""
if psu.ErrorDescription != nil {
detail = *psu.ErrorDescription
}
db.Record("psu:"+slot, source, st, detail)
switch st {
case "Critical":
worstStatus = "Critical"
case "Warning":
if worstStatus != "Critical" {
worstStatus = "Warning"
}
}
}
db.Record("psu:all", source, worstStatus, "")
}
func ReadRuntimeHealth(path string) (schema.RuntimeHealth, error) {
raw, err := os.ReadFile(path)
if err != nil {