Add continuous hardware health monitoring and component detail view

- kmsg watcher now records kernel errors (GPU Xid, MCE, EDAC, storage I/O) at all times,
  not only during SAT tasks; flushImmediate writes directly to ComponentStatusDB
- New health_poller: polls ipmitool sdr every 60s for PSU health (watchdog:psu source)
- Hardware Summary card auto-refreshes every 30s via htmx without page reload
- Component rows (CPU/Memory/Storage/GPU/PSU) are now clickable -- opens a modal
  with per-component status, source, timestamp and last 20 history entries

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Mikhail Chusavitin
2026-05-06 09:56:39 +03:00
parent ca78b9df65
commit ae80d7711e
5 changed files with 272 additions and 12 deletions

View File

@@ -1679,6 +1679,56 @@ func (h *handler) handleAPIBenchmarkResults(w http.ResponseWriter, r *http.Reque
fmt.Fprint(w, renderBenchmarkResultsCard(h.opts.ExportDir))
}
// ── Hardware summary / component detail ──────────────────────────────────────
// handleAPIHardwareSummary returns the hardware summary card HTML fragment for
// htmx polling (hx-get="/api/hardware-summary" hx-swap="outerHTML").
func (h *handler) handleAPIHardwareSummary(w http.ResponseWriter, _ *http.Request) {
w.Header().Set("Content-Type", "text/html; charset=utf-8")
w.Header().Set("Cache-Control", "no-store")
fmt.Fprint(w, renderHardwareSummaryCard(h.opts))
}
// handleAPIComponentDetail returns an HTML fragment describing the current and
// historical status for one component type (cpu, memory, storage, gpu, psu).
func (h *handler) handleAPIComponentDetail(w http.ResponseWriter, r *http.Request) {
compType := r.PathValue("type")
var exact, prefixes []string
var title string
switch compType {
case "cpu":
title = "CPU"
exact = []string{"cpu:all"}
case "memory":
title = "Memory"
exact = []string{"memory:all"}
prefixes = []string{"memory:"}
case "storage":
title = "Storage"
exact = []string{"storage:all"}
prefixes = []string{"storage:"}
case "gpu":
title = "GPU"
prefixes = []string{"pcie:gpu:"}
case "psu":
title = "PSU"
prefixes = []string{"psu:"}
default:
http.NotFound(w, r)
return
}
var records []app.ComponentStatusRecord
if h.opts.App != nil && h.opts.App.StatusDB != nil {
all := h.opts.App.StatusDB.All()
records = matchedRecords(all, exact, prefixes)
}
w.Header().Set("Content-Type", "text/html; charset=utf-8")
w.Header().Set("Cache-Control", "no-store")
fmt.Fprint(w, renderComponentDetail(title, records))
}
func (h *handler) rollbackPendingNetworkChange() error {
h.pendingNetMu.Lock()
pnc := h.pendingNet