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:
@@ -23,7 +23,7 @@ func TestApplyLatestSATStatusesMarksStorageByDevice(t *testing.T) {
|
||||
usb := schema.HardwareStorage{Telemetry: map[string]any{"linux_device": "/dev/sda"}}
|
||||
snap := schema.HardwareSnapshot{Storage: []schema.HardwareStorage{nvme, usb}}
|
||||
|
||||
applyLatestSATStatuses(&snap, baseDir)
|
||||
applyLatestSATStatuses(&snap, baseDir, nil)
|
||||
|
||||
if snap.Storage[0].Status == nil || *snap.Storage[0].Status != "OK" {
|
||||
t.Fatalf("nvme status=%v want OK", snap.Storage[0].Status)
|
||||
@@ -53,7 +53,7 @@ func TestApplyLatestSATStatusesMarksAMDGPUs(t *testing.T) {
|
||||
}},
|
||||
}
|
||||
|
||||
applyLatestSATStatuses(&snap, baseDir)
|
||||
applyLatestSATStatuses(&snap, baseDir, nil)
|
||||
|
||||
if snap.PCIeDevices[0].Status == nil || *snap.PCIeDevices[0].Status != "Critical" {
|
||||
t.Fatalf("gpu status=%v want Critical", snap.PCIeDevices[0].Status)
|
||||
|
||||
Reference in New Issue
Block a user