fd722692a4
- 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>
62 lines
1.9 KiB
Go
62 lines
1.9 KiB
Go
package app
|
|
|
|
import (
|
|
"os"
|
|
"path/filepath"
|
|
"testing"
|
|
|
|
"bee/audit/internal/schema"
|
|
)
|
|
|
|
func TestApplyLatestSATStatusesMarksStorageByDevice(t *testing.T) {
|
|
baseDir := t.TempDir()
|
|
runDir := filepath.Join(baseDir, "storage-20260325-161151")
|
|
if err := os.MkdirAll(runDir, 0755); err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
raw := "run_at_utc=2026-03-25T16:11:51Z\nnvme0n1_nvme_smart_log_status=OK\nsda_smartctl_health_status=FAILED\noverall_status=FAILED\n"
|
|
if err := os.WriteFile(filepath.Join(runDir, "summary.txt"), []byte(raw), 0644); err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
|
|
nvme := schema.HardwareStorage{Telemetry: map[string]any{"linux_device": "/dev/nvme0n1"}}
|
|
usb := schema.HardwareStorage{Telemetry: map[string]any{"linux_device": "/dev/sda"}}
|
|
snap := schema.HardwareSnapshot{Storage: []schema.HardwareStorage{nvme, usb}}
|
|
|
|
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)
|
|
}
|
|
if snap.Storage[1].Status == nil || *snap.Storage[1].Status != "Critical" {
|
|
t.Fatalf("sda status=%v want Critical", snap.Storage[1].Status)
|
|
}
|
|
}
|
|
|
|
func TestApplyLatestSATStatusesMarksAMDGPUs(t *testing.T) {
|
|
baseDir := t.TempDir()
|
|
runDir := filepath.Join(baseDir, "gpu-amd-20260325-161436")
|
|
if err := os.MkdirAll(runDir, 0755); err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
raw := "run_at_utc=2026-03-25T16:14:36Z\noverall_status=FAILED\n"
|
|
if err := os.WriteFile(filepath.Join(runDir, "summary.txt"), []byte(raw), 0644); err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
|
|
class := "DisplayController"
|
|
manufacturer := "Advanced Micro Devices, Inc. [AMD/ATI]"
|
|
snap := schema.HardwareSnapshot{
|
|
PCIeDevices: []schema.HardwarePCIeDevice{{
|
|
DeviceClass: &class,
|
|
Manufacturer: &manufacturer,
|
|
}},
|
|
}
|
|
|
|
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)
|
|
}
|
|
}
|