Add guest root cause diagnostics

agent_test.go

@@ -69,6 +69,21 @@ func TestClassifyAgentService(t *testing.T) {
 	}
 }
 
+func TestAgentServiceDiagnosticsHelpers(t *testing.T) {
+	if got := compactSystemdExec(`{ path=/usr/bin/example ; argv[]=/usr/bin/example --serve ; }`); got != "/usr/bin/example" {
+		t.Fatalf("unexpected executable: %q", got)
+	}
+	fields := limitedFields("a b c d", 2)
+	if len(fields) != 2 || fields[0] != "a" || fields[1] != "b" {
+		t.Fatalf("unexpected limited fields: %#v", fields)
+	}
+	ports := appendUniqueInt([]int{80}, 80)
+	ports = appendUniqueInt(ports, 443)
+	if len(ports) != 2 || ports[1] != 443 {
+		t.Fatalf("unexpected ports: %#v", ports)
+	}
+}
+
 func TestAgentReportAuthenticationAndOfflineState(t *testing.T) {
 	store, err := openStore(":memory:")
 	if err != nil {
@@ -110,3 +125,22 @@ func TestAgentProblemsBecomeMaintenanceAwareAlerts(t *testing.T) {
 		t.Fatalf("active=%d planned=%d alerts=%#v", len(active), len(planned), alerts)
 	}
 }
+
+func TestAgentDiagnosticsBecomeAlerts(t *testing.T) {
+	metrics := dashboardMetrics{Agents: []ManagedAgent{{ID: "node", Name: "app", VMID: 105, Online: true, Report: AgentReport{
+		Services:    []AgentService{{Name: "web.service", State: "active", Flapping: true, Restarts: 8, StartedAt: time.Now().Unix()}},
+		Filesystems: []AgentFilesystem{{Mountpoint: "/data", TotalBytes: 1000, UsedBytes: 950, UsedPercent: 95}},
+	}}}}
+	alerts := evaluateAlerts(metrics, defaultThresholds())
+	wanted := map[string]bool{"agent-flapping-node-web.service-105": false, "agent-filesystem-node-/data-105": false}
+	for _, alert := range alerts {
+		if _, ok := wanted[alert.ID]; ok {
+			wanted[alert.ID] = true
+		}
+	}
+	for id, found := range wanted {
+		if !found {
+			t.Fatalf("missing alert %s in %#v", id, alerts)
+		}
+	}
+}