Skip to content

Commit 6ab4fe5

Browse files
Add new ignored interfaces to NodeNetworkInterfaceDown Alert (#3279)
Signed-off-by: João Vilaça <[email protected]>
1 parent aa76863 commit 6ab4fe5

File tree

1 file changed

+14
-2
lines changed

1 file changed

+14
-2
lines changed

pkg/monitoring/observability/rules/alerts/cluster_alerts.go

+14-2
Original file line numberDiff line numberDiff line change
@@ -1,11 +1,23 @@
11
package alerts
22

33
import (
4+
"fmt"
5+
"strings"
6+
47
promv1 "github.com/prometheus-operator/prometheus-operator/pkg/apis/monitoring/v1"
58
"k8s.io/apimachinery/pkg/util/intstr"
69
"k8s.io/utils/ptr"
710
)
811

12+
var ignoredInterfacesForNetworkDown = []string{
13+
"lo", // loopback interface
14+
"tunbr", // tunnel bridge
15+
"veth.+", // virtual ethernet devices
16+
"ovs-system", // OVS internal system interface
17+
"genev_sys.+", // OVN Geneve overlay/encapsulation interfaces
18+
"br-int", // OVN integration bridge
19+
}
20+
921
func clusterAlerts() []promv1.Rule {
1022
return []promv1.Rule{
1123
{
@@ -23,7 +35,7 @@ func clusterAlerts() []promv1.Rule {
2335
},
2436
{
2537
Alert: "HAControlPlaneDown",
26-
Expr: intstr.FromString("kube_node_role{role=\"control-plane\"} * on(node) kube_node_status_condition{condition=\"Ready\",status=\"true\"} == 0"),
38+
Expr: intstr.FromString("kube_node_role{role='control-plane'} * on(node) kube_node_status_condition{condition='Ready',status='true'} == 0"),
2739
For: ptr.To(promv1.Duration("5m")),
2840
Annotations: map[string]string{
2941
"summary": "Control plane node {{ $labels.node }} is not ready",
@@ -36,7 +48,7 @@ func clusterAlerts() []promv1.Rule {
3648
},
3749
{
3850
Alert: "NodeNetworkInterfaceDown",
39-
Expr: intstr.FromString("count by (instance) (node_network_up{device!~\"veth.+|tunbr\"} == 0) > 0"),
51+
Expr: intstr.FromString(fmt.Sprintf("count by (instance) (node_network_up{device!~'%s'} == 0) > 0", strings.Join(ignoredInterfacesForNetworkDown, "|"))),
4052
For: ptr.To(promv1.Duration("5m")),
4153
Annotations: map[string]string{
4254
"summary": "Network interfaces are down",

0 commit comments

Comments
 (0)