added repo
This commit is contained in:
Your Name
+30
@@ -0,0 +1,30 @@
|
||||
groups:
|
||||
- name: EKS-central-Cilium-Alerts
|
||||
rules:
|
||||
- alert: central-MapOps-Crossed-Threshold
|
||||
expr: topk(5, avg(rate(cilium_bpf_map_ops_total{k8s_app="cilium", map_name=~"snat_v4_external", operation=~"delete", cluster=~".*central.*"}[5m])) by (kubernetes_pod_name, instance, map_name, operation, cluster)) <= 40
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: infra
|
||||
team: devops
|
||||
service: eks-cilium
|
||||
env: prd
|
||||
priority: p0
|
||||
annotations:
|
||||
summary: "central Cilium Map Ops has crossed 40 Ops per Second for Map Name - snat_v4_external, operation - delete, Pod - {{ $labels.kubernetes_pod_name }}, Instance - {{ $labels.instance }}, cluster - {{ $labels.cluster }} and the value is {{ $value }}"
|
||||
description: "central Cilium Map Ops has crossed 40 Ops per Second for Map Name - snat_v4_external, operation - delete, Pod - {{ $labels.kubernetes_pod_name }}, Instance - {{ $labels.instance }}, cluster - {{ $labels.cluster }} and the value is {{ $value }}\n Labels - {{ $labels }}"
|
||||
|
||||
- alert: SubnetOutofIpsForCentralCluster
|
||||
expr: sum(cilium_operator_ipam_available_ips_per_subnet{cluster=~".*central.*",subnet_id!~"(subnet-068af921836ca6723|subnet-025917a40be07542c)"}) by (cluster) < 700
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: infra
|
||||
team: devops
|
||||
service: eks-cilium
|
||||
env: prd
|
||||
priority: p0
|
||||
annotations:
|
||||
summary: "Cluster {{ $labels.cluster }} has ip address less than 700. Please check"
|
||||
description: "Cluster {{ $labels.cluster }} is left with ip address of VALUE = {{ $value }} which is less than 700.\n LABELS: {{ $labels }}"
|
||||
+58
@@ -0,0 +1,58 @@
|
||||
groups:
|
||||
- name: EKS-Cilium-Alerts
|
||||
rules:
|
||||
- alert: CiliumClusterMeshFailureAlert
|
||||
expr: sum(cilium_clustermesh_remote_cluster_failures) by (cluster, source_cluster, target_cluster) > 0
|
||||
for: 5m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: infra
|
||||
team: devops
|
||||
service: eks-cilium
|
||||
env: prd
|
||||
priority: p0
|
||||
annotations:
|
||||
summary: "Cilium clustermesh failure from {{ $labels.source_cluster }} to {{ $labels.target_cluster }}"
|
||||
description: "Cilium clustermesh failure VALUE = {{ $value }}\n LABELS: {{ $labels }}"
|
||||
|
||||
- alert: DroppedEgressPackets
|
||||
expr: sum(rate(cilium_drop_count_total{direction="EGRESS", k8s_app="cilium", reason=~"No mapping for NAT masquerade|FIB lookup failed"}[1m])) by (kubernetes_pod_name, instance, reason, cluster) >= 5
|
||||
for: 5m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: infra
|
||||
team: devops
|
||||
service: eks-cilium
|
||||
env: prd
|
||||
priority: p0
|
||||
annotations:
|
||||
summary: "Cilium Dropped Egress Packets has crossed 5 Ops per Second for Reason - {{ $labels.reason }}, Pod - {{ $labels.kubernetes_pod_name }}, Instance - {{ $labels.instance }}, cluster - {{ $labels.cluster }} and the value is {{ $value }}"
|
||||
description: "Cilium Dropped Egress Packets has crossed 5 Ops per Second for Reason - {{ $labels.reason }}, Pod - {{ $labels.kubernetes_pod_name }}, Instance - {{ $labels.instance }}, cluster - {{ $labels.cluster }} and the value is {{ $value }}\n Labels - {{ $labels }}"
|
||||
|
||||
# - alert: SubnetOutofIpsByCilium
|
||||
# expr: sum(cilium_operator_ipam_available_ips_per_subnet) by (cluster, subnet_id) < 300
|
||||
# for: 1m
|
||||
# labels:
|
||||
# severity: warning
|
||||
# bu: infra
|
||||
# team: devops
|
||||
# service: eks-cilium
|
||||
# env: prd
|
||||
# priority: p0
|
||||
# annotations:
|
||||
# summary: "Subnet {{ $labels.subnet_id }} has ip address less than 300. Please check"
|
||||
# description: "Subnet {{ $labels.subnet_id }} is left with ip address of VALUE = {{ $value }} which is less than 500.\n LABELS: {{ $labels }}"
|
||||
|
||||
# - alert: SubnetOutofIpsByCilium_100
|
||||
# expr: sum(cilium_operator_ipam_available_ips_per_subnet) by (cluster, subnet_id) < 100
|
||||
# for: 1m
|
||||
# labels:
|
||||
# severity: critical
|
||||
# bu: infra
|
||||
# team: devops
|
||||
# service: eks-cilium
|
||||
# env: prd
|
||||
# priority: p0
|
||||
# annotations:
|
||||
# summary: "Subnet {{ $labels.subnet_id }} has ip address less than 100. Please check"
|
||||
# description: "Subnet {{ $labels.subnet_id }} is left with ip address of VALUE = {{ $value }} which is less than 100.\n LABELS: {{ $labels }}"
|
||||
+30
@@ -0,0 +1,30 @@
|
||||
groups:
|
||||
- name: EKS-dataplatform-Cilium-Alerts
|
||||
rules:
|
||||
- alert: dataplatform-MapOps-Crossed-Threshold
|
||||
expr: topk(5, avg(rate(cilium_bpf_map_ops_total{k8s_app="cilium", map_name=~"snat_v4_external", operation=~"delete", cluster=~".*dataplatform.*"}[5m])) by (kubernetes_pod_name, instance, map_name, operation, cluster)) <= 60
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: infra
|
||||
team: devops
|
||||
service: eks-cilium
|
||||
env: prd
|
||||
priority: p0
|
||||
annotations:
|
||||
summary: "dataplatform Cilium Map Ops has crossed 40 Ops per Second for Map Name - snat_v4_external, operation - delete, Pod - {{ $labels.kubernetes_pod_name }}, Instance - {{ $labels.instance }}, cluster - {{ $labels.cluster }} and the value is {{ $value }}"
|
||||
description: "dataplatform Cilium Map Ops has crossed 40 Ops per Second for Map Name - snat_v4_external, operation - delete, Pod - {{ $labels.kubernetes_pod_name }}, Instance - {{ $labels.instance }}, cluster - {{ $labels.cluster }} and the value is {{ $value }}\n Labels - {{ $labels }}"
|
||||
|
||||
- alert: SubnetOutofIpsForDataplatformCluster
|
||||
expr: sum(cilium_operator_ipam_available_ips_per_subnet{cluster=~".*dataplatform.*"}) by (cluster) < 1000
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: infra
|
||||
team: devops
|
||||
service: eks-cilium
|
||||
env: prd
|
||||
priority: p0
|
||||
annotations:
|
||||
summary: "Cluster {{ $labels.cluster }} has ip address less than 1000. Please check"
|
||||
description: "Cluster {{ $labels.cluster }} is left with ip address of VALUE = {{ $value }} which is less than 1000.\n LABELS: {{ $labels }}"
|
||||
+30
@@ -0,0 +1,30 @@
|
||||
groups:
|
||||
- name: EKS-datascience-Cilium-Alerts
|
||||
rules:
|
||||
- alert: datascience-MapOps-Crossed-Threshold
|
||||
expr: topk(5, avg(rate(cilium_bpf_map_ops_total{k8s_app="cilium", map_name=~"snat_v4_external", operation=~"delete", cluster=~".*datascience.*"}[5m])) by (kubernetes_pod_name, instance, map_name, operation, cluster)) <= 50
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: infra
|
||||
team: devops
|
||||
service: eks-cilium
|
||||
env: prd
|
||||
priority: p0
|
||||
annotations:
|
||||
summary: "datascience Cilium Map Ops has crossed 40 Ops per Second for Map Name - snat_v4_external, operation - delete, Pod - {{ $labels.kubernetes_pod_name }}, Instance - {{ $labels.instance }}, cluster - {{ $labels.cluster }} and the value is {{ $value }}"
|
||||
description: "datascience Cilium Map Ops has crossed 40 Ops per Second for Map Name - snat_v4_external, operation - delete, Pod - {{ $labels.kubernetes_pod_name }}, Instance - {{ $labels.instance }}, cluster - {{ $labels.cluster }} and the value is {{ $value }}\n Labels - {{ $labels }}"
|
||||
|
||||
- alert: SubnetOutofIpsForDatascienceCluster
|
||||
expr: sum(cilium_operator_ipam_available_ips_per_subnet{cluster=~".*datascience.*"}) by (cluster) < 6000
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: infra
|
||||
team: devops
|
||||
service: eks-cilium
|
||||
env: prd
|
||||
priority: p0
|
||||
annotations:
|
||||
summary: "Cluster {{ $labels.cluster }} has ip address less than 6000. Please check"
|
||||
description: "Cluster {{ $labels.cluster }} is left with ip address of VALUE = {{ $value }} which is less than 6000.\n LABELS: {{ $labels }}"
|
||||
+30
@@ -0,0 +1,30 @@
|
||||
groups:
|
||||
- name: EKS-demand-Cilium-Alerts
|
||||
rules:
|
||||
- alert: demand-MapOps-Crossed-Threshold
|
||||
expr: topk(5, avg(rate(cilium_bpf_map_ops_total{k8s_app="cilium", map_name=~"snat_v4_external", operation=~"delete", cluster=~".*demand.*"}[5m])) by (kubernetes_pod_name, instance, map_name, operation, cluster)) <= 30
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: infra
|
||||
team: devops
|
||||
service: eks-cilium
|
||||
env: prd
|
||||
priority: p0
|
||||
annotations:
|
||||
summary: "demand Cilium Map Ops has crossed 40 Ops per Second for Map Name - snat_v4_external, operation - delete, Pod - {{ $labels.kubernetes_pod_name }}, Instance - {{ $labels.instance }}, cluster - {{ $labels.cluster }} and the value is {{ $value }}"
|
||||
description: "demand Cilium Map Ops has crossed 40 Ops per Second for Map Name - snat_v4_external, operation - delete, Pod - {{ $labels.kubernetes_pod_name }}, Instance - {{ $labels.instance }}, cluster - {{ $labels.cluster }} and the value is {{ $value }}\n Labels - {{ $labels }}"
|
||||
|
||||
- alert: SubnetOutofIpsForDemandCluster
|
||||
expr: sum(cilium_operator_ipam_available_ips_per_subnet{cluster=~".*demand.*"}) by (cluster) < 6000
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: infra
|
||||
team: devops
|
||||
service: eks-cilium
|
||||
env: prd
|
||||
priority: p0
|
||||
annotations:
|
||||
summary: "Cluster {{ $labels.cluster }} has ip address less than 6000. Please check"
|
||||
description: "Cluster {{ $labels.cluster }} is left with ip address of VALUE = {{ $value }} which is less than 6000.\n LABELS: {{ $labels }}"
|
||||
+16
@@ -0,0 +1,16 @@
|
||||
groups:
|
||||
- name: EKS-dp-starburst-Cilium-Alerts
|
||||
rules:
|
||||
- alert: dp-starburst-MapOps-Crossed-Threshold
|
||||
expr: topk(5, avg(rate(cilium_bpf_map_ops_total{k8s_app="cilium", map_name=~"snat_v4_external", operation=~"delete", cluster=~".*dp-starburst.*"}[5m])) by (kubernetes_pod_name, instance, map_name, operation, cluster)) <= 20
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: infra
|
||||
team: devops
|
||||
service: eks-cilium
|
||||
env: prd
|
||||
priority: p0
|
||||
annotations:
|
||||
summary: "dp-starburst Cilium Map Ops has crossed 40 Ops per Second for Map Name - snat_v4_external, operation - delete, Pod - {{ $labels.kubernetes_pod_name }}, Instance - {{ $labels.instance }}, cluster - {{ $labels.cluster }} and the value is {{ $value }}"
|
||||
description: "dp-starburst Cilium Map Ops has crossed 40 Ops per Second for Map Name - snat_v4_external, operation - delete, Pod - {{ $labels.kubernetes_pod_name }}, Instance - {{ $labels.instance }}, cluster - {{ $labels.cluster }} and the value is {{ $value }}\n Labels - {{ $labels }}"
|
||||
+44
@@ -0,0 +1,44 @@
|
||||
groups:
|
||||
- name: EKS-prod-ops-Cilium-Alerts
|
||||
rules:
|
||||
- alert: prod-ops-MapOps-Crossed-Threshold
|
||||
expr: topk(5, avg(rate(cilium_bpf_map_ops_total{k8s_app="cilium", map_name=~"snat_v4_external", operation=~"delete", cluster=~".*prod-ops.*"}[5m])) by (kubernetes_pod_name, instance, map_name, operation, cluster)) <= 40
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: infra
|
||||
team: devops
|
||||
service: eks-cilium
|
||||
env: prd
|
||||
priority: p0
|
||||
annotations:
|
||||
summary: "prod-ops Cilium Map Ops has crossed 40 Ops per Second for Map Name - snat_v4_external, operation - delete, Pod - {{ $labels.kubernetes_pod_name }}, Instance - {{ $labels.instance }}, cluster - {{ $labels.cluster }} and the value is {{ $value }}"
|
||||
description: "prod-ops Cilium Map Ops has crossed 40 Ops per Second for Map Name - snat_v4_external, operation - delete, Pod - {{ $labels.kubernetes_pod_name }}, Instance - {{ $labels.instance }}, cluster - {{ $labels.cluster }} and the value is {{ $value }}\n Labels - {{ $labels }}"
|
||||
|
||||
- alert: CiliumRemoteClusterCountForProdOpsCluster
|
||||
expr: avg(cilium_clustermesh_remote_clusters{cluster=~"prod-ops-cluster"}) by (cluster, source_cluster, target_cluster) < 5
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: infra
|
||||
team: devops
|
||||
service: eks-cilium
|
||||
env: prd
|
||||
priority: p0
|
||||
annotations:
|
||||
summary: "Cilium remote cluster count less than actual remote clusters connected for {{ $labels.cluster }}"
|
||||
description: "Cilium remote cluster count less than actual remote clusters connected. Value = {{ $value }}\n LABELS: {{ $labels }}"
|
||||
|
||||
- alert: SubnetOutofIpsForOpsCluster
|
||||
expr: sum(cilium_operator_ipam_available_ips_per_subnet{cluster=~".*ops.*"}) by (cluster) < 500
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: infra
|
||||
team: devops
|
||||
service: eks-cilium
|
||||
env: prd
|
||||
priority: p0
|
||||
annotations:
|
||||
summary: "Cluster {{ $labels.cluster }} has ip address less than 500. Please check"
|
||||
description: "Cluster {{ $labels.cluster }} is left with ip address of VALUE = {{ $value }} which is less than 500.\n LABELS: {{ $labels }}"
|
||||
+30
@@ -0,0 +1,30 @@
|
||||
groups:
|
||||
- name: EKS-supply-Cilium-Alerts
|
||||
rules:
|
||||
- alert: supply-MapOps-Crossed-Threshold
|
||||
expr: topk(5, avg(rate(cilium_bpf_map_ops_total{k8s_app="cilium", map_name=~"snat_v4_external", operation=~"delete", cluster=~".*supply.*"}[5m])) by (kubernetes_pod_name, instance, map_name, operation, cluster)) <= 40
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: infra
|
||||
team: devops
|
||||
service: eks-cilium
|
||||
env: prd
|
||||
priority: p0
|
||||
annotations:
|
||||
summary: "supply Cilium Map Ops has crossed 40 Ops per Second for Map Name - snat_v4_external, operation - delete, Pod - {{ $labels.kubernetes_pod_name }}, Instance - {{ $labels.instance }}, cluster - {{ $labels.cluster }} and the value is {{ $value }}"
|
||||
description: "supply Cilium Map Ops has crossed 40 Ops per Second for Map Name - snat_v4_external, operation - delete, Pod - {{ $labels.kubernetes_pod_name }}, Instance - {{ $labels.instance }}, cluster - {{ $labels.cluster }} and the value is {{ $value }}\n Labels - {{ $labels }}"
|
||||
|
||||
- alert: SubnetOutofIpsForSupplyCluster
|
||||
expr: sum(cilium_operator_ipam_available_ips_per_subnet{cluster=~".*supply.*"}) by (cluster) < 2500
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: infra
|
||||
team: devops
|
||||
service: eks-cilium
|
||||
env: prd
|
||||
priority: p0
|
||||
annotations:
|
||||
summary: "Cluster {{ $labels.cluster }} has ip address less than 2500. Please check"
|
||||
description: "Cluster {{ $labels.cluster }} is left with ip address of VALUE = {{ $value }} which is less than 2500.\n LABELS: {{ $labels }}"
|
||||
Reference in New Issue
Block a user