XeLabs/awesome-prometheus-alerts
2
0
Fork 0
mirror of https://github.com/samber/awesome-prometheus-alerts.git synced 2026-06-24 18:36:59 +08:00
Code Issues Projects Releases Packages Wiki Activity

fix: use job label instead of k8s_app, switch to single-quoted YAML strings

Browse source
This commit is contained in:
Samuel Berthe 2026-03-16 16:43:24 +01:00
parent 9453f2693d
commit fe98b117fb
1 changed files with 4 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

8
_data/rules.yml
View file

@ -3924,7 +3924,7 @@ groups:
for: 5m
- name: Cilium agent high restart rate
description: "Cilium agent has restarted more than twice in the last 15 minutes. It might be crashlooping."
query: 'changes(process_start_time_seconds{k8s_app="cilium"}[15m]) > 2'
query: 'changes(process_start_time_seconds{job=~".*cilium.*"}[15m]) > 2'
severity: warning
# Endpoints
- name: Cilium agent endpoint failures
@ -4007,12 +4007,12 @@ groups:
# Identity
- name: Cilium node-local high identity allocation
description: "Cilium agent {{ $labels.pod }} node-local identity allocation is above 80%. Approaching the 65535 identity limit."
query: "(sum(cilium_identity{type=\"node_local\"}) by (pod) / (2^16-1)) > 0.8"
query: '(sum(cilium_identity{type="node_local"}) by (pod) / (2^16-1)) > 0.8'
severity: warning
for: 5m
- name: Cilium cluster high identity allocation
description: "Cilium cluster-wide identity allocation is above 80%. Approaching the maximum identity limit."
query: "(sum(cilium_identity{type=\"cluster_local\"}) by () / (2^16-256)) > 0.8"
query: '(sum(cilium_identity{type="cluster_local"}) by () / (2^16-256)) > 0.8'
severity: warning
for: 5m
# IPAM
@ -4078,7 +4078,7 @@ groups:
for: 5m
- name: Cilium Hubble high DNS error rate
description: "Cilium Hubble on {{ $labels.pod }} is observing more than 10% DNS error responses."
query: "sum(rate(hubble_dns_responses_total{rcode!=\"No Error\"}[5m])) by (pod) / sum(rate(hubble_dns_responses_total[5m])) by (pod) > 0.1 and sum(rate(hubble_dns_responses_total[5m])) by (pod) > 0"
query: 'sum(rate(hubble_dns_responses_total{rcode!="No Error"}[5m])) by (pod) / sum(rate(hubble_dns_responses_total[5m])) by (pod) > 0.1 and sum(rate(hubble_dns_responses_total[5m])) by (pod) > 0'
severity: warning
for: 5m
comments: Threshold of 10% is a rough default. Some DNS errors may be normal depending on your workload.