From f715e51e30d46514d77d7cb72fe7a30a9d141b66 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nick=20J=C3=BCttner?= Date: Thu, 14 Dec 2023 15:32:11 +0100 Subject: [PATCH] increase the timewindow for `NodeConnTrackAlmostExhausted` (#989) --- CHANGELOG.md | 1 + .../alerting-rules/node.management_cluster.rules.yml | 6 +++--- .../alerting-rules/node.workload_cluster.rules.yml | 6 +++--- 3 files changed, 7 insertions(+), 6 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 3cb223c6d..057a24af0 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -9,6 +9,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 ### Changed +- Increase the time window for `NodeConnTrackAlmostExhausted`. - Fix expression for KongDeploymentNotSatisfied ### Removed diff --git a/helm/prometheus-rules/templates/alerting-rules/node.management_cluster.rules.yml b/helm/prometheus-rules/templates/alerting-rules/node.management_cluster.rules.yml index 7486a46e8..a9a0fc865 100644 --- a/helm/prometheus-rules/templates/alerting-rules/node.management_cluster.rules.yml +++ b/helm/prometheus-rules/templates/alerting-rules/node.management_cluster.rules.yml @@ -50,10 +50,10 @@ spec: topic: kubernetes - alert: NodeConnTrackAlmostExhausted annotations: - description: '{{`Node {{ $labels.node }} reports a connection usage above 90%.`}}' + description: '{{`Node {{ $labels.node }} reports a connection usage above 85% for the last 15 minutes.`}}' opsrecipe: node-conntrack-limits/ - expr: node_nf_conntrack_entries / node_nf_conntrack_entries_limit >= 0.90 - for: 5m + expr: node_nf_conntrack_entries / node_nf_conntrack_entries_limit >= 0.85 + for: 15m labels: area: kaas cancel_if_outside_working_hours: {{ include "workingHoursOnly" . }} diff --git a/helm/prometheus-rules/templates/alerting-rules/node.workload_cluster.rules.yml b/helm/prometheus-rules/templates/alerting-rules/node.workload_cluster.rules.yml index 34ea70022..2f8c5f59b 100644 --- a/helm/prometheus-rules/templates/alerting-rules/node.workload_cluster.rules.yml +++ b/helm/prometheus-rules/templates/alerting-rules/node.workload_cluster.rules.yml @@ -78,10 +78,10 @@ spec: topic: kubernetes - alert: NodeConnTrackAlmostExhausted annotations: - description: '{{`Node {{ $labels.node }} reports a connection usage above 90%.`}}' + description: '{{`Node {{ $labels.node }} reports a connection usage above 85% for the last 15 minutes.`}}' opsrecipe: node-conntrack-limits/ - expr: node_nf_conntrack_entries / node_nf_conntrack_entries_limit >= 0.90 - for: 5m + expr: node_nf_conntrack_entries / node_nf_conntrack_entries_limit >= 0.85 + for: 15m labels: area: kaas cancel_if_outside_working_hours: {{ include "workingHoursOnly" . }}