commit 25962c5cb30ce67ab5da5b712b7208a062df10e7 parent 714350f45ca1e577b72935a9c9d5000c541f0dfb Author: MTRNord <mtrnord1@gmail.com> Date: Sat, 17 Jun 2023 23:15:18 +0200 Add alert for coredns Diffstat:
| M | apps/production/kube-prometheus-stack-values.yaml | | | 95 | +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ |
1 file changed, 95 insertions(+), 0 deletions(-)
diff --git a/apps/production/kube-prometheus-stack-values.yaml b/apps/production/kube-prometheus-stack-values.yaml @@ -11,6 +11,101 @@ spec: apiVersion: 1 groups: - orgId: 1 + name: Kube-system + folder: Cluster + interval: 1m + rules: + - uid: d2b94d3a-2483-4be4-bf2a-2fd9f9fac406 + title: Coredns Failure + condition: Thresh + data: + - refId: Count + queryType: range + relativeTimeRange: + from: 600 + to: 0 + datasourceUid: loki + model: + datasource: + type: loki + uid: loki + editorMode: builder + expr: rate({namespace="kube-system", app="coredns"} |= `i/o timeout` [15m]) + hide: false + intervalMs: 1000 + maxDataPoints: 43200 + queryType: range + range: true + refId: Count + - refId: Thresh + relativeTimeRange: + from: 600 + to: 0 + datasourceUid: __expr__ + model: + conditions: + - evaluator: + params: + - 1 + type: gt + operator: + type: and + query: + params: + - C + reducer: + params: [] + type: last + type: query + datasource: + type: __expr__ + uid: __expr__ + expression: A + hide: false + intervalMs: 1000 + maxDataPoints: 43200 + refId: Thresh + type: threshold + - refId: A + relativeTimeRange: + from: 600 + to: 0 + datasourceUid: __expr__ + model: + conditions: + - evaluator: + params: + - 0 + - 0 + type: gt + operator: + type: and + query: + params: [] + reducer: + params: [] + type: avg + type: query + datasource: + name: Expression + type: __expr__ + uid: __expr__ + expression: Count + intervalMs: 1000 + maxDataPoints: 43200 + reducer: last + refId: A + settings: + mode: replaceNN + replaceWithValue: 0 + type: reduce + noDataState: NoData + execErrState: Error + for: 5m + annotations: + summary: High amount of i/o timeouts in coredns + isPaused: false + - orgId: 1 name: 'Matrix Synapse' folder: Matrix interval: 1m