cluster

Infrastructure files for Nordgedanken and Midnightthoughts.
git clone git://archive.git.mtrnord.blog/MTRNord/cluster.git
Log | Files | Refs | README

commit 0209af64966520d7c53f43887bb8f34763bebf50
parent 772a6720d6756323499ecfc95ad89eab19cd2307
Author: MTRNord <mtrnord1@gmail.com>
Date:   Sun,  6 Aug 2023 12:59:09 +0200

Reduce noise

Diffstat:
Mapps/production/kube-prometheus-stack-values.yaml | 302+++++++++++++++++++++++++++++++++++++++---------------------------------------
1 file changed, 151 insertions(+), 151 deletions(-)

diff --git a/apps/production/kube-prometheus-stack-values.yaml b/apps/production/kube-prometheus-stack-values.yaml @@ -27,8 +27,8 @@ spec: datasourceUid: loki model: datasource: - type: loki - uid: loki + type: loki + uid: loki editorMode: builder expr: rate({namespace="kube-system", app="coredns"} |= `i/o timeout` [15m]) hide: false @@ -44,22 +44,22 @@ spec: datasourceUid: __expr__ model: conditions: - - evaluator: - params: - - 1 - type: gt - operator: - type: and - query: - params: - - C - reducer: - params: [] - type: last - type: query + - evaluator: + params: + - 1 + type: gt + operator: + type: and + query: + params: + - C + reducer: + params: [] + type: last + type: query datasource: - type: __expr__ - uid: __expr__ + type: __expr__ + uid: __expr__ expression: A hide: false intervalMs: 1000 @@ -73,31 +73,31 @@ spec: datasourceUid: __expr__ model: conditions: - - evaluator: - params: - - 0 - - 0 - type: gt - operator: - type: and - query: - params: [] - reducer: - params: [] - type: avg - type: query + - evaluator: + params: + - 0 + - 0 + type: gt + operator: + type: and + query: + params: [] + reducer: + params: [] + type: avg + type: query datasource: - name: Expression - type: __expr__ - uid: __expr__ + name: Expression + type: __expr__ + uid: __expr__ expression: Count intervalMs: 1000 maxDataPoints: 43200 reducer: last refId: A settings: - mode: replaceNN - replaceWithValue: 0 + mode: replaceNN + replaceWithValue: 0 type: reduce noDataState: OK execErrState: Error @@ -106,7 +106,7 @@ spec: summary: High amount of i/o timeouts in coredns isPaused: false - orgId: 1 - name: 'Matrix Synapse' + name: "Matrix Synapse" folder: Matrix interval: 1m rules: @@ -122,8 +122,8 @@ spec: datasourceUid: loki model: datasource: - type: loki - uid: loki + type: loki + uid: loki editorMode: builder expr: rate({namespace="matrix", app="matrix-synapse"} |= `DNSQueryRefusedError` [15m]) hide: false @@ -139,22 +139,22 @@ spec: datasourceUid: __expr__ model: conditions: - - evaluator: - params: - - 1 - type: gt - operator: - type: and - query: - params: - - C - reducer: - params: [] - type: last - type: query + - evaluator: + params: + - 1 + type: gt + operator: + type: and + query: + params: + - C + reducer: + params: [] + type: last + type: query datasource: - type: __expr__ - uid: __expr__ + type: __expr__ + uid: __expr__ expression: A hide: false intervalMs: 1000 @@ -168,33 +168,33 @@ spec: datasourceUid: __expr__ model: conditions: - - evaluator: - params: - - 0 - - 0 - type: gt - operator: - type: and - query: - params: [] - reducer: - params: [] - type: avg - type: query + - evaluator: + params: + - 0 + - 0 + type: gt + operator: + type: and + query: + params: [] + reducer: + params: [] + type: avg + type: query datasource: - name: Expression - type: __expr__ - uid: __expr__ + name: Expression + type: __expr__ + uid: __expr__ expression: Count intervalMs: 1000 maxDataPoints: 43200 reducer: last refId: A settings: - mode: replaceNN - replaceWithValue: 0 + mode: replaceNN + replaceWithValue: 0 type: reduce - noDataState: NoData + noDataState: OK execErrState: Error for: 5m annotations: @@ -212,8 +212,8 @@ spec: datasourceUid: loki model: datasource: - type: loki - uid: loki + type: loki + uid: loki editorMode: builder expr: rate({namespace="matrix", app="matrix-synapse"} |= `psycopg2.errors.ReadOnlySqlTransaction` [15m]) hide: false @@ -229,22 +229,22 @@ spec: datasourceUid: __expr__ model: conditions: - - evaluator: - params: - - 0.1 - type: gt - operator: - type: and - query: - params: - - C - reducer: - params: [] - type: last - type: query + - evaluator: + params: + - 0.1 + type: gt + operator: + type: and + query: + params: + - C + reducer: + params: [] + type: last + type: query datasource: - type: __expr__ - uid: __expr__ + type: __expr__ + uid: __expr__ expression: A hide: false intervalMs: 1000 @@ -258,31 +258,31 @@ spec: datasourceUid: __expr__ model: conditions: - - evaluator: - params: - - 0 - - 0 - type: gt - operator: - type: and - query: - params: [] - reducer: - params: [] - type: avg - type: query + - evaluator: + params: + - 0 + - 0 + type: gt + operator: + type: and + query: + params: [] + reducer: + params: [] + type: avg + type: query datasource: - name: Expression - type: __expr__ - uid: __expr__ + name: Expression + type: __expr__ + uid: __expr__ expression: Count intervalMs: 1000 maxDataPoints: 43200 reducer: last refId: A settings: - mode: replaceNN - replaceWithValue: 0 + mode: replaceNN + replaceWithValue: 0 type: reduce noDataState: OK execErrState: Error @@ -291,7 +291,7 @@ spec: summary: Matrix Database rolled over but synapse crashed isPaused: false - uid: d16dc343-31d9-466a-bdc1-c2466b0bc18f - title: 'Unusual synapse logging' + title: "Unusual synapse logging" condition: Thresh data: - refId: Count @@ -302,8 +302,8 @@ spec: datasourceUid: loki model: datasource: - type: loki - uid: loki + type: loki + uid: loki editorMode: builder expr: sum by(level) (count_over_time({namespace="matrix", app="matrix-synapse"} | pattern `<_> - <component> - <_> - <level> - <trace>- <detail>` | level != `INFO` [$__interval])) hide: false @@ -319,22 +319,22 @@ spec: datasourceUid: __expr__ model: conditions: - - evaluator: - params: - - 20 - type: gt - operator: - type: and - query: - params: - - C - reducer: - params: [] - type: last - type: query + - evaluator: + params: + - 20 + type: gt + operator: + type: and + query: + params: + - C + reducer: + params: [] + type: last + type: query datasource: - type: __expr__ - uid: __expr__ + type: __expr__ + uid: __expr__ expression: A hide: false intervalMs: 1000 @@ -348,31 +348,31 @@ spec: datasourceUid: __expr__ model: conditions: - - evaluator: - params: - - 0 - - 0 - type: gt - operator: - type: and - query: - params: [] - reducer: - params: [] - type: avg - type: query + - evaluator: + params: + - 0 + - 0 + type: gt + operator: + type: and + query: + params: [] + reducer: + params: [] + type: avg + type: query datasource: - name: Expression - type: __expr__ - uid: __expr__ + name: Expression + type: __expr__ + uid: __expr__ expression: Count intervalMs: 1000 maxDataPoints: 43200 reducer: last refId: A settings: - mode: replaceNN - replaceWithValue: 0 + mode: replaceNN + replaceWithValue: 0 type: reduce noDataState: OK execErrState: Error @@ -384,21 +384,21 @@ spec: apiVersion: 1 contactPoints: - orgId: 1 - name: 'MidnightThoughts Ops' + name: "MidnightThoughts Ops" receivers: - - uid: '1' - name: 'MidnightThoughts Ops' - type: 'email' + - uid: "1" + name: "MidnightThoughts Ops" + type: "email" sendReminder: true - frequency: '1m' + frequency: "1m" settings: - addresses: 'ops@nordgedanken.dev;mtrnord@nordgedanken.dev;mtrnord1@gmail.com' + addresses: "ops@nordgedanken.dev;mtrnord@nordgedanken.dev;mtrnord1@gmail.com" policies.yaml: apiVersion: 1 policies: - orgId: 1 - receiver: 'MidnightThoughts Ops' - group_by: ['grafana_folder', 'alertname'] + receiver: "MidnightThoughts Ops" + group_by: ["grafana_folder", "alertname"] ingress: enabled: true