[fluentd-elasticsearch] Issue 86: Configure PrometheusRules to match …

…metrics service job name (#87) * Issue 86: Configure PrometheusRules to match metrics service job name Signed-off-by: Jared Burns <[email protected]> * fix ci Signed-off-by: André Bauer <[email protected]> * update several github actions Signed-off-by: André Bauer <[email protected]> Co-authored-by: André Bauer <[email protected]>
kokuwaio · Aug 13, 2021 · 772dbb4 · 772dbb4
1 parent 07e6936
commit 772dbb4
Show file tree

Hide file tree

Showing 8 changed files with 22 additions and 16 deletions.
diff --git a/.github/kubeval.sh b/.github/kubeval.sh
@@ -6,7 +6,7 @@
 set -o errexit
 set -o pipefail
 
-CHART_DIRS="$(git diff --find-renames --name-only "$(git rev-parse --abbrev-ref HEAD)" remotes/origin/main -- zammad | grep '[cC]hart.yaml' | sed -e 's#/[Cc]hart.yaml##g')"
+CHART_DIRS="$(git diff --find-renames --name-only "$(git rev-parse --abbrev-ref HEAD)" remotes/origin/main -- charts | grep '[cC]hart.yaml' | sed -e 's#/[Cc]hart.yaml##g')"
 SCHEMA_LOCATION="https://raw.githubusercontent.com/yannh/kubernetes-json-schema/master/"
 
 # install kubeval

diff --git a/.github/workflows/ci.yaml b/.github/workflows/ci.yaml
@@ -6,7 +6,7 @@ on:
  - 'charts/**/**'
 
 env:
- helm-version: "v3.6.2"
+ helm-version: "v3.6.3"
  kubeval-version: "v0.16.1"
 
 jobs:
@@ -33,14 +33,14 @@ jobs:
  with:
  fetch-depth: 0
  - name: Set up Helm
- uses: azure/setup-helm@v1
+ uses: azure/setup-helm@v1.1
  with:
  version: "${{ env.helm-version }}"
  - uses: actions/setup-python@v2
  with:
  python-version: 3.7
  - name: Set up chart-testing
- uses: helm/chart-testing-action@v2.0.1
+ uses: helm/chart-testing-action@v2.1.0
  - name: Run chart-testing (lint)
  run: ct lint --config .github/ct.yaml
 
@@ -80,7 +80,7 @@ jobs:
  with:
  fetch-depth: 0
  - name: Set up Helm
- uses: azure/setup-helm@v1
+ uses: azure/setup-helm@v1.1
  with:
  version: "${{ env.helm-version }}"
  - name: Run kubeval
@@ -109,7 +109,7 @@ jobs:
  with:
  fetch-depth: 0
  - name: Set up Helm
- uses: azure/setup-helm@v1
+ uses: azure/setup-helm@v1.1
  with:
  version: "${{ env.helm-version }}"
  - uses: actions/setup-python@v2
@@ -125,7 +125,7 @@ jobs:
  echo "::set-output name=changed::true"
  fi
  - name: Create kind cluster
- uses: helm/kind-action@v1.1.0
+ uses: helm/kind-action@v1.2.0
  if: steps.list-changed.outputs.changed == 'true'
  with:
  config: .github/kind-config.yaml

diff --git a/.github/workflows/release.yaml b/.github/workflows/release.yaml
@@ -6,7 +6,7 @@ on:
  - main
 
 env:
- helm-version: "v3.6.2"
+ helm-version: "v3.6.3"
 
 jobs:
  release:

diff --git a/charts/fluentd-elasticsearch/Chart.yaml b/charts/fluentd-elasticsearch/Chart.yaml
@@ -1,6 +1,6 @@
 apiVersion: v2
 name: fluentd-elasticsearch
-version: 11.13.0
+version: 11.14.0
 appVersion: 3.2.0
 type: application
 home: https://www.fluentd.org/

diff --git a/charts/fluentd-elasticsearch/README.md b/charts/fluentd-elasticsearch/README.md
@@ -171,7 +171,7 @@ The following table lists the configurable parameters of the Fluentd elasticsear
 | `serviceMonitor.labels` | Optional labels for serviceMonitor | `{}` |
 | `serviceMonitor.metricRelabelings` | Optional metric relabel configs to apply to samples before ingestion | `[]` |
 | `serviceMonitor.relabelings` | Optional relabel configs to apply to samples before scraping | `[]` |
-| `serviceMonitor.jobLabel` | Label whose value will define the job name    | `app.kubernetes.io/instance`  |
+| `serviceMonitor.jobLabel` | PrometheusRule jobLabel. Uses the created metrics service name if not set. | Not Set |
 | `serviceMonitor.type` | Optional the type of the metrics service | `ClusterIP` |
 | `tolerations` | Optional daemonset tolerations | `[]` |
 | `updateStrategy` | Optional daemonset update strategy | `type: RollingUpdate` |

diff --git a/charts/fluentd-elasticsearch/templates/_helpers.tpl b/charts/fluentd-elasticsearch/templates/_helpers.tpl
@@ -60,3 +60,10 @@ Create the name of the service account to use
 {{- default "default" .Values.serviceAccount.name }}
 {{- end }}
 {{- end }}
+
+{{/*
+Create the name of the metrics service
+*/}}
+{{- define "fluentd-elasticsearch.metricsServiceName" -}}
+{{- include "fluentd-elasticsearch.fullname" . }}-metrics
+{{- end }}
diff --git a/charts/fluentd-elasticsearch/templates/metrics-service.yaml b/charts/fluentd-elasticsearch/templates/metrics-service.yaml
@@ -2,7 +2,7 @@
 apiVersion: v1
 kind: Service
 metadata:
- name: {{ include "fluentd-elasticsearch.fullname" $ }}-metrics
+ name: {{ include "fluentd-elasticsearch.metricsServiceName" . }}
  labels:
  {{- include "fluentd-elasticsearch.labels" . | nindent 4 }}
  addonmanager.kubernetes.io/mode: Reconcile

diff --git a/charts/fluentd-elasticsearch/values.yaml b/charts/fluentd-elasticsearch/values.yaml
@@ -283,7 +283,6 @@ serviceMonitor:
  labels: {}
  metricRelabelings: []
  relabelings: []
- jobLabel: "app.kubernetes.io/instance"
  type: ClusterIP
 
 serviceMetric:
@@ -301,7 +300,7 @@ prometheusRule:
  labels: {}
  rules:
  - alert: FluentdNodeDown
- expr: up{job="{{ include "fluentd-elasticsearch.fullname" . }}"} == 0
+ expr: up{job="{{ include "fluentd-elasticsearch.metricsServiceName" . }}"} == 0
  for: 10m
  labels:
  service: fluentd
@@ -310,7 +309,7 @@ prometheusRule:
  summary: fluentd cannot be scraped
  description: Prometheus could not scrape {{ "{{ $labels.job }}" }} for more than 10 minutes
  - alert: FluentdNodeDown
- expr: up{job="{{ include "fluentd-elasticsearch.fullname" . }}"} == 0
+ expr: up{job="{{ include "fluentd-elasticsearch.metricsServiceName" . }}"} == 0
  for: 30m
  labels:
  service: fluentd
@@ -338,8 +337,8 @@ prometheusRule:
  description: In the last 5 minutes, fluentd queues increased 50%. Current value is {{ "{{ $value }}" }}
  - alert: FluentdRecordsCountsHigh
  expr: >
- sum(rate(fluentd_output_status_emit_records{job="{{ tpl .Release.Name . }}"}[5m]))
- BY (instance) > (3 * sum(rate(fluentd_output_status_emit_records{job="{{ tpl .Release.Name . }}"}[15m]))
+ sum(rate(fluentd_output_status_emit_records{job="{{ include "fluentd-elasticsearch.metricsServiceName" . }}"}[5m]))
+ BY (instance) > (3 * sum(rate(fluentd_output_status_emit_records{job="{{ include "fluentd-elasticsearch.metricsServiceName" . }}"}[15m]))
  BY (instance))
  for: 1m
  labels: