diff --git a/terraform/layer2-k8s/examples/eks-kube-prometheus-stack.tf b/terraform/layer2-k8s/eks-kube-prometheus-stack.tf similarity index 100% rename from terraform/layer2-k8s/examples/eks-kube-prometheus-stack.tf rename to terraform/layer2-k8s/eks-kube-prometheus-stack.tf diff --git a/terraform/layer2-k8s/examples/eks-loki-stack.tf b/terraform/layer2-k8s/eks-loki-stack.tf similarity index 99% rename from terraform/layer2-k8s/examples/eks-loki-stack.tf rename to terraform/layer2-k8s/eks-loki-stack.tf index f10210e0..89a1f025 100644 --- a/terraform/layer2-k8s/examples/eks-loki-stack.tf +++ b/terraform/layer2-k8s/eks-loki-stack.tf @@ -22,6 +22,7 @@ resource "helm_release" "loki_stack" { values = [ local.loki_stack_template ] + } resource "random_string" "grafana_loki_password" { diff --git a/terraform/layer2-k8s/templates/cluster-autoscaler-values.yaml b/terraform/layer2-k8s/templates/cluster-autoscaler-values.yaml index ed588064..e924132a 100644 --- a/terraform/layer2-k8s/templates/cluster-autoscaler-values.yaml +++ b/terraform/layer2-k8s/templates/cluster-autoscaler-values.yaml @@ -13,10 +13,9 @@ autoDiscovery: clusterName: ${cluster_name} serviceMonitor: - enabled: false + enabled: true + interval: 10s namespace: monitoring - selector: - prometheus: prometheus-operator path: /metrics affinity: diff --git a/terraform/layer2-k8s/templates/external-dns.yaml b/terraform/layer2-k8s/templates/external-dns.yaml index d6e6da37..4ce68356 100644 --- a/terraform/layer2-k8s/templates/external-dns.yaml +++ b/terraform/layer2-k8s/templates/external-dns.yaml @@ -18,8 +18,6 @@ metrics: serviceMonitor: enabled: false namespace: monitoring - selector: - prometheus: prometheus-operator sources: - service diff --git a/terraform/layer2-k8s/templates/loki-stack-values.tmpl b/terraform/layer2-k8s/templates/loki-stack-values.tmpl index 39fbfffc..5b856fd9 100644 --- a/terraform/layer2-k8s/templates/loki-stack-values.tmpl +++ b/terraform/layer2-k8s/templates/loki-stack-values.tmpl @@ -15,9 +15,6 @@ loki: serviceMonitor: enabled: true interval: "" - additionalLabels: - app: kube-prometheus-stack-operator - release: kube-prometheus-stack annotations: {} scrapeTimeout: 10s @@ -29,9 +26,6 @@ promtail: serviceMonitor: enabled: true interval: "" - additionalLabels: - app: kube-prometheus-stack-operator - release: kube-prometheus-stack annotations: {} # scrapeTimeout: 10s tolerations: @@ -122,4 +116,6 @@ grafana: dashboards: logs: logs: - url: https://gist.githubusercontent.com/khalezin/49766ed2976d49b0dc84a9c7809392e5/raw/53c0d067713e4da0e6cf187c6515a19e5dd996f5/loki-dashboard-quick-search.json + ## Dashboard for quick search application logs for loki with two datasources loki and prometheus - https://grafana.com/grafana/dashboards/12019 + url: https://s3.amazonaws.com/grafana-dashboards.maddevs.org/common/aws-eks-base/loki-dashboard-quick-search.json + diff --git a/terraform/layer2-k8s/templates/nginx-ingress-certmanager-ssl-termination-values.yaml b/terraform/layer2-k8s/templates/nginx-ingress-certmanager-ssl-termination-values.yaml index c333c9e0..ca5cc2bb 100644 --- a/terraform/layer2-k8s/templates/nginx-ingress-certmanager-ssl-termination-values.yaml +++ b/terraform/layer2-k8s/templates/nginx-ingress-certmanager-ssl-termination-values.yaml @@ -30,9 +30,7 @@ controller: metrics: enabled: true serviceMonitor: - enabled: false - additionalLabels: - release: prometheus-operator + enabled: true affinity: nodeAffinity: @@ -41,7 +39,7 @@ controller: - matchExpressions: - key: node.kubernetes.io/lifecycle operator: In - values: + values: - ondemand rbac: diff --git a/terraform/layer2-k8s/templates/nginx-ingress-values.yaml b/terraform/layer2-k8s/templates/nginx-ingress-values.yaml index fdc73ad2..ebb34c95 100644 --- a/terraform/layer2-k8s/templates/nginx-ingress-values.yaml +++ b/terraform/layer2-k8s/templates/nginx-ingress-values.yaml @@ -21,9 +21,7 @@ controller: metrics: enabled: true serviceMonitor: - enabled: false - additionalLabels: - release: prometheus-operator + enabled: true podAnnotations: co.elastic.logs/module: nginx @@ -37,7 +35,7 @@ controller: - matchExpressions: - key: node.kubernetes.io/lifecycle operator: In - values: + values: - ondemand rbac: diff --git a/terraform/layer2-k8s/templates/prometheus-mysql-exporter.yaml b/terraform/layer2-k8s/templates/prometheus-mysql-exporter.yaml index 1724ed94..17fbf40a 100644 --- a/terraform/layer2-k8s/templates/prometheus-mysql-exporter.yaml +++ b/terraform/layer2-k8s/templates/prometheus-mysql-exporter.yaml @@ -1,7 +1,5 @@ serviceMonitor: - enabled: false - additionalLabels: - release: prometheus-operator + enabled: true mysql: existingSecret: mysql-exporter @@ -13,5 +11,5 @@ affinity: - matchExpressions: - key: node.kubernetes.io/lifecycle operator: In - values: + values: - spot diff --git a/terraform/layer2-k8s/templates/prometheus-postgresql-exporter.tmpl b/terraform/layer2-k8s/templates/prometheus-postgresql-exporter.tmpl index f2b7a4b8..84400e0b 100644 --- a/terraform/layer2-k8s/templates/prometheus-postgresql-exporter.tmpl +++ b/terraform/layer2-k8s/templates/prometheus-postgresql-exporter.tmpl @@ -12,9 +12,6 @@ serviceMonitor: namespace: monitoring interval: 30s telemetryPath: /metrics - labels: - app: kube-prometheus-stack-operator - release: kube-prometheus-stack timeout: 10s affinity: diff --git a/terraform/layer2-k8s/templates/prometheus-values.tmpl b/terraform/layer2-k8s/templates/prometheus-values.tmpl index 625f693e..c8eac4cd 100644 --- a/terraform/layer2-k8s/templates/prometheus-values.tmpl +++ b/terraform/layer2-k8s/templates/prometheus-values.tmpl @@ -13,6 +13,7 @@ prometheus: - hosts: - ${prometheus_domain_name} prometheusSpec: + serviceMonitorSelectorNilUsesHelmValues: false storageSpec: volumeClaimTemplate: spec: @@ -125,13 +126,22 @@ grafana: dashboards: logs: logs: - url: https://gist.githubusercontent.com/khalezin/49766ed2976d49b0dc84a9c7809392e5/raw/53c0d067713e4da0e6cf187c6515a19e5dd996f5/loki-dashboard-quick-search.json + ## Dashboard for quick search application logs for loki with two datasources loki and prometheus - https://grafana.com/grafana/dashboards/12019 + url: https://s3.amazonaws.com/grafana-dashboards.maddevs.org/common/aws-eks-base/loki-dashboard-quick-search.json + k8s: nginx-ingress: - gnetId: 6927 + ## Dashboard for nginx-ingress metrics - https://grafana.com/grafana/dashboards/9614 + gnetId: 9614 datasource: Prometheus loki-promtail: - url: https://gist.githubusercontent.com/khalezin/dd63440a404afc7ff13815dded04e74a/raw/613f52a7c57b824ec52c15a8e89ff6ba2ba2f73d/loki-promtail.json + ## Dashboard for loki and promtail metrics - https://grafana.com/grafana/dashboards/10880 + gnetId: 10880 + datasource: Prometheus + cluster-autoscaler: + ## Dashboard for cluster-autoscaler metrics - https://grafana.com/grafana/dashboards/3831 + gnetId: 3831 + datasource: Prometheus affinity: nodeAffinity: