[rancher-monitoring] some more fixes

packages/rancher-grafana/generated-changes/patch/README.md.patch

@@ -11,3 +11,14 @@
  | `image.pullPolicy`                        | Image pull policy                             | `IfNotPresent`                                          |
  | `image.pullSecrets`                       | Image pull secrets                            | `{}`                                                    |
  | `service.enabled`                         | Enable grafana service                        | `true`                                                  |
+@@ -188,8 +188,8 @@
+ | `rbac.extraRoleRules`                     | Additional rules to add to the Role           | []                                                      |
+ | `rbac.extraClusterRoleRules`              | Additional rules to add to the ClusterRole    | []                                                      |
+ | `command`                     | Define command to be executed by grafana container at startup  | `nil`                                              |
+-| `testFramework.enabled`                   | Whether to create test-related resources      | `true`                                                  |
+-| `testFramework.image`                     | `test-framework` image repository.            | `bats/bats`                                             |
++| `testFramework.enabled`                   | Whether to create test-related resources      | `false`                                                  |
++| `testFramework.image`                     | `test-framework` image repository.            | `rancher/mirrored-bats-bats`                                             |
+ | `testFramework.tag`                       | `test-framework` image tag.                   | `v1.1.0`                                                |
+ | `testFramework.imagePullPolicy`           | `test-framework` image pull policy.           | `IfNotPresent`                                          |
+ | `testFramework.securityContext`           | `test-framework` securityContext              | `{}`                                                    |

packages/rancher-grafana/generated-changes/patch/templates/tests/test.yaml.patch

@@ -0,0 +1,11 @@
+--- charts-original/templates/tests/test.yaml
++++ charts/templates/tests/test.yaml
+@@ -33,7 +33,7 @@
+   {{- end }}
+   containers:
+     - name: {{ .Release.Name }}-test
+-      image: "{{ .Values.testFramework.image}}:{{ .Values.testFramework.tag }}"
++      image: "{{ template "system_default_registry" . }}{{ .Values.testFramework.image}}:{{ .Values.testFramework.tag }}"
+       imagePullPolicy: "{{ .Values.testFramework.imagePullPolicy}}"
+       command: ["/opt/bats/bin/bats", "-t", "/tests/run.sh"]
+       volumeMounts:

packages/rancher-grafana/generated-changes/patch/values.yaml.patch

@@ -36,11 +36,13 @@
    sha: ""
    pullPolicy: IfNotPresent
  
-@@ -83,12 +97,15 @@
+@@ -82,13 +96,16 @@
+   #   - myRegistrKeySecretName
  
  testFramework:
-   enabled: true
+-  enabled: true
 -  image: "bats/bats"
++  enabled: false
 +  image: "rancher/mirrored-bats-bats"
    tag: "v1.1.0"
    imagePullPolicy: IfNotPresent
@@ -65,6 +67,15 @@
    sha: ""
    pullPolicy: IfNotPresent
  
+@@ -189,7 +206,7 @@
+   labels: {}
+   path: /
+ 
+-  # pathType is only for k8s >= 1.1=
++  # pathType is only for k8s >= 1.18
+   pathType: Prefix
+ 
+   hosts:
 @@ -303,7 +320,7 @@
    ## initChownData container image
    ##

packages/rancher-kube-state-metrics/generated-changes/patch/templates/role.yaml.patch

@@ -0,0 +1,9 @@
+--- charts-original/templates/role.yaml
++++ charts/templates/role.yaml
+@@ -1,3 +1,6 @@
++{{- if not (kindIs "slice" .Values.collectors) }}
++{{- fail "Collectors need to be a List since kube-state-metrics chart 3.2.2. Please check README for more information."}}
++{{- end }}
+ {{- if and (eq .Values.rbac.create true) (not .Values.rbac.useExistingRole) -}}
+ {{- range (split "," .Values.namespaces) }}
+ ---

packages/rancher-monitoring/generated-changes/patch/templates/exporters/kube-state-metrics/serviceMonitor.yaml.patch

@@ -0,0 +1,10 @@
+--- charts-original/templates/exporters/kube-state-metrics/serviceMonitor.yaml
++++ charts/templates/exporters/kube-state-metrics/serviceMonitor.yaml
+@@ -1,4 +1,7 @@
+ {{- if .Values.kubeStateMetrics.enabled }}
++{{- if .Values.kubeStateMetrics.serviceMonitor.namespaceOverride }}
++{{- fail "kubeStateMetrics.serviceMonitor.namespaceOverride was removed. Please use kube-state-metrics.namespaceOverride instead." }}
++{{- end }}
+ apiVersion: monitoring.coreos.com/v1
+ kind: ServiceMonitor
+ metadata:

packages/rancher-monitoring/generated-changes/patch/templates/grafana/dashboards-1.14/alertmanager-overview.yaml.patch

@@ -0,0 +1,23 @@
+--- charts-original/templates/grafana/dashboards-1.14/alertmanager-overview.yaml
++++ charts/templates/grafana/dashboards-1.14/alertmanager-overview.yaml
+@@ -5,10 +5,11 @@
+ */ -}}
+ {{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }}
+ {{- if and (or .Values.grafana.enabled .Values.grafana.forceDeployDashboards) (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.grafana.defaultDashboardsEnabled }}
++{{- if and .Values.alertmanager.enabled .Values.alertmanager.serviceMonitor.selfMonitor }}
+ apiVersion: v1
+ kind: ConfigMap
+ metadata:
+-  namespace: {{ template "kube-prometheus-stack-grafana.namespace" . }}
++  namespace: {{ .Values.grafana.defaultDashboards.namespace }}
+   name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" $) "alertmanager-overview" | trunc 63 | trimSuffix "-" }}
+   annotations:
+ {{ toYaml .Values.grafana.sidecar.dashboards.annotations | indent 4 }}
+@@ -607,4 +608,5 @@
+         "uid": "alertmanager-overview",
+         "version": 0
+     }
+-{{- end }}
+\ No newline at end of file
++{{- end }}
++{{- end }}

packages/rancher-monitoring/generated-changes/patch/templates/grafana/dashboards-1.14/cluster-total.yaml.patch

@@ -9,3 +9,12 @@
    name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" $) "cluster-total" | trunc 63 | trimSuffix "-" }}
    annotations:
  {{ toYaml .Values.grafana.sidecar.dashboards.annotations | indent 4 }}
+@@ -1831,7 +1831,7 @@
+                     "options": [
+ 
+                     ],
+-                    "query": "label_values(up{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\"}, cluster)",
++                    "query": "label_values(up{job=\"{{ include "exporter.kubelet.jobName" . }}\", metrics_path=\"/metrics/cadvisor\"}, cluster)",
+                     "refresh": 2,
+                     "regex": "",
+                     "sort": 0,

packages/rancher-monitoring/generated-changes/patch/templates/grafana/dashboards-1.14/controller-manager.yaml.patch

@@ -133,6 +133,24 @@
                                  "format": "time_series",
                                  "intervalFactor": 2,
                                  "legendFormat": "{{`{{`}}instance{{`}}`}}",
+@@ -1100,7 +1105,7 @@
+                     "options": [
+ 
+                     ],
+-                    "query": "label_values(up{job=\"kube-controller-manager\"}, cluster)",
++                    "query": "label_values(up{job=\"{{ include "exporter.kubeControllerManager.jobName" . }}\"}, cluster)",
+                     "refresh": 2,
+                     "regex": "",
+                     "sort": 1,
+@@ -1126,7 +1131,7 @@
+                     "options": [
+ 
+                     ],
+-                    "query": "label_values(up{cluster=\"$cluster\", job=\"kube-controller-manager\"}, instance)",
++                    "query": "label_values(up{cluster=\"$cluster\", job=\"{{ include "exporter.kubeControllerManager.jobName" . }}\"}, instance)",
+                     "refresh": 2,
+                     "regex": "",
+                     "sort": 1,
 @@ -1174,4 +1179,5 @@
          "uid": "72e0e05bef5099e5f049b05fdc429ed4",
          "version": 0

packages/rancher-monitoring/generated-changes/patch/templates/grafana/dashboards-1.14/k8s-resources-cluster.yaml.patch

@@ -9,3 +9,12 @@
    name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" $) "k8s-resources-cluster" | trunc 63 | trimSuffix "-" }}
    annotations:
  {{ toYaml .Values.grafana.sidecar.dashboards.annotations | indent 4 }}
+@@ -2973,7 +2973,7 @@
+                     "options": [
+ 
+                     ],
+-                    "query": "label_values(up{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\"}, cluster)",
++                    "query": "label_values(up{job=\"{{ include "exporter.kubelet.jobName" . }}\", metrics_path=\"/metrics/cadvisor\"}, cluster)",
+                     "refresh": 2,
+                     "regex": "",
+                     "sort": 1,

packages/rancher-monitoring/generated-changes/patch/templates/grafana/dashboards-1.14/namespace-by-pod.yaml.patch

@@ -9,3 +9,12 @@
    name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" $) "namespace-by-pod" | trunc 63 | trimSuffix "-" }}
    annotations:
  {{ toYaml .Values.grafana.sidecar.dashboards.annotations | indent 4 }}
+@@ -1301,7 +1301,7 @@
+                     "options": [
+ 
+                     ],
+-                    "query": "label_values(up{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\"}, cluster)",
++                    "query": "label_values(up{job=\"{{ include "exporter.kubelet.jobName" . }}\", metrics_path=\"/metrics/cadvisor\"}, cluster)",
+                     "refresh": 2,
+                     "regex": "",
+                     "sort": 0,

packages/rancher-monitoring/generated-changes/patch/templates/grafana/dashboards-1.14/namespace-by-workload.yaml.patch

@@ -9,3 +9,12 @@
    name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" $) "namespace-by-workload" | trunc 63 | trimSuffix "-" }}
    annotations:
  {{ toYaml .Values.grafana.sidecar.dashboards.annotations | indent 4 }}
+@@ -1541,7 +1541,7 @@
+                     "options": [
+ 
+                     ],
+-                    "query": "label_values(up{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\"}, cluster)",
++                    "query": "label_values(up{job=\"{{ include "exporter.kubelet.jobName" . }}\", metrics_path=\"/metrics/cadvisor\"}, cluster)",
+                     "refresh": 2,
+                     "regex": "",
+                     "sort": 0,

packages/rancher-monitoring/generated-changes/patch/templates/grafana/dashboards-1.14/pod-total.yaml.patch

@@ -9,3 +9,12 @@
    name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" $) "pod-total" | trunc 63 | trimSuffix "-" }}
    annotations:
  {{ toYaml .Values.grafana.sidecar.dashboards.annotations | indent 4 }}
+@@ -1033,7 +1033,7 @@
+                     "options": [
+ 
+                     ],
+-                    "query": "label_values(up{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\"}, cluster)",
++                    "query": "label_values(up{job=\"{{ include "exporter.kubelet.jobName" . }}\", metrics_path=\"/metrics/cadvisor\"}, cluster)",
+                     "refresh": 2,
+                     "regex": "",
+                     "sort": 0,

packages/rancher-monitoring/generated-changes/patch/templates/grafana/dashboards-1.14/scheduler.yaml.patch

@@ -172,6 +172,15 @@
                                  "format": "time_series",
                                  "intervalFactor": 2,
                                  "legendFormat": "{{`{{`}}instance{{`}}`}}",
+@@ -1023,7 +1028,7 @@
+                     "options": [
+ 
+                     ],
+-                    "query": "label_values(up{job=\"kube-scheduler\"}, cluster)",
++                    "query": "label_values(up{job=\"{{ include "exporter.kubeScheduler.jobName" . }}\"}, cluster)",
+                     "refresh": 2,
+                     "regex": "",
+                     "sort": 1,
 @@ -1049,7 +1054,7 @@
                      "options": [
  

packages/rancher-monitoring/generated-changes/patch/templates/prometheus-operator/deployment.yaml.patch

@@ -24,6 +24,18 @@
              {{- end }}
              - --config-reloader-cpu-request={{ .Values.prometheusOperator.configReloaderCpu }}
              - --config-reloader-cpu-limit={{ .Values.prometheusOperator.configReloaderCpu }}
+@@ -81,9 +81,9 @@
+             - --prometheus-instance-namespaces={{ .Values.prometheusOperator.prometheusInstanceNamespaces | join "," }}
+             {{- end }}
+             {{- if .Values.prometheusOperator.thanosImage.sha }}
+-            - --thanos-default-base-image={{ .Values.prometheusOperator.thanosImage.repository }}:{{ .Values.prometheusOperator.thanosImage.tag }}@sha256:{{ .Values.prometheusOperator.thanosImage.sha }}
++            - --thanos-default-base-image={{ template "system_default_registry" . }}{{ .Values.prometheusOperator.thanosImage.repository }}:{{ .Values.prometheusOperator.thanosImage.tag }}@sha256:{{ .Values.prometheusOperator.thanosImage.sha }}
+             {{- else }}
+-            - --thanos-default-base-image={{ .Values.prometheusOperator.thanosImage.repository }}:{{ .Values.prometheusOperator.thanosImage.tag }}
++            - --thanos-default-base-image={{ template "system_default_registry" . }}{{ .Values.prometheusOperator.thanosImage.repository }}:{{ .Values.prometheusOperator.thanosImage.tag }}
+             {{- end }} 
+             {{- if .Values.prometheusOperator.thanosRulerInstanceNamespaces }}
+             - --thanos-ruler-instance-namespaces={{ .Values.prometheusOperator.thanosRulerInstanceNamespaces | join "," }}
 @@ -137,16 +137,16 @@
        hostNetwork: true
        dnsPolicy: ClusterFirstWithHostNet

packages/rancher-monitoring/generated-changes/patch/templates/prometheus/rules-1.14/alertmanager.rules.yaml.patch

@@ -0,0 +1,18 @@
+--- charts-original/templates/prometheus/rules-1.14/alertmanager.rules.yaml
++++ charts/templates/prometheus/rules-1.14/alertmanager.rules.yaml
+@@ -7,6 +7,7 @@
+ {{- if and (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.defaultRules.create .Values.defaultRules.rules.alertmanager }}
+ {{- $alertmanagerJob := printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "alertmanager" }}
+ {{- $namespace := printf "%s" (include "kube-prometheus-stack.namespace" .) }}
++{{- if and .Values.alertmanager.enabled .Values.alertmanager.serviceMonitor.selfMonitor }}
+ apiVersion: monitoring.coreos.com/v1
+ kind: PrometheusRule
+ metadata:
+@@ -172,4 +173,5 @@
+ {{- if .Values.defaultRules.additionalRuleLabels }}
+ {{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
+ {{- end }}
+-{{- end }}
+\ No newline at end of file
++{{- end }}
++{{- end }}

packages/rancher-monitoring/generated-changes/patch/values.yaml.patch

@@ -706,7 +706,7 @@
  
    ## If true, create a serviceMonitor for grafana
    ##
-@@ -773,6 +1357,14 @@
+@@ -773,6 +1357,17 @@
      #   replacement: $1
      #   action: replace
  
@@ -717,11 +717,14 @@
 +    requests:
 +      memory: 100Mi
 +      cpu: 100m
++
++  testFramework:
++    enabled: false
 +
  ## Component scraping the kube api server
  ##
  kubeApiServer:
-@@ -952,7 +1544,7 @@
+@@ -952,7 +1547,7 @@
  ## Component scraping the kube controller manager
  ##
  kubeControllerManager:
@@ -730,7 +733,7 @@
  
    ## If your kube controller manager is not deployed as a pod, specify IPs it can be found on
    ##
-@@ -1110,7 +1702,7 @@
+@@ -1110,7 +1705,7 @@
  ## Component scraping etcd
  ##
  kubeEtcd:
@@ -739,7 +742,7 @@
  
    ## If your etcd is not deployed as a pod, specify IPs it can be found on
    ##
-@@ -1177,7 +1769,7 @@
+@@ -1177,7 +1772,7 @@
  ## Component scraping kube scheduler
  ##
  kubeScheduler:
@@ -748,7 +751,7 @@
  
    ## If your kube scheduler is not deployed as a pod, specify IPs it can be found on
    ##
-@@ -1237,7 +1829,7 @@
+@@ -1237,7 +1832,7 @@
  ## Component scraping kube proxy
  ##
  kubeProxy:
@@ -757,7 +760,7 @@
  
    ## If your kube proxy is not deployed as a pod, specify IPs it can be found on
    ##
-@@ -1337,6 +1929,13 @@
+@@ -1337,6 +1932,13 @@
      create: true
    podSecurityPolicy:
      enabled: true
@@ -771,7 +774,7 @@
  
  ## Deploy node exporter as a daemonset to all nodes
  ##
-@@ -1392,6 +1991,16 @@
+@@ -1392,6 +1994,16 @@
    extraArgs:
      - --collector.filesystem.ignored-mount-points=^/(dev|proc|sys|var/lib/docker/.+|var/lib/kubelet/.+)($|/)
      - --collector.filesystem.ignored-fs-types=^(autofs|binfmt_misc|bpf|cgroup2?|configfs|debugfs|devpts|devtmpfs|fusectl|hugetlbfs|iso9660|mqueue|nsfs|overlay|proc|procfs|pstore|rpc_pipefs|securityfs|selinuxfs|squashfs|sysfs|tracefs)$
@@ -788,7 +791,7 @@
  
  ## Manages Prometheus and Alertmanager components
  ##
-@@ -1404,8 +2013,8 @@
+@@ -1404,8 +2016,8 @@
      enabled: true
      # Value must match version names from https://golang.org/pkg/crypto/tls/#pkg-constants
      tlsMinVersion: VersionTLS13
@@ -799,7 +802,7 @@
  
    ## Admission webhook support for PrometheusRules resources added in Prometheus Operator 0.30 can be enabled to prevent incorrectly formatted
    ## rules from making their way into prometheus and potentially preventing the container from starting
-@@ -1422,9 +2031,9 @@
+@@ -1422,9 +2034,9 @@
      patch:
        enabled: true
        image:
@@ -811,7 +814,7 @@
          pullPolicy: IfNotPresent
        resources: {}
        ## Provide a priority class name to the webhook patching job
-@@ -1571,13 +2180,13 @@
+@@ -1571,13 +2183,13 @@
  
    ## Resource limits & requests
    ##
@@ -832,7 +835,7 @@
  
    # Required for use in managed kubernetes clusters (such as AWS EKS) with custom CNI (such as calico),
    # because control-plane managed by AWS cannot communicate with pods' IP CIDR and admission webhooks are not working
-@@ -1630,7 +2239,7 @@
+@@ -1630,7 +2242,7 @@
    ## Prometheus-operator image
    ##
    image:
@@ -841,7 +844,7 @@
      tag: v0.50.0
      sha: ""
      pullPolicy: IfNotPresent
-@@ -1646,7 +2255,7 @@
+@@ -1646,7 +2258,7 @@
    ## Prometheus-config-reloader image to use for config and rule reloading
    ##
    prometheusConfigReloaderImage:
@@ -850,7 +853,16 @@
      tag: v0.50.0
      sha: ""
  
-@@ -1781,7 +2390,7 @@
+@@ -1661,7 +2273,7 @@
+   ## Thanos side-car image when configured
+   ##
+   thanosImage:
+-    repository: quay.io/thanos/thanos
++    repository: rancher/mirrored-thanos-thanos
+     tag: v0.17.2
+     sha: ""
+ 
+@@ -1781,7 +2393,7 @@
      port: 9090
  
      ## To be used with a proxy extraContainer port
@@ -859,7 +871,7 @@
  
      ## List of IP addresses at which the Prometheus server service is available
      ## Ref: https://kubernetes.io/docs/user-guide/services/#external-ips
-@@ -2054,7 +2663,7 @@
+@@ -2054,7 +2666,7 @@
      ## Image of Prometheus.
      ##
      image:
@@ -868,19 +880,7 @@
        tag: v2.28.1
        sha: ""
  
-@@ -2117,6 +2726,11 @@
+@@ -2149,7 +2761,7 @@
-     ##
-     externalUrl: ""
- 
-+    ## Ignore NamespaceSelector settings from the PodMonitor and ServiceMonitor configs
-+    ## If true, PodMonitors and ServiceMonitors can only discover Pods and Services within the namespace they are deployed into
-+    ##
-+    ignoreNamespaceSelectors: false
-+
-     ## Define which Nodes the Pods are scheduled on.
-     ## ref: https://kubernetes.io/docs/user-guide/node-selection/
-     ##
-@@ -2149,7 +2763,7 @@
      ## prometheus resource to be created with selectors based on values in the helm deployment,
      ## which will also match the PrometheusRule resources created
      ##
@@ -889,7 +889,7 @@
  
      ## PrometheusRules to be selected for target discovery.
      ## If {}, select all PrometheusRules
-@@ -2174,7 +2788,7 @@
+@@ -2174,7 +2786,7 @@
      ## prometheus resource to be created with selectors based on values in the helm deployment,
      ## which will also match the servicemonitors created
      ##
@@ -898,7 +898,7 @@
  
      ## ServiceMonitors to be selected for target discovery.
      ## If {}, select all ServiceMonitors
-@@ -2197,7 +2811,7 @@
+@@ -2197,7 +2809,7 @@
      ## prometheus resource to be created with selectors based on values in the helm deployment,
      ## which will also match the podmonitors created
      ##
@@ -907,7 +907,7 @@
  
      ## PodMonitors to be selected for target discovery.
      ## If {}, select all PodMonitors
-@@ -2328,9 +2942,13 @@
+@@ -2328,9 +2940,13 @@
  
      ## Resource limits & requests
      ##
@@ -924,7 +924,7 @@
  
      ## Prometheus StorageSpec for persistent data
      ## ref: https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/user-guides/storage.md
-@@ -2353,7 +2971,13 @@
+@@ -2353,7 +2969,13 @@
      #    medium: Memory
  
      # Additional volumes on the output StatefulSet definition.
@@ -939,7 +939,7 @@
  
      # Additional VolumeMounts on the output StatefulSet definition.
      volumeMounts: []
-@@ -2475,9 +3099,34 @@
+@@ -2475,9 +3097,34 @@
        #         fileName: "objstore.yaml"
        # objectStorageConfigFile: /var/secrets/object-store.yaml
  
@@ -975,7 +975,7 @@
  
      ## InitContainers allows injecting additional initContainers. This is meant to allow doing some changes
      ## (permissions, dir tree) on mounted volumes before starting prometheus
-@@ -2485,7 +3134,7 @@
+@@ -2485,7 +3132,7 @@
  
      ## PortName to use for Prometheus.
      ##

packages/rancher-node-exporter/generated-changes/exclude/ci/port-values.yaml

@@ -0,0 +1,3 @@
+service:
+  targetPort: 9102
+  port: 9102

packages/rancher-prometheus-adapter/generated-changes/exclude/ci/external-rules-values.yaml

@@ -0,0 +1,9 @@
+rules:
+  external:
+  - seriesQuery: '{__name__=~"^some_metric_count$"}'
+    resources:
+      template: <<.Resource>>
+    name:
+      matches: ""
+      as: "my_custom_metric"
+    metricsQuery: sum(<<.Series>>{<<.LabelMatchers>>}) by (<<.GroupBy>>)