Delete chart exporter-kube-api because it has been replaced by kube-controller-manager alerts

2025-04-21 03:38:43 +00:00 · 2017-12-23 09:41:12 +01:00 · 2017-12-23 09:41:12 +01:00 · 59421f7018
commit 59421f7018
parent 3923139e40
64 changed files with 7171 additions and 7201 deletions
--- a/.gitignore
+++ b/.gitignore
@ -8,3 +8,4 @@ requirements.lock
 .DS_Store
 __pycache__
 .env/
+.history/
--- a/contrib/kube-prometheus/assets/prometheus/rules/kube-controller-manager.rules.yaml
+++ b/contrib/kube-prometheus/assets/prometheus/rules/kube-controller-manager.rules.yaml
@ -10,4 +10,4 @@ groups:
      description: There is no running K8S controller manager. Deployments and replication
        controllers are not making progress.
      runbook: https://coreos.com/tectonic/docs/latest/troubleshooting/controller-recovery.html#recovering-a-controller-manager
-      summary: Controller manager is down
+      summary: Controller manager is down
--- a/contrib/kube-prometheus/hack/grafana-dashboards-configmap-generator/bin/grafana_dashboards_generate.sh
+++ b/contrib/kube-prometheus/hack/grafana-dashboards-configmap-generator/bin/grafana_dashboards_generate.sh
@ -203,7 +203,7 @@ addArrayToConfigMap() {
    # Dashboard foot
    test "$type" = "dashboard" && cat $DASHBOARD_FOOT_FILE
  done
-  #echo "---"
+  echo "---"

  IFS=$OLDIFS
  return 0
--- a/helm/alertmanager/Chart.yaml
+++ b/helm/alertmanager/Chart.yaml
@ -4,6 +4,8 @@ engine: gotpl
 maintainers:
  - name: Michael Goodness
    email: mgoodness@gmail.com
+  - name: Giancarlo Rubio
+    email: gianrubio@gmail.com
 name: alertmanager
 sources:
  - https://github.com/coreos/prometheus-operator
--- a/helm/alertmanager/README.md
+++ b/helm/alertmanager/README.md
@ -46,13 +46,14 @@ Parameter | Description | Default
 `config` | Alertmanager configuration directives | `{}`
 `externalUrl` | External URL at which Alertmanager will be reachable | `""`
 `image.repository` | Image | `quay.io/prometheus/alertmanager`
-`image.tag` | Image tag | `v0.9.1`
+`image.tag` | Image tag | `v0.12.0`
 `ingress.enabled` | If true, Alertmanager Ingress will be created | `false`
 `ingress.annotations` | Annotations for Alertmanager Ingress` | `{}`
 `ingress.fqdn` | Alertmanager Ingress fully-qualified domain name | `""`
 `ingress.tls` | TLS configuration for Alertmanager Ingress | `[]`
 `nodeSelector` | Node labels for pod assignment | `{}`
 `paused` | If true, the Operator won't process any Alertmanager configuration changes | `false`
+`prometheusRules` | Prometheus rules | `[templates/alertmanager.rules.yaml](templates/alertmanager.rules.yaml)`
 `replicaCount` | Number of Alertmanager replicas desired | `1`
 `resources` | Pod resource requests & limits | `{}`
 `service.annotations` | Annotations to be added to the Alertmanager Service | `{}`
--- a/helm/alertmanager/templates/alertmanager.rules.yaml
+++ b/helm/alertmanager/templates/alertmanager.rules.yaml
@ -0,0 +1,32 @@
+{{ define "alertmanager.rules.yaml.tpl" }}
+groups:
+- name: alertmanager.rules
+  rules:
+  - alert: AlertmanagerConfigInconsistent
+    expr: count_values("config_hash", alertmanager_config_hash) BY (service) / ON(service)
+      GROUP_LEFT() label_replace(prometheus_operator_alertmanager_spec_replicas, "service",
+      "alertmanager-$1", "alertmanager", "(.*)") != 1
+    for: 5m
+    labels:
+      severity: critical
+    annotations:
+      description: The configuration of the instances of the Alertmanager cluster
+        `{{`{{$labels.service}}`}}` are out of sync.
+  - alert: AlertmanagerDownOrMissing
+    expr: label_replace(prometheus_operator_alertmanager_spec_replicas, "job", "alertmanager-$1",
+      "alertmanager", "(.*)") / ON(job) GROUP_RIGHT() sum(up) BY (job) != 1
+    for: 5m
+    labels:
+      severity: warning
+    annotations:
+      description: An unexpected number of Alertmanagers are scraped or Alertmanagers
+        disappeared from discovery.
+  - alert: AlertmanagerFailedReload
+    expr: alertmanager_config_last_reload_successful == 0
+    for: 10m
+    labels:
+      severity: warning
+    annotations:
+      description: Reloading Alertmanager's configuration has failed for {{`{{ $labels.namespace
+        }}`}}/{{`{{ $labels.pod}}`}}.
+{{ end }}
--- a/helm/alertmanager/templates/configmap.yaml
+++ b/helm/alertmanager/templates/configmap.yaml
@ -0,0 +1,21 @@
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  labels:
+    app: "alertmanager"
+    chart: {{ .Chart.Name }}-{{ .Chart.Version }}
+    heritage: {{ .Release.Service }}
+    prometheus: {{ .Release.Name }}
+    release: {{ .Release.Name }}
+  name: {{ template "fullname" . }}
+data:
+{{- if .Values.prometheusRules }}
+{{- $root := . }}
+{{- range $key, $val := .Values.prometheusRules }}
+  {{ $key }}: |-
+{{ $val | indent 4}}
+{{- end }}
+{{ else }}
+  alertmanager.rules: |-
+    {{- include "alertmanager.rules.yaml.tpl" . | indent 4}}
+{{ end }}
--- a/helm/alertmanager/templates/servicemonitor.yaml
+++ b/helm/alertmanager/templates/servicemonitor.yaml
@ -11,7 +11,7 @@ metadata:
    prometheus: {{ .Release.Name }}
  name: {{ template "fullname" . }}
 spec:
-  jobLabel: {{ template "name" . }}
+  jobLabel: {{ template "fullname" . }}
  selector:
    matchLabels:
      alertmanager: {{ .Release.Name }}
--- a/helm/alertmanager/values.yaml
+++ b/helm/alertmanager/values.yaml
@ -49,7 +49,7 @@ selfServiceMonitor: true
 ##
 image:
  repository: quay.io/prometheus/alertmanager
-  tag: v0.9.1
+  tag: v0.12.0

 ## Labels to be added to the Alertmanager
 ##
@ -150,36 +150,6 @@ storageSpec: {}
 #         requests:
 #           storage: 50Gi
 #   selector: {}
-# WARNING: Don't change this file after this lines, it's automatically appended by helm/hack/sync_kube_prometheus.py
-ruleFiles:
-  alertmanager.rules: |-
-    groups:
-    - name: alertmanager.rules
-      rules:
-      - alert: AlertmanagerConfigInconsistent
-        expr: count_values("config_hash", alertmanager_config_hash) BY (service) / ON(service)
-          GROUP_LEFT() label_replace(prometheus_operator_alertmanager_spec_replicas, "service",
-          "alertmanager-$1", "alertmanager", "(.*)") != 1
-        for: 5m
-        labels:
-          severity: critical
-        annotations:
-          description: The configuration of the instances of the Alertmanager cluster
-            `{{$labels.service}}` are out of sync.
-      - alert: AlertmanagerDownOrMissing
-        expr: label_replace(prometheus_operator_alertmanager_spec_replicas, "job", "alertmanager-$1",
-          "alertmanager", "(.*)") / ON(job) GROUP_RIGHT() sum(up) BY (job) != 1
-        for: 5m
-        labels:
-          severity: warning
-        annotations:
-          description: An unexpected number of Alertmanagers are scraped or Alertmanagers
-            disappeared from discovery.
-      - alert: AlertmanagerFailedReload
-        expr: alertmanager_config_last_reload_successful == 0
-        for: 10m
-        labels:
-          severity: warning
-        annotations:
-          description: Reloading Alertmanager's configuration has failed for {{ $labels.namespace
-            }}/{{ $labels.pod}}.
+
+# default rules are in templates/alertmanager.rules.yaml
+# prometheusRules: {}
--- a/helm/exporter-kube-api/.helmignore
+++ b/helm/exporter-kube-api/.helmignore
@ -1,21 +0,0 @@
-# Patterns to ignore when building packages.
-# This supports shell glob matching, relative path matching, and
-# negation (prefixed with !). Only one pattern per line.
-.DS_Store
-# Common VCS dirs
-.git/
-.gitignore
-.bzr/
-.bzrignore
-.hg/
-.hgignore
-.svn/
-# Common backup files
-*.swp
-*.bak
-*.tmp
-*~
-# Various IDEs
-.project
-.idea/
-*.tmproj
--- a/helm/exporter-kube-api/Chart.yaml
+++ b/helm/exporter-kube-api/Chart.yaml
@ -1,7 +0,0 @@
-apiVersion: v1
-description: A Helm chart for Kubernetes
-name: exporter-kube-api
-version: 0.1.1
-maintainers:
-  - name: Cloud Posse LLC
-    email: hello@cloudposse.com
--- a/helm/exporter-kube-api/templates/_helpers.tpl
+++ b/helm/exporter-kube-api/templates/_helpers.tpl
@ -1,16 +0,0 @@
-{{/* vim: set filetype=mustache: */}}
-{{/*
-Expand the name of the chart.
-*/}}
-{{- define "name" -}}
-{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" -}}
-{{- end -}}
-
-{{/*
-Create a default fully qualified app name.
-We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec).
-*/}}
-{{- define "fullname" -}}
-{{- $name := default .Chart.Name .Values.nameOverride -}}
-{{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" -}}
-{{- end -}}
--- a/helm/exporter-kube-api/templates/service.yaml
+++ b/helm/exporter-kube-api/templates/service.yaml
@ -1,21 +0,0 @@
-apiVersion: v1
-kind: Service
-metadata:
-  labels:
-    app: {{ template "name" . }}
-    component: kube-api
-    heritage: {{ .Release.Service }}
-    release: {{ .Release.Name }}
-    chart: {{ .Chart.Name }}-{{ .Chart.Version | replace "+" "_" }}
-  name: {{ template "fullname" . }}
-  namespace: kube-system
-spec:
-  clusterIP: None
-  ports:
-    - name: https-metrics
-      port: 443
-      protocol: TCP
-      targetPort: 443
-  selector:
-    k8s-app: kube-apiserver
-  type: ClusterIP
--- a/helm/exporter-kube-api/templates/servicemonitor.yaml
+++ b/helm/exporter-kube-api/templates/servicemonitor.yaml
@ -1,29 +0,0 @@
-apiVersion: monitoring.coreos.com/v1
-kind: ServiceMonitor
-metadata:
-  labels:
-    chart: "{{ .Chart.Name }}-{{ .Chart.Version }}"
-    component: kube-api
-    heritage: "{{ .Release.Service }}"
-    release: "{{ .Release.Name }}"
-    prometheus: {{ .Release.Name }}
-  name: {{ template "fullname" . }}
-spec:
-  jobLabel: {{ template "fullname" . }}
-  selector:
-    matchLabels:
-      app: {{ template "name" . }}
-      component: kube-api
-  namespaceSelector:
-    matchNames:
-      - "kube-system"
-  endpoints:
-  - port: https-metrics
-    interval: 15s
-    scheme: https
-    tlsConfig:
-      caFile: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
-      # Skip verification until we have resolved why the certificate validation
-      # for the kubelet on API server nodes fail.
-      insecureSkipVerify: true
-    bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token
--- a/helm/exporter-kube-api/values.yaml
+++ b/helm/exporter-kube-api/values.yaml
@ -1,93 +0,0 @@
-# This is a YAML-formatted file.
-# Declare variables to be passed into your templates.
-ruleFiles:
-  kube-api.rules: |-
-    # NOTE: These rules were kindly contributed by the SoundCloud engineering team.
-
-    ALERT K8SApiServerLatency
-      IF histogram_quantile(
-          0.99,
-          sum without (instance,node,resource) (apiserver_request_latencies_bucket{subresource!="log",verb!~"CONNECT|WATCHLIST|WATCH"})
-        ) / 1e6 > 1.0
-      FOR 10m
-      LABELS {
-        service = "k8s",
-        severity = "warning"
-      }
-      ANNOTATIONS {
-        summary = "Kubernetes apiserver latency is high",
-        description = "99th percentile Latency for {{`{{ $labels.verb }}`}} requests to the kube-apiserver is higher than 1s.",
-      }
-
-    ### API latency ###
-
-    # Raw metrics are in microseconds. Convert to seconds.
-    cluster_resource_verb:apiserver_latency:quantile_seconds{quantile="0.99"} =
-      histogram_quantile(
-        0.99,
-        sum by(le,cluster,job,resource,verb) (apiserver_request_latencies_bucket)
-      ) / 1e6
-    cluster_resource_verb:apiserver_latency:quantile_seconds{quantile="0.9"} =
-      histogram_quantile(
-        0.9,
-        sum by(le,cluster,job,resource,verb) (apiserver_request_latencies_bucket)
-      ) / 1e6
-    cluster_resource_verb:apiserver_latency:quantile_seconds{quantile="0.5"} =
-      histogram_quantile(
-        0.5,
-        sum by(le,cluster,job,resource,verb) (apiserver_request_latencies_bucket)
-      ) / 1e6
-
-    ### File descriptor alerts
-
-    instance:fd_utilization = process_open_fds / process_max_fds
-
-    # alert if file descriptors are likely to exhaust within the next 4 hours
-    ALERT FdExhaustionClose
-      IF predict_linear(instance:fd_utilization[1h], 3600 * 4) > 1
-      FOR 10m
-      LABELS
-      {
-        severity = "warning"
-      }
-      ANNOTATIONS {
-        summary = "file descriptors soon exhausted",
-        description = "{{`{{ $labels.job }}`}} instance {{`{{ $labels.instance }}`}} will exhaust in file descriptors soon",
-      }
-
-    # alert if file descriptors are likely to exhaust within the next hour
-    ALERT FdExhaustionClose
-      IF predict_linear(instance:fd_utilization[10m], 3600) > 1
-      FOR 10m
-      LABELS {
-        severity = "critical"
-      }
-      ANNOTATIONS
-      {
-        summary = "file descriptors soon exhausted",
-        description = "{{`{{ $labels.job }}`}} instance {{`{{ $labels.instance }}`}} will exhaust in file descriptors soon",
-      }
-
-    ALERT K8STooManyOpenFiles
-      IF 100*process_open_fds{job=~"kubelets|kubernetes"} / process_max_fds > 50
-      FOR 10m
-      LABELS {
-        service = "k8s",
-        severity = "warning"
-      }
-      ANNOTATIONS {
-        summary = "{{`{{ $labels.job }}`}} has too many open file descriptors",
-        description = "{{`{{ $labels.node }}`}} is using {{`{{ $value }}`}}% of the available file/socket descriptors.",
-      }
-
-    ALERT K8STooManyOpenFiles
-      IF 100*process_open_fds{job=~"kubelets|kubernetes"} / process_max_fds > 80
-      FOR 10m
-      LABELS {
-        service = "k8s",
-        severity = "critical"
-      }
-      ANNOTATIONS {
-        summary = "{{`{{ $labels.job }}`}} has too many open file descriptors",
-        description = "{{`{{ $labels.node }}`}} is using {{`{{ $value }}`}}% of the available file/socket descriptors.",
-      }
--- a/helm/exporter-kube-controller-manager/Chart.yaml
+++ b/helm/exporter-kube-controller-manager/Chart.yaml
@ -1,7 +1,9 @@
 apiVersion: v1
 description: A Helm chart for Kubernetes
 name: exporter-kube-controller-manager
-version: 0.1.1
+version: 0.1.2
 maintainers:
-  - name: Cloud Posse LLC
-    email: hello@cloudposse.com
+  - name: Michael Goodness
+    email: mgoodness@gmail.com
+  - name: Giancarlo Rubio
+    email: gianrubio@gmail.com
--- a/helm/exporter-kube-controller-manager/templates/configmap.yaml
+++ b/helm/exporter-kube-controller-manager/templates/configmap.yaml
@ -9,8 +9,13 @@ metadata:
    release: {{ .Release.Name }}
  name: {{ template "fullname" . }}
 data:
+{{- if .Values.prometheusRules }}
 {{- $root := . }}
-{{- range $key, $val := .Values.ruleFiles }}
+{{- range $key, $val := .Values.prometheusRules }}
  {{ $key }}: |-
 {{ $val | indent 4}}
 {{- end }}
+{{ else }}
+  kube-controller-manager.rules: |-
+    {{- include "kube-controller-manager.rules.yaml.tpl" . | indent 4}}
+{{ end }}
--- a/helm/exporter-kube-controller-manager/templates/kube-controller-manager.rules.yaml
+++ b/helm/exporter-kube-controller-manager/templates/kube-controller-manager.rules.yaml
@ -0,0 +1,15 @@
+{{ define "kube-controller-manager.rules.yaml.tpl" }}
+groups:
+- name: kube-controller-manager.rules
+  rules:
+  - alert: K8SControllerManagerDown
+    expr: absent(up{job="{{ template "fullname" .  }}"} == 1)
+    for: 5m
+    labels:
+      severity: critical
+    annotations:
+      description: There is no running K8S controller manager. Deployments and replication
+        controllers are not making progress.
+      runbook: https://coreos.com/tectonic/docs/latest/troubleshooting/controller-recovery.html#recovering-a-controller-manager
+      summary: Controller manager is down
+{{ end }}
--- a/helm/exporter-kube-controller-manager/values.yaml
+++ b/helm/exporter-kube-controller-manager/values.yaml
@ -1,16 +1,2 @@
-# WARNING: Don't touch this file, it's automatically generated by helm/hack/sync-kube-prometheus.sh
-ruleFiles:
-  kube-controller-manager.rules: |-
-    groups:
-    - name: kube-controller-manager.rules
-      rules:
-      - alert: K8SControllerManagerDown
-        expr: absent(up{job="kube-controller-manager"} == 1)
-        for: 5m
-        labels:
-          severity: critical
-        annotations:
-          description: There is no running K8S controller manager. Deployments and replication
-            controllers are not making progress.
-          runbook: https://coreos.com/tectonic/docs/latest/troubleshooting/controller-recovery.html#recovering-a-controller-manager
-          summary: Controller manager is down
+# default rules are in templates/kube-controller-manager.rules.yaml
+# prometheusRules: {}
--- a/helm/exporter-kube-dns/Chart.yaml
+++ b/helm/exporter-kube-dns/Chart.yaml
@ -1,7 +1,9 @@
 apiVersion: v1
 description: A Helm chart singleton for kube-state-metrics
 name: exporter-kube-dns
-version: 0.1.1
+version: 0.1.2
 maintainers:
-  - name: Cloud Posse LLC
-    email: hello@cloudposse.com
+  - name: Michael Goodness
+    email: mgoodness@gmail.com
+  - name: Giancarlo Rubio
+    email: gianrubio@gmail.com
--- a/helm/exporter-kube-dns/templates/servicemonitor.yaml
+++ b/helm/exporter-kube-dns/templates/servicemonitor.yaml
@ -9,7 +9,7 @@ metadata:
    prometheus: {{ .Release.Name }}
  name: {{ template "fullname" . }}
 spec:
-  jobLabel: {{ template "name" . }}
+  jobLabel: {{ template "fullname" . }}
  selector:
    matchLabels:
      app: {{ template "name" . }}
--- a/helm/exporter-kube-etcd/Chart.yaml
+++ b/helm/exporter-kube-etcd/Chart.yaml
@ -1,7 +1,9 @@
 apiVersion: v1
 description: A Helm chart for Kubernetes
 name: exporter-kube-etcd
-version: 0.1.1
+version: 0.1.2
 maintainers:
-  - name: Cloud Posse LLC
-    email: hello@cloudposse.com
+  - name: Michael Goodness
+    email: mgoodness@gmail.com
+  - name: Giancarlo Rubio
+    email: gianrubio@gmail.com
--- a/helm/exporter-kube-etcd/templates/configmap.yaml
+++ b/helm/exporter-kube-etcd/templates/configmap.yaml
@ -9,8 +9,13 @@ metadata:
    release: {{ .Release.Name }}
  name: {{ template "fullname" . }}
 data:
+{{- if .Values.prometheusRules }}
 {{- $root := . }}
-{{- range $key, $val := .Values.ruleFiles }}
+{{- range $key, $val := .Values.prometheusRules }}
  {{ $key }}: |-
-{{ $val | indent 4}}
+{{ tpl $val $root | indent 4}}
 {{- end }}
+{{ else }}
+  etcd3.rules: |-
+    {{- include "etcd3.rules.yaml.tpl" . | indent 4}}
+{{ end }}
--- a/helm/exporter-kube-etcd/templates/etcd3.rules.yaml
+++ b/helm/exporter-kube-etcd/templates/etcd3.rules.yaml
@ -0,0 +1,125 @@
+{{ define "etcd3.rules.yaml.tpl" }}
+groups:
+- name: ./etcd3.rules
+  rules:
+  - alert: InsufficientMembers
+    expr: count(up{job="{{ template "fullname" .  }}"} == 0) > (count(up{job="{{ template "fullname" .  }}"}) / 2 - 1)
+    for: 3m
+    labels:
+      severity: critical
+    annotations:
+      description: If one more etcd member goes down the cluster will be unavailable
+      summary: etcd cluster insufficient members
+  - alert: NoLeader
+    expr: etcd_server_has_leader{job="{{ template "fullname" .  }}"} == 0
+    for: 1m
+    labels:
+      severity: critical
+    annotations:
+      description: etcd member {{`{{ $labels.instance }}`}} has no leader
+      summary: etcd member has no leader
+  - alert: HighNumberOfLeaderChanges
+    expr: increase(etcd_server_leader_changes_seen_total{job="{{ template "fullname" .  }}"}[1h]) > 3
+    labels:
+      severity: warning
+    annotations:
+      description: etcd instance {{`{{ $labels.instance }}`}} has seen {{`{{ $value }}`}} leader
+        changes within the last hour
+      summary: a high number of leader changes within the etcd cluster are happening
+  - alert: HighNumberOfFailedGRPCRequests
+    expr: sum(rate(grpc_server_handled_total{grpc_code!="OK",job="{{ template "fullname" .  }}"}[5m])) BY (grpc_service, grpc_method)
+      / sum(rate(grpc_server_handled_total{job="{{ template "fullname" .  }}"}[5m])) BY (grpc_service, grpc_method) > 0.01
+    for: 10m
+    labels:
+      severity: warning
+    annotations:
+      description: '{{`{{ $value }}`}}% of requests for {{`{{ $labels.grpc_method }}`}} failed
+        on etcd instance {{`{{ $labels.instance }}`}}'
+      summary: a high number of gRPC requests are failing
+  - alert: HighNumberOfFailedGRPCRequests
+    expr: sum(rate(grpc_server_handled_total{grpc_code!="OK",job="{{ template "fullname" .  }}"}[5m])) BY (grpc_service, grpc_method)
+      / sum(rate(grpc_server_handled_total{job="{{ template "fullname" .  }}"}[5m])) BY (grpc_service, grpc_method) > 0.05
+    for: 5m
+    labels:
+      severity: critical
+    annotations:
+      description: '{{`{{ $value }}`}}% of requests for {{`{{ $labels.grpc_method }}`}} failed
+        on etcd instance {{`{{ $labels.instance }}`}}'
+      summary: a high number of gRPC requests are failing
+  - alert: GRPCRequestsSlow
+    expr: histogram_quantile(0.99, sum(rate(grpc_server_handling_seconds_bucket{job="{{ template "fullname" .  }}",grpc_type="unary"}[5m])) by (grpc_service, grpc_method, le))
+      > 0.15
+    for: 10m
+    labels:
+      severity: critical
+    annotations:
+      description: on etcd instance {{`{{ $labels.instance }}`}} gRPC requests to {{`{{ $labels.grpc_method
+        }}`}} are slow
+      summary: slow gRPC requests
+  - alert: HighNumberOfFailedHTTPRequests
+    expr: sum(rate(etcd_http_failed_total{job="{{ template "fullname" .  }}"}[5m])) BY (method) / sum(rate(etcd_http_received_total{job="{{ template "fullname" .  }}"}[5m]))
+      BY (method) > 0.01
+    for: 10m
+    labels:
+      severity: warning
+    annotations:
+      description: '{{`{{ $value }}`}}% of requests for {{`{{ $labels.method }}`}} failed on etcd
+        instance {{`{{ $labels.instance }}`}}'
+      summary: a high number of HTTP requests are failing
+  - alert: HighNumberOfFailedHTTPRequests
+    expr: sum(rate(etcd_http_failed_total{job="{{ template "fullname" .  }}"}[5m])) BY (method) / sum(rate(etcd_http_received_total{job="{{ template "fullname" .  }}"}[5m]))
+      BY (method) > 0.05
+    for: 5m
+    labels:
+      severity: critical
+    annotations:
+      description: '{{`{{ $value }}`}}% of requests for {{`{{ $labels.method }}`}} failed on etcd
+        instance {{`{{ $labels.instance }}`}}'
+      summary: a high number of HTTP requests are failing
+  - alert: HTTPRequestsSlow
+    expr: histogram_quantile(0.99, rate(etcd_http_successful_duration_seconds_bucket[5m]))
+      > 0.15
+    for: 10m
+    labels:
+      severity: warning
+    annotations:
+      description: on etcd instance {{`{{ $labels.instance }}`}} HTTP requests to {{`{{ $labels.method
+        }}`}} are slow
+      summary: slow HTTP requests
+  - alert: EtcdMemberCommunicationSlow
+    expr: histogram_quantile(0.99, rate(etcd_network_member_round_trip_time_seconds_bucket[5m]))
+      > 0.15
+    for: 10m
+    labels:
+      severity: warning
+    annotations:
+      description: etcd instance {{`{{ $labels.instance }}`}} member communication with
+        {{`{{ $labels.To }}`}} is slow
+      summary: etcd member communication is slow
+  - alert: HighNumberOfFailedProposals
+    expr: increase(etcd_server_proposals_failed_total{job="{{ template "fullname" .  }}"}[1h]) > 5
+    labels:
+      severity: warning
+    annotations:
+      description: etcd instance {{`{{ $labels.instance }}`}} has seen {{`{{ $value }}`}} proposal
+        failures within the last hour
+      summary: a high number of proposals within the etcd cluster are failing
+  - alert: HighFsyncDurations
+    expr: histogram_quantile(0.99, rate(etcd_disk_wal_fsync_duration_seconds_bucket[5m]))
+      > 0.5
+    for: 10m
+    labels:
+      severity: warning
+    annotations:
+      description: etcd instance {{`{{ $labels.instance }}`}} fync durations are high
+      summary: high fsync durations
+  - alert: HighCommitDurations
+    expr: histogram_quantile(0.99, rate(etcd_disk_backend_commit_duration_seconds_bucket[5m]))
+      > 0.25
+    for: 10m
+    labels:
+      severity: warning
+    annotations:
+      description: etcd instance {{`{{ $labels.instance }}`}} commit durations are high
+      summary: high commit durations
+{{ end }}
--- a/helm/exporter-kube-etcd/values.yaml
+++ b/helm/exporter-kube-etcd/values.yaml
@ -1,128 +1,2 @@
-# This is a YAML-formatted file.
-# Declare variables to be passed into your templates.
-# WARNING: Don't change this file after this lines, it's automatically appended by helm/hack/sync_kube_prometheus.py
-ruleFiles:
-  etcd3.rules: |-
-    groups:
-    - name: ./etcd3.rules
-      rules:
-      - alert: InsufficientMembers
-        expr: count(up{job="etcd"} == 0) > (count(up{job="etcd"}) / 2 - 1)
-        for: 3m
-        labels:
-          severity: critical
-        annotations:
-          description: If one more etcd member goes down the cluster will be unavailable
-          summary: etcd cluster insufficient members
-      - alert: NoLeader
-        expr: etcd_server_has_leader{job="etcd"} == 0
-        for: 1m
-        labels:
-          severity: critical
-        annotations:
-          description: etcd member {{ $labels.instance }} has no leader
-          summary: etcd member has no leader
-      - alert: HighNumberOfLeaderChanges
-        expr: increase(etcd_server_leader_changes_seen_total{job="etcd"}[1h]) > 3
-        labels:
-          severity: warning
-        annotations:
-          description: etcd instance {{ $labels.instance }} has seen {{ $value }} leader
-            changes within the last hour
-          summary: a high number of leader changes within the etcd cluster are happening
-      - alert: HighNumberOfFailedGRPCRequests
-        expr: sum(rate(grpc_server_handled_total{grpc_code!="OK",job="etcd"}[5m])) BY (grpc_service, grpc_method)
-          / sum(rate(grpc_server_handled_total{job="etcd"}[5m])) BY (grpc_service, grpc_method) > 0.01
-        for: 10m
-        labels:
-          severity: warning
-        annotations:
-          description: '{{ $value }}% of requests for {{ $labels.grpc_method }} failed
-            on etcd instance {{ $labels.instance }}'
-          summary: a high number of gRPC requests are failing
-      - alert: HighNumberOfFailedGRPCRequests
-        expr: sum(rate(grpc_server_handled_total{grpc_code!="OK",job="etcd"}[5m])) BY (grpc_service, grpc_method)
-          / sum(rate(grpc_server_handled_total{job="etcd"}[5m])) BY (grpc_service, grpc_method) > 0.05
-        for: 5m
-        labels:
-          severity: critical
-        annotations:
-          description: '{{ $value }}% of requests for {{ $labels.grpc_method }} failed
-            on etcd instance {{ $labels.instance }}'
-          summary: a high number of gRPC requests are failing
-      - alert: GRPCRequestsSlow
-        expr: histogram_quantile(0.99, sum(rate(grpc_server_handling_seconds_bucket{job="etcd",grpc_type="unary"}[5m])) by (grpc_service, grpc_method, le))
-          > 0.15
-        for: 10m
-        labels:
-          severity: critical
-        annotations:
-          description: on etcd instance {{ $labels.instance }} gRPC requests to {{ $labels.grpc_method
-            }} are slow
-          summary: slow gRPC requests
-      - alert: HighNumberOfFailedHTTPRequests
-        expr: sum(rate(etcd_http_failed_total{job="etcd"}[5m])) BY (method) / sum(rate(etcd_http_received_total{job="etcd"}[5m]))
-          BY (method) > 0.01
-        for: 10m
-        labels:
-          severity: warning
-        annotations:
-          description: '{{ $value }}% of requests for {{ $labels.method }} failed on etcd
-            instance {{ $labels.instance }}'
-          summary: a high number of HTTP requests are failing
-      - alert: HighNumberOfFailedHTTPRequests
-        expr: sum(rate(etcd_http_failed_total{job="etcd"}[5m])) BY (method) / sum(rate(etcd_http_received_total{job="etcd"}[5m]))
-          BY (method) > 0.05
-        for: 5m
-        labels:
-          severity: critical
-        annotations:
-          description: '{{ $value }}% of requests for {{ $labels.method }} failed on etcd
-            instance {{ $labels.instance }}'
-          summary: a high number of HTTP requests are failing
-      - alert: HTTPRequestsSlow
-        expr: histogram_quantile(0.99, rate(etcd_http_successful_duration_seconds_bucket[5m]))
-          > 0.15
-        for: 10m
-        labels:
-          severity: warning
-        annotations:
-          description: on etcd instance {{ $labels.instance }} HTTP requests to {{ $labels.method
-            }} are slow
-          summary: slow HTTP requests
-      - alert: EtcdMemberCommunicationSlow
-        expr: histogram_quantile(0.99, rate(etcd_network_member_round_trip_time_seconds_bucket[5m]))
-          > 0.15
-        for: 10m
-        labels:
-          severity: warning
-        annotations:
-          description: etcd instance {{ $labels.instance }} member communication with
-            {{ $labels.To }} is slow
-          summary: etcd member communication is slow
-      - alert: HighNumberOfFailedProposals
-        expr: increase(etcd_server_proposals_failed_total{job="etcd"}[1h]) > 5
-        labels:
-          severity: warning
-        annotations:
-          description: etcd instance {{ $labels.instance }} has seen {{ $value }} proposal
-            failures within the last hour
-          summary: a high number of proposals within the etcd cluster are failing
-      - alert: HighFsyncDurations
-        expr: histogram_quantile(0.99, rate(etcd_disk_wal_fsync_duration_seconds_bucket[5m]))
-          > 0.5
-        for: 10m
-        labels:
-          severity: warning
-        annotations:
-          description: etcd instance {{ $labels.instance }} fync durations are high
-          summary: high fsync durations
-      - alert: HighCommitDurations
-        expr: histogram_quantile(0.99, rate(etcd_disk_backend_commit_duration_seconds_bucket[5m]))
-          > 0.25
-        for: 10m
-        labels:
-          severity: warning
-        annotations:
-          description: etcd instance {{ $labels.instance }} commit durations are high
-          summary: high commit durations
+# default rules are in templates/etcd3.rules.yaml
+# prometheusRules: {}
--- a/helm/exporter-kube-scheduler/Chart.yaml
+++ b/helm/exporter-kube-scheduler/Chart.yaml
@ -1,7 +1,9 @@
 apiVersion: v1
 description: A Helm chart singleton for kube-state-metrics
 name: exporter-kube-scheduler
-version: 0.1.1
+version: 0.1.2
 maintainers:
-  - name: Cloud Posse LLC
-    email: hello@cloudposse.com
+  - name: Michael Goodness
+    email: mgoodness@gmail.com
+  - name: Giancarlo Rubio
+    email: gianrubio@gmail.com
--- a/helm/exporter-kube-scheduler/templates/configmap.yaml
+++ b/helm/exporter-kube-scheduler/templates/configmap.yaml
@ -9,8 +9,13 @@ metadata:
    release: {{ .Release.Name }}
  name: {{ template "fullname" . }}
 data:
+{{- if .Values.prometheusRules }}
 {{- $root := . }}
-{{- range $key, $val := .Values.ruleFiles }}
+{{- range $key, $val := .Values.prometheusRules }}
  {{ $key }}: |-
-{{ $val | indent 4}}
+{{ tpl $val $root | indent 4}}
 {{- end }}
+{{ else }}
+  kube-scheduler.rules: |-
+    {{- include "kube-scheduler.rules.yaml.tpl" . | indent 4}}
+{{ end }}
--- a/helm/exporter-kube-scheduler/templates/kube-scheduler.rules.yaml
+++ b/helm/exporter-kube-scheduler/templates/kube-scheduler.rules.yaml
@ -0,0 +1,60 @@
+{{ define "kube-scheduler.rules.yaml.tpl" }}
+groups:
+- name: kube-scheduler.rules
+  rules:
+  - record: cluster:scheduler_e2e_scheduling_latency_seconds:quantile
+    expr: histogram_quantile(0.99, sum(scheduler_e2e_scheduling_latency_microseconds_bucket)
+      BY (le, cluster)) / 1e+06
+    labels:
+      quantile: "0.99"
+  - record: cluster:scheduler_e2e_scheduling_latency_seconds:quantile
+    expr: histogram_quantile(0.9, sum(scheduler_e2e_scheduling_latency_microseconds_bucket)
+      BY (le, cluster)) / 1e+06
+    labels:
+      quantile: "0.9"
+  - record: cluster:scheduler_e2e_scheduling_latency_seconds:quantile
+    expr: histogram_quantile(0.5, sum(scheduler_e2e_scheduling_latency_microseconds_bucket)
+      BY (le, cluster)) / 1e+06
+    labels:
+      quantile: "0.5"
+  - record: cluster:scheduler_scheduling_algorithm_latency_seconds:quantile
+    expr: histogram_quantile(0.99, sum(scheduler_scheduling_algorithm_latency_microseconds_bucket)
+      BY (le, cluster)) / 1e+06
+    labels:
+      quantile: "0.99"
+  - record: cluster:scheduler_scheduling_algorithm_latency_seconds:quantile
+    expr: histogram_quantile(0.9, sum(scheduler_scheduling_algorithm_latency_microseconds_bucket)
+      BY (le, cluster)) / 1e+06
+    labels:
+      quantile: "0.9"
+  - record: cluster:scheduler_scheduling_algorithm_latency_seconds:quantile
+    expr: histogram_quantile(0.5, sum(scheduler_scheduling_algorithm_latency_microseconds_bucket)
+      BY (le, cluster)) / 1e+06
+    labels:
+      quantile: "0.5"
+  - record: cluster:scheduler_binding_latency_seconds:quantile
+    expr: histogram_quantile(0.99, sum(scheduler_binding_latency_microseconds_bucket)
+      BY (le, cluster)) / 1e+06
+    labels:
+      quantile: "0.99"
+  - record: cluster:scheduler_binding_latency_seconds:quantile
+    expr: histogram_quantile(0.9, sum(scheduler_binding_latency_microseconds_bucket)
+      BY (le, cluster)) / 1e+06
+    labels:
+      quantile: "0.9"
+  - record: cluster:scheduler_binding_latency_seconds:quantile
+    expr: histogram_quantile(0.5, sum(scheduler_binding_latency_microseconds_bucket)
+      BY (le, cluster)) / 1e+06
+    labels:
+      quantile: "0.5"
+  - alert: K8SSchedulerDown
+    expr: absent(up{job="{{ template "fullname" .  }}"} == 1)
+    for: 5m
+    labels:
+      severity: critical
+    annotations:
+      description: There is no running K8S scheduler. New pods are not being assigned
+        to nodes.
+      runbook: https://coreos.com/tectonic/docs/latest/troubleshooting/controller-recovery.html#recovering-a-scheduler
+      summary: Scheduler is down
+{{ end }}
--- a/helm/exporter-kube-scheduler/values.yaml
+++ b/helm/exporter-kube-scheduler/values.yaml
@ -1,63 +1,2 @@
-# This is a YAML-formatted file.
-# Declare variables to be passed into your templates.
-# WARNING: Don't change this file after this lines, it's automatically appended by helm/hack/sync_kube_prometheus.py
-ruleFiles:
-  kube-scheduler.rules: |-
-    groups:
-    - name: kube-scheduler.rules
-      rules:
-      - record: cluster:scheduler_e2e_scheduling_latency_seconds:quantile
-        expr: histogram_quantile(0.99, sum(scheduler_e2e_scheduling_latency_microseconds_bucket)
-          BY (le, cluster)) / 1e+06
-        labels:
-          quantile: "0.99"
-      - record: cluster:scheduler_e2e_scheduling_latency_seconds:quantile
-        expr: histogram_quantile(0.9, sum(scheduler_e2e_scheduling_latency_microseconds_bucket)
-          BY (le, cluster)) / 1e+06
-        labels:
-          quantile: "0.9"
-      - record: cluster:scheduler_e2e_scheduling_latency_seconds:quantile
-        expr: histogram_quantile(0.5, sum(scheduler_e2e_scheduling_latency_microseconds_bucket)
-          BY (le, cluster)) / 1e+06
-        labels:
-          quantile: "0.5"
-      - record: cluster:scheduler_scheduling_algorithm_latency_seconds:quantile
-        expr: histogram_quantile(0.99, sum(scheduler_scheduling_algorithm_latency_microseconds_bucket)
-          BY (le, cluster)) / 1e+06
-        labels:
-          quantile: "0.99"
-      - record: cluster:scheduler_scheduling_algorithm_latency_seconds:quantile
-        expr: histogram_quantile(0.9, sum(scheduler_scheduling_algorithm_latency_microseconds_bucket)
-          BY (le, cluster)) / 1e+06
-        labels:
-          quantile: "0.9"
-      - record: cluster:scheduler_scheduling_algorithm_latency_seconds:quantile
-        expr: histogram_quantile(0.5, sum(scheduler_scheduling_algorithm_latency_microseconds_bucket)
-          BY (le, cluster)) / 1e+06
-        labels:
-          quantile: "0.5"
-      - record: cluster:scheduler_binding_latency_seconds:quantile
-        expr: histogram_quantile(0.99, sum(scheduler_binding_latency_microseconds_bucket)
-          BY (le, cluster)) / 1e+06
-        labels:
-          quantile: "0.99"
-      - record: cluster:scheduler_binding_latency_seconds:quantile
-        expr: histogram_quantile(0.9, sum(scheduler_binding_latency_microseconds_bucket)
-          BY (le, cluster)) / 1e+06
-        labels:
-          quantile: "0.9"
-      - record: cluster:scheduler_binding_latency_seconds:quantile
-        expr: histogram_quantile(0.5, sum(scheduler_binding_latency_microseconds_bucket)
-          BY (le, cluster)) / 1e+06
-        labels:
-          quantile: "0.5"
-      - alert: K8SSchedulerDown
-        expr: absent(up{job="kube-scheduler"} == 1)
-        for: 5m
-        labels:
-          severity: critical
-        annotations:
-          description: There is no running K8S scheduler. New pods are not being assigned
-            to nodes.
-          runbook: https://coreos.com/tectonic/docs/latest/troubleshooting/controller-recovery.html#recovering-a-scheduler
-          summary: Scheduler is down
+# default rules are in templates/kube-scheduler.rules.yaml
+# prometheusRules: {}
--- a/helm/exporter-kube-state/Chart.yaml
+++ b/helm/exporter-kube-state/Chart.yaml
@ -3,5 +3,7 @@ description: A Helm chart singleton for kube-state-metrics
 name: exporter-kube-state
 version: 0.1.3
 maintainers:
-  - name: Cloud Posse LLC
-    email: hello@cloudposse.com
+  - name: Michael Goodness
+    email: mgoodness@gmail.com
+  - name: Giancarlo Rubio
+    email: gianrubio@gmail.com
--- a/helm/exporter-kube-state/templates/configmap.yaml
+++ b/helm/exporter-kube-state/templates/configmap.yaml
@ -9,8 +9,13 @@ metadata:
    release: {{ .Release.Name }}
  name: {{ template "fullname" . }}
 data:
+{{- if .Values.prometheusRules }}
 {{- $root := . }}
-{{- range $key, $val := .Values.ruleFiles }}
+{{- range $key, $val := .Values.prometheusRules }}
  {{ $key }}: |-
 {{ $val | indent 4}}
 {{- end }}
+{{ else }}
+  kube-state-metrics.rules: |-
+    {{- include "kube-state-metrics.rules.yaml.tpl" . | indent 4}}
+{{ end }}
--- a/helm/exporter-kube-state/templates/kube-state-metrics.rules.yaml
+++ b/helm/exporter-kube-state/templates/kube-state-metrics.rules.yaml
@ -0,0 +1,57 @@
+{{ define "kube-state-metrics.rules.yaml.tpl" }}
+groups:
+- name: kube-state-metrics.rules
+  rules:
+  - alert: DeploymentGenerationMismatch
+    expr: kube_deployment_status_observed_generation != kube_deployment_metadata_generation
+    for: 15m
+    labels:
+      severity: warning
+    annotations:
+      description: Observed deployment generation does not match expected one for
+        deployment {{`{{$labels.namespaces}}`}}{{`{{$labels.deployment}}`}}
+  - alert: DeploymentReplicasNotUpdated
+    expr: ((kube_deployment_status_replicas_updated != kube_deployment_spec_replicas)
+      or (kube_deployment_status_replicas_available != kube_deployment_spec_replicas))
+      unless (kube_deployment_spec_paused == 1)
+    for: 15m
+    labels:
+      severity: warning
+    annotations:
+      description: Replicas are not updated and available for deployment {{`{{$labels.namespaces}}`}}/{{`{{$labels.deployment}}`}}
+  - alert: DaemonSetRolloutStuck
+    expr: kube_daemonset_status_current_number_ready / kube_daemonset_status_desired_number_scheduled
+      * 100 < 100
+    for: 15m
+    labels:
+      severity: warning
+    annotations:
+      description: Only {{`{{$value}}`}}% of desired pods scheduled and ready for daemon
+        set {{`{{$labels.namespaces}}`}}/{{`{{$labels.daemonset}}`}}
+  - alert: K8SDaemonSetsNotScheduled
+    expr: kube_daemonset_status_desired_number_scheduled - kube_daemonset_status_current_number_scheduled
+      > 0
+    for: 10m
+    labels:
+      severity: warning
+    annotations:
+      description: A number of daemonsets are not scheduled.
+      summary: Daemonsets are not scheduled correctly
+  - alert: DaemonSetsMissScheduled
+    expr: kube_daemonset_status_number_misscheduled > 0
+    for: 10m
+    labels:
+      severity: warning
+    annotations:
+      description: A number of daemonsets are running where they are not supposed
+        to run.
+      summary: Daemonsets are not scheduled correctly
+  - alert: PodFrequentlyRestarting
+    expr: increase(kube_pod_container_status_restarts[1h]) > 5
+    for: 10m
+    labels:
+      severity: warning
+    annotations:
+      description: Pod {{`{{$labels.namespaces}}`}}/{{`{{$labels.pod}}`}} is was restarted {{`{{$value}}`}}
+        times within the last hour
+{{ end }}
--- a/helm/exporter-kube-state/templates/servicemonitor.yaml
+++ b/helm/exporter-kube-state/templates/servicemonitor.yaml
@ -9,7 +9,7 @@ metadata:
    prometheus: {{ .Release.Name }}
  name: {{ template "fullname" . }}
 spec:
-  jobLabel: {{ template "name" . }}
+  jobLabel: {{ template "fullname" . }}
  selector:
    matchLabels:
      app: {{ template "name" . }}
--- a/helm/exporter-kube-state/values.yaml
+++ b/helm/exporter-kube-state/values.yaml
@ -25,61 +25,6 @@ addon_resizer:
    requests:
      cpu: 100m
      memory: 30Mi
-# WARNING: Don't change this file after this lines, it's automatically appended by helm/hack/sync_kube_prometheus.py
-ruleFiles:
-  kube-state-metrics.rules: |-
-    groups:
-    - name: kube-state-metrics.rules
-      rules:
-      - alert: DeploymentGenerationMismatch
-        expr: kube_deployment_status_observed_generation != kube_deployment_metadata_generation
-        for: 15m
-        labels:
-          severity: warning
-        annotations:
-          description: Observed deployment generation does not match expected one for
-            deployment {{$labels.namespaces}}{{$labels.deployment}}
-      - alert: DeploymentReplicasNotUpdated
-        expr: ((kube_deployment_status_replicas_updated != kube_deployment_spec_replicas)
-          or (kube_deployment_status_replicas_available != kube_deployment_spec_replicas))
-          unless (kube_deployment_spec_paused == 1)
-        for: 15m
-        labels:
-          severity: warning
-        annotations:
-          description: Replicas are not updated and available for deployment {{$labels.namespaces}}/{{$labels.deployment}}
-      - alert: DaemonSetRolloutStuck
-        expr: kube_daemonset_status_current_number_ready / kube_daemonset_status_desired_number_scheduled
-          * 100 < 100
-        for: 15m
-        labels:
-          severity: warning
-        annotations:
-          description: Only {{$value}}% of desired pods scheduled and ready for daemon
-            set {{$labels.namespaces}}/{{$labels.daemonset}}
-      - alert: K8SDaemonSetsNotScheduled
-        expr: kube_daemonset_status_desired_number_scheduled - kube_daemonset_status_current_number_scheduled
-          > 0
-        for: 10m
-        labels:
-          severity: warning
-        annotations:
-          description: A number of daemonsets are not scheduled.
-          summary: Daemonsets are not scheduled correctly
-      - alert: DaemonSetsMissScheduled
-        expr: kube_daemonset_status_number_misscheduled > 0
-        for: 10m
-        labels:
-          severity: warning
-        annotations:
-          description: A number of daemonsets are running where they are not supposed
-            to run.
-          summary: Daemonsets are not scheduled correctly
-      - alert: PodFrequentlyRestarting
-        expr: increase(kube_pod_container_status_restarts[1h]) > 5
-        for: 10m
-        labels:
-          severity: warning
-        annotations:
-          description: Pod {{$labels.namespaces}}/{{$labels.pod}} is was restarted {{$value}}
-            times within the last hour
+
+# default rules are in templates/kube-state-metrics.rules.yaml
+# prometheusRules: {}
--- a/helm/exporter-kubelets/Chart.yaml
+++ b/helm/exporter-kubelets/Chart.yaml
@ -1,7 +1,9 @@
 apiVersion: v1
 description: A Helm chart for Kubernetes
 name: exporter-kubelets
-version: 0.1.1
+version: 0.1.2
 maintainers:
-  - name: Cloud Posse LLC
-    email: hello@cloudposse.com
+  - name: Michael Goodness
+    email: mgoodness@gmail.com
+  - name: Giancarlo Rubio
+    email: gianrubio@gmail.com
--- a/helm/exporter-kubelets/templates/configmap.yaml
+++ b/helm/exporter-kubelets/templates/configmap.yaml
@ -9,8 +9,13 @@ metadata:
    release: {{ .Release.Name }}
  name: {{ template "fullname" . }}
 data:
+{{- if .Values.prometheusRules }}
 {{- $root := . }}
-{{- range $key, $val := .Values.ruleFiles }}
+{{- range $key, $val := .Values.prometheusRules }}
  {{ $key }}: |-
 {{ $val | indent 4}}
 {{- end }}
+{{ else }}
+  kubelet.rules: |-
+    {{- include "kubelet.rules.yaml.tpl" . | indent 4}}
+{{ end }}
--- a/helm/exporter-kubelets/templates/kubelet.rules.yaml
+++ b/helm/exporter-kubelets/templates/kubelet.rules.yaml
@ -0,0 +1,49 @@
+{{ define "kubelet.rules.yaml.tpl" }}
+groups:
+- name: kubelet.rules
+  rules:
+  - alert: K8SNodeNotReady
+    expr: kube_node_status_condition{condition="Ready",status="true"} == 0
+    for: 1h
+    labels:
+      severity: warning
+    annotations:
+      description: The Kubelet on {{`{{ $labels.node }}`}} has not checked in with the API,
+        or has set itself to NotReady, for more than an hour
+      summary: Node status is NotReady
+  - alert: K8SManyNodesNotReady
+    expr: count(kube_node_status_condition{condition="Ready",status="true"} == 0)
+      > 1 and (count(kube_node_status_condition{condition="Ready",status="true"} ==
+      0) / count(kube_node_status_condition{condition="Ready",status="true"})) > 0.2
+    for: 1m
+    labels:
+      severity: critical
+    annotations:
+      description: '{{`{{ $value }}`}}% of Kubernetes nodes are not ready'
+  - alert: K8SKubeletDown
+    expr: count(up{job="kubelet"} == 0) / count(up{job="kubelet"}) * 100 > 3
+    for: 1h
+    labels:
+      severity: warning
+    annotations:
+      description: Prometheus failed to scrape {{`{{ $value }}`}}% of kubelets.
+  - alert: K8SKubeletDown
+    expr: (absent(up{job="kubelet"} == 1) or count(up{job="kubelet"} == 0) / count(up{job="kubelet"}))
+      * 100 > 1
+    for: 1h
+    labels:
+      severity: critical
+    annotations:
+      description: Prometheus failed to scrape {{`{{ $value }}`}}% of kubelets, or all Kubelets
+        have disappeared from service discovery.
+      summary: Many Kubelets cannot be scraped
+  - alert: K8SKubeletTooManyPods
+    expr: kubelet_running_pod_count > 100
+    for: 10m
+    labels:
+      severity: warning
+    annotations:
+      description: Kubelet {{`{{$labels.instance}}`}} is running {{`{{$value}}`}} pods, close
+        to the limit of 110
+      summary: Kubelet is close to pod limit
+{{ end }}
--- a/helm/exporter-kubelets/values.yaml
+++ b/helm/exporter-kubelets/values.yaml
@ -1,52 +1,2 @@
-# This is a YAML-formatted file.
-# Declare variables to be passed into your templates.
-# WARNING: Don't change this file after this lines, it's automatically appended by helm/hack/sync_kube_prometheus.py
-ruleFiles:
-  kubelet.rules: |-
-    groups:
-    - name: kubelet.rules
-      rules:
-      - alert: K8SNodeNotReady
-        expr: kube_node_status_condition{condition="Ready",status="true"} == 0
-        for: 1h
-        labels:
-          severity: warning
-        annotations:
-          description: The Kubelet on {{ $labels.node }} has not checked in with the API,
-            or has set itself to NotReady, for more than an hour
-          summary: Node status is NotReady
-      - alert: K8SManyNodesNotReady
-        expr: count(kube_node_status_condition{condition="Ready",status="true"} == 0)
-          > 1 and (count(kube_node_status_condition{condition="Ready",status="true"} ==
-          0) / count(kube_node_status_condition{condition="Ready",status="true"})) > 0.2
-        for: 1m
-        labels:
-          severity: critical
-        annotations:
-          description: '{{ $value }}% of Kubernetes nodes are not ready'
-      - alert: K8SKubeletDown
-        expr: count(up{job="kubelet"} == 0) / count(up{job="kubelet"}) * 100 > 3
-        for: 1h
-        labels:
-          severity: warning
-        annotations:
-          description: Prometheus failed to scrape {{ $value }}% of kubelets.
-      - alert: K8SKubeletDown
-        expr: (absent(up{job="kubelet"} == 1) or count(up{job="kubelet"} == 0) / count(up{job="kubelet"}))
-          * 100 > 1
-        for: 1h
-        labels:
-          severity: critical
-        annotations:
-          description: Prometheus failed to scrape {{ $value }}% of kubelets, or all Kubelets
-            have disappeared from service discovery.
-          summary: Many Kubelets cannot be scraped
-      - alert: K8SKubeletTooManyPods
-        expr: kubelet_running_pod_count > 100
-        for: 10m
-        labels:
-          severity: warning
-        annotations:
-          description: Kubelet {{$labels.instance}} is running {{$value}} pods, close
-            to the limit of 110
-          summary: Kubelet is close to pod limit
+# default rules are in templates/kubelet.rules.yaml
+# prometheusRules: {}
--- a/helm/exporter-kubernetes/Chart.yaml
+++ b/helm/exporter-kubernetes/Chart.yaml
@ -1,7 +1,9 @@
 apiVersion: v1
 description: A Helm chart for Kubernetes
 name: exporter-kubernetes
-version: 0.1.1
+version: 0.1.2
 maintainers:
-  - name: Cloud Posse LLC
-    email: hello@cloudposse.com
+  - name: Michael Goodness
+    email: mgoodness@gmail.com
+  - name: Giancarlo Rubio
+    email: gianrubio@gmail.com
--- a/helm/exporter-kubernetes/templates/configmap.yaml
+++ b/helm/exporter-kubernetes/templates/configmap.yaml
@ -9,8 +9,13 @@ metadata:
    release: {{ .Release.Name }}
  name: {{ template "fullname" . }}
 data:
+{{- if .Values.prometheusRules }}
 {{- $root := . }}
-{{- range $key, $val := .Values.ruleFiles }}
+{{- range $key, $val := .Values.prometheusRules }}
  {{ $key }}: |-
 {{ $val | indent 4}}
 {{- end }}
+{{ else }}
+  kubernetes.rules: |-
+    {{- include "kubernetes.rules.yaml.tpl" . | indent 4}}
+{{ end }}
--- a/helm/exporter-kubernetes/templates/kubernetes.rules.yaml
+++ b/helm/exporter-kubernetes/templates/kubernetes.rules.yaml
@ -0,0 +1,88 @@
+{{ define "kubernetes.rules.yaml.tpl" }}
+groups:
+- name: kubernetes.rules
+  rules:
+  - record: pod_name:container_memory_usage_bytes:sum
+    expr: sum(container_memory_usage_bytes{container_name!="POD",pod_name!=""}) BY
+      (pod_name)
+  - record: pod_name:container_spec_cpu_shares:sum
+    expr: sum(container_spec_cpu_shares{container_name!="POD",pod_name!=""}) BY (pod_name)
+  - record: pod_name:container_cpu_usage:sum
+    expr: sum(rate(container_cpu_usage_seconds_total{container_name!="POD",pod_name!=""}[5m]))
+      BY (pod_name)
+  - record: pod_name:container_fs_usage_bytes:sum
+    expr: sum(container_fs_usage_bytes{container_name!="POD",pod_name!=""}) BY (pod_name)
+  - record: namespace:container_memory_usage_bytes:sum
+    expr: sum(container_memory_usage_bytes{container_name!=""}) BY (namespace)
+  - record: namespace:container_spec_cpu_shares:sum
+    expr: sum(container_spec_cpu_shares{container_name!=""}) BY (namespace)
+  - record: namespace:container_cpu_usage:sum
+    expr: sum(rate(container_cpu_usage_seconds_total{container_name!="POD"}[5m]))
+      BY (namespace)
+  - record: cluster:memory_usage:ratio
+    expr: sum(container_memory_usage_bytes{container_name!="POD",pod_name!=""}) BY
+      (cluster) / sum(machine_memory_bytes) BY (cluster)
+  - record: cluster:container_spec_cpu_shares:ratio
+    expr: sum(container_spec_cpu_shares{container_name!="POD",pod_name!=""}) / 1000
+      / sum(machine_cpu_cores)
+  - record: cluster:container_cpu_usage:ratio
+    expr: sum(rate(container_cpu_usage_seconds_total{container_name!="POD",pod_name!=""}[5m]))
+      / sum(machine_cpu_cores)
+  - record: apiserver_latency_seconds:quantile
+    expr: histogram_quantile(0.99, rate(apiserver_request_latencies_bucket[5m])) /
+      1e+06
+    labels:
+      quantile: "0.99"
+  - record: apiserver_latency:quantile_seconds
+    expr: histogram_quantile(0.9, rate(apiserver_request_latencies_bucket[5m])) /
+      1e+06
+    labels:
+      quantile: "0.9"
+  - record: apiserver_latency_seconds:quantile
+    expr: histogram_quantile(0.5, rate(apiserver_request_latencies_bucket[5m])) /
+      1e+06
+    labels:
+      quantile: "0.5"
+  - alert: APIServerLatencyHigh
+    expr: apiserver_latency_seconds:quantile{quantile="0.99",subresource!="log",verb!~"^(?:WATCH|WATCHLIST|PROXY|CONNECT)$"}
+      > 1
+    for: 10m
+    labels:
+      severity: warning
+    annotations:
+      description: the API server has a 99th percentile latency of {{`{{ $value }}`}} seconds
+        for {{`{{$labels.verb}}`}} {{`{{$labels.resource}}`}}
+  - alert: APIServerLatencyHigh
+    expr: apiserver_latency_seconds:quantile{quantile="0.99",subresource!="log",verb!~"^(?:WATCH|WATCHLIST|PROXY|CONNECT)$"}
+      > 4
+    for: 10m
+    labels:
+      severity: critical
+    annotations:
+      description: the API server has a 99th percentile latency of {{`{{ $value }}`}} seconds
+        for {{`{{$labels.verb}}`}} {{`{{$labels.resource}}`}}
+  - alert: APIServerErrorsHigh
+    expr: rate(apiserver_request_count{code=~"^(?:5..)$"}[5m]) / rate(apiserver_request_count[5m])
+      * 100 > 2
+    for: 10m
+    labels:
+      severity: warning
+    annotations:
+      description: API server returns errors for {{`{{ $value }}`}}% of requests
+  - alert: APIServerErrorsHigh
+    expr: rate(apiserver_request_count{code=~"^(?:5..)$"}[5m]) / rate(apiserver_request_count[5m])
+      * 100 > 5
+    for: 10m
+    labels:
+      severity: critical
+    annotations:
+      description: API server returns errors for {{`{{ $value }}`}}% of requests
+  - alert: K8SApiserverDown
+    expr: absent(up{job="kubernetes"} == 1)
+    for: 20m
+    labels:
+      severity: critical
+    annotations:
+      description: No API servers are reachable or all have disappeared from service
+        discovery
+{{ end }}
--- a/helm/exporter-kubernetes/values.yaml
+++ b/helm/exporter-kubernetes/values.yaml
@ -1,91 +1,2 @@
-# This is a YAML-formatted file.
-# Declare variables to be passed into your templates.
-# WARNING: Don't change this file after this lines, it's automatically appended by helm/hack/sync_kube_prometheus.py
-ruleFiles:
-  kubernetes.rules: |-
-    groups:
-    - name: kubernetes.rules
-      rules:
-      - record: pod_name:container_memory_usage_bytes:sum
-        expr: sum(container_memory_usage_bytes{container_name!="POD",pod_name!=""}) BY
-          (pod_name)
-      - record: pod_name:container_spec_cpu_shares:sum
-        expr: sum(container_spec_cpu_shares{container_name!="POD",pod_name!=""}) BY (pod_name)
-      - record: pod_name:container_cpu_usage:sum
-        expr: sum(rate(container_cpu_usage_seconds_total{container_name!="POD",pod_name!=""}[5m]))
-          BY (pod_name)
-      - record: pod_name:container_fs_usage_bytes:sum
-        expr: sum(container_fs_usage_bytes{container_name!="POD",pod_name!=""}) BY (pod_name)
-      - record: namespace:container_memory_usage_bytes:sum
-        expr: sum(container_memory_usage_bytes{container_name!=""}) BY (namespace)
-      - record: namespace:container_spec_cpu_shares:sum
-        expr: sum(container_spec_cpu_shares{container_name!=""}) BY (namespace)
-      - record: namespace:container_cpu_usage:sum
-        expr: sum(rate(container_cpu_usage_seconds_total{container_name!="POD"}[5m]))
-          BY (namespace)
-      - record: cluster:memory_usage:ratio
-        expr: sum(container_memory_usage_bytes{container_name!="POD",pod_name!=""}) BY
-          (cluster) / sum(machine_memory_bytes) BY (cluster)
-      - record: cluster:container_spec_cpu_shares:ratio
-        expr: sum(container_spec_cpu_shares{container_name!="POD",pod_name!=""}) / 1000
-          / sum(machine_cpu_cores)
-      - record: cluster:container_cpu_usage:ratio
-        expr: sum(rate(container_cpu_usage_seconds_total{container_name!="POD",pod_name!=""}[5m]))
-          / sum(machine_cpu_cores)
-      - record: apiserver_latency_seconds:quantile
-        expr: histogram_quantile(0.99, rate(apiserver_request_latencies_bucket[5m])) /
-          1e+06
-        labels:
-          quantile: "0.99"
-      - record: apiserver_latency:quantile_seconds
-        expr: histogram_quantile(0.9, rate(apiserver_request_latencies_bucket[5m])) /
-          1e+06
-        labels:
-          quantile: "0.9"
-      - record: apiserver_latency_seconds:quantile
-        expr: histogram_quantile(0.5, rate(apiserver_request_latencies_bucket[5m])) /
-          1e+06
-        labels:
-          quantile: "0.5"
-      - alert: APIServerLatencyHigh
-        expr: apiserver_latency_seconds:quantile{quantile="0.99",subresource!="log",verb!~"^(?:WATCH|WATCHLIST|PROXY|CONNECT)$"}
-          > 1
-        for: 10m
-        labels:
-          severity: warning
-        annotations:
-          description: the API server has a 99th percentile latency of {{ $value }} seconds
-            for {{$labels.verb}} {{$labels.resource}}
-      - alert: APIServerLatencyHigh
-        expr: apiserver_latency_seconds:quantile{quantile="0.99",subresource!="log",verb!~"^(?:WATCH|WATCHLIST|PROXY|CONNECT)$"}
-          > 4
-        for: 10m
-        labels:
-          severity: critical
-        annotations:
-          description: the API server has a 99th percentile latency of {{ $value }} seconds
-            for {{$labels.verb}} {{$labels.resource}}
-      - alert: APIServerErrorsHigh
-        expr: rate(apiserver_request_count{code=~"^(?:5..)$"}[5m]) / rate(apiserver_request_count[5m])
-          * 100 > 2
-        for: 10m
-        labels:
-          severity: warning
-        annotations:
-          description: API server returns errors for {{ $value }}% of requests
-      - alert: APIServerErrorsHigh
-        expr: rate(apiserver_request_count{code=~"^(?:5..)$"}[5m]) / rate(apiserver_request_count[5m])
-          * 100 > 5
-        for: 10m
-        labels:
-          severity: critical
-        annotations:
-          description: API server returns errors for {{ $value }}% of requests
-      - alert: K8SApiserverDown
-        expr: absent(up{job="apiserver"} == 1)
-        for: 20m
-        labels:
-          severity: critical
-        annotations:
-          description: No API servers are reachable or all have disappeared from service
-            discovery
+# default rules are in templates/kubernetes.rules.yaml
+# prometheusRules: {}
--- a/helm/exporter-node/Chart.yaml
+++ b/helm/exporter-node/Chart.yaml
@ -1,7 +1,9 @@
 apiVersion: v1
 description: A Helm chart for Kubernetes
 name: exporter-node
-version: 0.1.1
+version: 0.1.2
 maintainers:
-  - name: Cloud Posse LLC
-    email: hello@cloudposse.com
+  - name: Michael Goodness
+    email: mgoodness@gmail.com
+  - name: Giancarlo Rubio
+    email: gianrubio@gmail.com
--- a/helm/exporter-node/templates/configmap.yaml
+++ b/helm/exporter-node/templates/configmap.yaml
@ -9,8 +9,13 @@ metadata:
    release: {{ .Release.Name }}
  name: {{ template "fullname" . }}
 data:
+{{- if .Values.prometheusRules }}
 {{- $root := . }}
-{{- range $key, $val := .Values.ruleFiles }}
+{{- range $key, $val := .Values.prometheusRules }}
  {{ $key }}: |-
 {{ $val | indent 4}}
 {{- end }}
+{{ else }}
+  node.rules: |-
+    {{- include "node.rules.yaml.tpl" . | indent 4}}
+{{ end }}
--- a/helm/exporter-node/templates/node.rules.yaml
+++ b/helm/exporter-node/templates/node.rules.yaml
@ -0,0 +1,46 @@
+{{ define "node.rules.yaml.tpl" }}
+groups:
+- name: node.rules
+  rules:
+  - record: instance:node_cpu:rate:sum
+    expr: sum(rate(node_cpu{mode!="idle",mode!="iowait",mode!~"^(?:guest.*)$"}[3m]))
+      BY (instance)
+  - record: instance:node_filesystem_usage:sum
+    expr: sum((node_filesystem_size{mountpoint="/"} - node_filesystem_free{mountpoint="/"}))
+      BY (instance)
+  - record: instance:node_network_receive_bytes:rate:sum
+    expr: sum(rate(node_network_receive_bytes[3m])) BY (instance)
+  - record: instance:node_network_transmit_bytes:rate:sum
+    expr: sum(rate(node_network_transmit_bytes[3m])) BY (instance)
+  - record: instance:node_cpu:ratio
+    expr: sum(rate(node_cpu{mode!="idle"}[5m])) WITHOUT (cpu, mode) / ON(instance)
+      GROUP_LEFT() count(sum(node_cpu) BY (instance, cpu)) BY (instance)
+  - record: cluster:node_cpu:sum_rate5m
+    expr: sum(rate(node_cpu{mode!="idle"}[5m]))
+  - record: cluster:node_cpu:ratio
+    expr: cluster:node_cpu:rate5m / count(sum(node_cpu) BY (instance, cpu))
+  - alert: NodeExporterDown
+    expr: absent(up{job="{{ template "fullname" .  }}"} == 1)
+    for: 10m
+    labels:
+      severity: warning
+    annotations:
+      description: Prometheus could not scrape a node-exporter for more than 10m,
+        or node-exporters have disappeared from discovery
+  - alert: NodeDiskRunningFull
+    expr: predict_linear(node_filesystem_free[6h], 3600 * 24) < 0
+    for: 30m
+    labels:
+      severity: warning
+    annotations:
+      description: device {{`{{$labels.device}}`}} on node {{`{{$labels.instance}}`}} is running
+        full within the next 24 hours (mounted at {{`{{$labels.mountpoint}}`}})
+  - alert: NodeDiskRunningFull
+    expr: predict_linear(node_filesystem_free[30m], 3600 * 2) < 0
+    for: 10m
+    labels:
+      severity: critical
+    annotations:
+      description: device {{`{{$labels.device}}`}} on node {{`{{$labels.instance}}`}} is running
+        full within the next 2 hours (mounted at {{`{{$labels.mountpoint}}`}})
+{{ end }}
--- a/helm/exporter-node/templates/servicemonitor.yaml
+++ b/helm/exporter-node/templates/servicemonitor.yaml
@ -9,7 +9,7 @@ metadata:
    prometheus: {{ .Release.Name }}
  name: {{ template "fullname" . }}
 spec:
-  jobLabel: {{ template "name" . }}
+  jobLabel: {{ template "fullname" . }}
  selector:
    matchLabels:
      app: {{ template "name" . }}
--- a/helm/exporter-node/values.yaml
+++ b/helm/exporter-node/values.yaml
@ -3,7 +3,7 @@
 replicaCount: 1
 image:
  repository: quay.io/prometheus/node-exporter
-  tag: v0.15.1
+  tag: v0.15.2
  pullPolicy: IfNotPresent
 service:
  type: ClusterIP
@ -16,50 +16,6 @@ resources:
  requests:
    cpu: 100m
    memory: 30Mi
-# WARNING: Don't change this file after this lines, it's automatically appended by helm/hack/sync_kube_prometheus.py
-ruleFiles:
-  node.rules: |-
-    groups:
-    - name: node.rules
-      rules:
-      - record: instance:node_cpu:rate:sum
-        expr: sum(rate(node_cpu{mode!="idle",mode!="iowait",mode!~"^(?:guest.*)$"}[3m]))
-          BY (instance)
-      - record: instance:node_filesystem_usage:sum
-        expr: sum((node_filesystem_size{mountpoint="/"} - node_filesystem_free{mountpoint="/"}))
-          BY (instance)
-      - record: instance:node_network_receive_bytes:rate:sum
-        expr: sum(rate(node_network_receive_bytes[3m])) BY (instance)
-      - record: instance:node_network_transmit_bytes:rate:sum
-        expr: sum(rate(node_network_transmit_bytes[3m])) BY (instance)
-      - record: instance:node_cpu:ratio
-        expr: sum(rate(node_cpu{mode!="idle"}[5m])) WITHOUT (cpu, mode) / ON(instance)
-          GROUP_LEFT() count(sum(node_cpu) BY (instance, cpu)) BY (instance)
-      - record: cluster:node_cpu:sum_rate5m
-        expr: sum(rate(node_cpu{mode!="idle"}[5m]))
-      - record: cluster:node_cpu:ratio
-        expr: cluster:node_cpu:rate5m / count(sum(node_cpu) BY (instance, cpu))
-      - alert: NodeExporterDown
-        expr: absent(up{job="node-exporter"} == 1)
-        for: 10m
-        labels:
-          severity: warning
-        annotations:
-          description: Prometheus could not scrape a node-exporter for more than 10m,
-            or node-exporters have disappeared from discovery
-      - alert: NodeDiskRunningFull
-        expr: predict_linear(node_filesystem_free[6h], 3600 * 24) < 0
-        for: 30m
-        labels:
-          severity: warning
-        annotations:
-          description: device {{$labels.device}} on node {{$labels.instance}} is running
-            full within the next 24 hours (mounted at {{$labels.mountpoint}})
-      - alert: NodeDiskRunningFull
-        expr: predict_linear(node_filesystem_free[30m], 3600 * 2) < 0
-        for: 10m
-        labels:
-          severity: critical
-        annotations:
-          description: device {{$labels.device}} on node {{$labels.instance}} is running
-            full within the next 2 hours (mounted at {{$labels.mountpoint}})
+
+# default rules are in templates/node.rules.yaml
+# prometheusRules: {}
--- a/helm/grafana/templates/dashboards-configmap.yaml
+++ b/helm/grafana/templates/dashboards-configmap.yaml
@ -9,7 +9,9 @@ metadata:
  name: {{ template "grafana.server.fullname" . }}
 data:
  {{- if .Values.serverDashboardFiles }}
-{{ toYaml .Values.serverDashboardFiles | indent 2 }}
+  {{ toYaml .Values.serverDashboardFiles | indent 2 }}
+  {{ else }}
+  {{- include "grafana-dashboards.yaml.tpl" . | indent 2}}
  {{- end }}
  {{- if .Values.dataSource }}
 {{ toYaml .Values.dataSource | indent 2 }}
--- a/helm/grafana/templates/grafana-dashboards.yaml
+++ b/helm/grafana/templates/grafana-dashboards.yaml
--- a/helm/grafana/values.yaml
+++ b/helm/grafana/values.yaml
--- a/helm/hack/sync_kube_prometheus.py
+++ b/helm/hack/sync_kube_prometheus.py
@ -1,63 +1,73 @@
 #!/usr/bin/env python
+import os
+import re
+from ruamel import yaml 
+  
+def escape(s):
+  return s.replace("{{","{{`{{").replace("}}","}}`}}")
+  
+def get_header(file_name):
+  return "{{ define \"" + file_name + ".tpl\" }}\n" 
+
 #####
-## This script read the kube-prometheus rules and convert into helm charts format
+## Step 1 - Sync prometheus alert rules, create template file
 ####
-### ----------------------------
-###  Sync all prometheus rules
-###
-charts = [{'file_name': 'alertmanager', 'search_var': 'ruleFiles',
-'source':'contrib/kube-prometheus/assets/prometheus/rules/alertmanager.rules.yaml',
-'destination': 'helm/alertmanager/values.yaml'},
-{'file_name': 'kube-controller-manager', 'search_var': 'ruleFiles', 'source':'contrib/kube-prometheus/assets/prometheus/rules/kube-controller-manager.rules.yaml',
-'destination': 'helm/exporter-kube-controller-manager/values.yaml'},
-{'file_name': 'kube-scheduler', 'search_var': 'ruleFiles', 'source':'contrib/kube-prometheus/assets/prometheus/rules/kube-scheduler.rules.yaml',
-'destination': 'helm/exporter-kube-scheduler/values.yaml'},
-{'file_name': 'kube-state-metrics',  'search_var': 'ruleFiles', 'source':'contrib/kube-prometheus/assets/prometheus/rules/kube-state-metrics.rules.yaml',
-'destination': 'helm/exporter-kube-state/values.yaml'},
-{'file_name': 'node',  'search_var': 'ruleFiles', 'source':'contrib/kube-prometheus/assets/prometheus/rules/node.rules.yaml',
-'destination': 'helm/exporter-node/values.yaml'},
-{'file_name': 'prometheus',  'search_var': 'ruleFiles', 'source':'contrib/kube-prometheus/assets/prometheus/rules/prometheus.rules.yaml', 
-'destination': 'helm/prometheus/values.yaml'},
-{'file_name': 'etcd3',  'search_var': 'ruleFiles', 'source':'contrib/kube-prometheus/assets/prometheus/rules/etcd3.rules.yaml', 
-'destination': 'helm/exporter-kube-etcd/values.yaml'},
-# //TODO add {'file_name': 'general',  'search_var': 'ruleFiles', 'source':'contrib/kube-prometheus/assets/prometheus/rules/general.rules.yaml', 
-# 'destination': 'helm/kube-prometheus/general_rules.yaml'},
-{'file_name': 'kubelet',  'search_var': 'ruleFiles', 'source':'contrib/kube-prometheus/assets/prometheus/rules/kubelet.rules.yaml', 
-'destination': 'helm/exporter-kubelets/values.yaml'},
-{'file_name': 'kubernetes',  'search_var': 'ruleFiles', 'source':'contrib/kube-prometheus/assets/prometheus/rules/kubernetes.rules.yaml', 
-'destination': 'helm/exporter-kubernetes/values.yaml'},
-### 
-###  Sync grafana dashboards
-###
-{'file_name': 'grafana-dashboards-0', 'search_var': 'serverDashboardFiles', 'source':'contrib/kube-prometheus/manifests/grafana/grafana-dashboards.yaml', 
-'destination': 'helm/grafana/values.yaml'},
+charts = [
+{'source':'contrib/kube-prometheus/assets/prometheus/rules/alertmanager.rules.yaml',
+'destination': 'helm/alertmanager/', 'job_replace_by': '{{ template \"fullname\" .  }}'},
+{'source': 'contrib/kube-prometheus/assets/prometheus/rules/kube-controller-manager.rules.yaml',
+'destination': 'helm/exporter-kube-controller-manager/', 'job_replace_by': '{{ template \"fullname\" .  }}'},
+{'source':'contrib/kube-prometheus/assets/prometheus/rules/kube-scheduler.rules.yaml',
+'destination': 'helm/exporter-kube-scheduler/', 'job_replace_by': '{{ template \"fullname\" .  }}'},
+{'source':'contrib/kube-prometheus/assets/prometheus/rules/kube-state-metrics.rules.yaml',
+'destination': 'helm/exporter-kube-state/', 'job_replace_by': '{{ template \"fullname\" .  }}'},
+{'source':'contrib/kube-prometheus/assets/prometheus/rules/node.rules.yaml',
+'destination': 'helm/exporter-node/', 'job_replace_by': '{{ template \"fullname\" .  }}'},
+{'source':'contrib/kube-prometheus/assets/prometheus/rules/prometheus.rules.yaml', 
+'destination': 'helm/prometheus/', 'job_replace_by': '{{ template \"fullname\" .  }}'},
+{'source':'contrib/kube-prometheus/assets/prometheus/rules/etcd3.rules.yaml', 
+'destination': 'helm/exporter-kube-etcd/', 'job_replace_by': '{{ template \"fullname\" .  }}'},
+{'source':'contrib/kube-prometheus/assets/prometheus/rules/general.rules.yaml', 
+'destination': 'helm/kube-prometheus/', 'job_replace_by': '{{ template \"fullname\" .  }}'},
+{'source':'contrib/kube-prometheus/assets/prometheus/rules/kubelet.rules.yaml', 
+'destination': 'helm/exporter-kubelets/', 'job_replace_by': 'kubelet'},
+{'source':'contrib/kube-prometheus/assets/prometheus/rules/kubernetes.rules.yaml', 
+'destination': 'helm/exporter-kubernetes/', 'job_replace_by': 'kubernetes'},
 ]

+# read the rules, create a new template file
 for chart in charts:
-  lines = ""
-  ## parse current values.yaml file
-  f = open(chart['destination'], 'r')
-  for l in f.readlines():

-    # stop reading file after the rule
-    if "{}:".format(chart['search_var']) in l:
-        break
-    lines+= l
+  _, name = os.path.split(chart['source'])
+  lines = get_header(name)

-  lines+= "{}:\n".format(chart['search_var'])
-  lines+= "  {}.rules: |-\n".format(chart['file_name'])
-
-
-  ## parse kube-prometheus rule
-  f =  open(chart['source'])
-  for l in f.readlines():
-    lines += "    {}".format(l)
+  f = open(chart['source'], 'r')
+  lines += escape(f.read())
+  lines = re.sub("job=\"(.*?)\"", "job=\"" + chart['job_replace_by'] + "\"", lines) #replace the job name by chart variable
+ 
+  lines += "{{ end }}" # footer
+  
+  new_f = "{}/templates/{}".format(chart['destination'], name)

  # recreate the file  
-  with open(chart['destination'], 'w') as f:
+  with open(new_f, 'w') as f:
      f.write(lines)

+  print "Generated {}".format(new_f)

-### ----------------------------
-### 2 
-###
+######
+## Step 2 - Parse grafana dashboards, create a template file
+######
+
+with open('contrib/kube-prometheus/manifests/grafana/grafana-dashboards.yaml', 'r') as s:
+  data = yaml.load(s, Loader=yaml.RoundTripLoader)['data']
+
+# prometheus datasource it's not required now 
+del data['prometheus-datasource.json']
+
+data_s = get_header("grafana-dashboards.yaml.tpl")
+data_s += escape(yaml.dump(data, Dumper=yaml.RoundTripDumper))
+data_s += "{{ end }}" # footer
+
+with open('helm/grafana/templates/grafana-dashboards.yaml', 'w') as f:
+  f.write(data_s)
--- a/helm/kube-prometheus/Chart.yaml
+++ b/helm/kube-prometheus/Chart.yaml
@ -4,6 +4,8 @@ engine: gotpl
 maintainers:
  - name: Michael Goodness
    email: mgoodness@gmail.com
+  - name: Giancarlo Rubio
+    email: gianrubio@gmail.com
 name: kube-prometheus
 sources:
  - https://github.com/coreos/prometheus-operator
--- a/helm/kube-prometheus/requirements.yaml
+++ b/helm/kube-prometheus/requirements.yaml
@ -1,62 +1,63 @@
 dependencies:
  - name: alertmanager
    version: 0.0.6
-    repository: file://../alertmanager
-    #repository: https://s3-eu-west-1.amazonaws.com/coreos-charts/stable/
+    #e2e-repository: file://../alertmanager
+    repository: https://s3-eu-west-1.amazonaws.com/coreos-charts/stable/
  
  - name: prometheus
    version: 0.0.8
-    repository: file://../prometheus
-    #repository: https://s3-eu-west-1.amazonaws.com/coreos-charts/stable/
+    #e2e-repository: file://../prometheus
+    repository: https://s3-eu-west-1.amazonaws.com/coreos-charts/stable/
 
-  - name: exporter-kube-api
-    version: 0.1.1
-    repository: file://../exporter-kube-api
-    #repository: https://s3-eu-west-1.amazonaws.com/coreos-charts/stable/
-
  - name: exporter-kube-controller-manager
-    version: 0.1.1
-    repository: file://../exporter-kube-controller-manager
-    #repository: https://s3-eu-west-1.amazonaws.com/coreos-charts/stable/
+    version: 0.1.2
+    #e2e-repository: file://../exporter-kube-controller-manager
+    repository: https://s3-eu-west-1.amazonaws.com/coreos-charts/stable/

  - name: exporter-kube-dns
-    version: 0.1.1
-    repository: file://../exporter-kube-dns
-    #repository: https://s3-eu-west-1.amazonaws.com/coreos-charts/stable/
+    version: 0.1.2
+    #e2e-repository: file://../exporter-kube-dns
+    repository: https://s3-eu-west-1.amazonaws.com/coreos-charts/stable/

  - name: exporter-kube-etcd
-    version: 0.1.1
-    repository: file://../exporter-kube-etcd
-    #repository: https://s3-eu-west-1.amazonaws.com/coreos-charts/stable/
+    version: 0.1.2
+    #e2e-repository: file://../exporter-kube-etcd
+    repository: https://s3-eu-west-1.amazonaws.com/coreos-charts/stable/

  - name: exporter-kube-scheduler
-    version: 0.1.1
-    repository: file://../exporter-kube-scheduler
-    #repository: https://s3-eu-west-1.amazonaws.com/coreos-charts/stable/
+    version: 0.1.2
+    #e2e-repository: file://../exporter-kube-scheduler
+    repository: https://s3-eu-west-1.amazonaws.com/coreos-charts/stable/

  - name: exporter-kube-state
    version: 0.1.3
-    repository: file://../exporter-kube-state
-    #repository: https://s3-eu-west-1.amazonaws.com/coreos-charts/stable/
+    #e2e-repository: file://../exporter-kube-state
+    repository: https://s3-eu-west-1.amazonaws.com/coreos-charts/stable/

  - name: exporter-kubelets
-    version: 0.1.1
-    repository: file://../exporter-kubelets
-    #repository: https://s3-eu-west-1.amazonaws.com/coreos-charts/stable/
+    version: 0.1.2
+    #e2e-repository: file://../exporter-kubelets
+    repository: https://s3-eu-west-1.amazonaws.com/coreos-charts/stable/

  - name: exporter-kubernetes
-    version: 0.1.1
-    repository: file://../exporter-kubernetes
-    #repository: https://s3-eu-west-1.amazonaws.com/coreos-charts/stable/
+    version: 0.1.2
+    #e2e-repository: file://../exporter-kubernetes
+    repository: https://s3-eu-west-1.amazonaws.com/coreos-charts/stable/

  - name: exporter-node
-    version: 0.1.1
-    repository: file://../exporter-node
-    # repository: https://s3-eu-west-1.amazonaws.com/coreos-charts/stable/
+    version: 0.1.2
+    #e2e-repository: file://../exporter-node
+    repository: https://s3-eu-west-1.amazonaws.com/coreos-charts/stable/
    condition: deployExporterNode

  - name: grafana
    version: 0.0.5
-    repository: file://../grafana
-    #repository: https://s3-eu-west-1.amazonaws.com/coreos-charts/stable/
+    #e2e-repository: file://../grafana
+    repository: https://s3-eu-west-1.amazonaws.com/coreos-charts/stable/
    condition: deployGrafana
+
+  - name: prometheus-operator
+    version: 0.0.8
+    #e2e-repository: file://../prometheus-operator
+    repository: https://s3-eu-west-1.amazonaws.com/coreos-charts/stable/
+    condition: deployPrometheusOperator
--- a/helm/exporter-kube-api/templates/configmap.yaml
+++ b/helm/exporter-kube-api/templates/configmap.yaml
@ -9,8 +9,13 @@ metadata:
    release: {{ .Release.Name }}
  name: {{ template "fullname" . }}
 data:
+{{- if .Values.prometheusRules }}
 {{- $root := . }}
-{{- range $key, $val := .Values.ruleFiles }}
+{{- range $key, $val := .Values.prometheusRules }}
  {{ $key }}: |-
 {{ $val | indent 4}}
 {{- end }}
+{{ else }}
+  general.rules: |-
+    {{- include "general.rules.yaml.tpl" . | indent 4}}
+{{ end }}
--- a/helm/kube-prometheus/templates/general.rules.yaml
+++ b/helm/kube-prometheus/templates/general.rules.yaml
@ -0,0 +1,41 @@
+{{ define "general.rules.yaml.tpl" }}
+groups:
+- name: general.rules
+  rules:
+  - alert: TargetDown
+    expr: 100 * (count(up == 0) BY (job) / count(up) BY (job)) > 10
+    for: 10m
+    labels:
+      severity: warning
+    annotations:
+      description: '{{`{{ $value }}`}}% of {{`{{ $labels.job }}`}} targets are down.'
+      summary: Targets are down
+  - alert: DeadMansSwitch
+    expr: vector(1)
+    labels:
+      severity: none
+    annotations:
+      description: This is a DeadMansSwitch meant to ensure that the entire Alerting
+        pipeline is functional.
+      summary: Alerting DeadMansSwitch
+  - record: fd_utilization
+    expr: process_open_fds / process_max_fds
+  - alert: FdExhaustionClose
+    expr: predict_linear(fd_utilization[1h], 3600 * 4) > 1
+    for: 10m
+    labels:
+      severity: warning
+    annotations:
+      description: '{{`{{ $labels.job }}`}}: {{`{{ $labels.namespace }}`}}/{{`{{ $labels.pod }}`}} instance
+        will exhaust in file/socket descriptors within the next 4 hours'
+      summary: file descriptors soon exhausted
+  - alert: FdExhaustionClose
+    expr: predict_linear(fd_utilization[10m], 3600) > 1
+    for: 10m
+    labels:
+      severity: critical
+    annotations:
+      description: '{{`{{ $labels.job }}`}}: {{`{{ $labels.namespace }}`}}/{{`{{ $labels.pod }}`}} instance
+        will exhaust in file/socket descriptors within the next hour'
+      summary: file descriptors soon exhausted
+{{ end }}
--- a/helm/kube-prometheus/values.yaml
+++ b/helm/kube-prometheus/values.yaml
@ -4,6 +4,9 @@ deployExporterNode: True
 # Grafana
 deployGrafana: True

+# Prometheus operator
+deployPrometheusOperator: False
+
 alertmanager:
  ## Alertmanager configuration directives
  ## Ref: https://prometheus.io/docs/alerting/configuration/
@ -24,7 +27,6 @@ alertmanager:
    receivers:
    - name: 'null'

-
  ## External URL at which Alertmanager will be reachable
  ##
  externalUrl: ""
@ -338,3 +340,6 @@ prometheus:
  #     requests:
  #       storage: 16Gi
  #   selector: {}
+
+# default rules are in templates/general.rules.yaml
+# prometheusRules: {}
--- a/helm/prometheus-operator/Chart.yaml
+++ b/helm/prometheus-operator/Chart.yaml
@ -4,6 +4,8 @@ engine: gotpl
 maintainers:
  - name: Michael Goodness
    email: mgoodness@gmail.com
+  - name: Giancarlo Rubio
+    email: gianrubio@gmail.com
 name: prometheus-operator
 sources:
  - https://github.com/coreos/prometheus-operator
--- a/helm/prometheus-operator/templates/servicemonitor-configmap.yaml
+++ b/helm/prometheus-operator/templates/servicemonitor-configmap.yaml
@ -26,4 +26,4 @@ data:
            - {{ .Release.Namespace | quote }}
        endpoints:
        - port: http
-          interval: 30s
+          interval: 30s
--- a/helm/prometheus/Chart.yaml
+++ b/helm/prometheus/Chart.yaml
@ -2,7 +2,7 @@ apiVersion: v1
 description: Prometheus instance created by the CoreOS Prometheus Operator
 engine: gotpl
 maintainers:
-  - name: Michael Goodness
+  - name: Giancarlo Rubio
    email: mgoodness@gmail.com
 name: prometheus
 sources:
--- a/helm/prometheus/README.md
+++ b/helm/prometheus/README.md
@ -55,6 +55,7 @@ Parameter | Description | Default
 `ingress.tls` | TLS configuration for Prometheus Ingress | `[]`
 `nodeSelector` | Node labels for pod assignment | `{}`
 `paused` | If true, the Operator won't process any Prometheus configuration changes | `false`
+`prometheusRules` | Prometheus rules | `[templates/prometheus.rules.yaml](templates/prometheus.rules.yaml)`
 `replicaCount` | Number of Prometheus replicas desired | `1`
 `resources` | Pod resource requests & limits | `{}`
 `retention` | How long to retain metrics | `24h`
--- a/helm/prometheus/templates/configmap.yaml
+++ b/helm/prometheus/templates/configmap.yaml
@ -0,0 +1,21 @@
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  labels:
+    app: "prometheus"
+    chart: {{ .Chart.Name }}-{{ .Chart.Version }}
+    heritage: {{ .Release.Service }}
+    prometheus: {{ .Release.Name }}
+    release: {{ .Release.Name }}
+  name: {{ template "fullname" . }}
+data:
+{{- if .Values.prometheusRules }}
+{{- $root := . }}
+{{- range $key, $val := .Values.prometheusRules }}
+  {{ $key }}: |-
+{{ $val | indent 4}}
+{{- end }}
+{{ else }}
+  prometheus.rules: |-
+    {{- include "prometheus.rules.yaml.tpl" . | indent 4}}
+{{ end }}
--- a/helm/prometheus/templates/prometheus.rules.yaml
+++ b/helm/prometheus/templates/prometheus.rules.yaml
@ -0,0 +1,73 @@
+{{ define "prometheus.rules.yaml.tpl" }}
+groups:
+- name: prometheus.rules
+  rules:
+  - alert: PrometheusConfigReloadFailed
+    expr: prometheus_config_last_reload_successful == 0
+    for: 10m
+    labels:
+      severity: warning
+    annotations:
+      description: Reloading Prometheus' configuration has failed for {{`{{$labels.namespace}}`}}/{{`{{$labels.pod}}`}}
+  - alert: PrometheusNotificationQueueRunningFull
+    expr: predict_linear(prometheus_notifications_queue_length[5m], 60 * 30) > prometheus_notifications_queue_capacity
+    for: 10m
+    labels:
+      severity: warning
+    annotations:
+      description: Prometheus' alert notification queue is running full for {{`{{$labels.namespace}}`}}/{{`{{
+        $labels.pod}}`}}
+  - alert: PrometheusErrorSendingAlerts
+    expr: rate(prometheus_notifications_errors_total[5m]) / rate(prometheus_notifications_sent_total[5m])
+      > 0.01
+    for: 10m
+    labels:
+      severity: warning
+    annotations:
+      description: Errors while sending alerts from Prometheus {{`{{$labels.namespace}}`}}/{{`{{
+        $labels.pod}}`}} to Alertmanager {{`{{$labels.Alertmanager}}`}}
+  - alert: PrometheusErrorSendingAlerts
+    expr: rate(prometheus_notifications_errors_total[5m]) / rate(prometheus_notifications_sent_total[5m])
+      > 0.03
+    for: 10m
+    labels:
+      severity: critical
+    annotations:
+      description: Errors while sending alerts from Prometheus {{`{{$labels.namespace}}`}}/{{`{{
+        $labels.pod}}`}} to Alertmanager {{`{{$labels.Alertmanager}}`}}
+  - alert: PrometheusNotConnectedToAlertmanagers
+    expr: prometheus_notifications_alertmanagers_discovered < 1
+    for: 10m
+    labels:
+      severity: warning
+    annotations:
+      description: Prometheus {{`{{ $labels.namespace }}`}}/{{`{{ $labels.pod}}`}} is not connected
+        to any Alertmanagers
+  - alert: PrometheusTSDBReloadsFailing
+    expr: increase(prometheus_tsdb_reloads_failures_total[2h]) > 0
+    for: 12h
+    labels:
+      severity: warning
+    annotations:
+      description: '{{`{{$labels.job}}`}} at {{`{{$labels.instance}}`}} had {{`{{$value | humanize}}`}}
+        reload failures over the last four hours.'
+      summary: Prometheus has issues reloading data blocks from disk
+  - alert: PrometheusTSDBCompactionsFailing
+    expr: increase(prometheus_tsdb_compactions_failed_total[2h]) > 0
+    for: 12h
+    labels:
+      severity: warning
+    annotations:
+      description: '{{`{{$labels.job}}`}} at {{`{{$labels.instance}}`}} had {{`{{$value | humanize}}`}}
+        compaction failures over the last four hours.'
+      summary: Prometheus has issues compacting sample blocks
+  - alert: PrometheusTSDBWALCorruptions
+    expr: tsdb_wal_corruptions_total > 0
+    for: 4h
+    labels:
+      severity: warning
+    annotations:
+      description: '{{`{{$labels.job}}`}} at {{`{{$labels.instance}}`}} has a corrupted write-ahead
+        log (WAL).'
+      summary: Prometheus write-ahead log is corrupted
+{{ end }}
--- a/helm/prometheus/templates/servicemonitor-prometheus.yaml
+++ b/helm/prometheus/templates/servicemonitor-prometheus.yaml
@ -10,7 +10,7 @@ metadata:
    prometheus: {{ .Release.Name }}
  name: {{ template "fullname" . }}
 spec:
-  jobLabel: {{ template "name" . }}
+  jobLabel: {{ template "fullname" . }}
  selector:
    matchLabels:
      app: {{ template "name" . }}
--- a/helm/prometheus/values.yaml
+++ b/helm/prometheus/values.yaml
@ -248,77 +248,6 @@ storageSpec: {}
 #         requests:
 #           storage: 50Gi
 #   selector: {}
-# WARNING: Don't change this file after this lines, it's automatically appended by helm/hack/sync_kube_prometheus.py
-ruleFiles:
-  prometheus.rules: |-
-    groups:
-    - name: prometheus.rules
-      rules:
-      - alert: PrometheusConfigReloadFailed
-        expr: prometheus_config_last_reload_successful == 0
-        for: 10m
-        labels:
-          severity: warning
-        annotations:
-          description: Reloading Prometheus' configuration has failed for {{$labels.namespace}}/{{$labels.pod}}
-      - alert: PrometheusNotificationQueueRunningFull
-        expr: predict_linear(prometheus_notifications_queue_length[5m], 60 * 30) > prometheus_notifications_queue_capacity
-        for: 10m
-        labels:
-          severity: warning
-        annotations:
-          description: Prometheus' alert notification queue is running full for {{$labels.namespace}}/{{
-            $labels.pod}}
-      - alert: PrometheusErrorSendingAlerts
-        expr: rate(prometheus_notifications_errors_total[5m]) / rate(prometheus_notifications_sent_total[5m])
-          > 0.01
-        for: 10m
-        labels:
-          severity: warning
-        annotations:
-          description: Errors while sending alerts from Prometheus {{$labels.namespace}}/{{
-            $labels.pod}} to Alertmanager {{$labels.Alertmanager}}
-      - alert: PrometheusErrorSendingAlerts
-        expr: rate(prometheus_notifications_errors_total[5m]) / rate(prometheus_notifications_sent_total[5m])
-          > 0.03
-        for: 10m
-        labels:
-          severity: critical
-        annotations:
-          description: Errors while sending alerts from Prometheus {{$labels.namespace}}/{{
-            $labels.pod}} to Alertmanager {{$labels.Alertmanager}}
-      - alert: PrometheusNotConnectedToAlertmanagers
-        expr: prometheus_notifications_alertmanagers_discovered < 1
-        for: 10m
-        labels:
-          severity: warning
-        annotations:
-          description: Prometheus {{ $labels.namespace }}/{{ $labels.pod}} is not connected
-            to any Alertmanagers
-      - alert: PrometheusTSDBReloadsFailing
-        expr: increase(prometheus_tsdb_reloads_failures_total[2h]) > 0
-        for: 12h
-        labels:
-          severity: warning
-        annotations:
-          description: '{{$labels.job}} at {{$labels.instance}} had {{$value | humanize}}
-            reload failures over the last four hours.'
-          summary: Prometheus has issues reloading data blocks from disk
-      - alert: PrometheusTSDBCompactionsFailing
-        expr: increase(prometheus_tsdb_compactions_failed_total[2h]) > 0
-        for: 12h
-        labels:
-          severity: warning
-        annotations:
-          description: '{{$labels.job}} at {{$labels.instance}} had {{$value | humanize}}
-            compaction failures over the last four hours.'
-          summary: Prometheus has issues compacting sample blocks
-      - alert: PrometheusTSDBWALCorruptions
-        expr: tsdb_wal_corruptions_total > 0
-        for: 4h
-        labels:
-          severity: warning
-        annotations:
-          description: '{{$labels.job}} at {{$labels.instance}} has a corrupted write-ahead
-            log (WAL).'
-          summary: Prometheus write-ahead log is corrupted
+
+# default rules are in templates/prometheus.rules.yaml
+# prometheusRules: {}