Integrate collectd, prometheus and grafana.

In this patch, made neccessary changes in collectd and prometheus
helm charts such that prometheus can pull data from collectd.
Prometheus GUI and Grafana GUI are verified as well.

Issue-ID: MULTICLOUD-1082
Signed-off-by: Rajamohan Raj <rajamohan.raj@intel.com>
Change-Id: I39b7e20f46aa789272be671056a76dd926701068

1 files changed, 84 insertions, 0 deletions

diff --git a/kud/tests/vnfs/comp-app/collection/app2/helm/prometheus-operator/templates/prometheus/rules-1.14/kubernetes-system-kubelet.yaml b/kud/tests/vnfs/comp-app/collection/app2/helm/prometheus-operator/templates/prometheus/rules-1.14/kubernetes-system-kubelet.yaml
new file mode 100755
index 00000000..bb7a2838
--- /dev/null
+++ b/kud/tests/vnfs/comp-app/collection/app2/helm/prometheus-operator/templates/prometheus/rules-1.14/kubernetes-system-kubelet.yaml
@@ -0,0 +1,84 @@
+{{- /*
+Generated from 'kubernetes-system-kubelet' group from https://raw.githubusercontent.com/coreos/kube-prometheus/master/manifests/prometheus-rules.yaml
+Do not change in-place! In order to change this file first read following link:
+https://github.com/helm/charts/tree/master/stable/prometheus-operator/hack
+*/ -}}
+{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }}
+{{- if and (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.defaultRules.create .Values.defaultRules.rules.kubernetesSystem }}
+apiVersion: monitoring.coreos.com/v1
+kind: PrometheusRule
+metadata:
+  name: {{ printf "%s-%s" (include "prometheus-operator.fullname" .) "kubernetes-system-kubelet" | trunc 63 | trimSuffix "-" }}
+  namespace: {{ template "prometheus-operator.namespace" . }}
+  labels:
+    app: {{ template "prometheus-operator.name" . }}
+{{ include "prometheus-operator.labels" . | indent 4 }}
+{{- if .Values.defaultRules.labels }}
+{{ toYaml .Values.defaultRules.labels | indent 4 }}
+{{- end }}
+{{- if .Values.defaultRules.annotations }}
+  annotations:
+{{ toYaml .Values.defaultRules.annotations | indent 4 }}
+{{- end }}
+spec:
+  groups:
+  - name: kubernetes-system-kubelet
+    rules:
+    - alert: KubeNodeNotReady
+      annotations:
+        message: '{{`{{`}} $labels.node {{`}}`}} has been unready for more than 15 minutes.'
+        runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubenodenotready
+      expr: kube_node_status_condition{job="kube-state-metrics",condition="Ready",status="true"} == 0
+      for: 15m
+      labels:
+        severity: warning
+    - alert: KubeNodeUnreachable
+      annotations:
+        message: '{{`{{`}} $labels.node {{`}}`}} is unreachable and some workloads may be rescheduled.'
+        runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubenodeunreachable
+      expr: (kube_node_spec_taint{job="kube-state-metrics",key="node.kubernetes.io/unreachable",effect="NoSchedule"} unless ignoring(key,value) kube_node_spec_taint{job="kube-state-metrics",key="ToBeDeletedByClusterAutoscaler"}) == 1
+      labels:
+        severity: warning
+    - alert: KubeletTooManyPods
+      annotations:
+        message: Kubelet '{{`{{`}} $labels.node {{`}}`}}' is running at {{`{{`}} $value | humanizePercentage {{`}}`}} of its Pod capacity.
+        runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubelettoomanypods
+      expr: max(max(kubelet_running_pod_count{job="kubelet", metrics_path="/metrics"}) by(instance) * on(instance) group_left(node) kubelet_node_name{job="kubelet", metrics_path="/metrics"}) by(node) / max(kube_node_status_capacity_pods{job="kube-state-metrics"} != 1) by(node) > 0.95
+      for: 15m
+      labels:
+        severity: warning
+    - alert: KubeNodeReadinessFlapping
+      annotations:
+        message: The readiness status of node {{`{{`}} $labels.node {{`}}`}} has changed {{`{{`}} $value {{`}}`}} times in the last 15 minutes.
+        runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubenodereadinessflapping
+      expr: sum(changes(kube_node_status_condition{status="true",condition="Ready"}[15m])) by (node) > 2
+      for: 15m
+      labels:
+        severity: warning
+    - alert: KubeletPlegDurationHigh
+      annotations:
+        message: The Kubelet Pod Lifecycle Event Generator has a 99th percentile duration of {{`{{`}} $value {{`}}`}} seconds on node {{`{{`}} $labels.node {{`}}`}}.
+        runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubeletplegdurationhigh
+      expr: node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile{quantile="0.99"} >= 10
+      for: 5m
+      labels:
+        severity: warning
+    - alert: KubeletPodStartUpLatencyHigh
+      annotations:
+        message: Kubelet Pod startup 99th percentile latency is {{`{{`}} $value {{`}}`}} seconds on node {{`{{`}} $labels.node {{`}}`}}.
+        runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubeletpodstartuplatencyhigh
+      expr: histogram_quantile(0.99, sum(rate(kubelet_pod_worker_duration_seconds_bucket{job="kubelet", metrics_path="/metrics"}[5m])) by (instance, le)) * on(instance) group_left(node) kubelet_node_name{job="kubelet", metrics_path="/metrics"} > 60
+      for: 15m
+      labels:
+        severity: warning
+{{- if .Values.prometheusOperator.kubeletService.enabled }}
+    - alert: KubeletDown
+      annotations:
+        message: Kubelet has disappeared from Prometheus target discovery.
+        runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubeletdown
+      expr: absent(up{job="kubelet", metrics_path="/metrics"} == 1)
+      for: 15m
+      labels:
+        severity: critical
+{{- end }}
+{{- end }}