Refactoring Observability stack (#6333)

* feat(opentelemetry): Refactoring Operator and Collector

Signed-off-by: Nicolas Lamirault <[email protected]>

* feat(argo-cd): typo

Signed-off-by: Nicolas Lamirault <[email protected]>

* feat(alloy): refactoring stack

Signed-off-by: Nicolas Lamirault <[email protected]>

* feat(opentelemetry): cleanup

Signed-off-by: Nicolas Lamirault <[email protected]>

---------

Signed-off-by: Nicolas Lamirault <[email protected]>

gitops/argocd/charts/opentelemetry/alloy-otel/Chart.yaml

@@ -0,0 +1,37 @@
+# SPDX-FileCopyrightText: Copyright (C) Nicolas Lamirault <[email protected]>
+# SPDX-License-Identifier: Apache-2.0
+
+---
+apiVersion: v2
+type: application
+name: alloy
+version: 1.0.0
+appVersion: 1.0.0
+dependencies:
+- name: alloy
+  repository: https://grafana.github.io/helm-charts
+  version: 0.11.0
+  alias: alloy-metrics
+- name: alloy
+  repository: https://grafana.github.io/helm-charts
+  version: 0.11.0
+  alias: alloy-logs
+- name: alloy
+  repository: https://grafana.github.io/helm-charts
+  version: 0.11.0
+  alias: alloy-traces
+- name: alloy
+  repository: https://grafana.github.io/helm-charts
+  version: 0.11.0
+  alias: alloy-events
+- name: alloy
+  repository: https://grafana.github.io/helm-charts
+  version: 0.11.0
+  alias: alloy-profiles
+- name: alloy
+  repository: https://grafana.github.io/helm-charts
+  version: 0.11.0
+  alias: alloy-frontend
+- name: alloy-mixin
+  repository: oci://ghcr.io/portefaix/charts
+  version: 0.3.1

gitops/argocd/charts/opentelemetry/alloy-otel/templates/alloy/_global.alloy

@@ -0,0 +1,24 @@
+{{ define "alloy.config.global" }}
+
+// ********************************************
+// * G E N E R A L
+// ********************************************
+
+local.file "cluster_name" {
+  filename  = "/etc/alloy/cluster_name"
+}
+
+logging {
+  level  = "info"
+  format = "json"
+}
+
+// tracing {
+//   sampling_fraction = 1
+//   write_to = [
+//     otelcol.exporter.otlp.local.input,
+//     // otelcol.exporter.otlp.grafana_cloud.input
+//   ]
+// }
+
+{{ end }}

gitops/argocd/charts/opentelemetry/alloy-otel/templates/alloy/endpoints/_endpoints_metrics.alloy

@@ -0,0 +1,54 @@
+{{ define "alloy.config.endpoints.metrics" }}
+
+// ********************************************
+// * M E T R I C S
+// ********************************************
+
+// [Mimir Local]
+
+prometheus.remote_write "local" {
+  endpoint {
+    url = {{ .Values.observability.metrics.prometheus | quote }}
+
+    headers = {
+      // "X-Scope-OrgID" = {{ .Values.observability.cluster_name | quote }},
+      "X-Scope-OrgID" = local.file.cluster_name.content,
+    }
+  }
+
+  external_labels = {
+    // cluster = {{ .Values.observability.cluster_name | quote }},
+    cluster = local.file.cluster_name.content,
+    {{- range $k, $v := .Values.observability.metrics.externalLabels }}
+    {{ $k }} = {{ $v | quote }},
+    {{- end }}
+  }
+}
+
+// [Grafana Cloud]
+
+prometheus.remote_write "grafana_cloud" {
+  endpoint {
+    url = {{ .Values.observability.metrics.grafana_cloud | quote }}
+
+    basic_auth {
+      username = env("GRAFANA_CLOUD_METRICS_ID")
+      password = env("GRAFANA_CLOUD_METRICS_APIKEY")
+    }
+
+    headers = {
+      // "X-Scope-OrgID" = {{ .Values.observability.cluster_name | quote }},
+      "X-Scope-OrgID" = local.file.cluster_name.content,
+    }
+  }
+
+  external_labels = {
+    // cluster = {{ .Values.observability.cluster_name | quote }},
+    cluster = local.file.cluster_name.content,
+    {{- range $k, $v := .Values.observability.metrics.externalLabels }}
+    {{ $k }} = {{ $v | quote }},
+    {{- end }}
+  }
+}
+
+{{ end }}

gitops/argocd/charts/opentelemetry/alloy-otel/templates/alloy/metrics/_metrics_prom_operator.alloy

@@ -0,0 +1,52 @@
+{{ define "alloy.config.metrics.prom_operator" }}
+
+// ********************************************
+// * P R O M E T H E U S  O P E R A T O R
+// ********************************************
+
+// ServiceMonitor
+
+prometheus.operator.servicemonitors "service_monitors" {
+  forward_to = [
+    prometheus.remote_write.local.receiver,
+    // prometheus.remote_write.grafana_cloud.receiver,
+  ]
+
+  selector {
+    match_labels = {
+      monitoring = "portefaix",
+    }
+  }
+}
+
+// PodMonitor
+
+prometheus.operator.podmonitors "pod_monitors" {
+  forward_to = [
+    prometheus.remote_write.local.receiver,
+    // prometheus.remote_write.grafana_cloud.receiver,
+  ]
+
+  selector {
+    match_labels = {
+      monitoring = "portefaix",
+    }
+  }
+}
+
+// Probes
+
+prometheus.operator.probes "probes" {
+  forward_to = [
+    prometheus.remote_write.local.receiver,
+    // prometheus.remote_write.grafana_cloud.receiver,
+  ]
+
+  selector {
+    match_labels = {
+      monitoring = "portefaix",
+    }
+  }
+}
+
+{{ end }}

gitops/argocd/charts/opentelemetry/alloy-otel/templates/configmap-metrics.yaml

@@ -0,0 +1,49 @@
+# SPDX-FileCopyrightText: Copyright (C) Nicolas Lamirault <[email protected]>
+# SPDX-License-Identifier: Apache-2.0
+
+---
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  {{- with .Values.additionalAnnotations }}
+  annotations:
+  {{ toYaml . | indent 4 }}
+  {{- end }}
+  labels:
+    {{- include "alloy.labels" (index .Subcharts "alloy-metrics") | nindent 4 }}
+    portefaix.xyz/version: v0.54.0
+  name: {{ include "alloy.fullname" (index .Subcharts "alloy-metrics") }}
+  namespace: {{ .Release.Namespace }}
+data:
+  cluster_name: {{ .Values.observability.cluster_name }}
+  config.alloy: |-
+{{- include "alloy.config.global" . | indent 4}}
+
+{{- include "alloy.config.portefaix" . | indent 4 }}
+
+{{- include "alloy.config.endpoints.metrics" . | indent 4 }}
+
+{{- include "alloy.config.metrics.router" . | indent 4 }}
+{{- include "alloy.config.metrics.otlp" . | indent 4 }}
+{{- include "alloy.config.metrics.prom_operator" . | indent 4 }}
+{{- include "alloy.config.metrics.rules" . | indent 4 }}
+
+{{- if .Values.observability.cloud.aws.enabled -}}
+{{- include "alloy.config.cloud.aws" . | indent 4 }}
+{{- end }}
+
+{{- if .Values.observability.cloud.azure.enabled -}}
+{{- include "alloy.config.cloud.azure" . | indent 4 }}
+{{- end }}
+
+{{- if .Values.observability.cloud.gcp.enable -}}
+{{- include "alloy.config.cloud.gcp" . | indent 4 }}
+{{- end }}
+
+{{- if .Values.observability.cloud.digitalocean.enabled -}}
+{{- include "alloy.config.cloud.digitalocean" . | indent 4 }}
+{{- end }}
+
+{{- if .Values.observability.cloud.scaleway.enabled -}}
+{{- include "alloy.config.cloud.scaleway" . | indent 4 }}
+{{- end }}