chore: initial otel & prometheus config

config/dev.exs

@@ -118,3 +118,5 @@ config :git_hooks,
       ]
     ]
   ]
+
+config :opentelemetry, traces_exporter: {:otel_exporter_stdout, []}

config/prod.exs

@@ -37,3 +37,12 @@ config :libcluster,
       ]
     ]
   ]
+
+config :opentelemetry,
+  resource: %{service: %{name: "tr_app"}},
+  span_processor: :batch,
+  traces_exporter: :otlp
+
+config :opentelemetry_exporter,
+  otlp_protocol: :http_protobuf,
+  otlp_endpoint: "http://opentelemetrycollector.monitoring.svc:4318"

lib/tr/application.ex

@@ -9,6 +9,10 @@ defmodule Tr.Application do
   def start(_type, _args) do
     topologies = Application.get_env(:libcluster, :topologies, [])
 
+    :opentelemetry_cowboy.setup()
+    OpentelemetryPhoenix.setup(adapter: :cowboy2)
+    OpentelemetryEcto.setup([:dice_game, :repo])
+
     children = [
       # Start the Cluster supervisor for libcluster
       {Cluster.Supervisor, [topologies, [name: Tr.ClusterSupervisor]]},

lib/tr_web/endpoint.ex

@@ -1,6 +1,8 @@
 defmodule TrWeb.Endpoint do
   use Phoenix.Endpoint, otp_app: :tr
 
+  plug Plug.Telemetry, event_prefix: [:phoenix, :endpoint]
+
   if Application.compile_env(:tr, :sql_sandbox) do
     plug Phoenix.Ecto.SQL.Sandbox
   end

lib/tr_web/live/beard_live.ex

@@ -72,18 +72,64 @@ defmodule TrWeb.BeardLive do
           </ul>
         </p>
 
-        <br>
+        <h4 class="mx-auto"><%= gettext("Wondering how we can help you?") %></h4>
+        <p class="text-lg mt-2">
+          <ul class="list-outside mt-2 text-left inline-block ml-60">
+            <li>
+            <%= gettext("Audit and validate your architecture, ask yourself:") %>
+              <ul>
+                <li>
+                  <%= gettext("is our infrastructure secure? do we have the right security groups, access control lists,
+                  policies? encryption in place?") %>
+                </li>
+                <li>
+                <%= gettext("Does our network have the capacity to grow and connect to other environments?") %>
+                </li>
+                <li>
+                <%= gettext("is our infrastructure cost efficient?") %>
+                </li>
+              </ul>
+            </li>
+            <li>
+              <%= gettext("Migrate projects to the cloud or back on-premises") %>
+            </li>
+            <li>
+              <%= gettext("Optimize and automate processes to free your team from repetitive, time-consuming tasks") %>
+            </li>
+            <li>
+             <%= gettext("Establish conventions and best practices to ensure consistency and scalability") %>
+             </li>
+            <li>
+             <%= gettext("Set up observability and monitoring") %>
+              <ul>
+                <li>
+                  <%= gettext("is our app fast and reliable?") %>
+                </li>
+                <li>
+                <%= gettext("are we caching data efficiently (or at all)?") %>
+                </li>
+                <li>
+                <%= gettext("Is the database properly sized? Do we have working backups?") %>
+                </li>
+              </ul>
+             </li>
+            <li>
+             <%= gettext("We can help you find answers to these questions and so much more. Schedule a call and let’s get started!") %>
+             </li>
+          </ul>
+        </p>
+
+        <br />
         <h3 class="text-xl font-bold">
           <% locale = if Gettext.get_locale(TrWeb.Gettext) == "en", do: "es", else: "en" %>
           <%= gettext("Looking for the ") %>
-            <.link aria-label="language-toggle" navigate={~p"/#{locale}"}>
-             <%= gettext "spanish" %>
-            </.link>
-          <%= gettext "version?" %>
+          <.link aria-label="language-toggle" navigate={~p"/#{locale}"}>
+            <%= gettext("spanish") %>
+          </.link>
+          <%= gettext("version?") %>
 
           <%= gettext("Or the ") %><a href={~p"/#{Gettext.get_locale(TrWeb.Gettext)}/blog"}>blog?</a>
         </h3>
-
       </section>
 
       <section class="mt-12 grid grid-cols-1 md:grid-cols-2 lg:grid-cols-3 gap-6 px-8">

lib/tr_web/live/post_live.ex

@@ -1,5 +1,8 @@
 defmodule TrWeb.PostLive do
   use TrWeb, :live_view
+
+  require OpenTelemetry.Tracer, as: Tracer
+
   alias Tr.Blog
   alias Tr.Post
   alias TrWeb.CommentComponent
@@ -9,60 +12,63 @@ defmodule TrWeb.PostLive do
 
   @impl true
   def mount(params, _session, socket) do
-    changeset = Tr.Post.change_comment(%Tr.Post.Comment{})
-    post_id = Map.get(params, "id")
+    Tracer.with_span("post") do
+      changeset = Tr.Post.change_comment(%Tr.Post.Comment{})
+      post_id = Map.get(params, "id")
 
-    if connected?(socket) do
-      # Comments PubSub
-      Post.subscribe(post_id)
+      if connected?(socket) do
+        # Comments PubSub
+        Post.subscribe(post_id)
 
-      # Presence PubSub
-      Phoenix.PubSub.subscribe(Tr.PubSub, post_id)
+        # Presence PubSub
+        Phoenix.PubSub.subscribe(Tr.PubSub, post_id)
 
-      # Track browser session
-      {:ok, _} =
-        Presence.track(self(), post_id, @topic, %{})
-    end
+        # Track browser session
+        {:ok, _} =
+          Presence.track(self(), post_id, @topic, %{})
+      end
 
-    connected_users = calculate_connected_users(post_id)
-
-    post = Blog.get_post_by_id!(Gettext.get_locale(TrWeb.Gettext), post_id)
-
-    socket =
-      socket
-      |> assign(:page_title, post.title)
-      |> assign(:params, params)
-      |> assign(:post, post)
-      |> assign(check_errors: false)
-      |> assign_form(changeset)
-      |> assign(:comments, Tr.Post.get_parent_comments_for_post(post_id))
-      |> assign(:children, Tr.Post.get_children_comments_for_post(post_id))
-      |> assign(:parent_comment_id, nil)
-      |> assign(:connected_users, connected_users)
-      |> assign(:diff, nil)
-      |> assign(:reactions, Tr.Post.get_reactions(post_id))
-      |> assign(
-        :rocket_launch,
-        get_styled_reaction(post.id, "rocket-launch", socket.assigns.current_user)
-      )
-      |> assign(
-        :hand_thumb_up,
-        get_styled_reaction(post.id, "hand-thumb-up", socket.assigns.current_user)
-      )
-      |> assign(
-        :heart,
-        get_styled_reaction(post.id, "heart", socket.assigns.current_user)
-      )
-      |> assign(
-        :oauth_google_url,
-        ElixirAuthGoogle.generate_oauth_url(TrWeb.Endpoint.url())
-      )
-      |> assign(
-        :oauth_github_url,
-        ElixirAuthGithub.login_url(%{scopes: ["user:email"]})
-      )
+      connected_users = calculate_connected_users(post_id)
 
-    {:ok, socket, temporary_assigns: [form: nil]}
+      post = Blog.get_post_by_id!(Gettext.get_locale(TrWeb.Gettext), post_id)
+
+      socket =
+        socket
+        |> assign(:page_title, post.title)
+        |> assign(:params, params)
+        |> assign(:post, post)
+        |> assign(check_errors: false)
+        |> assign_form(changeset)
+        |> assign(:comments, Tr.Post.get_parent_comments_for_post(post_id))
+        |> assign(:children, Tr.Post.get_children_comments_for_post(post_id))
+        |> assign(:parent_comment_id, nil)
+        |> assign(:connected_users, connected_users)
+        |> assign(:diff, nil)
+        |> assign(:reactions, Tr.Post.get_reactions(post_id))
+        |> assign(
+          :rocket_launch,
+          get_styled_reaction(post.id, "rocket-launch", socket.assigns.current_user)
+        )
+        |> assign(
+          :hand_thumb_up,
+          get_styled_reaction(post.id, "hand-thumb-up", socket.assigns.current_user)
+        )
+        |> assign(
+          :heart,
+          get_styled_reaction(post.id, "heart", socket.assigns.current_user)
+        )
+        |> assign(
+          :oauth_google_url,
+          ElixirAuthGoogle.generate_oauth_url(TrWeb.Endpoint.url())
+        )
+        |> assign(
+          :oauth_github_url,
+          ElixirAuthGithub.login_url(%{scopes: ["user:email"]})
+        )
+
+      Tracer.set_attribute(:post, post.id)
+      {:ok, socket, temporary_assigns: [form: nil]}
+    end
   end
 
   @impl true

manifests/monitoring/00-namespace.yaml

@@ -0,0 +1,4 @@
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: monitoring

manifests/monitoring/01-rbac.yaml

@@ -0,0 +1,33 @@
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRole
+metadata:
+  name: prometheus
+rules:
+- apiGroups: [""]
+  resources:
+  - nodes
+  - nodes/proxy
+  - services
+  - endpoints
+  - pods
+  verbs: ["get", "list", "watch"]
+- apiGroups:
+  - extensions
+  resources:
+  - ingresses
+  verbs: ["get", "list", "watch"]
+- nonResourceURLs: ["/metrics"]
+  verbs: ["get"]
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRoleBinding
+metadata:
+  name: prometheus
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: prometheus
+subjects:
+- kind: ServiceAccount
+  name: default
+  namespace: monitoring

manifests/monitoring/02-config.yaml

@@ -0,0 +1,46 @@
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: prometheus-k8s-conf
+  labels:
+    name: prometheus-k8s-conf
+  namespace: monitoring
+data:
+  prometheus.yml: |-
+    global:
+      scrape_interval: 10s
+    scrape_configs:
+    - job_name: 'monitoring-job'
+      static_configs:
+      - targets: ['opentelemetrycollector.monitoring.svc.cluster.local:9090']
+---
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: collector-config
+  namespace: monitoring
+data:
+  collector.yaml: |
+    receivers:
+      otlp:
+        protocols: 
+          grpc:
+    processors:
+      batch:
+        send_batch_size: 10000
+        timeout: 5s
+    exporters:
+      prometheus:
+        endpoint: ":9090"
+      logging:
+        loglevel: debug
+    service:
+      pipelines:
+        traces:
+          receivers: [otlp]
+          processors: [batch]
+          exporters: [logging]
+        metrics:
+          receivers: [otlp]
+          processors: [batch]
+          exporters: [prometheus, logging]

manifests/monitoring/03-prometheus.yaml

@@ -0,0 +1,46 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: prometheus-k8s
+  namespace: monitoring
+  labels:
+    app: prometheus-k8s
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: prometheus-k8s
+  template:
+    metadata:
+      labels:
+        app: prometheus-k8s
+    spec:
+      containers:
+        - name: prometheus
+          image: quay.io/prometheus/prometheus
+          imagePullPolicy: IfNotPresent
+          args:
+            - "--storage.tsdb.retention.time=24h"
+            - "--config.file=/etc/prometheus/prometheus.yml"
+            - "--storage.tsdb.path=/prometheus/"
+          ports:
+            - containerPort: 9090
+          resources:
+            requests:
+              cpu: 500m
+              memory: 500M
+            limits:
+              cpu: 1
+              memory: 1Gi
+          volumeMounts:
+            - name: prometheus-config-volume
+              mountPath: /etc/prometheus/
+            - name: prometheus-storage-volume
+              mountPath: /prometheus/
+      volumes:
+        - name: prometheus-config-volume
+          configMap:
+            defaultMode: 420
+            name: prometheus-k8s-conf
+        - name: prometheus-storage-volume
+          emptyDir: {}

manifests/monitoring/04-service.yaml

@@ -0,0 +1,15 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: prometheus-service
+  namespace: monitoring
+  annotations:
+      prometheus.io/scrape: 'true'
+      prometheus.io/port:   '9090'
+spec:
+  selector: 
+    app: prometheus-k8s
+  type: NodePort  
+  ports:
+    - port: 9090
+      targetPort: 9090