Prod-like telemetry into staging

11 files changed, 121 insertions, 349 deletions

diff --git a/cluster/staging/app/telemetry/config/apm-config.yaml b/cluster/staging/app/telemetry/config/apm-config.yaml
deleted file mode 100644
index 07a88bd..0000000
--- a/cluster/staging/app/telemetry/config/apm-config.yaml
+++ /dev/null
@@ -1,20 +0,0 @@
-apm-server:
-  # Defines the host and port the server is listening on. Use "unix:/path/to.sock" to listen on a unix domain socket.
-  host: "0.0.0.0:8200"
-#-------------------------- Elasticsearch output --------------------------
-output.elasticsearch:
-  # Array of hosts to connect to.
-  # Scheme and port can be left out and will be set to the default (`http` and `9200`).
-  # In case you specify and additional path, the scheme is required: `http://localhost:9200/path`.
-  # IPv6 addresses should always be defined as: `https://[2001:db8::1]:9200`.
-  hosts: ["localhost:9200"]
-  username: "elastic"
-  password: "{{ key "secrets/telemetry/elastic_passwords/elastic" }}"
-
-instrumentation:
-  enabled: true
-  environment: staging
-
-logging:
-  level: warning
-  to_stderr: true
diff --git a/cluster/staging/app/telemetry/config/filebeat.yml b/cluster/staging/app/telemetry/config/filebeat.yml
deleted file mode 100644
index 310afd1..0000000
--- a/cluster/staging/app/telemetry/config/filebeat.yml
+++ /dev/null
@@ -1,46 +0,0 @@
-# see https://github.com/elastic/beats/blob/master/filebeat/filebeat.reference.yml
-filebeat.modules:
-- module: system
-  syslog:
-    enabled: true
-  auth:
-    enabled: true
-
-#filebeat.inputs:
-#- type: container
-#  enabled: true
-#  paths:
-#    -/var/lib/docker/containers/*/*.log
-#  stream: all # can be all, stdout or stderr
-
-#========================== Filebeat autodiscover ==============================
-filebeat.autodiscover:
-  providers:
-    - type: docker
-      # https://www.elastic.co/guide/en/beats/filebeat/current/configuration-autodiscover-hints.html
-      # This URL alos contains instructions on multi-line logs
-      hints.enabled: true
-
-#================================ Processors ===================================
-processors:
-# - add_cloud_metadata: ~
-- add_docker_metadata: ~
-- add_locale:
-    format: offset
-- add_host_metadata:
-    netinfo.enabled: true
-
-#========================== Elasticsearch output ===============================
-output.elasticsearch:
-  hosts: ["localhost:9200"]
-  username: elastic
-  password: {{ key "secrets/telemetry/elastic_passwords/elastic" }}
-
-#============================== Dashboards =====================================
-setup.dashboards:
-  enabled: false
-
-#============================== Xpack Monitoring ===============================
-xpack.monitoring:
-  enabled: true
-  elasticsearch:
diff --git a/cluster/staging/app/telemetry/config/grafana-datasource-prometheus.yaml b/cluster/staging/app/telemetry/config/grafana-datasource-prometheus.yaml
new file mode 100644
index 0000000..36b67e6
--- /dev/null
+++ b/cluster/staging/app/telemetry/config/grafana-datasource-prometheus.yaml
@@ -0,0 +1,7 @@
+apiVersion: 1
+
+datasources:
+  - name: DS_PROMETHEUS
+    type: prometheus
+    access: proxy
+    url: http://prometheus.service.staging.consul:9090
diff --git a/cluster/staging/app/telemetry/config/grafana/provisioning/datasources/elastic.yaml b/cluster/staging/app/telemetry/config/grafana/provisioning/datasources/elastic.yaml
deleted file mode 100644
index 7d2277c..0000000
--- a/cluster/staging/app/telemetry/config/grafana/provisioning/datasources/elastic.yaml
+++ /dev/null
@@ -1,21 +0,0 @@
-apiVersion: 1
-
-datasources:
-  - name: DS_ELASTICSEARCH
-    type: elasticsearch
-    access: proxy
-    url: http://localhost:9200
-    password: '{{ key "secrets/telemetry/elastic_passwords/elastic" }}'
-    user: 'elastic'
-    database: metrics-*
-    basicAuth: false
-    isDefault: true
-    jsonData:
-      esVersion: "8.2.0"
-      includeFrozen: false
-      logLevelField: ''
-      logMessageField: ''
-      maxConcurrentShardRequests: 5
-      timeField: "@timestamp"
-      timeInterval: "5s"
-    readOnly: false
diff --git a/cluster/staging/app/telemetry/config/otel-config.yaml b/cluster/staging/app/telemetry/config/otel-config.yaml
deleted file mode 100644
index bcf1baa..0000000
--- a/cluster/staging/app/telemetry/config/otel-config.yaml
+++ /dev/null
@@ -1,56 +0,0 @@
-receivers:
-  # Data sources: metrics, traces
-  otlp:
-    protocols:
-      grpc:
-        endpoint: ":4317"
-      http:
-        endpoint: ":55681"
-  # Data sources: metrics
-  prometheus:
-    config:
-      scrape_configs:
-        - job_name: "garage"
-          scrape_interval: 5s
-          static_configs:
-            - targets:
-              - "{{ env "attr.unique.network.ip-address" }}:3909"
-        - job_name: "node_exporter"
-          scrape_interval: 5s
-          static_configs:
-            - targets:
-              - "{{ env "attr.unique.network.ip-address" }}:9100"
-
-exporters:
-  logging:
-    logLevel: info
-  # see https://www.elastic.co/guide/en/apm/get-started/current/open-telemetry-elastic.html#open-telemetry-collector
-  otlp/elastic:
-    endpoint: "localhost:8200"
-    tls:
-      insecure: true
-
-processors:
-  batch:
-  probabilistic_sampler:
-    hash_seed: 42
-    sampling_percentage: 10
-
-extensions:
-  health_check:
-  pprof:
-    endpoint: :1888
-  zpages:
-    endpoint: :55679
-
-service:
-  extensions: [pprof, zpages, health_check]
-  pipelines:
-    traces:
-      receivers: [otlp]
-      processors: [probabilistic_sampler, batch]
-      exporters: [logging, otlp/elastic]
-    metrics:
-      receivers: [otlp, prometheus]
-      processors: [batch]
-      exporters: [logging, otlp/elastic]
diff --git a/cluster/staging/app/telemetry/config/prometheus.yml b/cluster/staging/app/telemetry/config/prometheus.yml
new file mode 100644
index 0000000..e0e786d
--- /dev/null
+++ b/cluster/staging/app/telemetry/config/prometheus.yml
@@ -0,0 +1,30 @@
+global:
+  scrape_interval:     15s # By default, scrape targets every 15 seconds.
+
+scrape_configs:
+  - job_name: 'prometheus'
+    static_configs:
+      - targets: ['localhost:9090']
+
+  - job_name: 'node-exporter'
+    consul_sd_configs:
+    - server: 'https://localhost:8501'
+      services:
+        - 'node-exporter'
+      tls_config:
+        ca_file: /etc/prometheus/consul.crt
+        cert_file: /etc/prometheus/consul-client.crt
+        key_file: /etc/prometheus/consul-client.key
+
+  - job_name: 'garage'
+    authorization:
+      type: Bearer
+      credentials: {{ key "secrets/garage-staging/metrics_token" }}
+    consul_sd_configs:
+    - server: 'https://localhost:8501'
+      services:
+        - 'garage-staging-admin'
+      tls_config:
+        ca_file: /etc/prometheus/consul.crt
+        cert_file: /etc/prometheus/consul-client.crt
+        key_file: /etc/prometheus/consul-client.key
diff --git a/cluster/staging/app/telemetry/deploy/telemetry-system.hcl b/cluster/staging/app/telemetry/deploy/telemetry-system.hcl
index 3e26c2e..e2bad61 100644
--- a/cluster/staging/app/telemetry/deploy/telemetry-system.hcl
+++ b/cluster/staging/app/telemetry/deploy/telemetry-system.hcl
@@ -1,182 +1,49 @@
 job "telemetry-system" {
-  datacenters = ["neptune"]
-  type = "system"
+	datacenters = ["neptune"]
+	type = "system"
+	priority = "100"
 
-  group "elasticsearch" {
+	group "collector" {
     network {
-      port "elastic" {
-        static = 9200
-      }
-      port "elastic_internal" {
-        static = 9300
-      }
+      port "node_exporter" { static = 9100 }
     }
 
-    task "elastic" {
-      driver = "docker"
-      config {
-        image = "docker.elastic.co/elasticsearch/elasticsearch:8.2.0"
-        network_mode = "host"
-        volumes = [
-          "/mnt/ssd/telemetry/es_data:/usr/share/elasticsearch/data",
-          "secrets/elastic-certificates.p12:/usr/share/elasticsearch/config/elastic-certificates.p12",
-        ]
-        ports = [ "elastic", "elastic_internal" ]
-        sysctl = {
-          #"vm.max_map_count" = "262144",
-        }
-        ulimit = {
-          memlock = "9223372036854775807:9223372036854775807", 
+		task "node_exporter" {
+			driver = "docker"
+
+			config {
+				image = "quay.io/prometheus/node-exporter:v1.1.2"
+				network_mode = "host"
+				volumes = [
+					"/:/host:ro,rslave"
+				]
+				args = [ "--path.rootfs=/host" ]
+			}
+
+			resources {
+				cpu = 50
+				memory = 40
+			}
+
+      service {
+        tags = [ "telemetry" ]
+        port = 9100
+        address_mode = "driver"
+        name = "node-exporter"
+        check {
+          type = "http"
+          path = "/"
+          port = 9100
+          address_mode = "driver"
+          interval = "60s"
+          timeout = "5s"
+          check_restart {
+            limit = 3
+            grace = "90s"
+            ignore_warnings = false
+          }
         }
       }
-
-      user = "1000"
-
-      resources {
-        memory = 1500
-        cpu = 500
-      }
-
-      template {
-        data = "{{ key \"secrets/telemetry/elasticsearch/elastic-certificates.p12\" }}"
-        destination = "secrets/elastic-certificates.p12"
-      }
-
-      template {
-        data = <<EOH
-node.name={{ env "attr.unique.hostname" }}
-http.port=9200
-transport.port=9300
-cluster.name=es-deuxfleurs
-cluster.initial_master_nodes=carcajou,caribou,cariacou
-discovery.seed_hosts=carcajou,caribou,cariacou
-bootstrap.memory_lock=true
-xpack.security.enabled=true
-xpack.security.authc.api_key.enabled=true
-xpack.security.transport.ssl.enabled=true
-xpack.security.transport.ssl.verification_mode=certificate
-xpack.security.transport.ssl.client_authentication=required
-xpack.security.transport.ssl.keystore.path=/usr/share/elasticsearch/config/elastic-certificates.p12
-xpack.security.transport.ssl.truststore.path=/usr/share/elasticsearch/config/elastic-certificates.p12
-cluster.routing.allocation.disk.watermark.high=75%
-cluster.routing.allocation.disk.watermark.low=65%
-ES_JAVA_OPTS=-Xms512M -Xmx512M
-EOH
-        destination = "secrets/env"
-        env = true
-      }
-    }
-  }
-
-  group "collector" {
-    network {
-      port "otel_grpc" {
-        static = 4317
-      }
-      port "apm" {
-        static = 8200
-      }
-      port "node_exporter" {
-        static = 9100
-      }
-    }
-
-    task "otel" {
-      driver = "docker"
-      config {
-        image = "otel/opentelemetry-collector-contrib:0.46.0"
-        args = [
-          "--config=/etc/otel-config.yaml",
-        ]
-        network_mode = "host"
-        ports= [ "otel_grpc" ]
-        volumes = [
-          "secrets/otel-config.yaml:/etc/otel-config.yaml"
-        ]
-      }
-
-      template {
-        data = file("../config/otel-config.yaml")
-        destination = "secrets/otel-config.yaml"
-      }
-
-      resources {
-        memory = 100
-        cpu = 100
-      }
-    }
-
-    task "apm" {
-      driver = "docker"
-      config {
-        image = "docker.elastic.co/apm/apm-server:8.2.0"
-        network_mode = "host"
-        ports = [ "apm" ]
-        args = [ "--strict.perms=false" ]
-        volumes = [
-          "secrets/apm-config.yaml:/usr/share/apm-server/apm-server.yml:ro"
-        ]
-      }
-
-      template {
-        data = file("../config/apm-config.yaml")
-        destination = "secrets/apm-config.yaml"
-      }
-
-      resources {
-        memory = 100
-        cpu = 100
-      }
-    }
-
-/*
-    task "node_exporter" {
-      driver = "docker"
-      config {
-        image = "quay.io/prometheus/node-exporter:v1.1.2"
-        network_mode = "host"
-        ports = [ "node_exporter" ]
-        volumes = [
-          "/:/host:ro,rslave"
-        ]
-        args = [ "--path.rootfs=/host" ]
-      }
-
-      resources {
-        cpu = 50
-        memory = 40
-      }
-    }
-*/
-
-    task "filebeat" {
-      driver = "docker"
-      config {
-        image = "docker.elastic.co/beats/filebeat:8.2.0"
-        network_mode = "host"
-        volumes = [
-          "/mnt/ssd/telemetry/filebeat:/usr/share/filebeat/data",
-          "secrets/filebeat.yml:/usr/share/filebeat/filebeat.yml",
-          "/var/run/docker.sock:/var/run/docker.sock",
-          "/var/lib/docker/containers/:/var/lib/docker/containers/:ro",
-          "/var/log/:/var/log/:ro",
-        ]
-        args = [ "--strict.perms=false" ]
-        privileged = true
-      }
-      user = "root"
-
-
-      template {
-        data = file("../config/filebeat.yml")
-        destination = "secrets/filebeat.yml"
-      }
-
-      resources {
-        memory = 100
-        cpu = 100
-      }
-    }
-  }
+		}
+	}
 }
-  
diff --git a/cluster/staging/app/telemetry/deploy/telemetry.hcl b/cluster/staging/app/telemetry/deploy/telemetry.hcl
index 21685a1..cfd26f3 100644
--- a/cluster/staging/app/telemetry/deploy/telemetry.hcl
+++ b/cluster/staging/app/telemetry/deploy/telemetry.hcl
@@ -2,51 +2,59 @@ job "telemetry" {
   datacenters = ["neptune"]
   type = "service"
 
-  group "kibana" {
+  group "prometheus" {
     count = 1
 
     network {
-      port "kibana" {
-        static = 5601
+      port "prometheus" {
+        static = 9090
       }
     }
 
-    task "kibana" {
+    task "prometheus" {
       driver = "docker"
       config {
-        image = "docker.elastic.co/kibana/kibana:8.2.0"
+        image = "prom/prometheus:v2.38.0"
         network_mode = "host"
-        ports = [ "kibana" ]
+        ports = [ "prometheus" ]
+        volumes = [
+          "secrets:/etc/prometheus"
+        ]
       }
 
       template {
-        data = <<EOH
-SERVER_NAME={{ env "attr.unique.hostname" }}
-ELASTICSEARCH_HOSTS=http://localhost:9200
-ELASTICSEARCH_USERNAME=kibana_system
-ELASTICSEARCH_PASSWORD={{ key "secrets/telemetry/elastic_passwords/kibana_system" }}
-SERVER_PUBLICBASEURL=https://kibana.home.adnab.me
-EOH
-        destination = "secrets/env"
-        env = true
+        data = file("../config/prometheus.yml")
+        destination = "secrets/prometheus.yml"
+      }
+
+      template {
+        data = "{{ key \"secrets/consul/consul.crt\" }}"
+        destination = "secrets/consul.crt"
+      }
+
+      template {
+        data = "{{ key \"secrets/consul/consul-client.crt\" }}"
+        destination = "secrets/consul-client.crt"
+      }
+
+      template {
+        data = "{{ key \"secrets/consul/consul-client.key\" }}"
+        destination = "secrets/consul-client.key"
       }
 
       resources {
-        memory = 1000
+        memory = 500
         cpu = 500
       }
 
       service {
-        tags = [
-            "kibana",
-            "tricot kibana.staging.deuxfleurs.org",
-        ]
-        port = 5601
+        port = 9090
         address_mode = "driver"
-        name = "kibana"
+        name = "prometheus"
         check {
-          type = "tcp"
-          port = 5601
+          type = "http"
+          path = "/"
+          port = 9090
           address_mode = "driver"
           interval = "60s"
           timeout = "5s"
@@ -59,13 +67,13 @@ EOH
       }
     }
   }
-  
+
   group "grafana" {
     count = 1
 
     network {
       port "grafana" {
-        static = 3333
+        static = 3719
       }
     }
 
@@ -107,19 +115,19 @@ EOH
         ports = [ "grafana" ]
         volumes = [
           "../alloc/data:/var/lib/grafana",
-          "secrets/elastic.yaml:/etc/grafana/provisioning/datasources/elastic.yaml"
+          "secrets/prometheus.yaml:/etc/grafana/provisioning/datasources/prometheus.yaml"
         ]
       }
 
       template {
-        data = file("../config/grafana/provisioning/datasources/elastic.yaml")
-        destination = "secrets/elastic.yaml"
+        data = file("../config/grafana-datasource-prometheus.yaml")
+        destination = "secrets/prometheus.yaml"
       }
 
       template {
         data = <<EOH
 GF_INSTALL_PLUGINS=grafana-clock-panel,grafana-simple-json-datasource,grafana-piechart-panel,grafana-worldmap-panel,grafana-polystat-panel
-GF_SERVER_HTTP_PORT=3333
+GF_SERVER_HTTP_PORT=3719
 EOH
         destination = "secrets/env"
         env = true
@@ -135,12 +143,12 @@ EOH
             "grafana",
             "tricot grafana.staging.deuxfleurs.org",
         ]
-        port = 3333
+        port = 3719
         address_mode = "driver"
         name = "grafana"
         check {
           type = "tcp"
-          port = 3333
+          port = 3719
           address_mode = "driver"
           interval = "60s"
           timeout = "5s"
diff --git a/cluster/staging/app/telemetry/secrets/telemetry/grafana/admin_password b/cluster/staging/app/telemetry/secrets/telemetry/grafana/admin_password
new file mode 100644
index 0000000..2f36e97
--- /dev/null
+++ b/cluster/staging/app/telemetry/secrets/telemetry/grafana/admin_password
@@ -0,0 +1 @@
+CMD openssl rand -base64 12
diff --git a/cluster/staging/app/telemetry/secrets/telemetry/grafana/s3_access_key b/cluster/staging/app/telemetry/secrets/telemetry/grafana/s3_access_key
new file mode 100644
index 0000000..c7e41a4
--- /dev/null
+++ b/cluster/staging/app/telemetry/secrets/telemetry/grafana/s3_access_key
@@ -0,0 +1 @@
+USER S3 access key for grafana db
diff --git a/cluster/staging/app/telemetry/secrets/telemetry/grafana/s3_secret_key b/cluster/staging/app/telemetry/secrets/telemetry/grafana/s3_secret_key
new file mode 100644
index 0000000..051f41a
--- /dev/null
+++ b/cluster/staging/app/telemetry/secrets/telemetry/grafana/s3_secret_key
@@ -0,0 +1 @@
+USER S3 secret key for grafana db