Add observability platform Ansible project

Deploys the Grafana stack (Prometheus/Alertmanager/Loki/Tempo/Grafana with Alloy as collector) and the ELK stack (Filebeat/Logstash/Elasticsearch/ Kibana) via Docker Compose on a target host. External to the application repo, pre-built by the mentor.
2026-09-05 08:11:34 +03:30
parent eb99cdbb8c
commit bffc42c9d3
26 changed files with 1056 additions and 0 deletions
@@ -0,0 +1,18 @@
+global:
+  resolve_timeout: 5m
+
+route:
+  receiver: default
+  group_by: [alertname, instance]
+  group_wait: 30s
+  group_interval: 5m
+  repeat_interval: 4h
+
+receivers:
+  - name: default
+{% if alertmanager_webhook_url | length > 0 %}
+    webhook_configs:
+      - url: "{{ alertmanager_webhook_url }}"
+        send_resolved: true
+{% endif %}
+
@@ -0,0 +1,51 @@
+logging {
+  level = "info"
+}
+
+discovery.docker "local" {
+  host = "unix:///var/run/docker.sock"
+}
+
+discovery.relabel "docker" {
+  targets = discovery.docker.local.targets
+
+  rule {
+    source_labels = ["__meta_docker_container_name"]
+    regex         = "/(.*)"
+    target_label  = "container"
+  }
+}
+
+loki.source.docker "local" {
+  host       = "unix:///var/run/docker.sock"
+  targets    = discovery.relabel.docker.output
+  forward_to = [loki.write.default.receiver]
+}
+
+loki.write "default" {
+  endpoint {
+    url = "http://loki:3100/loki/api/v1/push"
+  }
+}
+
+otelcol.receiver.otlp "default" {
+  grpc {
+    endpoint = "0.0.0.0:4317"
+  }
+  http {
+    endpoint = "0.0.0.0:4318"
+  }
+  output {
+    traces = [otelcol.exporter.otlp.tempo.input]
+  }
+}
+
+otelcol.exporter.otlp "tempo" {
+  client {
+    endpoint = "tempo:4317"
+    tls {
+      insecure = true
+    }
+  }
+}
+
@@ -0,0 +1,54 @@
+apiVersion: 1
+
+datasources:
+  - name: Prometheus
+    uid: prometheus
+    type: prometheus
+    access: proxy
+    url: http://prometheus:9090
+    isDefault: true
+    editable: true
+    jsonData:
+      exemplarTraceIdDestinations:
+        - datasourceUid: tempo
+          name: trace_id
+
+  - name: Loki
+    uid: loki
+    type: loki
+    access: proxy
+    url: http://loki:3100
+    editable: true
+    jsonData:
+      derivedFields:
+        - datasourceUid: tempo
+          matcherRegex: 'trace[_-]?id["=: ]+([a-fA-F0-9]+)'
+          name: TraceID
+          url: '$${__value.raw}'
+
+  - name: Tempo
+    uid: tempo
+    type: tempo
+    access: proxy
+    url: http://tempo:3200
+    editable: true
+    jsonData:
+      tracesToLogsV2:
+        datasourceUid: loki
+        filterByTraceID: true
+        spanStartTimeShift: -1m
+        spanEndTimeShift: 1m
+      serviceMap:
+        datasourceUid: prometheus
+      nodeGraph:
+        enabled: true
+
+  - name: Alertmanager
+    uid: alertmanager
+    type: alertmanager
+    access: proxy
+    url: http://alertmanager:9093
+    editable: true
+    jsonData:
+      implementation: prometheus
+
@@ -0,0 +1,34 @@
+auth_enabled: false
+
+server:
+  http_listen_port: 3100
+
+common:
+  path_prefix: /var/loki
+  replication_factor: 1
+  ring:
+    instance_addr: 127.0.0.1
+    kvstore:
+      store: inmemory
+
+schema_config:
+  configs:
+    - from: 2024-01-01
+      store: tsdb
+      object_store: filesystem
+      schema: v13
+      index:
+        prefix: index_
+        period: 24h
+
+storage_config:
+  filesystem:
+    directory: /var/loki/chunks
+
+compactor:
+  working_directory: /var/loki/compactor
+
+limits_config:
+  retention_period: 336h
+  allow_structured_metadata: true
+
@@ -0,0 +1,43 @@
+global:
+  scrape_interval: 15s
+  evaluation_interval: 15s
+
+rule_files:
+  - /etc/prometheus/rules/*.yml
+
+alerting:
+  alertmanagers:
+    - static_configs:
+        - targets: ["alertmanager:9093"]
+
+scrape_configs:
+  - job_name: prometheus
+    static_configs:
+      - targets: ["prometheus:9090"]
+
+  - job_name: node-exporter
+    static_configs:
+      - targets: ["node-exporter:9100"]
+
+  - job_name: loki
+    static_configs:
+      - targets: ["loki:3100"]
+
+  - job_name: tempo
+    static_configs:
+      - targets: ["tempo:3200"]
+
+  - job_name: alloy
+    static_configs:
+      - targets: ["alloy:12345"]
+
+  - job_name: grafana
+    static_configs:
+      - targets: ["grafana:3000"]
+
+{% for job in prometheus_extra_scrape_jobs %}
+  - job_name: "{{ job.job_name }}"
+    static_configs:
+      - targets: {{ job.targets | to_json }}
+{% endfor %}
+
@@ -0,0 +1,21 @@
+groups:
+  - name: host.rules
+    rules:
+      - alert: HostExporterDown
+        expr: up{job="node-exporter"} == 0
+        for: 2m
+        labels:
+          severity: critical
+        annotations:
+          summary: "Node exporter is unavailable"
+          description: "Prometheus has failed to scrape {{ '{{' }} $labels.instance {{ '}}' }} for more than two minutes."
+
+      - alert: HostHighCPU
+        expr: 100 - (avg by(instance) (rate(node_cpu_seconds_total{mode="idle"}[5m])) * 100) > 85
+        for: 10m
+        labels:
+          severity: warning
+        annotations:
+          summary: "High CPU utilization"
+          description: "CPU utilization on {{ '{{' }} $labels.instance {{ '}}' }} has exceeded 85% for ten minutes."
+
@@ -0,0 +1,42 @@
+server:
+  http_listen_port: 3200
+
+distributor:
+  receivers:
+    otlp:
+      protocols:
+        grpc:
+          endpoint: 0.0.0.0:4317
+        http:
+          endpoint: 0.0.0.0:4318
+
+ingester:
+  max_block_duration: 5m
+
+compactor:
+  compaction:
+    block_retention: 336h
+
+storage:
+  trace:
+    backend: local
+    wal:
+      path: /var/tempo/wal
+    local:
+      path: /var/tempo/blocks
+
+metrics_generator:
+  registry:
+    external_labels:
+      source: tempo
+  storage:
+    path: /var/tempo/generator/wal
+    remote_write:
+      - url: http://prometheus:9090/api/v1/write
+        send_exemplars: true
+
+overrides:
+  defaults:
+    metrics_generator:
+      processors: [service-graphs, span-metrics, local-blocks]
+