Adding prometheus , otel monitoring setup and docs

docker/monitoring/docker-compose.yaml

@@ -0,0 +1,41 @@
+version: "3"
+services:
+ otel-collector:
+  container_name: "otel-collector"
+  image: otel/opentelemetry-collector-contrib
+  restart: always
+  command: 
+    - --config=/etc/otelcol-contrib/otel-config.yaml
+  volumes:
+    - ./otel-collector-config.yaml:/etc/otelcol-contrib/otel-config.yaml
+  ports:
+    - "1888:1888" # pprof extension
+    - "8888:8888" # Prometheus metrics exposed by the Collector
+    - "8889:8889" # Prometheus exporter metrics
+    - "13133:13133" # health_check extension
+    - "4317:4317" # OTLP gRPC receiver
+    - "4318:4318" # OTLP http receiver
+    - "55679:55679" # zpages extension
+
+ prometheus:
+  image: prom/prometheus
+  container_name: prometheus
+  restart: always
+  command:
+      - --config.file=/etc/prometheus/prometheus.yml
+  ports:
+      - "9090:9090"
+  volumes:
+      - ./prometheus.yml:/etc/prometheus/prometheus.yml
+      - prometheus-data:/prometheus
+
+ grafana:
+    container_name: grafana
+    image: grafana/grafana
+    volumes:
+      - ./grafana-datasources.yml:/etc/grafana/provisioning/datasources/datasources.yml
+    ports:
+      - "3000:3000"
+
+volumes:
+  prometheus-data:

docker/monitoring/grafana-datasources.yml

@@ -0,0 +1,15 @@
+apiVersion: 1
+
+datasources:
+  - name: Prometheus
+    type: prometheus
+    uid: prometheus
+    access: proxy
+    orgId: 1
+    url: http://prometheus:9090
+    basicAuth: false
+    isDefault: false
+    version: 1
+    editable: false
+    jsonData:
+      httpMethod: GET

docker/monitoring/otel-collector-config.yaml

@@ -0,0 +1,32 @@
+receivers:
+  otlp:
+    protocols:
+      http:
+
+processors:
+  # batch metrics before sending to reduce API usage
+  batch:
+
+exporters:
+  prometheus:
+    endpoint: "0.0.0.0:8889"
+    const_labels:
+      label: juno
+
+
+# /~https://github.com/open-telemetry/opentelemetry-collector/blob/main/extension/README.md
+extensions:
+  # responsible for responding to health check calls on behalf of the collector.
+  health_check:
+  # fetches the collector’s performance data
+  pprof:
+  # serves as an http endpoint that provides live debugging data about instrumented components.
+  zpages:
+
+service:
+  extensions: [health_check, pprof, zpages]
+  pipelines:
+    metrics:
+      receivers: [otlp]
+      processors: [batch]
+      exporters: [prometheus]

docker/monitoring/prometheus.yml

@@ -0,0 +1,12 @@
+global:
+  scrape_interval: 10s
+  evaluation_interval: 10s
+
+scrape_configs:
+  - job_name: 'otel-collector'
+    static_configs:
+      - targets: ['otel-collector:8889'] # Otlp
+  # uncomment to enable prometheus metrics
+  #- job_name: 'prometheus'
+  #  static_configs:
+  #    - targets: ['localhost:9090'] # Prometheus itself

docs/otel_monitoring.md

@@ -0,0 +1,59 @@
+## Monitor Juno Metrics using Prometheus
+
+#### A simple setup to push the metrics on prometheus using otel-collector is shown below. Grafana can be further used to create visualizations from the available metrics.
+
+<img
+  src="otel_mon.png"
+  style="display: margin: 0 auto;">
+
+  #### Setup 
+
+  ##### Configure proxy and storage to push metrics to otel endpoint
+
+- Juno proxy and storage services are configured to push the metrics on open telemetry collector endpoint http://localhost:4318/v1/metrics . Add/Update the [OTEL] section in the respective config.toml files
+
+```yaml
+[OTEL]
+  Enabled = true
+  Environment = "qa"
+  Host = "0.0.0.0"
+  Poolname = "junoserv-ai"
+  Port = 4318
+  Resolution = 10
+  UrlPath = "/v1/metrics"
+  UseTls = false
+
+```
+
+- Now the proxy and storage services are uploading metrics to otel endpoint. 
+
+##### Set up otel-collector, prometheus and grafana
+- Open telemetry collector, prometheus and grafana are run as docker containers.
+- otel-collector , prometheus and grafana configurations are required to be mounted as volumes in the containers
+- docker-compose.yaml and configuration files for each of the services available in junodb/docker/monitoring
+
+
+```bash
+cd junodb/docker/monitoring
+
+docker compose up -d
+```
+
+- Check the running containers. prometheus, otel-collector and grafana should be running
+
+```bash
+CONTAINER ID   IMAGE                                  COMMAND                  CREATED       STATUS       PORTS                                                                                                                                                       NAMES
+bcb1e7ece6b7   prom/prometheus                        "/bin/prometheus --c…"   3 hours ago   Up 3 hours   0.0.0.0:9090->9090/tcp                                                                                                                                      prometheus
+c3816c006f85   otel/opentelemetry-collector-contrib   "/otelcol-contrib --…"   3 hours ago   Up 3 hours   0.0.0.0:1888->1888/tcp, 0.0.0.0:4317-4318->4317-4318/tcp, 0.0.0.0:8888-8889->8888-8889/tcp, 0.0.0.0:13133->13133/tcp, 0.0.0.0:55679->55679/tcp, 55678/tcp   otel-collector
+e41e33696606   grafana/grafana                        "/run.sh"                3 hours ago   Up 3 hours   0.0.0.0:3000->3000/tcp                                                                                                                                      grafana
+
+```
+
+- Check the promethus server running at <host_ip>:9090 as shown below. Search for juno metrics.
+
+<img
+  src="prometheus.png"
+  style="display: margin: 0 auto;">
+
+
+