feast-dev
diff --git a/README.md b/README.md
@@ -17,7 +17,6 @@
 [![GitHub Release](https://img.shields.io/github/v/release/feast-dev/feast.svg?style=flat&sort=semver&color=blue)](https://github.com/feast-dev/feast/releases)
 
 ## Join us on Slack!
-
 👋👋👋 [Come say hi on Slack!](https://join.slack.com/t/feastopensource/signup)
 
 ## Overview
@@ -231,4 +230,4 @@ Thanks goes to these incredible people:
 
 <a href="https://github.com/feast-dev/feast/graphs/contributors">
   <img src="https://contrib.rocks/image?repo=feast-dev/feast" />
-</a>
+</a>
@@ -44,8 +44,12 @@ See [here](https://github.com/feast-dev/feast/tree/master/examples/python-helm-d
 | imagePullSecrets | list | `[]` |  |
 | livenessProbe.initialDelaySeconds | int | `30` |  |
 | livenessProbe.periodSeconds | int | `30` |  |
+| metrics.enabled | bool | `false` |  |
+| metrics.otelCollector.endpoint | string | `""` |  |
+| metrics.otelCollector.port | int | `4317` |  |
 | nameOverride | string | `""` |  |
 | nodeSelector | object | `{}` |  |
+| otel_service.name | string | `"otelcol"` |  |
 | podAnnotations | object | `{}` |  |
 | podSecurityContext | object | `{}` |  |
 | readinessProbe.initialDelaySeconds | int | `20` |  |

@@ -0,0 +1,108 @@
+## Adding Monitoring
+To add monitoring to the Feast Feature Server, follow these steps:
+
+### Workflow
+
+Feast instrumentation Using OpenTelemetry and Prometheus - 
+![Workflow](samples/workflow.png)
+
+### Deploy Prometheus Operator
+Follow the Prometheus Operator documentation to install the operator - 
+https://github.com/prometheus-operator/prometheus-operator/blob/main/Documentation/user-guides/getting-started.md
+
+### Deploy OpenTelemetry Operator
+Before installing OTEL Operator, install `cert-manager` and validate the `pods` should spin up --
+```
+kubectl apply -f https://github.com/open-telemetry/opentelemetry-operator/releases/latest/download/opentelemetry-operator.yaml
+```
+
+Follow the documentation for further installation steps - 
+https://github.com/open-telemetry/opentelemetry-operator
+
+### Configure OpenTelemetry Collector
+Add the OpenTelemetry Collector configuration under the metrics section in your values.yaml file.
+
+Example values.yaml:
+
+```
+metrics:
+  enabled: true
+  otelCollector:
+    endpoint: "otel-collector.default.svc.cluster.local:4317" #sample
+    headers:
+      api-key: "your-api-key"
+```
+
+### Add instrumentation annotation and environment variables in the deployment.yaml 
+
+```
+template:
+    metadata:
+    {{- with .Values.podAnnotations }}
+      annotations:
+        {{- toYaml . | nindent 8 }}
+        instrumentation.opentelemetry.io/inject-python: "true"
+```
+
+```
+- name: OTEL_EXPORTER_OTLP_ENDPOINT
+    value: http://{{ .Values.service.name }}-collector.{{ .Release.namespace }}.svc.cluster.local:{{ .Values.metrics.endpoint.port}}
+- name: OTEL_EXPORTER_OTLP_INSECURE
+              value: "true"     
+```
+
+### Add checks
+Add metric checks to all manifests and deployment file -
+
+```
+{{ if .Values.metrics.enabled }}
+apiVersion: opentelemetry.io/v1alpha1
+kind: Instrumentation
+metadata:
+  name: feast-instrumentation
+spec:
+  exporter:
+    endpoint: http://{{ .Values.service.name }}-collector.{{ .Release.Namespace }}.svc.cluster.local:4318 # This is the default port for the OpenTelemetry Collector
+  env:
+  propagators:
+    - tracecontext
+    - baggage
+  python:
+    env:
+      - name: OTEL_METRICS_EXPORTER
+        value: console,otlp_proto_http
+      - name: OTEL_LOGS_EXPORTER
+        value: otlp_proto_http
+      - name: OTEL_PYTHON_LOGGING_AUTO_INSTRUMENTATION_ENABLED
+        value: "true"
+{{end}}
+```
+
+### Add manifests to the chart 
+Add Instrumentation, OpenTelemetryCollector, ServiceMonitors, Prometheus Instance and RBAC rules as provided in the [samples/](https://github.com/feast-dev/feast/tree/91540703c483f1cd03b534a1a45bc4ccdcf79f81/infra/charts/feast-feature-server/samples) directory.
+
+For latest updates please refer the official repository - https://github.com/open-telemetry/opentelemetry-operator
+
+### Deploy Feast 
+Deploy Feast and set `metrics` value to `true`.
+
+Example - 
+```
+helm install feast-release infra/charts/feast-feature-server --set metric=true --set feature_store_yaml_base64=""
+```
+
+## See logs 
+Once the opentelemetry is deployed, you can search the logs to see the required metrics - 
+
+```
+oc logs otelcol-collector-0 | grep "Name: feast_feature_server_memory_usage\|Value: 0.*"
+oc logs otelcol-collector-0 | grep "Name: feast_feature_server_cpu_usage\|Value: 0.*"
+```
+```
+ -> Name: feast_feature_server_memory_usage
+Value: 0.579426
+```
+```
+-> Name: feast_feature_server_cpu_usage
+Value: 0.000000
+```
@@ -0,0 +1,19 @@
+apiVersion: opentelemetry.io/v1alpha1
+kind: Instrumentation
+metadata:
+  name: feast-instrumentation
+spec:
+  exporter:
+    endpoint: <endpoint> # eg: http://{{ .Values.service.name }}-collector.{{ .Release.Namespace }}.svc.cluster.local:4318 
+  env:
+  propagators:
+    - tracecontext
+    - baggage
+  python:
+    env:
+      - name: OTEL_METRICS_EXPORTER
+        value: console,otlp_proto_http
+      - name: OTEL_LOGS_EXPORTER
+        value: otlp_proto_http
+      - name: OTEL_PYTHON_LOGGING_AUTO_INSTRUMENTATION_ENABLED
+        value: "true"
@@ -0,0 +1,53 @@
+# API reference https://github.com/open-telemetry/opentelemetry-operator/blob/main/docs/api.md
+# Refs for v1beta1 config: https://github.com/open-telemetry/opentelemetry-operator/issues/3011#issuecomment-2154118998
+apiVersion: opentelemetry.io/v1beta1
+kind: OpenTelemetryCollector
+metadata:
+  name: otelcol
+spec:
+  mode: statefulset
+  image: otel/opentelemetry-collector-contrib:0.102.1
+  targetAllocator:
+    enabled: true
+    serviceAccount: opentelemetry-targetallocator-sa
+    prometheusCR:
+      enabled: true
+      podMonitorSelector: {}
+      serviceMonitorSelector: {}
+      ## If uncommented, only service monitors with this label will get picked up
+      #   app: feast
+  config:
+    receivers:
+      otlp:
+        protocols:
+          grpc: {}
+          http: {}
+      prometheus:
+        config:
+          scrape_configs:
+            - job_name: 'otelcol-collector'
+              scrape_interval: 10s
+              static_configs:
+              - targets: [ '0.0.0.0:8888' ]
+
+    processors:
+      batch: {}
+
+    exporters:
+      logging:
+        verbosity: detailed
+
+    service:
+      pipelines:
+        traces:
+          receivers: [otlp]
+          processors: [batch]
+          exporters: [logging]
+        metrics:
+          receivers: [otlp, prometheus]
+          processors: []
+          exporters: [logging]
+        logs:
+          receivers: [otlp]
+          processors: [batch]
+          exporters: [logging]
@@ -0,0 +1,16 @@
+apiVersion: monitoring.coreos.com/v1
+kind: ServiceMonitor
+metadata:
+  labels:
+    app: feast
+  name: otel-sm-1
+spec:
+  endpoints:
+    - port: metrics
+  namespaceSelector:
+    matchNames:
+      - <namespace> # helm value - {{ .Release.Namespace }}
+  selector:
+    matchLabels:
+      app.kubernetes.io/component: opentelemetry-collector
+      app.kubernetes.io/managed-by: opentelemetry-operator
@@ -0,0 +1,15 @@
+kind: Prometheus
+metadata:
+  name: prometheus
+spec:
+  evaluationInterval: 30s
+  podMonitorSelector:
+    matchLabels:
+      app: feast
+  portName: web
+  replicas: 1
+  scrapeInterval: 30s
+  serviceAccountName: prometheus-k8s
+  serviceMonitorSelector:
+    matchLabels:
+      app: feast
@@ -0,0 +1,68 @@
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: opentelemetry-targetallocator-sa
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRole
+metadata:
+  name: opentelemetry-targetallocator-role-1
+  annotations:
+    meta.helm.sh/release-name: "feast-release"
+    meta.helm.sh/release-namespace: "feast-val"
+  labels:
+    app.kubernetes.io/managed-by: "Helm"
+rules:
+- apiGroups:
+  - monitoring.coreos.com
+  resources:
+  - servicemonitors
+  - podmonitors
+  verbs:
+  - '*'
+- apiGroups: [""]
+  resources:
+  - namespaces
+  verbs: ["get", "list", "watch"]
+- apiGroups: [""]
+  resources:
+  - nodes
+  - nodes/metrics
+  - services
+  - endpoints
+  - pods
+  verbs: ["get", "list", "watch"]
+- apiGroups: [""]
+  resources:
+  - configmaps
+  verbs: ["get"]
+- apiGroups:
+  - discovery.k8s.io
+  resources:
+  - endpointslices
+  verbs: ["get", "list", "watch"]
+- apiGroups:
+  - networking.k8s.io
+  resources:
+  - ingresses
+  verbs: ["get", "list", "watch"]
+- nonResourceURLs: ["/metrics"]
+  verbs: ["get"]
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRoleBinding
+metadata:
+  name: opentelemetry-targetallocator-rb-1
+  annotations:
+    meta.helm.sh/release-name: "feast-release"
+    meta.helm.sh/release-namespace: "feast-val"
+  labels:
+    app.kubernetes.io/managed-by: "Helm"
+subjects:
+  - kind: ServiceAccount
+    name: opentelemetry-targetallocator-sa
+    namespace: <namespace> # helm value - {{ .Release.Namespace }}
+roleRef:
+  kind: ClusterRole
+  name: opentelemetry-targetallocator-role-1
+  apiGroup: rbac.authorization.k8s.io  
@@ -0,0 +1,16 @@
+apiVersion: monitoring.coreos.com/v1
+kind: ServiceMonitor
+metadata:
+  labels:
+    app: feast
+  name: otel-sm
+spec:
+  endpoints:
+    - port: metrics
+  namespaceSelector:
+    matchNames:
+      - <namespace> # helm value - {{ .Release.Namespace }}
+  selector:
+    matchLabels:
+      app.kubernetes.io/component: opentelemetry-collector
+      app.kubernetes.io/managed-by: opentelemetry-operator 
@@ -14,6 +14,9 @@ spec:
     {{- with .Values.podAnnotations }}
       annotations:
         {{- toYaml . | nindent 8 }}
+        {{- if .Values.metrics.enabled }}
+        instrumentation.opentelemetry.io/inject-python: "true"
+        {{- end }}
     {{- end }}
       labels:
         {{- include "feast-feature-server.selectorLabels" . | nindent 8 }}
@@ -48,10 +51,18 @@ spec:
             - "feast"
             - "serve_registry"
             {{- else }}
+            {{- if .Values.metrics.enlabled }}
             - "feast"
             - "serve"
+            - "--metrics"
             - "-h"
             - "0.0.0.0"
+            {{- else }}
+            - "feast"
+            - "serve"
+            - "-h"
+            - "0.0.0.0"
+            {{- end }}
             {{- end }}
           ports:
             - name: {{ .Values.feast_mode }}
@@ -88,4 +99,4 @@ spec:
       {{- with .Values.tolerations }}
       tolerations:
         {{- toYaml . | nindent 8 }}
-      {{- end }}
+      {{- end }}
@@ -11,5 +11,11 @@ spec:
       targetPort: {{ .Values.feast_mode }}
       protocol: TCP
       name: http
+    {{- if .Values.metrics.enabled }}  
+    - name: metrics
+      port: 8000
+      protocol: TCP
+      targetPort: 8000  # metrics port
+    {{- end }}  
   selector:
     {{- include "feast-feature-server.selectorLabels" . | nindent 4 }}
@@ -15,6 +15,12 @@ imagePullSecrets: []
 nameOverride: ""
 fullnameOverride: ""
 
+metrics:
+  enabled: false
+  otelCollector:
+    endpoint: ""  # sample endpoint: "otel-collector.default.svc.cluster.local:4317"
+    port: 4317
+
 # feature_store_yaml_base64 -- [required] a base64 encoded version of feature_store.yaml
 feature_store_yaml_base64: ""