refactor: remove OpenTelemetry Collector and integrate telemetry service

- Deleted the otel-collector job from GitHub workflows and related deployment configurations. - Updated Helm charts to remove references to the OpenTelemetry Collector, including its deployment and service definitions. - Added gRPC server functionality directly in the telemetry service to handle telemetry ingestion. - Updated environment variables and Docker configurations to reflect the removal of the OpenTelemetry Collector. - Adjusted telemetry service to support both HTTP and gRPC protocols for telemetry data.
2026-04-06 00:32:12 +02:00 · 2026-03-05 09:36:11 +00:00
parent 88a280031b
commit f9c90d7143
19 changed files with 412 additions and 448 deletions
--- a/.github/workflows/build.yml
+++ b/.github/workflows/build.yml
@@ -57,29 +57,6 @@ jobs:
          command: sudo docker build --no-cache -f ./Worker/Dockerfile .


-  docker-build-otel-collector:
-    runs-on: ubuntu-latest
-    env:
-      CI_PIPELINE_ID: ${{github.run_number}}
-    steps:
-      - name: Checkout 
-        uses: actions/checkout@v4
-
-      - name: Preinstall 
-        uses: nick-fields/retry@v3
-        with:
-          timeout_minutes: 10
-          max_attempts: 3
-          command: npm run prerun
-      
-      # build image for accounts service
-      - name: build docker image
-        uses: nick-fields/retry@v3
-        with:
-          timeout_minutes: 45
-          max_attempts: 3
-          command: sudo docker build --no-cache -f ./OTelCollector/Dockerfile .
-
  docker-build-app:
    runs-on: ubuntu-latest
    env:
--- a/.github/workflows/release.yml
+++ b/.github/workflows/release.yml
@@ -423,76 +423,6 @@ jobs:
            --platforms linux/amd64,linux/arm64 \
            --git-sha "${{ github.sha }}"

-  otel-collector-docker-image-deploy:
-    needs: [generate-build-number, read-version]
-    runs-on: ubuntu-latest
-    env:
-      QEMU_CPU: max
-    steps:
-      - name: Free Disk Space (Ubuntu)
-        uses: jlumbroso/free-disk-space@main
-        with:
-          tool-cache: false
-          android: true
-          dotnet: true
-          haskell: true
-          large-packages: true
-          docker-images: true
-          swap-storage: true
-      - name: Docker Meta
-        id: meta
-        uses: docker/metadata-action@v4
-        with:
-          images: |
-            oneuptime/otel-collector
-            ghcr.io/oneuptime/otel-collector
-          tags: |
-            type=raw,value=release,enable=true
-            type=semver,value=${{needs.read-version.outputs.major_minor}},pattern={{version}},enable=true
-
-      - uses: actions/checkout@v4
-        with:
-          ref: ${{ github.ref }}
-
-      - uses: actions/setup-node@v4
-        with:
-          node-version: latest
-
-      - name: Set up QEMU
-        uses: docker/setup-qemu-action@v3
-        with:
-          image: tonistiigi/binfmt:qemu-v10.0.4
-          
-
-
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
-
-      - name: Generate Dockerfile from Dockerfile.tpl
-        run: npm run prerun
-
-      # Build and deploy otel-collector.
-
-      - name: Login to Docker Hub
-        run: |
-          echo "${{ secrets.DOCKERHUB_PASSWORD }}" | docker login --username "${{ secrets.DOCKERHUB_USERNAME }}" --password-stdin
-
-      - name: Login to GitHub Container Registry
-        run: |
-          echo "${{ secrets.GITHUB_TOKEN }}" | docker login ghcr.io --username "${{ github.repository_owner }}" --password-stdin
-
-      - name: Build and push
-        run: |
-          bash ./Scripts/GHA/build_docker_images.sh \
-            --image otel-collector \
-            --version "${{needs.read-version.outputs.major_minor}}" \
-            --dockerfile ./OTelCollector/Dockerfile \
-            --context . \
-            --platforms linux/amd64,linux/arm64 \
-            --git-sha "${{ github.sha }}"
-
-
-
  test-docker-image-deploy:
    needs: [generate-build-number, read-version]
    runs-on: ubuntu-latest
@@ -1001,7 +931,6 @@ jobs:
      - e2e-docker-image-deploy
      - home-docker-image-deploy
      - test-server-docker-image-deploy
-      - otel-collector-docker-image-deploy
      - test-docker-image-deploy
      - telemetry-docker-image-deploy
      - probe-docker-image-deploy
@@ -1020,7 +949,6 @@ jobs:
          "e2e",
          "home",
          "test-server",
-          "otel-collector",
          "test",
          "telemetry",
          "probe",
@@ -1073,7 +1001,7 @@ jobs:

  test-e2e-release-saas:
    runs-on: ubuntu-latest
-    needs: [telemetry-docker-image-deploy, ai-agent-docker-image-deploy, app-docker-image-deploy, home-docker-image-deploy, worker-docker-image-deploy, otel-collector-docker-image-deploy, probe-docker-image-deploy, test-docker-image-deploy, test-server-docker-image-deploy, publish-npm-packages, e2e-docker-image-deploy, helm-chart-deploy, generate-build-number, read-version, nginx-docker-image-deploy]
+    needs: [telemetry-docker-image-deploy, ai-agent-docker-image-deploy, app-docker-image-deploy, home-docker-image-deploy, worker-docker-image-deploy, probe-docker-image-deploy, test-docker-image-deploy, test-server-docker-image-deploy, publish-npm-packages, e2e-docker-image-deploy, helm-chart-deploy, generate-build-number, read-version, nginx-docker-image-deploy]
    env:
      CI_PIPELINE_ID: ${{github.run_number}}
    steps:
@@ -1204,7 +1132,7 @@ jobs:
  test-e2e-release-self-hosted:
    runs-on: ubuntu-latest
    # After all the jobs runs
-    needs: [telemetry-docker-image-deploy, ai-agent-docker-image-deploy, app-docker-image-deploy, home-docker-image-deploy, worker-docker-image-deploy, otel-collector-docker-image-deploy, probe-docker-image-deploy, test-docker-image-deploy, test-server-docker-image-deploy, publish-npm-packages, e2e-docker-image-deploy, helm-chart-deploy, generate-build-number, read-version, nginx-docker-image-deploy]
+    needs: [telemetry-docker-image-deploy, ai-agent-docker-image-deploy, app-docker-image-deploy, home-docker-image-deploy, worker-docker-image-deploy, probe-docker-image-deploy, test-docker-image-deploy, test-server-docker-image-deploy, publish-npm-packages, e2e-docker-image-deploy, helm-chart-deploy, generate-build-number, read-version, nginx-docker-image-deploy]
    env:
      CI_PIPELINE_ID: ${{github.run_number}}
    steps:
--- a/.github/workflows/test-release.yaml
+++ b/.github/workflows/test-release.yaml
@@ -297,76 +297,6 @@ jobs:
            --extra-tags test \
            --extra-enterprise-tags enterprise-test

-  otel-collector-docker-image-deploy:
-    needs: [read-version, generate-build-number]
-    runs-on: ubuntu-latest
-    env:
-      QEMU_CPU: max
-    steps:
-      - name: Free Disk Space (Ubuntu)
-        uses: jlumbroso/free-disk-space@main
-        with:
-          tool-cache: false
-          android: true
-          dotnet: true
-          haskell: true
-          large-packages: true
-          docker-images: true
-          swap-storage: true
-      - name: Docker Meta
-        id: meta
-        uses: docker/metadata-action@v4
-        with:
-          images: |
-            oneuptime/otel-collector
-            ghcr.io/oneuptime/otel-collector
-          tags: |
-            type=raw,value=test,enable=true
-            type=raw,value=${{needs.read-version.outputs.major_minor}}-test,enable=true
-            
-
-      - uses: actions/checkout@v4
-        with:
-          ref: ${{ github.ref }}
-
-      - uses: actions/setup-node@v4
-        with:
-          node-version: latest
-
-      - name: Set up QEMU
-        uses: docker/setup-qemu-action@v3
-        with:
-          image: tonistiigi/binfmt:qemu-v10.0.4
-          
-
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
-
-      - name: Generate Dockerfile from Dockerfile.tpl
-        run: npm run prerun
-
-      # Build and deploy otel-collector.
-
-      - name: Login to Docker Hub
-        run: |
-          echo "${{ secrets.DOCKERHUB_PASSWORD }}" | docker login --username "${{ secrets.DOCKERHUB_USERNAME }}" --password-stdin
-
-      - name: Login to GitHub Container Registry
-        run: |
-          echo "${{ secrets.GITHUB_TOKEN }}" | docker login ghcr.io --username "${{ github.repository_owner }}" --password-stdin
-
-      - name: Build and push
-        run: |
-          bash ./Scripts/GHA/build_docker_images.sh \
-            --image otel-collector \
-            --version "${{needs.read-version.outputs.major_minor}}-test" \
-            --dockerfile ./OTelCollector/Dockerfile \
-            --context . \
-            --platforms linux/amd64,linux/arm64 \
-            --git-sha "${{ github.sha }}" \
-            --extra-tags test \
-            --extra-enterprise-tags enterprise-test
-
  home-docker-image-deploy:
    needs: [read-version, generate-build-number]
    runs-on: ubuntu-latest
@@ -879,7 +809,7 @@ jobs:

  test-helm-chart:
    runs-on: ubuntu-latest
-    needs: [infrastructure-agent-deploy, publish-terraform-provider, telemetry-docker-image-deploy, worker-docker-image-deploy, home-docker-image-deploy, test-server-docker-image-deploy, test-docker-image-deploy, probe-docker-image-deploy, app-docker-image-deploy, ai-agent-docker-image-deploy, otel-collector-docker-image-deploy, nginx-docker-image-deploy, e2e-docker-image-deploy]
+    needs: [infrastructure-agent-deploy, publish-terraform-provider, telemetry-docker-image-deploy, worker-docker-image-deploy, home-docker-image-deploy, test-server-docker-image-deploy, test-docker-image-deploy, probe-docker-image-deploy, app-docker-image-deploy, ai-agent-docker-image-deploy, nginx-docker-image-deploy, e2e-docker-image-deploy]
    env:
      CI_PIPELINE_ID: ${{github.run_number}}
    steps:
--- a/HelmChart/Public/oneuptime/templates/_helpers.tpl
+++ b/HelmChart/Public/oneuptime/templates/_helpers.tpl
@@ -113,8 +113,6 @@ Usage:
  value: {{ $.Release.Name }}-telemetry.{{ $.Release.Namespace }}.svc.{{ $.Values.global.clusterDomain }}
 - name: SERVER_TELEMETRY_HOSTNAME
  value: {{ $.Release.Name }}-telemetry.{{ $.Release.Namespace }}.svc.{{ $.Values.global.clusterDomain }}
- name: SERVER_OTEL_COLLECTOR_HOSTNAME
-  value: {{ $.Release.Name }}-otel-collector.{{ $.Release.Namespace }}.svc.{{ $.Values.global.clusterDomain }}
 - name: APP_PORT
  value: {{ $.Values.app.ports.http | squote }}
 - name: TELEMETRY_PORT
--- a/HelmChart/Public/oneuptime/templates/otel-collector.yaml
+++ b/HelmChart/Public/oneuptime/templates/otel-collector.yaml
@@ -1,147 +1 @@
-{{- if $.Values.openTelemetryCollector.enabled }}
-# OneUptime otel-collector Deployment
-
-apiVersion: apps/v1
-kind: Deployment
-metadata:
-  name: {{ printf "%s-%s" $.Release.Name "otel-collector"  }}
-  namespace: {{ $.Release.Namespace }}
-  labels:
-    app: {{ printf "%s-%s" $.Release.Name "otel-collector"  }}
-    app.kubernetes.io/part-of: oneuptime
-    app.kubernetes.io/managed-by: Helm
-    appname: oneuptime
-    {{- if $.Values.deployment.includeTimestampLabel }}
-    date: "{{ now | unixEpoch }}"
-    {{- end }}
-spec:
-  selector:
-    matchLabels:
-      app: {{ printf "%s-%s" $.Release.Name "otel-collector"  }}
-  {{- if $.Values.openTelemetryCollector.replicaCount }}
-  replicas: {{ $.Values.openTelemetryCollector.replicaCount }}
-  {{- else }}
-  {{- if or (not $.Values.autoscaling.enabled) ($.Values.openTelemetryCollector.disableAutoscaler) }}
-  replicas: {{ $.Values.deployment.replicaCount }}
-  {{- end }}
-  {{- end }}
-  strategy: {{- toYaml $.Values.deployment.updateStrategy | nindent 4 }}
-  template:
-    metadata:
-      labels:
-        app: {{ printf "%s-%s" $.Release.Name "otel-collector"  }}
-        {{- if $.Values.deployment.includeTimestampLabel }}
-        date: "{{ now | unixEpoch }}"
-        {{- end }}
-        appname: oneuptime
-    spec:
-      volumes:
-        - name: greenlockrc
-          emptyDir:
-            sizeLimit: "1Gi"
-      {{- if $.Values.openTelemetryCollector.podSecurityContext }}
-      securityContext:
-        {{- toYaml $.Values.openTelemetryCollector.podSecurityContext | nindent 8 }}
-      {{- else if $.Values.podSecurityContext }}
-      securityContext:
-        {{- toYaml $.Values.podSecurityContext | nindent 8 }}
-      {{- end }}
-      {{- if $.Values.imagePullSecrets }}
-      imagePullSecrets:
-        {{- toYaml $.Values.imagePullSecrets | nindent 8 }}
-      {{- end }}
-      {{- if $.Values.affinity }}
-      affinity: {{- $.Values.affinity | toYaml | nindent 8 }}
-      {{- end }}
-      {{- if $.Values.tolerations }}
-      tolerations: {{- $.Values.tolerations | toYaml | nindent 8 }}
-      {{- end }}
-      {{- if $.Values.openTelemetryCollector.nodeSelector }}
-      nodeSelector:
-        {{- toYaml $.Values.openTelemetryCollector.nodeSelector | nindent 8 }}
-      {{- else if $.Values.nodeSelector }}
-      nodeSelector:
-        {{- toYaml $.Values.nodeSelector | nindent 8 }}
-      {{- end }}
-      containers:
-        - image: {{ include "oneuptime.image" (dict "Values" $.Values "ServiceName" "otel-collector") }}
-          name: {{ printf "%s-%s" $.Release.Name "otel-collector"  }}
-          # Liveness probe
-          {{- if $.Values.startupProbe.enabled }}
-          # Startup probe
-          startupProbe:
-            httpGet:
-              path: /health/status
-              port: 13133
-            periodSeconds: {{ $.Values.startupProbe.periodSeconds }}
-            failureThreshold: {{ $.Values.startupProbe.failureThreshold }}
-          {{- end }}
-          {{- if $.Values.livenessProbe.enabled }}
-          # Liveness probe
-          livenessProbe:
-            httpGet:
-              path: /health/status
-              port: 13133
-            periodSeconds: {{ $.Values.livenessProbe.periodSeconds }}
-            timeoutSeconds: {{ $.Values.livenessProbe.timeoutSeconds }}
-            initialDelaySeconds: {{ $.Values.livenessProbe.initialDelaySeconds }}
-          {{- end }}
-          {{- if $.Values.readinessProbe.enabled }}
-          # Readyness Probe
-          readinessProbe:
-            httpGet:
-              path: /health/status
-              port: 13133
-            periodSeconds: {{ $.Values.readinessProbe.periodSeconds }}
-            initialDelaySeconds: {{ $.Values.readinessProbe.initialDelaySeconds }}
-            timeoutSeconds: {{ $.Values.readinessProbe.timeoutSeconds }}
-          {{- end }}
-          {{- if $.Values.openTelemetryCollector.containerSecurityContext }}
-          securityContext:
-            {{- toYaml $.Values.openTelemetryCollector.containerSecurityContext | nindent 12 }}
-          {{- else if $.Values.containerSecurityContext }}
-          securityContext:
-            {{- toYaml $.Values.containerSecurityContext | nindent 12 }}
-          {{- end }}
-          imagePullPolicy: {{ $.Values.image.pullPolicy }}
-          env:
-            {{- include "oneuptime.env.common" . | nindent 12 }}
-            {{- include "oneuptime.env.runtime" (dict "Values" $.Values "Release" $.Release) | nindent 12 }}
-            - name: PORT
-              value: {{ $.Values.openTelemetryCollector.ports.grpc | quote }}
-            - name: OPENTELEMETRY_COLLECTOR_SENDING_QUEUE_ENABLED
-              value: {{ $.Values.openTelemetryCollector.sendingQueue.enabled | quote }}
-            - name: OPENTELEMETRY_COLLECTOR_SENDING_QUEUE_NUM_CONSUMERS
-              value: {{ $.Values.openTelemetryCollector.sendingQueue.numConsumers | quote }}
-            - name: OPENTELEMETRY_COLLECTOR_SENDING_QUEUE_SIZE
-              value: {{ $.Values.openTelemetryCollector.sendingQueue.size | quote }}
-            - name: DISABLE_TELEMETRY
-              value: {{ $.Values.openTelemetryCollector.disableTelemetryCollection | quote }}
-          ports:
-            - containerPort: {{ $.Values.openTelemetryCollector.ports.http }}
-              protocol: TCP
-              name: http
-            - containerPort: {{ $.Values.openTelemetryCollector.ports.grpc }}
-              protocol: TCP
-              name: grpc
-          {{- if $.Values.openTelemetryCollector.resources }}
-          resources:
-            {{- toYaml $.Values.openTelemetryCollector.resources | nindent 12 }}
-          {{- end }}
-      restartPolicy: {{ $.Values.image.restartPolicy }}
---
-
-# OneUptime otel-collector autoscaler
-{{- if not $.Values.openTelemetryCollector.disableAutoscaler }}
-{{- $identityAutoScalerArgs := dict "ServiceName" "otel-collector" "Release" $.Release "Values" $.Values -}}
-{{- include "oneuptime.autoscaler" $identityAutoScalerArgs }}
-{{- end }}
---
-
-{{- end }}
-
-# OneUptime otel-collector Service
-{{- $otelCollectorPorts := dict "grpc" $.Values.openTelemetryCollector.ports.grpc "http" $.Values.openTelemetryCollector.ports.http -}}
-{{- $identityServiceArgs := dict "ServiceName" "otel-collector" "Ports" $otelCollectorPorts "Release" $.Release "Values" $.Values -}}
-{{- include "oneuptime.service" $identityServiceArgs }}
---
+{{- /* OTel Collector has been removed. Telemetry ingestion (gRPC + HTTP) is now handled directly by the telemetry service. */ -}}
--- a/HelmChart/Public/oneuptime/templates/telemetry.yaml
+++ b/HelmChart/Public/oneuptime/templates/telemetry.yaml
@@ -117,6 +117,9 @@ spec:
            - containerPort: {{ $.Values.telemetry.ports.http }}
              protocol: TCP
              name: http
+            - containerPort: {{ $.Values.telemetry.ports.grpc }}
+              protocol: TCP
+              name: grpc
          {{- if $.Values.telemetry.resources }}
          resources:
            {{- toYaml $.Values.telemetry.resources | nindent 12 }}
@@ -135,7 +138,7 @@ spec:
 ---

 # OneUptime telemetry Service
-{{- $telemetryPorts := dict "port" $.Values.telemetry.ports.http -}}
+{{- $telemetryPorts := dict "http" $.Values.telemetry.ports.http "grpc" $.Values.telemetry.ports.grpc -}}
 {{- $telemetryServiceArgs := dict "ServiceName" "telemetry" "Ports" $telemetryPorts "Release" $.Release "Values" $.Values -}}
 {{- include "oneuptime.service" $telemetryServiceArgs }}
 ---
--- a/HelmChart/Public/oneuptime/values.schema.json
+++ b/HelmChart/Public/oneuptime/values.schema.json
@@ -1262,63 +1262,6 @@
      },
      "additionalProperties": false
    },
-    "openTelemetryCollector": {
-      "type": "object",
-      "properties": {
-        "enabled": {
-          "type": "boolean"
-        },
-        "replicaCount": {
-          "type": "integer"
-        },
-        "disableTelemetryCollection": {
-          "type": "boolean"
-        },
-        "disableAutoscaler": {
-          "type": "boolean"
-        },
-        "ports": {
-          "type": "object",
-          "properties": {
-            "grpc": {
-              "type": "integer"
-            },
-            "http": {
-              "type": "integer"
-            }
-          },
-          "additionalProperties": false
-        },
-        "sendingQueue": {
-          "type": "object",
-          "properties": {
-            "enabled": {
-              "type": "boolean"
-            },
-            "size": {
-              "type": "integer"
-            },
-            "numConsumers": {
-              "type": "integer"
-            }
-          },
-          "additionalProperties": false
-        },
-        "resources": {
-          "type": ["object", "null"]
-        },
-        "nodeSelector": {
-          "type": "object"
-        },
-        "podSecurityContext": {
-          "type": "object"
-        },
-        "containerSecurityContext": {
-          "type": "object"
-        }
-      },
-      "additionalProperties": false
-    },
    "home": {
      "type": "object",
      "properties": {
@@ -1528,6 +1471,9 @@
          "properties": {
            "http": {
              "type": "integer"
+            },
+            "grpc": {
+              "type": "integer"
            }
          },
          "additionalProperties": false
--- a/HelmChart/Public/oneuptime/values.yaml
+++ b/HelmChart/Public/oneuptime/values.yaml
@@ -558,25 +558,6 @@ readinessProbe: # Readiness probe configuration
  initialDelaySeconds: 10
  timeoutSeconds: 120

-# OpenTelemetry Collector Configuration
-openTelemetryCollector:
-  enabled: true
-  replicaCount: 1
-  disableTelemetryCollection: false
-  disableAutoscaler: false
-  ports:
-    grpc: 4317
-    http: 4318
-  sendingQueue:
-    enabled: true
-    size: 1000
-    numConsumers: 3
-  resources: {}
-  nodeSelector: {}
-  podSecurityContext: {}
-  containerSecurityContext: {}
-
-
 home:
  enabled: true
  replicaCount: 1
@@ -636,6 +617,7 @@ telemetry:
  concurrency: 100
  ports:
    http: 3403
+    grpc: 4317
  resources:
  nodeSelector: {}
  podSecurityContext: {}
--- a/Nginx/default.conf.template
+++ b/Nginx/default.conf.template
@@ -19,12 +19,8 @@ upstream home {
    server ${SERVER_HOME_HOSTNAME}:${HOME_PORT} weight=10 max_fails=3 fail_timeout=30s;
 }

-upstream opentelemetry-collector-http {
-    server ${SERVER_OTEL_COLLECTOR_HOSTNAME}:4318;
-}
-
-upstream opentelemetry-collector-grpc {
-    server ${SERVER_OTEL_COLLECTOR_HOSTNAME}:4317;
+upstream opentelemetry-grpc {
+    server ${SERVER_TELEMETRY_HOSTNAME}:4317;
 }

 # Status Pages
@@ -472,12 +468,12 @@ ${PROVISION_SSL_CERTIFICATE_KEY_DIRECTIVE}

    location /otlp/ {

-        # This is for nginx not to crash when service is not available. 
+        # This is for nginx not to crash when service is not available.
        resolver 127.0.0.1 valid=30s;
        proxy_set_header Host $host;
        proxy_set_header X-Real-IP $remote_addr;
        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
-        proxy_set_header X-Forwarded-Proto $scheme; 
+        proxy_set_header X-Forwarded-Proto $scheme;

        # enable WebSockets (for ws://sockjs not connected error in the accounts source: https://stackoverflow.com/questions/41381444/websocket-connection-failed-error-during-websocket-handshake-unexpected-respon)
        proxy_http_version 1.1;
@@ -485,14 +481,14 @@ ${PROVISION_SSL_CERTIFICATE_KEY_DIRECTIVE}
        proxy_set_header Connection "upgrade";


-        proxy_pass http://opentelemetry-collector-http/;
+        proxy_pass http://telemetry/otlp/;
    }


    location ~ /opentelemetry.proto.collector* {
-        # This is for nginx not to crash when service is not available. 
+        # This is for nginx not to crash when service is not available.
        resolver 127.0.0.1 valid=30s;
-        grpc_pass grpc://opentelemetry-collector-grpc;
+        grpc_pass grpc://opentelemetry-grpc;
    }

    location /notification {
--- a/Telemetry/GrpcServer.ts
+++ b/Telemetry/GrpcServer.ts
@@ -0,0 +1,262 @@
+import * as grpc from "@grpc/grpc-js";
+import * as protoLoader from "@grpc/proto-loader";
+import path from "path";
+import logger from "Common/Server/Utils/Logger";
+import ObjectID from "Common/Types/ObjectID";
+import ProductType from "Common/Types/MeteredPlan/ProductType";
+import TelemetryIngestionKeyService from "Common/Server/Services/TelemetryIngestionKeyService";
+import TelemetryIngestionKey from "Common/Models/DatabaseModels/TelemetryIngestionKey";
+import { TelemetryRequest } from "Common/Server/Middleware/TelemetryIngest";
+import TracesQueueService from "./Services/Queue/TracesQueueService";
+import LogsQueueService from "./Services/Queue/LogsQueueService";
+import MetricsQueueService from "./Services/Queue/MetricsQueueService";
+
+const GRPC_PORT: number = 4317;
+
+const PROTO_DIR: string = path.resolve(
+  __dirname,
+  "ProtoFiles",
+  "OTel",
+  "v1",
+);
+
+type GrpcCallback = (
+  error: grpc.ServiceError | null,
+  response?: Record<string, unknown>,
+) => void;
+
+interface GrpcCall {
+  request: Record<string, unknown>;
+  metadata: grpc.Metadata;
+}
+
+async function authenticateRequest(
+  metadata: grpc.Metadata,
+): Promise<ObjectID | null> {
+  const tokenValues: grpc.MetadataValue[] =
+    metadata.get("x-oneuptime-token");
+
+  let oneuptimeToken: string | undefined = tokenValues[0]?.toString();
+
+  if (!oneuptimeToken) {
+    const serviceTokenValues: grpc.MetadataValue[] = metadata.get(
+      "x-oneuptime-service-token",
+    );
+    oneuptimeToken = serviceTokenValues[0]?.toString();
+  }
+
+  if (!oneuptimeToken) {
+    logger.error("gRPC: Missing metadata: x-oneuptime-token");
+    return null;
+  }
+
+  const token: TelemetryIngestionKey | null =
+    await TelemetryIngestionKeyService.findOneBy({
+      query: {
+        secretKey: new ObjectID(oneuptimeToken),
+      },
+      select: {
+        projectId: true,
+      },
+      props: {
+        isRoot: true,
+      },
+    });
+
+  if (!token || !token.projectId) {
+    logger.error("gRPC: Invalid service token: " + oneuptimeToken);
+    return null;
+  }
+
+  return token.projectId as ObjectID;
+}
+
+function buildTelemetryRequest(
+  body: Record<string, unknown>,
+  metadata: grpc.Metadata,
+  projectId: ObjectID,
+  productType: ProductType,
+): TelemetryRequest {
+  const headers: Record<string, string> = {};
+
+  for (const key of metadata.keys()) {
+    const values: grpc.MetadataValue[] = metadata.get(key);
+    if (values.length > 0) {
+      headers[key] = values[0]!.toString();
+    }
+  }
+
+  const req: Partial<TelemetryRequest> = {
+    body: body,
+    headers: headers,
+    projectId: projectId,
+    productType: productType,
+    path: `/otlp/v1/${productType}`,
+    url: `/otlp/v1/${productType}`,
+  };
+
+  return req as TelemetryRequest;
+}
+
+async function handleExport(
+  call: GrpcCall,
+  callback: GrpcCallback,
+  productType: ProductType,
+  queueFn: (req: TelemetryRequest) => Promise<void>,
+): Promise<void> {
+  try {
+    const projectId: ObjectID | null = await authenticateRequest(
+      call.metadata,
+    );
+
+    if (!projectId) {
+      // Return success to avoid OTel SDK retries
+      callback(null, {});
+      return;
+    }
+
+    const body: Record<string, unknown> = call.request;
+
+    const req: TelemetryRequest = buildTelemetryRequest(
+      body,
+      call.metadata,
+      projectId,
+      productType,
+    );
+
+    await queueFn(req);
+
+    callback(null, {});
+  } catch (err) {
+    logger.error(`gRPC ${productType} export error:`);
+    logger.error(err);
+    // Return success to avoid OTel SDK retries
+    callback(null, {});
+  }
+}
+
+export function startGrpcServer(): void {
+  const traceServiceDef: protoLoader.PackageDefinition = protoLoader.loadSync(
+    path.join(PROTO_DIR, "trace_service.proto"),
+    {
+      keepCase: false,
+      longs: String,
+      enums: String,
+      defaults: true,
+      oneofs: true,
+      includeDirs: [PROTO_DIR],
+    },
+  );
+
+  const logsServiceDef: protoLoader.PackageDefinition = protoLoader.loadSync(
+    path.join(PROTO_DIR, "logs_service.proto"),
+    {
+      keepCase: false,
+      longs: String,
+      enums: String,
+      defaults: true,
+      oneofs: true,
+      includeDirs: [PROTO_DIR],
+    },
+  );
+
+  const metricsServiceDef: protoLoader.PackageDefinition =
+    protoLoader.loadSync(
+      path.join(PROTO_DIR, "metrics_service.proto"),
+      {
+        keepCase: false,
+        longs: String,
+        enums: String,
+        defaults: true,
+        oneofs: true,
+        includeDirs: [PROTO_DIR],
+      },
+    );
+
+  const traceProto: grpc.GrpcObject =
+    grpc.loadPackageDefinition(traceServiceDef);
+  const logsProto: grpc.GrpcObject =
+    grpc.loadPackageDefinition(logsServiceDef);
+  const metricsProto: grpc.GrpcObject =
+    grpc.loadPackageDefinition(metricsServiceDef);
+
+  type ProtoServiceDef = {
+    service: grpc.ServiceDefinition;
+  };
+
+  function getServiceDefinition(
+    proto: grpc.GrpcObject,
+    ...path: Array<string>
+  ): grpc.ServiceDefinition {
+    let current: unknown = proto;
+    for (const key of path) {
+      current = (current as Record<string, unknown>)[key];
+    }
+    return (current as ProtoServiceDef).service;
+  }
+
+  const traceServiceDefinition: grpc.ServiceDefinition = getServiceDefinition(
+    traceProto,
+    "opentelemetry", "proto", "collector", "trace", "v1", "TraceService",
+  );
+
+  const logsServiceDefinition: grpc.ServiceDefinition = getServiceDefinition(
+    logsProto,
+    "opentelemetry", "proto", "collector", "logs", "v1", "LogsService",
+  );
+
+  const metricsServiceDefinition: grpc.ServiceDefinition = getServiceDefinition(
+    metricsProto,
+    "opentelemetry", "proto", "collector", "metrics", "v1", "MetricsService",
+  );
+
+  const server: grpc.Server = new grpc.Server({
+    "grpc.max_receive_message_length": 50 * 1024 * 1024, // 50MB
+  });
+
+  server.addService(traceServiceDefinition, {
+    Export: (call: GrpcCall, callback: GrpcCallback): void => {
+      handleExport(
+        call,
+        callback,
+        ProductType.Traces,
+        TracesQueueService.addTraceIngestJob.bind(TracesQueueService),
+      );
+    },
+  });
+
+  server.addService(logsServiceDefinition, {
+    Export: (call: GrpcCall, callback: GrpcCallback): void => {
+      handleExport(
+        call,
+        callback,
+        ProductType.Logs,
+        LogsQueueService.addLogIngestJob.bind(LogsQueueService),
+      );
+    },
+  });
+
+  server.addService(metricsServiceDefinition, {
+    Export: (call: GrpcCall, callback: GrpcCallback): void => {
+      handleExport(
+        call,
+        callback,
+        ProductType.Metrics,
+        MetricsQueueService.addMetricIngestJob.bind(MetricsQueueService),
+      );
+    },
+  });
+
+  server.bindAsync(
+    `0.0.0.0:${GRPC_PORT}`,
+    grpc.ServerCredentials.createInsecure(),
+    (err: Error | null, port: number): void => {
+      if (err) {
+        logger.error("Failed to start gRPC server:");
+        logger.error(err);
+        return;
+      }
+      logger.info(`gRPC OTLP server started on port: ${port}`);
+    },
+  );
+}
--- a/Telemetry/Index.ts
+++ b/Telemetry/Index.ts
@@ -24,6 +24,7 @@ import Telemetry from "Common/Server/Utils/Telemetry";
 import "./Jobs/TelemetryIngest/ProcessTelemetry";
 import { TELEMETRY_CONCURRENCY } from "./Config";
 import type { StatusAPIOptions } from "Common/Server/API/StatusAPI";
+import { startGrpcServer } from "./GrpcServer";
 import "ejs";

 const app: ExpressApplication = Express.getExpressApp();
@@ -104,6 +105,10 @@ const init: PromiseVoidFunction = async (): Promise<void> => {
    );

    await Realtime.init();
+
+    // Start gRPC OTLP server on port 4317
+    startGrpcServer();
+
    // add default routes
    await App.addDefaultRoutes();
  } catch (err) {
--- a/Telemetry/ProtoFiles/OTel/v1/logs_service.proto
+++ b/Telemetry/ProtoFiles/OTel/v1/logs_service.proto
@@ -0,0 +1,41 @@
+// Copyright 2020, OpenTelemetry Authors
+//
+// Licensed under the Apache License, Version 2.0 (the "License");
+// you may not use this file except in compliance with the License.
+// You may obtain a copy of the License at
+//
+//     http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+
+syntax = "proto3";
+
+package opentelemetry.proto.collector.logs.v1;
+
+import "./logs.proto";
+
+option java_multiple_files = true;
+option java_package = "io.opentelemetry.proto.collector.logs.v1";
+option java_outer_classname = "LogsServiceProto";
+option go_package = "go.opentelemetry.io/proto/otlp/collector/logs/v1";
+
+service LogsService {
+  rpc Export(ExportLogsServiceRequest) returns (ExportLogsServiceResponse) {}
+}
+
+message ExportLogsServiceRequest {
+  repeated opentelemetry.proto.logs.v1.ResourceLogs resource_logs = 1;
+}
+
+message ExportLogsServiceResponse {
+  ExportLogsPartialSuccess partial_success = 1;
+}
+
+message ExportLogsPartialSuccess {
+  int64 rejected_log_records = 1;
+  string error_message = 2;
+}
--- a/Telemetry/ProtoFiles/OTel/v1/metrics_service.proto
+++ b/Telemetry/ProtoFiles/OTel/v1/metrics_service.proto
@@ -0,0 +1,41 @@
+// Copyright 2019, OpenTelemetry Authors
+//
+// Licensed under the Apache License, Version 2.0 (the "License");
+// you may not use this file except in compliance with the License.
+// You may obtain a copy of the License at
+//
+//     http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+
+syntax = "proto3";
+
+package opentelemetry.proto.collector.metrics.v1;
+
+import "./metrics.proto";
+
+option java_multiple_files = true;
+option java_package = "io.opentelemetry.proto.collector.metrics.v1";
+option java_outer_classname = "MetricsServiceProto";
+option go_package = "go.opentelemetry.io/proto/otlp/collector/metrics/v1";
+
+service MetricsService {
+  rpc Export(ExportMetricsServiceRequest) returns (ExportMetricsServiceResponse) {}
+}
+
+message ExportMetricsServiceRequest {
+  repeated opentelemetry.proto.metrics.v1.ResourceMetrics resource_metrics = 1;
+}
+
+message ExportMetricsServiceResponse {
+  ExportMetricsPartialSuccess partial_success = 1;
+}
+
+message ExportMetricsPartialSuccess {
+  int64 rejected_data_points = 1;
+  string error_message = 2;
+}
--- a/Telemetry/ProtoFiles/OTel/v1/trace_service.proto
+++ b/Telemetry/ProtoFiles/OTel/v1/trace_service.proto
@@ -0,0 +1,41 @@
+// Copyright 2019, OpenTelemetry Authors
+//
+// Licensed under the Apache License, Version 2.0 (the "License");
+// you may not use this file except in compliance with the License.
+// You may obtain a copy of the License at
+//
+//     http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+
+syntax = "proto3";
+
+package opentelemetry.proto.collector.trace.v1;
+
+import "./traces.proto";
+
+option java_multiple_files = true;
+option java_package = "io.opentelemetry.proto.collector.trace.v1";
+option java_outer_classname = "TraceServiceProto";
+option go_package = "go.opentelemetry.io/proto/otlp/collector/trace/v1";
+
+service TraceService {
+  rpc Export(ExportTraceServiceRequest) returns (ExportTraceServiceResponse) {}
+}
+
+message ExportTraceServiceRequest {
+  repeated opentelemetry.proto.trace.v1.ResourceSpans resource_spans = 1;
+}
+
+message ExportTraceServiceResponse {
+  ExportTracePartialSuccess partial_success = 1;
+}
+
+message ExportTracePartialSuccess {
+  int64 rejected_spans = 1;
+  string error_message = 2;
+}
--- a/Telemetry/package.json
+++ b/Telemetry/package.json
@@ -19,6 +19,8 @@
    "author": "OneUptime <hello@oneuptime.com> (https://oneuptime.com/)",
    "license": "Apache-2.0",
    "dependencies": {
+        "@grpc/grpc-js": "^1.12.5",
+        "@grpc/proto-loader": "^0.7.13",
        "Common": "file:../Common",
        "ejs": "^3.1.10",
        "protobufjs": "^7.3.2",
--- a/config.example.env
+++ b/config.example.env
@@ -96,14 +96,12 @@ TELEMETRY_HOSTNAME=telemetry:3403

 SERVER_APP_HOSTNAME=app
 SERVER_TELEMETRY_HOSTNAME=telemetry
-SERVER_OTEL_COLLECTOR_HOSTNAME=otel-collector
 SERVER_WORKER_HOSTNAME=worker
 #Ports. Usually they don't need to change.

 APP_PORT=3002
 TELEMETRY_PORT=3403
 TEST_SERVER_PORT=3800
-OTEL_COLLECTOR_HTTP_PORT=4318
 HOME_PORT=1444
 WORKER_PORT=1445
 # Plans
@@ -193,7 +191,7 @@ DISABLE_AUTOMATIC_ALERT_CREATION=false

 # If you're using an extrenal open telemetry collector, you can set the endpoint here - both server and client endpoint can be the same in this case. 

-# You can set the env var to http://otel-collector:4318 if you want instrumentation to be sent to otel collector.
+# You can set the env var to an OTLP endpoint if you want instrumentation to be exported.
 OPENTELEMETRY_EXPORTER_OTLP_ENDPOINT=

 # You can set the env var to "x-oneuptime-token=<YOUR_ONEUPTIME_TELEMETRY_INGEST_TOKEN>"
@@ -295,19 +293,12 @@ DISABLE_TELEMETRY_FOR_STATUS_PAGE=true
 DISABLE_TELEMETRY_FOR_DASHBOARD=true
 DISABLE_TELEMETRY_FOR_PROBE=true
 DISABLE_TELEMETRY_FOR_ADMIN_DASHBOARD=true
-DISABLE_TELEMETRY_FOR_OTEL_COLLECTOR=true
 DISABLE_TELEMETRY_FOR_INGRESS=true
 DISABLE_TELEMETRY_FOR_WORKER=true

 DISABLE_TELEMETRY_FOR_AI_AGENT=true


-# OPENTELEMETRY_COLLECTOR env vars
-OPENTELEMETRY_COLLECTOR_SENDING_QUEUE_ENABLED=true
-OPENTELEMETRY_COLLECTOR_SENDING_QUEUE_SIZE=1000
-OPENTELEMETRY_COLLECTOR_SENDING_QUEUE_NUM_CONSUMERS=3
-
-
 # Connect OneUptime with Slack App
 SLACK_APP_CLIENT_ID=
 SLACK_APP_CLIENT_SECRET=
--- a/docker-compose.base.yml
+++ b/docker-compose.base.yml
@@ -30,7 +30,6 @@ x-common-variables: &common-variables

    SERVER_APP_HOSTNAME: app
    SERVER_TELEMETRY_HOSTNAME: telemetry
-    SERVER_OTEL_COLLECTOR_HOSTNAME: otel-collector
    SERVER_WORKER_HOSTNAME: worker
    SERVER_HOME_HOSTNAME: home
    #Ports. Usually they don't need to change.
@@ -335,23 +334,6 @@ services:
            options:
                max-size: "1000m"

-    otel-collector:
-        networks:
-          - oneuptime
-        environment:
-            <<: *common-variables
-            DISABLE_TELEMETRY: ${DISABLE_TELEMETRY_FOR_OTEL_COLLECTOR}
-            OPENTELEMETRY_COLLECTOR_SENDING_QUEUE_ENABLED: ${OPENTELEMETRY_COLLECTOR_SENDING_QUEUE_ENABLED}
-            OPENTELEMETRY_COLLECTOR_SENDING_QUEUE_SIZE: ${OPENTELEMETRY_COLLECTOR_SENDING_QUEUE_SIZE}
-            OPENTELEMETRY_COLLECTOR_SENDING_QUEUE_NUM_CONSUMERS: ${OPENTELEMETRY_COLLECTOR_SENDING_QUEUE_NUM_CONSUMERS}
-        restart: always
-        logging:
-            driver: "local"
-            options:
-                max-size: "1000m"
-        ports: 
-          - 13133:13133 # Otel Collector Health Check Endpoint at /heath/status
-
    fluentd:
        networks:
          - oneuptime
--- a/docker-compose.dev.yml
+++ b/docker-compose.dev.yml
@@ -36,15 +36,6 @@ services:
            service: postgres


-    otel-collector:
-        extends:
-            file: ./docker-compose.base.yml
-            service: otel-collector
-        build:
-            network: host
-            context: .
-            dockerfile: ./OTelCollector/Dockerfile
-
    test-server:
        volumes:
            - ./TestServer:/usr/src/app:cached
--- a/docker-compose.yml
+++ b/docker-compose.yml
@@ -29,12 +29,6 @@ services:
            service: postgres


-    otel-collector:
-        image:  oneuptime/otel-collector:${APP_TAG}
-        extends:
-            file: ./docker-compose.base.yml
-            service: otel-collector
-
    app:
        image:  oneuptime/app:${APP_TAG}
        extends: