feat: add docker-compose file for dev and prod

add script for zero downtime deployment
NFDI4Chem · Aug 4, 2023 · 631eefc · 631eefc
1 parent b25ada4
commit 631eefc
Show file tree

Hide file tree

Showing 4 changed files with 323 additions and 2 deletions.
diff --git a/.github/workflows/prod-build.yml b/.github/workflows/prod-build.yml
@@ -1,7 +1,7 @@
 
 # This worklflow will perform following actions when the code is pushed to main branch:
 # - Build the latest docker image in development which needs test to pass first.
-# - Push the docker image to Docker Hub under namespace - caffeinejena with tag:[release_version].
+# - Push the docker image to Docker Hub under namespace - nfdi4chem with tag:[release_version].
 # 
 # Maintainers:
 #   - name: Nisha Sharma
@@ -17,7 +17,7 @@ env:
   DOCKER_HUB_USERNAME : ${{ secrets.DOCKER_USERNAME  }}
   DOCKER_HUB_PASSWORD : ${{ secrets.DOCKER_PASSWORD  }}
   REPOSITORY_NAME: nmrkit
-  REPOSITORY_NAMESPACE: caffeinejena
+  REPOSITORY_NAMESPACE: nfdi4chem
 
 jobs:
   push_to_registry:

diff --git a/ops/docker-compose-dev.yml b/ops/docker-compose-dev.yml
@@ -0,0 +1,117 @@
+version: "3.8"
+
+services:
+  traefik:
+    image: traefik:v2.10
+    container_name: traefik
+    command:
+      - "--api.insecure=true"
+      - "--providers.docker=true"
+      - "--providers.docker.exposedbydefault=false"
+      - "--entrypoints.web.address=:80"
+    ports:
+      - 80:80
+     # - 8080:8080 # Optional: Expose Traefik dashboard on port 8080
+    volumes:
+      - /var/run/docker.sock:/var/run/docker.sock
+
+  web:
+    image: nfdi4chem/nmrkit:dev-latest
+    pull_policy: always
+    labels:
+      - "traefik.enable=true"
+      - "traefik.http.routers.web.rule=Host(`dev.nmrkit.nmrxiv.org`)"
+      - "traefik.http.routers.web.entrypoints=web"
+      - "traefik.http.services.web.loadbalancer.server.port=80"
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:80/latest/registration/health"]
+      interval: 1m
+      timeout: 10s
+      retries: 10
+      start_period: 40s
+    env_file:
+      - ./.env
+
+  prometheus:
+    image: prom/prometheus
+    container_name: nmrkit_prometheus
+    ports:
+      - 9090:9090
+    volumes:
+      - ./../prometheus_data/prometheus.yml:/etc/prometheus/prometheus.yml
+    command:
+      - '--config.file=/etc/prometheus/prometheus.yml'
+
+  grafana:
+    image: grafana/grafana
+    container_name: nmrkit_grafana
+    ports:
+      - 3000:3000
+    volumes:
+      - /mnt/data/grafana_data:/var/lib/grafana
+
+  redis:
+    image: "redis:alpine"
+    ports:
+        - "${FORWARD_REDIS_PORT:-6379}:6379"
+    volumes:
+        - "/mnt/data/redis:/data"
+    networks:
+        - default
+    healthcheck:
+        test: ["CMD", "redis-cli", "ping"]
+        retries: 3
+        timeout: 5s
+
+  pgsql:
+    image: "informaticsmatters/rdkit-cartridge-debian"
+    ports:
+      - "${FORWARD_DB_PORT:-5432}:5432"
+    env_file:
+      - ./.env
+    volumes:
+      - "/mnt/data/pgsql:/var/lib/postgresql/data"
+    networks:
+      - default
+    healthcheck:
+      test:
+        [
+            "CMD",
+            "pg_isready",
+            "-q",
+            "-d",
+            "${POSTGRES_DB}",
+            "-U",
+            "${POSTGRES_USER}",
+        ]
+      retries: 3
+      timeout: 5s
+  minio:
+    image: 'minio/minio:latest'
+    ports:
+        - '${FORWARD_MINIO_PORT:-9001}:9001'
+        - '${FORWARD_MINIO_CONSOLE_PORT:-8900}:8900'
+    environment:
+      - ./.env
+    volumes:
+        - /mnt/data/minio:/data/minio
+    networks:
+        - default
+    command: minio server /data/minio --console-address ":8900"
+
+volumes:
+  prometheus_data:
+    driver: local
+    driver_opts:
+      o: bind
+      type: none
+      device: /mnt/data/prometheus_data
+  grafana_data:
+    driver: local
+    driver_opts:
+      o: bind
+      type: none
+      device: /mnt/data/grafana_data
+networks:
+  default:
+    name: nmrkit_vpc
diff --git a/ops/docker-compose-prod.yml b/ops/docker-compose-prod.yml
@@ -0,0 +1,117 @@
+version: "3.8"
+
+services:
+  traefik:
+    image: traefik:v2.10
+    container_name: traefik
+    command:
+      - "--api.insecure=true"
+      - "--providers.docker=true"
+      - "--providers.docker.exposedbydefault=false"
+      - "--entrypoints.web.address=:80"
+    ports:
+      - 80:80
+     # - 8080:8080 # Optional: Expose Traefik dashboard on port 8080
+    volumes:
+      - /var/run/docker.sock:/var/run/docker.sock
+
+  web:
+    image: nfdi4chem/nmrkit:v0.1.0
+    pull_policy: always
+    labels:
+      - "traefik.enable=true"
+      - "traefik.http.routers.web.rule=Host(`dev.nmrkit.nmrxiv.org`)"
+      - "traefik.http.routers.web.entrypoints=web"
+      - "traefik.http.services.web.loadbalancer.server.port=80"
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:80/latest/registration/health"]
+      interval: 1m
+      timeout: 10s
+      retries: 10
+      start_period: 40s
+    env_file:
+      - ./.env
+
+  prometheus:
+    image: prom/prometheus
+    container_name: nmrkit_prometheus
+    ports:
+      - 9090:9090
+    volumes:
+      - ./../prometheus_data/prometheus.yml:/etc/prometheus/prometheus.yml
+    command:
+      - '--config.file=/etc/prometheus/prometheus.yml'
+
+  grafana:
+    image: grafana/grafana
+    container_name: nmrkit_grafana
+    ports:
+      - 3000:3000
+    volumes:
+      - /mnt/data/grafana_data:/var/lib/grafana
+
+  redis:
+    image: "redis:alpine"
+    ports:
+        - "${FORWARD_REDIS_PORT:-6379}:6379"
+    volumes:
+        - "/mnt/data/redis:/data"
+    networks:
+        - default
+    healthcheck:
+        test: ["CMD", "redis-cli", "ping"]
+        retries: 3
+        timeout: 5s
+
+  pgsql:
+    image: "informaticsmatters/rdkit-cartridge-debian"
+    ports:
+      - "${FORWARD_DB_PORT:-5432}:5432"
+    env_file:
+      - ./.env
+    volumes:
+      - "/mnt/data/pgsql:/var/lib/postgresql/data"
+    networks:
+      - default
+    healthcheck:
+      test:
+        [
+            "CMD",
+            "pg_isready",
+            "-q",
+            "-d",
+            "${POSTGRES_DB}",
+            "-U",
+            "${POSTGRES_USER}",
+        ]
+      retries: 3
+      timeout: 5s
+  minio:
+    image: 'minio/minio:latest'
+    ports:
+        - '${FORWARD_MINIO_PORT:-9001}:9001'
+        - '${FORWARD_MINIO_CONSOLE_PORT:-8900}:8900'
+    environment:
+      - ./.env
+    volumes:
+        - /mnt/data/minio:/data/minio
+    networks:
+        - default
+    command: minio server /data/minio --console-address ":8900"
+
+volumes:
+  prometheus_data:
+    driver: local
+    driver_opts:
+      o: bind
+      type: none
+      device: /mnt/data/prometheus_data
+  grafana_data:
+    driver: local
+    driver_opts:
+      o: bind
+      type: none
+      device: /mnt/data/grafana_data
+networks:
+  default:
+    name: nmrkit_vpc
diff --git a/ops/zero-downtime-deployment-script.sh b/ops/zero-downtime-deployment-script.sh
@@ -0,0 +1,87 @@
+#!/bin/bash
+
+# Define variables
+COMPOSE_FILE="/mnt/data/nmrkit/ops/docker-compose-dev.yml"
+DOCKER_REPO_NAME="nfdi4chem/nmrkit:dev-latest"
+IMAGE_NAME="nfdi4chem/nmrkit:dev-latest"
+NEW_CONTAINER_ID=""
+IS_CONTAINER_HEALTHY=1
+
+# Function to check the health of the container
+check_health() {
+
+    HEALTH=$(docker inspect --format='{{json .State.Health.Status}}' $NEW_CONTAINER_ID)
+
+    if [[ $HEALTH == *"healthy"* ]]; then
+        echo "Container is healthy."
+        return 0
+    else
+        echo "Container is unhealthy or still starting"
+        return 1
+    fi
+
+}
+
+# Check if there is a new image available in the Docker repository
+if [ "$(docker pull $DOCKER_REPO_NAME | grep "Status: Image is up to date" | wc -l)" -eq 0 ]; then
+
+  # Scale up a new container
+   echo "Scale up new container.."
+   docker-compose -f $COMPOSE_FILE up -d --scale web=2 --no-recreate
+
+   NEW_CONTAINER_ID=$(docker ps -q -l)
+
+  echo "New Container Id is.."
+  echo "$NEW_CONTAINER_ID"
+
+  # Wait for new containers to start and health checks to pass
+   echo "Waiting for the new containers to start and health check to pass retry 5 times.."
+   n=0;
+   while [ $n -le 10 ]
+   do
+         if ! check_health; then
+                n=$(( $n + 1 ))
+                sleep 1m
+                echo "Container not healthy.. Check again.."
+         else
+                IS_CONTAINER_HEALTHY=0
+                break
+         fi
+   done
+
+  # Remove old containers and images
+  if [ $IS_CONTAINER_HEALTHY == 0 ] ; then
+
+        # Set the desired container name prefix
+        CONTAINER_NAME_PREFIX="ops_web"
+
+        # Retrieve the container IDs that match the prefix
+        container_ids=$(docker ps -a --filter "name=^/${CONTAINER_NAME_PREFIX}" --format "{{.ID}}")
+
+        # Sort the container IDs by creation date in ascending order
+        sorted_container_ids=$(echo "$container_ids" | xargs docker inspect --format='{{.Created}} {{.ID}}' | sort | awk '{print $2}')
+
+        # Get the oldest container ID
+        oldest_container_id=$(echo "$sorted_container_ids" | head -n 1)
+
+        # Check if any container IDs were found
+        if [[ -z "$oldest_container_id" ]]; then
+                echo "No containers found with the name prefix '${CONTAINER_NAME_PREFIX}'."
+                exit 1
+        fi
+
+        # Delete the old container and unused images
+        docker stop $oldest_container_id
+        docker rm $oldest_container_id
+        docker image prune -af
+        echo "Deleted the oldest container with ID: ${oldest_container_id}"
+
+  else
+        echo "Couldnot complete the deployment as the container is unhealthy.."
+        docker stop $NEW_CONTAINER_ID
+        docker rm $NEW_CONTAINER_ID
+  fi
+
+else
+       echo "Skipping deployment as no new image available.."
+fi