feat: add bash script for zero downtime deployment

ops/docker-compose-dev.yml

@@ -0,0 +1,63 @@
+version: "3.8"
+
+services:
+  traefik:
+    image: traefik:v2.10
+    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: caffeinejena/cheminfo-microservice:dev-latest
+    labels:
+      - "traefik.enable=true"
+      - "traefik.http.routers.web.rule=Host(`dev.api.naturalproducts.net`)"
+      - "traefik.http.routers.web.entrypoints=web"
+      - "traefik.http.services.web.loadbalancer.server.port=80"
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:80/latest/chem"]
+      interval: 1m
+      timeout: 10s
+      retries: 10
+      start_period: 40s
+
+  prometheus:
+    image: prom/prometheus
+    container_name: 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: grafana
+    ports:
+      - 3000:3000
+    volumes:
+      - /mnt/data/grafana_data:/var/lib/grafana
+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
+  postgres_data:
+networks:
+  default:
+    name: cpm_fastapi

docker-compose-prod.yml → ops/docker-compose-prod.yml

@@ -4,21 +4,21 @@ services:
   traefik:
     image: traefik:v2.10
     command:
-      - --api.insecure=true
-      - --providers.docker=true
-      - --providers.docker.exposedbydefault=false
-      - --entrypoints.web.address=:80
+      - "--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
+     # - 8080:8080 # Optional: Expose Traefik dashboard on port 8080
     volumes:
       - /var/run/docker.sock:/var/run/docker.sock
-      
+
   web:
     image: caffeinejena/cheminfo-microservice:dev-latest
     labels:
       - "traefik.enable=true"
-      - "traefik.http.routers.web.rule=Host(`nfdi4chem-oss1-vm11.ianchm.uni-jena.de`)"
+      - "traefik.http.routers.web.rule=Host(`api.naturalproducts.net`)"
       - "traefik.http.routers.web.entrypoints=web"
       - "traefik.http.services.web.loadbalancer.server.port=80"
     healthcheck:

ops/zero-downtime-deploy-bash-script.sh

@@ -0,0 +1,94 @@
+#!/bin/bash
+
+# Define variables
+COMPOSE_FILE="/mnt/data/cheminformatics-python-microservice/docker-compose-dev.yml"
+DOCKER_REPO_NAME="caffeinejena/cheminfo-microservice:dev-latest"
+IMAGE_NAME="caffeinejena/cheminfo-microservice: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
+  # Pull the latest image
+   echo "Pull the latest image.."
+   docker-compose -f $COMPOSE_FILE pull
+
+  # 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 once more.."
+         else
+                IS_CONTAINER_HEALTHY=0
+                break
+         fi
+   done
+
+  # Remove old containers and images
+   if [ $IS_CONTAINER_HEALTHY == 0 ] ; then
+
+        # Get the container IDs of running containers with the same image
+        container_ids=$(docker ps --filter ancestor=$IMAGE_NAME --format "{{.ID}}")
+
+        # Check if there are exactly two containers running with the same image
+        if [[ $(echo "$container_ids" | wc -l) -eq 2 ]]; then
+
+                # Get the creation timestamps of the two containers
+                timestamp1=$(docker inspect --format="{{.Created}}" $container_ids | head -n 1)
+                timestamp2=$(docker inspect --format="{{.Created}}" $container_ids | tail -n 1)
+
+                # Compare the timestamps to determine the older container
+                if [[ "$timestamp1" < "$timestamp2" ]]; then
+                        container_to_delete=$container_ids
+                else
+                        container_to_delete=$(echo "$container_ids" | tail -n 1)
+                fi
+
+                # Delete the older container and images
+                docker stop $container_to_delete
+                docker rm $container_to_delete
+                docker image prune -af
+
+                echo "Deleted container $container_to_delete"
+
+                else
+                        echo "Two running containers with the same image not found"
+                fi
+
+   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