validate/docker-compose.swarm.yml at main · buildingSMART/validate · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
# Docker Swarm deployment configuration
#
# Usage:
#   1. Build and push images:  make swarm-push
#   2. Deploy:                 make start-swarm
#   3. Scale workers:          make scale-workers WORKERS=5
#   4. Status:                 make swarm-status
#   5. Tear down:              make stop-swarm
#
# Prerequisites:
#   - docker swarm init
#   - Local registry: docker service create --name registry --publish 5000:5000 registry:2
#   - NFS server configured (see PR description)
#
# NFS: Set NFS_SERVER_IP in .env (default: 10.0.0.1).
# For local testing without NFS, override volumes with plain named volumes.

services:

    frontend:
        image: ${REGISTRY}/validationsvc-frontend
        ports:
            - 80:80
            - 443:443
        environment:
            CERTBOT_DOMAIN: ${CERTBOT_DOMAIN}
            CERTBOT_EMAIL: ${CERTBOT_EMAIL}
        volumes:
            - letsencrypt_data:/etc/letsencrypt
            - static_data:/app/backend/django_static
        networks:
            - validate
        deploy:
            replicas: 1
            placement:
                constraints: [node.role == manager]
            restart_policy:
                condition: on-failure
                delay: 5s

    backend:
        image: ${REGISTRY}/validationsvc-backend
        entrypoint: /app/backend/server-entrypoint.sh
        env_file: ${ENV_FILE}
        volumes:
            - static_data:/app/backend/django_static
            - files_data:/files_storage
            - gherkin_rules_log_data:/gherkin_logs
        expose:
            - 8000
        networks:
            - validate
        deploy:
            replicas: 1
            placement:
                constraints: [node.role == manager]
            restart_policy:
                condition: on-failure
                delay: 5s
            update_config:
                parallelism: 1
                delay: 30s
                failure_action: rollback
        healthcheck:
            test: ["CMD-SHELL", "python -c \"import urllib.request; urllib.request.urlopen('http://localhost:8000/api/')\""]
            interval: 30s
            timeout: 10s
            retries: 3
            start_period: 60s

    worker:
        image: ${REGISTRY}/validationsvc-backend
        entrypoint: /app/backend/worker-entrypoint.sh
        env_file: ${ENV_FILE}
        volumes:
            - files_data:/files_storage
            - gherkin_rules_log_data:/gherkin_logs
        networks:
            - validate
        deploy:
            replicas: 2
            # No placement constraint - workers run on any node
            restart_policy:
                condition: on-failure
                delay: 5s
            update_config:
                parallelism: 1
                delay: 30s
                failure_action: rollback
            # Resource limits applied post-deploy via:
            #   docker service update --limit-cpu 2 --limit-memory 2G validate_worker

    scheduler:
        image: ${REGISTRY}/validationsvc-backend
        entrypoint: /app/backend/worker-beat-entrypoint.sh
        env_file: ${ENV_FILE}
        volumes:
            - files_data:/files_storage
            - gherkin_rules_log_data:/gherkin_logs
        networks:
            - validate
        deploy:
            replicas: 1
            placement:
                constraints: [node.role == manager]
            restart_policy:
                condition: on-failure
                delay: 5s

    redis:
        image: redis:8.4-alpine
        command: redis-server --protected-mode no --bind 0.0.0.0
        expose:
            - 6379
        volumes:
            - redis_data:/data
        networks:
            - validate
        deploy:
            replicas: 1
            placement:
                constraints: [node.role == manager]
            restart_policy:
                condition: on-failure
                delay: 5s

    db:
        image: postgres:16.10-alpine
        environment:
            POSTGRES_DB: ${POSTGRES_NAME}
            POSTGRES_USER: ${POSTGRES_USER}
            POSTGRES_PASSWORD: ${POSTGRES_PASSWORD}
        expose:
            - 5432
        volumes:
            - postgres_data:/var/lib/postgresql/data/
        networks:
            - validate
        deploy:
            replicas: 1
            placement:
                constraints: [node.role == manager]
            restart_policy:
                condition: any
                delay: 5s

networks:
    validate:
        driver: overlay
        driver_opts:
            com.docker.network.driver.mtu: "1400"

volumes:
    static_data:
    letsencrypt_data:
    postgres_data:
    redis_data:
    files_data:
        driver: local
        driver_opts:
            type: nfs
            o: "addr=${NFS_SERVER_IP},nfsvers=4.1,rw,hard,timeo=600,retrans=2"
            device: ":/srv/nfs/files_data"
    gherkin_rules_log_data:
        driver: local
        driver_opts:
            type: nfs
            o: "addr=${NFS_SERVER_IP},nfsvers=4.1,rw,hard,timeo=600,retrans=2"
            device: ":/srv/nfs/gherkin_logs"
    clamav_data: