jeremy/hobbs-iac
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

infra: full IaC state after hf-pdocker-01 rebuild (2026-03-08)

Browse Source 
Replaces initial Nomad/Consul/Terraform skeleton with current Docker-based
infrastructure across all three nodes (hf-pdocker-01, hf-pdocker-02, bart).

Key changes:
- CLAUDE.md: updated service distribution reflecting hf-pdocker-01 restored
- docs/plans/2026-03-08-hf-pdocker-01-rebuild.md: new rebuild plan doc
- compose/bart/: ai-agents, guacamole, matrix, media, openvas, smarthome, watchtower
- compose/hf-pdocker-02/: traefik, monitoring, adguard, gitea, semaphore, wikijs,
  unifi, vaultwarden, actual-budget, mcpo, netclaw, trivy, watchtower, n8n
- compose/hf-pdocker-01/: frigate, frigate-notify, farm-agent
- stacks/: all Swarm stack definitions (monitoring, traefik, smarthome, matrix,
  guacamole, media, ai-agents, frigate, gitea, semaphore, wikijs, unifi, etc.)
- .gitignore: exclude .env credential files and acme.json certs
- .env.example: placeholder credential files for all services
- .claude/agents/: gitea-backup and other infrastructure agent configs
- scripts/: frigate media cleanup and NAS sync scripts

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
jeremy
2026-03-08 18:51:25 -05:00
parent b1d111a011
commit de1d9e1d93
102 changed files with 12634 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
stacks/monitoring/docker-compose.yml
+197
View File
@@ -0,0 +1,197 @@
services:
grafana:
image: grafana/grafana:latest
restart: unless-stopped
user: "104"
ports:
- "3001:3000"
volumes:
- /mnt/docker-data/configs/grafana:/var/lib/grafana
healthcheck:
test: ["CMD-SHELL", "wget -q --spider http://localhost:3000/api/health || exit 1"]
interval: 30s
timeout: 10s
retries: 3
start_period: 30s
logging:
driver: "json-file"
options:
max-size: "50m"
max-file: "3"
deploy:
mode: replicated
replicas: 1
placement:
constraints:
- node.hostname == hf-pdocker-01
resources:
limits:
memory: 512M
prometheus:
image: prom/prometheus:latest
restart: unless-stopped
ports:
- "9095:9090"
command:
- '--config.file=/etc/prometheus/prometheus.yml'
- '--storage.tsdb.path=/prometheus'
- '--web.console.libraries=/usr/share/prometheus/console_libraries'
- '--web.console.templates=/usr/share/prometheus/consoles'
- '--web.enable-lifecycle'
volumes:
- /mnt/docker-data/configs/prometheus:/etc/prometheus
healthcheck:
test: ["CMD-SHELL", "wget -q --spider http://localhost:9090/-/healthy || exit 1"]
interval: 30s
timeout: 10s
retries: 3
start_period: 30s
logging:
driver: "json-file"
options:
max-size: "50m"
max-file: "3"
deploy:
mode: replicated
replicas: 1
placement:
constraints:
- node.hostname == hf-pdocker-01
resources:
limits:
memory: 512M
alertmanager:
image: prom/alertmanager:latest
restart: unless-stopped
ports:
- "9093:9093"
command:
- '--config.file=/etc/alertmanager/alertmanager.yml'
- '--storage.path=/alertmanager'
volumes:
- /mnt/docker-data/configs/alertmanager:/etc/alertmanager
- alertmanager-data:/alertmanager
healthcheck:
test: ["CMD-SHELL", "wget -q --spider http://localhost:9093/-/healthy || exit 1"]
interval: 30s
timeout: 10s
retries: 3
start_period: 30s
logging:
driver: "json-file"
options:
max-size: "50m"
max-file: "3"
deploy:
mode: replicated
replicas: 1
placement:
constraints:
- node.hostname == hf-pdocker-01
resources:
limits:
memory: 256M
node-exporter:
image: prom/node-exporter:latest
restart: unless-stopped
ports:
- "9100:9100"
volumes:
- /proc:/host/proc:ro
- /sys:/host/sys:ro
- /:/rootfs:ro
command:
- '--path.procfs=/host/proc'
- '--path.rootfs=/rootfs'
- '--path.sysfs=/host/sys'
logging:
driver: "json-file"
options:
max-size: "50m"
max-file: "3"
deploy:
mode: global
resources:
limits:
memory: 128M
influxdb:
image: influxdb:1.8-alpine
restart: unless-stopped
volumes:
- /mnt/docker-data/configs/influxdb:/var/lib/influxdb
healthcheck:
test: ["CMD-SHELL", "wget -q --spider http://localhost:8086/ping || exit 1"]
interval: 30s
timeout: 10s
retries: 3
start_period: 30s
logging:
driver: "json-file"
options:
max-size: "50m"
max-file: "3"
deploy:
mode: replicated
replicas: 1
placement:
constraints:
- node.hostname == hf-pdocker-01
resources:
limits:
memory: 1G
matrix-alertmanager-receiver:
image: metio/matrix-alertmanager-receiver:2026.2.25
restart: unless-stopped
ports:
- "9094:9094"
volumes:
- /mnt/docker-data/configs/alertmanager/matrix-receiver-config.yml:/config/config.yml:ro
command: ["--config-path", "/config/config.yml"]
# NOTE: No healthcheck - this image is distroless (no shell), so CMD-SHELL healthchecks fail.
# The service is verified healthy by Alertmanager successfully POSTing to it.
logging:
driver: "json-file"
options:
max-size: "50m"
max-file: "3"
deploy:
mode: replicated
replicas: 1
placement:
constraints:
- node.hostname == hf-pdocker-01
resources:
limits:
memory: 128M
blackbox-exporter:
image: prom/blackbox-exporter:latest
restart: unless-stopped
ports:
- "9115:9115"
command:
- '--config.file=/config/blackbox.yml'
volumes:
- /mnt/docker-data/configs/blackbox:/config:ro
logging:
driver: "json-file"
options:
max-size: "50m"
max-file: "3"
deploy:
mode: replicated
replicas: 1
placement:
constraints:
- node.hostname == hf-pdocker-01
resources:
limits:
memory: 128M
volumes:
alertmanager-data: