Wire Beszel fleet filesystems, GPU telemetry, dashboard and alerts

This commit is contained in:
vh
2026-09-10 08:35:28 -07:00
parent 20bbb95113
commit eb75713c1b
18 changed files with 438 additions and 84 deletions
+20
View File
@@ -0,0 +1,20 @@
steps:
- name: Install Beszel alert bridge
sudo: true
upload:
src: services/beszel-althing/bridge.py
dest: /opt/beszel-althing/bridge.py
mode: '0644'
- name: Install Beszel alert bridge unit
sudo: true
upload:
src: services/beszel-althing/beszel-althing.service
dest: /etc/systemd/system/beszel-althing.service
mode: '0644'
- name: Start Beszel alert bridge
sudo: true
shell: systemctl daemon-reload && systemctl enable beszel-althing.service && systemctl restart beszel-althing.service
verify:
- name: Verify bridge process
shell: systemctl is-active beszel-althing.service && curl --retry 5 --retry-connrefused --retry-delay 1 -fsS http://10.100.10.50:8096/healthz
changed_when: 'false'
+22
View File
@@ -0,0 +1,22 @@
steps:
- name: Back up agent environment before filesystem wiring
sudo: true
shell: cp -p {{ stack_dir }}/.env {{ stack_dir }}/.env.before-fleet-wiring-20260910
creates: '{{ stack_dir }}/.env.before-fleet-wiring-20260910'
- name: Select canonical host filesystem override
sudo: true
shell: |
set -euo pipefail
cd {{ stack_dir }}
sed -i '/^COMPOSE_FILE=/d; /^BESZEL_EXTRA_FS=/d' .env
printf '\nCOMPOSE_FILE=compose.yaml:hosts/{{ host_name }}.yaml\nBESZEL_EXTRA_FS={{ extra_fs }}\n' >> .env
docker compose config --quiet
docker compose up -d --pull never beszel-agent
verify:
- name: Verify running mounts and process health
sudo: true
shell: |
docker inspect beszel-agent --format '{{json .Mounts}}'
docker inspect beszel-agent | python3 -c 'import json,sys; print([e for e in json.load(sys.stdin)[0]["Config"]["Env"] if e.startswith("EXTRA_FILESYSTEMS=")])'
docker exec beszel-agent /agent health
changed_when: 'false'