feat(backup): add ops-db backup commands, flow, and systemd timer
Adds pg_dump_ops_db, list_ops_backups, and cleanup_ops_backups to the agent command whitelist. Includes a backup_ops_db flow YAML (dump + 30-day retention), and a systemd service/timer for daily automated backups at 02:00. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
parent
aa1fd41bec
commit
4dd0490afc
4 changed files with 85 additions and 0 deletions
20
deploy/ops-agent/ops-db-backup.service
Normal file
20
deploy/ops-agent/ops-db-backup.service
Normal file
|
|
@ -0,0 +1,20 @@
|
|||
[Unit]
|
||||
Description=Daily backup of ops_dashboard database
|
||||
After=network.target ops-agent.service
|
||||
|
||||
[Service]
|
||||
Type=oneshot
|
||||
User=ops-agent
|
||||
Group=ops-agent
|
||||
# Reads the shared secret and POSTs to ops-agent to trigger the backup flow.
|
||||
# ops-agent must be running and backup_ops_db.yml must be installed in /etc/ops-agent/flows/.
|
||||
ExecStart=/usr/bin/bash -c '\
|
||||
SECRET=$(cat /etc/ops-agent/secret); \
|
||||
curl -sf -X POST http://127.0.0.1:3099/agent/v1/flow \
|
||||
-H "Authorization: Bearer $SECRET" \
|
||||
-H "Content-Type: application/json" \
|
||||
-d "{\"flow_key\":\"backup_ops_db\"}" \
|
||||
'
|
||||
StandardOutput=journal
|
||||
StandardError=journal
|
||||
SyslogIdentifier=ops-db-backup
|
||||
10
deploy/ops-agent/ops-db-backup.timer
Normal file
10
deploy/ops-agent/ops-db-backup.timer
Normal file
|
|
@ -0,0 +1,10 @@
|
|||
[Unit]
|
||||
Description=Daily backup of ops_dashboard database (timer)
|
||||
|
||||
[Timer]
|
||||
# Run every day at 02:00 local time.
|
||||
OnCalendar=*-*-* 02:00:00
|
||||
Persistent=true
|
||||
|
||||
[Install]
|
||||
WantedBy=timers.target
|
||||
|
|
@ -203,3 +203,36 @@ commands:
|
|||
- -c
|
||||
- "code=$(curl -s -o /dev/null -w '%{http_code}' --max-time 15 https://thuis.jp-visser.nl/api/products); echo \"HTTP $code\"; [ \"$code\" = \"200\" ] || [ \"$code\" = \"401\" ]"
|
||||
description: "Smoke test: /api/products must return 200 or 401"
|
||||
|
||||
# ── Ops-dashboard database backup ────────────────────────────────────────
|
||||
|
||||
pg_dump_ops_db:
|
||||
cmd:
|
||||
- sh
|
||||
- -c
|
||||
- |
|
||||
mkdir -p /srv/ops/backups
|
||||
FNAME="/srv/ops/backups/ops_db_$(date +%Y%m%d_%H%M).dump"
|
||||
docker exec postgres pg_dump -Fc ops_dashboard > "$FNAME"
|
||||
echo "Backup written: $FNAME"
|
||||
ls -lh "$FNAME"
|
||||
description: "Dump ops_dashboard DB via docker exec postgres to /srv/ops/backups/"
|
||||
|
||||
list_ops_backups:
|
||||
cmd:
|
||||
- sh
|
||||
- -c
|
||||
- "find /srv/ops/backups -maxdepth 1 -name '*.dump' -printf '%f\\t%s\\n' 2>/dev/null | sort -r || true"
|
||||
description: "List ops_dashboard backup files (filename TAB size_bytes, newest-first)"
|
||||
|
||||
cleanup_ops_backups:
|
||||
cmd:
|
||||
- find
|
||||
- /srv/ops/backups
|
||||
- -name
|
||||
- "*.dump"
|
||||
- -mtime
|
||||
- "+30"
|
||||
- -delete
|
||||
- -print
|
||||
description: "Delete ops_dashboard backup files older than 30 days"
|
||||
|
|
|
|||
22
ops-agent/flows.example/backup_ops_db.yml
Normal file
22
ops-agent/flows.example/backup_ops_db.yml
Normal file
|
|
@ -0,0 +1,22 @@
|
|||
# Backup the ops_dashboard database.
|
||||
# Copy to /etc/ops-agent/flows/backup_ops_db.yml on the host.
|
||||
#
|
||||
# Prerequisites:
|
||||
# - ops-agent user must be in the docker group (to run docker exec)
|
||||
# - /srv/ops/backups/ directory or its parent must be writable by ops-agent
|
||||
#
|
||||
# Steps:
|
||||
# 1. Dump ops_dashboard via pg_dump inside the postgres container
|
||||
# 2. Remove backup files older than 30 days (retention policy)
|
||||
#
|
||||
# Run on a schedule via ops-db-backup.timer (see deploy/ops-agent/).
|
||||
# Or trigger manually via the Ops Dashboard → Settings → Backups.
|
||||
|
||||
name: Backup Ops DB
|
||||
description: Dump ops_dashboard database and apply 30-day retention policy
|
||||
steps:
|
||||
- command_key: pg_dump_ops_db
|
||||
on_failure: abort
|
||||
|
||||
- command_key: cleanup_ops_backups
|
||||
on_failure: continue
|
||||
Loading…
Add table
Add a link
Reference in a new issue