Add verified Prometheus backup pull to Atlas

ansible/roles/profile_atlas/defaults/main.yml

@@ -115,6 +115,15 @@ atlas_monitor_notifier: "{{ atlas_usb_reminder_notifier }}"
 atlas_monitor_smart_devices: []
 atlas_monitor_timers: []
 atlas_monitor_failure_units: []
+atlas_monitor_effective_timers: >-
+  {{ atlas_monitor_timers
+     + ([{'name': 'atlas-prometheus-pull.timer', 'max_age_hours': 26}]
+        if atlas_manage_prometheus_backup_pull | bool and atlas_prometheus_pull_start_timer | bool
+        else []) }}
+atlas_monitor_effective_failure_units: >-
+  {{ atlas_monitor_failure_units
+     + (['atlas-prometheus-pull.service']
+        if atlas_manage_prometheus_backup_pull | bool else []) }}
 atlas_monitor_remote_capacity: {}
 atlas_monitor_pool_warning_percent: 80
 atlas_monitor_pool_critical_percent: 90
@@ -141,6 +150,19 @@ atlas_music_mountpoint: "{{ atlas_mount_root }}/{{ atlas_zfs_dataset_music }}"
 atlas_backup_mountpoint: "{{ atlas_mount_root }}/{{ atlas_zfs_dataset_backup }}"
 atlas_host_backups_mountpoint: "{{ atlas_mount_root }}/{{ atlas_zfs_dataset_host_backups }}"
 atlas_backup_prometheus_mountpoint: "{{ atlas_mount_root }}/{{ atlas_zfs_dataset_backup_prometheus }}"
+atlas_manage_prometheus_backup_pull: false
+atlas_prometheus_pull_ssh_dir: /etc/atlas-prometheus-pull
+atlas_prometheus_pull_private_key_path: "{{ atlas_prometheus_pull_ssh_dir }}/id_ed25519"
+atlas_prometheus_pull_known_hosts_path: "{{ atlas_prometheus_pull_ssh_dir }}/known_hosts"
+atlas_prometheus_ssh_host_key: ""
+atlas_prometheus_pull_source_user: prometheus-backup
+atlas_prometheus_pull_source_port: 22
+atlas_prometheus_pull_calendar: "*-*-* 03:00:00 Europe/Rome"
+atlas_prometheus_pull_start_timer: false
+atlas_prometheus_pull_keep_daily: 30
+atlas_prometheus_pull_keep_weekly: 8
+atlas_prometheus_pull_keep_monthly: 12
+atlas_prometheus_pull_max_age_hours: 24
 atlas_photobook_mountpoint: "{{ atlas_mount_root }}/{{ atlas_zfs_dataset_photobook }}"
 
 atlas_45drives_repo_url: https://repo.45drives.com/repofiles/rocky/45drives-enterprise.repo

ansible/roles/profile_atlas/files/atlas-prometheus-prune.py

@@ -0,0 +1,56 @@
+#!/usr/bin/env python3
+"""Prune only verified, named Prometheus backup versions after publication."""
+
+import datetime as dt
+import pathlib
+import re
+import shutil
+import sys
+
+
+def main() -> None:
+    if len(sys.argv) != 5:
+        raise SystemExit("Usage: atlas-prometheus-prune SNAPSHOTS DAILY WEEKLY MONTHLY")
+    root = pathlib.Path(sys.argv[1])
+    counts = [int(value) for value in sys.argv[2:]]
+    if not root.is_dir() or root.is_symlink() or min(counts) < 1:
+        raise SystemExit("Invalid backup directory or retention counts")
+    versions = []
+    for entry in root.iterdir():
+        if not entry.is_dir() or entry.is_symlink():
+            continue
+        if not re.fullmatch(r"[0-9]{8}T[0-9]{6}Z", entry.name):
+            continue
+        try:
+            when = dt.datetime.strptime(entry.name, "%Y%m%dT%H%M%SZ")
+        except ValueError:
+            continue
+        if not all((entry / name).is_file() for name in ("payload.tar", "payload.sha256", "metadata.json")):
+            continue
+        versions.append((when, entry))
+    versions.sort(reverse=True)
+    if not versions:
+        raise SystemExit("No published backup versions found; refusing to prune")
+
+    keep = {entry for _, entry in versions[: counts[0]]}
+    for count, key in (
+        (counts[1], lambda when: when.isocalendar()[:2]),
+        (counts[2], lambda when: (when.year, when.month)),
+    ):
+        periods = set()
+        for when, entry in versions:
+            period = key(when)
+            if period in periods:
+                continue
+            periods.add(period)
+            keep.add(entry)
+            if len(periods) >= count:
+                break
+
+    for _, entry in versions:
+        if entry not in keep:
+            shutil.rmtree(entry)
+
+
+if __name__ == "__main__":
+    main()

ansible/roles/profile_atlas/tasks/main.yml

@@ -23,6 +23,12 @@
 - name: Import Atlas offline USB backup tasks
   ansible.builtin.import_tasks: usb_backup.yml
 
+- name: Import Atlas Prometheus backup pull identity tasks
+  ansible.builtin.import_tasks: prometheus_pull_identity.yml
+
+- name: Import Atlas Prometheus backup pull job tasks
+  ansible.builtin.import_tasks: prometheus_pull_job.yml
+
 - name: Import Atlas health monitoring tasks
   ansible.builtin.import_tasks: monitoring.yml
 

ansible/roles/profile_atlas/tasks/monitoring.yml

@@ -7,8 +7,8 @@
       - atlas_zfs_pool != 'CHANGEME_ZFS_POOL'
       - atlas_monitor_calendar | length > 0
       - atlas_monitor_smart_devices | length > 0
-      - atlas_monitor_timers | length > 0
-      - atlas_monitor_failure_units | length > 0
+      - atlas_monitor_effective_timers | length > 0
+      - atlas_monitor_effective_failure_units | length > 0
       - atlas_monitor_remote_capacity.user == atlas_borg_repository_user
       - atlas_monitor_remote_capacity.host == atlas_borg_repository_host
       - atlas_monitor_remote_capacity.run_as == atlas_borg_username
@@ -49,7 +49,7 @@
     that:
       - item.name is match('^[a-zA-Z0-9@_.-]+\\.timer$')
       - item.max_age_hours | int >= 0
-  loop: "{{ atlas_monitor_timers }}"
+  loop: "{{ atlas_monitor_effective_timers }}"
   loop_control:
     label: "{{ item.name }}"
   when: atlas_manage_monitoring | bool
@@ -59,7 +59,7 @@
   ansible.builtin.assert:
     that:
       - item is match('^[a-zA-Z0-9@_.-]+\\.service$')
-  loop: "{{ atlas_monitor_failure_units }}"
+  loop: "{{ atlas_monitor_effective_failure_units }}"
   when: atlas_manage_monitoring | bool
 
 - name: Validate Atlas health monitor calendar
@@ -144,7 +144,7 @@
     owner: root
     group: root
     mode: "0755"
-  loop: "{{ atlas_monitor_failure_units }}"
+  loop: "{{ atlas_monitor_effective_failure_units }}"
   when: atlas_manage_monitoring | bool
 
 - name: Notify 45Drives Alerts when an Atlas job fails
@@ -155,7 +155,7 @@
     owner: root
     group: root
     mode: "0644"
-  loop: "{{ atlas_monitor_failure_units }}"
+  loop: "{{ atlas_monitor_effective_failure_units }}"
   when: atlas_manage_monitoring | bool
 
 - name: Reload systemd after installing Atlas monitoring

ansible/roles/profile_atlas/tasks/prometheus_pull_identity.yml

@@ -0,0 +1,66 @@
+---
+- name: Validate Atlas Prometheus pull identity inputs
+  tags: [atlas, backup, prometheus_backup, prometheus_backup_key]
+  ansible.builtin.assert:
+    that:
+      - atlas_prometheus_pull_ssh_dir.startswith('/etc/')
+      - atlas_prometheus_pull_private_key_path.startswith(atlas_prometheus_pull_ssh_dir ~ '/')
+      - atlas_prometheus_pull_known_hosts_path.startswith(atlas_prometheus_pull_ssh_dir ~ '/')
+      - atlas_prometheus_ssh_host_key.startswith(
+          (hostvars['prometheus'].ansible_host | string) ~ ' ssh-ed25519 '
+        )
+    fail_msg: Pin the verified Prometheus ED25519 SSH host key before enabling the pull.
+  when: atlas_manage_prometheus_backup_pull | bool
+
+- name: Create private Atlas Prometheus pull SSH directory
+  tags: [atlas, backup, prometheus_backup, prometheus_backup_key]
+  ansible.builtin.file:
+    path: "{{ atlas_prometheus_pull_ssh_dir }}"
+    state: directory
+    owner: root
+    group: root
+    mode: "0700"
+  when: atlas_manage_prometheus_backup_pull | bool
+
+- name: Generate Atlas-only Prometheus pull SSH identity
+  tags: [atlas, backup, prometheus_backup, prometheus_backup_key]
+  ansible.builtin.command:
+    argv:
+      - ssh-keygen
+      - -q
+      - -t
+      - ed25519
+      - -N
+      - ""
+      - -C
+      - atlas-prometheus-pull@atlas
+      - -f
+      - "{{ atlas_prometheus_pull_private_key_path }}"
+    creates: "{{ atlas_prometheus_pull_private_key_path }}"
+  when: atlas_manage_prometheus_backup_pull | bool
+
+- name: Protect Atlas-only Prometheus pull SSH identity
+  tags: [atlas, backup, prometheus_backup, prometheus_backup_key]
+  ansible.builtin.file:
+    path: "{{ item.path }}"
+    owner: root
+    group: root
+    mode: "{{ item.mode }}"
+  loop:
+    - { path: "{{ atlas_prometheus_pull_private_key_path }}", mode: "0600" }
+    - { path: "{{ atlas_prometheus_pull_private_key_path }}.pub", mode: "0644" }
+  loop_control:
+    label: "{{ item.path }}"
+  when:
+    - atlas_manage_prometheus_backup_pull | bool
+    - not ansible_check_mode
+
+- name: Pin Prometheus SSH host key on Atlas
+  tags: [atlas, backup, prometheus_backup, prometheus_backup_key]
+  ansible.builtin.copy:
+    content: "{{ atlas_prometheus_ssh_host_key }}\n"
+    dest: "{{ atlas_prometheus_pull_known_hosts_path }}"
+    owner: root
+    group: root
+    mode: "0600"
+  when: atlas_manage_prometheus_backup_pull | bool

ansible/roles/profile_atlas/tasks/prometheus_pull_job.yml

@@ -0,0 +1,90 @@
+---
+- name: Validate Atlas Prometheus backup pull inputs
+  tags: [atlas, backup, prometheus_backup]
+  ansible.builtin.assert:
+    that:
+      - atlas_manage_storage | bool
+      - atlas_prometheus_pull_source_user is match('^[a-z_][a-z0-9_-]*$')
+      - atlas_prometheus_pull_source_port | int > 0
+      - atlas_prometheus_pull_source_port | int < 65536
+      - atlas_prometheus_pull_keep_daily | int > 0
+      - atlas_prometheus_pull_keep_weekly | int > 0
+      - atlas_prometheus_pull_keep_monthly | int > 0
+      - atlas_prometheus_pull_max_age_hours | int > 0
+      - atlas_backup_prometheus_mountpoint.startswith(atlas_mount_root ~ '/')
+    fail_msg: Define the Atlas backup destination, source account, and retention before enabling the pull.
+  when: atlas_manage_prometheus_backup_pull | bool
+
+- name: Validate Atlas Prometheus backup pull calendar
+  tags: [atlas, backup, prometheus_backup]
+  ansible.builtin.command:
+    argv: [systemd-analyze, calendar, "{{ atlas_prometheus_pull_calendar }}"]
+  changed_when: false
+  check_mode: false
+  when: atlas_manage_prometheus_backup_pull | bool
+
+- name: Create private Atlas Prometheus backup version directory
+  tags: [atlas, backup, prometheus_backup]
+  ansible.builtin.file:
+    path: "{{ atlas_backup_prometheus_mountpoint }}/snapshots"
+    state: directory
+    owner: root
+    group: root
+    mode: "0700"
+  when: atlas_manage_prometheus_backup_pull | bool
+
+- name: Install Atlas Prometheus backup pull helper
+  tags: [atlas, backup, prometheus_backup]
+  ansible.builtin.template:
+    src: atlas-prometheus-pull.sh.j2
+    dest: /usr/local/sbin/atlas-prometheus-pull
+    owner: root
+    group: root
+    mode: "0750"
+  when: atlas_manage_prometheus_backup_pull | bool
+
+- name: Install Atlas Prometheus backup retention helper
+  tags: [atlas, backup, prometheus_backup]
+  ansible.builtin.copy:
+    src: atlas-prometheus-prune.py
+    dest: /usr/local/libexec/atlas-prometheus-prune
+    owner: root
+    group: root
+    mode: "0750"
+  when: atlas_manage_prometheus_backup_pull | bool
+
+- name: Install Atlas Prometheus backup pull systemd units
+  tags: [atlas, backup, prometheus_backup]
+  ansible.builtin.template:
+    src: "{{ item }}.j2"
+    dest: "/etc/systemd/system/{{ item }}"
+    owner: root
+    group: root
+    mode: "0644"
+  loop:
+    - atlas-prometheus-pull.service
+    - atlas-prometheus-pull.timer
+  loop_control:
+    label: "{{ item }}"
+  register: atlas_prometheus_pull_units
+  when: atlas_manage_prometheus_backup_pull | bool
+
+- name: Reload systemd after Atlas Prometheus pull unit changes
+  tags: [atlas, backup, prometheus_backup]
+  ansible.builtin.systemd:
+    daemon_reload: true
+  when:
+    - atlas_manage_prometheus_backup_pull | bool
+    - atlas_prometheus_pull_units is changed
+    - not ansible_check_mode
+
+- name: Enable Atlas Prometheus pull timer only after explicit activation
+  tags: [atlas, backup, prometheus_backup]
+  ansible.builtin.systemd:
+    name: atlas-prometheus-pull.timer
+    enabled: true
+    state: started
+  when:
+    - atlas_manage_prometheus_backup_pull | bool
+    - atlas_prometheus_pull_start_timer | bool
+    - not ansible_check_mode

ansible/roles/profile_atlas/templates/atlas-health-monitor.json.j2

@@ -3,8 +3,8 @@
   "backup_dataset": {{ (atlas_zfs_pool ~ '/' ~ atlas_zfs_dataset_backup) | to_json }},
   "notifier": {{ atlas_monitor_notifier | to_json }},
   "smart_devices": {{ atlas_monitor_smart_devices | to_json }},
-  "timers": {{ atlas_monitor_timers | to_json }},
-  "failure_units": {{ atlas_monitor_failure_units | to_json }},
+  "timers": {{ atlas_monitor_effective_timers | to_json }},
+  "failure_units": {{ atlas_monitor_effective_failure_units | to_json }},
   "remote_capacity": {{ atlas_monitor_remote_capacity | to_json }},
   "pool_warning_percent": {{ atlas_monitor_pool_warning_percent | int }},
   "pool_critical_percent": {{ atlas_monitor_pool_critical_percent | int }},

ansible/roles/profile_atlas/templates/atlas-prometheus-pull.service.j2

@@ -0,0 +1,19 @@
+[Unit]
+Description=Pull a prepared read-only Prometheus backup to Atlas
+RequiresMountsFor={{ atlas_backup_prometheus_mountpoint }}
+Wants=network-online.target
+After=network-online.target zfs.target
+ConditionFileIsExecutable=/usr/local/sbin/atlas-prometheus-pull
+ConditionPathExists={{ atlas_prometheus_pull_private_key_path }}
+ConditionPathExists={{ atlas_prometheus_pull_known_hosts_path }}
+
+[Service]
+Type=oneshot
+ExecStart=/usr/local/sbin/atlas-prometheus-pull
+User=root
+Group=root
+UMask=0077
+TimeoutStartSec=infinity
+Nice=15
+IOSchedulingClass=best-effort
+IOSchedulingPriority=7

ansible/roles/profile_atlas/templates/atlas-prometheus-pull.sh.j2

@@ -0,0 +1,75 @@
+#!/usr/bin/env bash
+set -Eeuo pipefail
+umask 077
+
+backup_root={{ atlas_backup_prometheus_mountpoint | quote }}
+snapshots="$backup_root/snapshots"
+stage=''
+exec 9>/run/lock/atlas-prometheus-pull.lock
+flock -n 9 || { echo 'A Prometheus pull is already running' >&2; exit 1; }
+
+cleanup() {
+  local rc=$?
+  trap - EXIT
+  if (( rc != 0 )) && [[ -n "$stage" && -d "$stage" ]]; then
+    rm -rf -- "$stage"
+  fi
+  exit "$rc"
+}
+trap cleanup EXIT
+
+zpool list -H -o name {{ atlas_zfs_pool | quote }} >/dev/null
+findmnt -rn --mountpoint "$backup_root" >/dev/null
+stage=$(mktemp -d "$backup_root/.staging.XXXXXXXX")
+ssh_cmd='/usr/bin/ssh -F /dev/null -o BatchMode=yes -o StrictHostKeyChecking=yes -o UserKnownHostsFile={{ atlas_prometheus_pull_known_hosts_path }} -o IdentitiesOnly=yes -i {{ atlas_prometheus_pull_private_key_path }} -p {{ atlas_prometheus_pull_source_port }}'
+rsync -a --partial --delay-updates -e "$ssh_cmd" \
+  {{ (atlas_prometheus_pull_source_user ~ '@' ~ hostvars['prometheus'].ansible_host ~ ':current/') | quote }} \
+  "$stage/"
+
+test -s "$stage/payload.tar"
+test -s "$stage/payload.sha256"
+test -s "$stage/metadata.json"
+(cd "$stage" && sha256sum -c payload.sha256)
+tar -tf "$stage/payload.tar" >/dev/null
+stamp=$(python3 - "$stage/metadata.json" <<'PY'
+import json
+import datetime as dt
+import re
+import sys
+
+with open(sys.argv[1], encoding="utf-8") as stream:
+    metadata = json.load(stream)
+stamp = metadata.get("created_utc", "")
+if metadata.get("schema") != 1 or metadata.get("host") != "prometheus":
+    raise SystemExit("Unexpected Prometheus backup metadata")
+if not re.fullmatch(r"[0-9]{8}T[0-9]{6}Z", stamp):
+    raise SystemExit("Invalid Prometheus backup timestamp")
+created = dt.datetime.strptime(stamp, "%Y%m%dT%H%M%SZ").replace(tzinfo=dt.timezone.utc)
+age = dt.datetime.now(dt.timezone.utc) - created
+if age.total_seconds() < -300 or age > dt.timedelta(hours={{ atlas_prometheus_pull_max_age_hours }}):
+    raise SystemExit("Prometheus backup is outside the configured freshness window")
+print(stamp)
+PY
+)
+if [[ -e "$snapshots/$stamp" ]]; then
+  cmp "$stage/payload.sha256" "$snapshots/$stamp/payload.sha256"
+  cmp "$stage/metadata.json" "$snapshots/$stamp/metadata.json"
+  (cd "$snapshots/$stamp" && sha256sum -c payload.sha256)
+  rm -rf -- "${stage:?}"
+  stage=''
+else
+  chown -R root:root "$stage"
+  chmod 0700 "$stage"
+  chmod 0600 "$stage/payload.tar" "$stage/payload.sha256" "$stage/metadata.json"
+  mv -- "$stage" "$snapshots/$stamp"
+  stage=''
+fi
+latest_link=$(readlink "$backup_root/latest" 2>/dev/null || true)
+latest_stamp=${latest_link##*/}
+if [[ -z "$latest_stamp" || "$stamp" > "$latest_stamp" ]]; then
+  ln -s "snapshots/$stamp" "$backup_root/.latest.new"
+  mv -Tf -- "$backup_root/.latest.new" "$backup_root/latest"
+fi
+python3 /usr/local/libexec/atlas-prometheus-prune "$snapshots" \
+  {{ atlas_prometheus_pull_keep_daily }} {{ atlas_prometheus_pull_keep_weekly }} {{ atlas_prometheus_pull_keep_monthly }}
+echo "Verified and published Prometheus backup $stamp"

ansible/roles/profile_atlas/templates/atlas-prometheus-pull.timer.j2

@@ -0,0 +1,10 @@
+[Unit]
+Description=Schedule Atlas pull of prepared Prometheus backups
+
+[Timer]
+OnCalendar={{ atlas_prometheus_pull_calendar }}
+Persistent=true
+Unit=atlas-prometheus-pull.service
+
+[Install]
+WantedBy=timers.target