mirror of
https://github.com/Security-Onion-Solutions/securityonion.git
synced 2026-07-22 00:35:42 +02:00
Mike Reeves
011749ad09
init-db.sh only runs on a fresh PGDATA (docker-entrypoint-initdb.d), so a cluster left partially initialized -- e.g. the container restarted mid first-init by a watch trigger -- never recovered: the so_postgres role existed but its schema grants and the so_telegraf database were missing, breaking SOC with "permission denied for schema public". - init-db.sh: make the role upsert race-safe. Try CREATE ROLE and fall back to ALTER on duplicate_object/unique_violation instead of IF NOT EXISTS, so a concurrent creator no longer aborts the script (set -e + ON_ERROR_STOP=1) before the grants and so_telegraf creation run. The whole script is now idempotent and safe to re-run. - postgres/enabled.sls: move postgres_wait_ready here (was telegraf-gated in telegraf_users.sls) and add postgres_bootstrap_soc_db, which re-runs init-db.sh every highstate so a partially-initialized cluster self-heals. - telegraf_users.sls: drop its now-duplicate postgres_wait_ready definition; it resolves from postgres.enabled via the existing include. - soup: remove bootstrap_so_soc_database and its post_to_3.2.0 call. The highstates soup runs before postupgrade now reconcile the SOC DB, making the one-shot bootstrap redundant.
84 lines
3.0 KiB
YAML+Jinja
84 lines
3.0 KiB
YAML+Jinja
# Copyright Security Onion Solutions LLC and/or licensed to Security Onion Solutions LLC under one
|
|
# or more contributor license agreements. Licensed under the Elastic License 2.0 as shown at
|
|
# https://securityonion.net/license; you may not use this file except in compliance with the
|
|
# Elastic License 2.0.
|
|
|
|
{% from 'allowed_states.map.jinja' import allowed_states %}
|
|
{% if sls.split('.')[0] in allowed_states %}
|
|
{% from 'vars/globals.map.jinja' import GLOBALS %}
|
|
{% from 'telegraf/map.jinja' import TELEGRAFMERGED %}
|
|
|
|
{# postgres_wait_ready and the so-postgres container are declared in
|
|
postgres.enabled; include it so the require references below resolve and so
|
|
state.apply postgres.telegraf_users on its own (e.g. from orch.deploy_newnode)
|
|
still has those IDs in scope. Salt de-duplicates the circular include. #}
|
|
include:
|
|
- postgres.enabled
|
|
|
|
{% set TG_OUT = TELEGRAFMERGED.output | upper %}
|
|
{% if TG_OUT in ['POSTGRES', 'BOTH'] %}
|
|
|
|
# Ensure the shared Telegraf database exists. init-db.sh only runs on a
|
|
# fresh data dir, so hosts upgraded onto an existing /nsm/postgres volume
|
|
# would otherwise never get so_telegraf.
|
|
postgres_create_telegraf_db:
|
|
cmd.run:
|
|
- name: /usr/sbin/so-telegraf-postgres create_db
|
|
- require:
|
|
- cmd: postgres_wait_ready
|
|
- file: postgres_sbin
|
|
|
|
# Provision the shared group role and schema once. Every per-minion role is a
|
|
# member of so_telegraf, and each Telegraf connection does SET ROLE so_telegraf
|
|
# (via options='-c role=so_telegraf' in the connection string) so tables created
|
|
# on first write are owned by the group role and every member can INSERT/SELECT.
|
|
postgres_telegraf_group_role:
|
|
cmd.run:
|
|
- name: /usr/sbin/so-telegraf-postgres group_role
|
|
- require:
|
|
- cmd: postgres_create_telegraf_db
|
|
- file: postgres_sbin
|
|
|
|
{% set creds = salt['pillar.get']('telegraf:postgres_creds', {}) %}
|
|
{% for mid, entry in creds.items() %}
|
|
{% if entry.get('user') and entry.get('pass') %}
|
|
{% set u = entry.user %}
|
|
{% set p = entry.pass %}
|
|
|
|
postgres_telegraf_role_{{ u }}:
|
|
cmd.run:
|
|
- name: /usr/sbin/so-telegraf-postgres user
|
|
- env:
|
|
- ROLE_USER: {{ u | tojson }}
|
|
- ROLE_PASS: {{ p | tojson }}
|
|
- hide_output: True
|
|
- require:
|
|
- file: postgres_sbin
|
|
- cmd: postgres_telegraf_group_role
|
|
|
|
{% endif %}
|
|
{% endfor %}
|
|
|
|
# Reconcile partman retention from pillar. Runs after role/schema setup so
|
|
# any partitioned parents Telegraf has already created get their retention
|
|
# refreshed whenever postgres.telegraf.retention_days changes.
|
|
{% set retention = salt['pillar.get']('postgres:telegraf:retention_days', 14) | int %}
|
|
postgres_telegraf_retention_reconcile:
|
|
cmd.run:
|
|
- name: /usr/sbin/so-telegraf-postgres retention
|
|
- env:
|
|
- RETENTION_DAYS: {{ retention }}
|
|
- require:
|
|
- cmd: postgres_telegraf_group_role
|
|
- file: postgres_sbin
|
|
|
|
{% endif %}
|
|
|
|
{% else %}
|
|
|
|
{{sls}}_state_not_allowed:
|
|
test.fail_without_changes:
|
|
- name: {{sls}}_state_not_allowed
|
|
|
|
{% endif %}
|