Files
securityonion/salt/postgres/telegraf_users.sls
T
Mike Reeves 5228668be0 Fix Telegraf→Postgres table creation and state.apply race
- Telegraf's partman template passed p_type:='native', which pg_partman
  5.x (the version shipped by postgresql-17-partman on Debian) rejects.
  Switched to 'range' so partman.create_parent() actually creates
  partitions and Telegraf's INSERTs succeed.
- Added a postgres_wait_ready gate in telegraf_users.sls so psql execs
  don't race the init-time restart that docker-entrypoint.sh performs.
- so-verify now ignores the literal "-v ON_ERROR_STOP=1" token in the
  setup log. Dropped the matching entry from so-log-check, which scans
  container stdout where that token never appears.
2026-04-17 13:00:12 -04:00

134 lines
5.0 KiB
Plaintext

# 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 %}
{% set TG_OUT = (GLOBALS.telegraf_output | default('INFLUXDB')) | upper %}
{% if TG_OUT in ['POSTGRES', 'BOTH'] %}
# docker_container.running returns as soon as the container starts, but on
# first-init docker-entrypoint.sh runs init scripts and then restarts
# postgres, so the next docker exec can hit "the database system is shutting
# down". Wait for pg_isready before any psql work.
postgres_wait_ready:
cmd.run:
- name: |
for i in $(seq 1 60); do
if docker exec so-postgres pg_isready -U postgres -q 2>/dev/null; then
exit 0
fi
sleep 2
done
echo "so-postgres did not become ready within 120s" >&2
exit 1
- require:
- docker_container: so-postgres
# Ensure the shared Telegraf database exists. init-users.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: |
docker exec -i so-postgres psql -v ON_ERROR_STOP=1 -U postgres -d postgres <<'EOSQL'
SELECT 'CREATE DATABASE so_telegraf'
WHERE NOT EXISTS (SELECT FROM pg_database WHERE datname = 'so_telegraf')\gexec
EOSQL
- require:
- cmd: postgres_wait_ready
# 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: |
docker exec -i so-postgres psql -v ON_ERROR_STOP=1 -U postgres -d so_telegraf <<'EOSQL'
DO $$
BEGIN
IF NOT EXISTS (SELECT FROM pg_catalog.pg_roles WHERE rolname = 'so_telegraf') THEN
CREATE ROLE so_telegraf NOLOGIN;
END IF;
END
$$;
GRANT CONNECT ON DATABASE so_telegraf TO so_telegraf;
CREATE SCHEMA IF NOT EXISTS telegraf AUTHORIZATION so_telegraf;
GRANT USAGE, CREATE ON SCHEMA telegraf TO so_telegraf;
CREATE SCHEMA IF NOT EXISTS partman;
CREATE EXTENSION IF NOT EXISTS pg_partman SCHEMA partman;
CREATE EXTENSION IF NOT EXISTS pg_cron;
-- Hourly partman maintenance. cron.schedule is idempotent by jobname.
SELECT cron.schedule(
'telegraf-partman-maintenance',
'17 * * * *',
'CALL partman.run_maintenance_proc()'
);
EOSQL
- require:
- cmd: postgres_create_telegraf_db
{% set users = salt['pillar.get']('postgres:auth:users', {}) %}
{% for key, entry in users.items() %}
{% if key.startswith('telegraf_') and entry.get('user') and entry.get('pass') %}
{% set u = entry.user %}
{% set p = entry.pass | replace("'", "''") %}
postgres_telegraf_role_{{ u }}:
cmd.run:
- name: |
docker exec -i so-postgres psql -v ON_ERROR_STOP=1 -U postgres -d so_telegraf <<'EOSQL'
DO $$
BEGIN
IF NOT EXISTS (SELECT FROM pg_catalog.pg_roles WHERE rolname = '{{ u }}') THEN
EXECUTE format('CREATE ROLE %I WITH LOGIN PASSWORD %L', '{{ u }}', '{{ p }}');
ELSE
EXECUTE format('ALTER ROLE %I WITH PASSWORD %L', '{{ u }}', '{{ p }}');
END IF;
END
$$;
GRANT CONNECT ON DATABASE so_telegraf TO "{{ u }}";
GRANT so_telegraf TO "{{ u }}";
EOSQL
- require:
- 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) %}
postgres_telegraf_retention_reconcile:
cmd.run:
- name: |
docker exec -i so-postgres psql -v ON_ERROR_STOP=1 -U postgres -d so_telegraf <<'EOSQL'
DO $$
BEGIN
IF EXISTS (SELECT 1 FROM pg_catalog.pg_extension WHERE extname = 'pg_partman') THEN
UPDATE partman.part_config
SET retention = '{{ retention }} days',
retention_keep_table = false
WHERE parent_table LIKE 'telegraf.%';
END IF;
END
$$;
EOSQL
- require:
- cmd: postgres_telegraf_group_role
{% endif %}
{% else %}
{{sls}}_state_not_allowed:
test.fail_without_changes:
- name: {{sls}}_state_not_allowed
{% endif %}