Files
securityonion/salt/postgres/tools/sbin/so-telegraf-postgres
T
Mike Reeves fe4f7ad2f7 Repair a stalled grid in one step, and only when it needs it
so-telegraf-partition-repair cleared the backlog but left the cause in place:
pg_cron's launcher is still dead, so the grid re-stalls as soon as it walks off
the premade window. Operators on the preview release need something they can run
once, before they soup, that leaves Telegraf collecting again.

Replace it with so-telegraf-repair, which fixes both halves. The running release
already creates the pg_cron extension and registers telegraf-partman-maintenance
in so_telegraf; only the launcher is missing, because so_telegraf did not exist
when the postmaster started. Restarting so-postgres is therefore enough to get
the existing job firing, so this touches no configuration and duplicates none of
the postgres state's SQL -- group_role still migrates the job to the postgres
database on the next soup. It also reconciles premake to 7 and prefers
so_admin.telegraf_maintenance() when that state has already landed.

Exit status separates healthy (0) from needs-repair (1) from does-not-apply (2),
which is what soup now gates on. postupgrade_changes runs after the highstate,
so the database is already converted by then and the backlog is the only thing
left to detect. Truncating is destructive and most grids were never affected --
fresh installs in particular, since they have no Telegraf history at all -- so
soup asks first and skips silently rather than clearing defaults on every host.
2026-08-10 10:05:16 -04:00

296 lines
11 KiB
Bash

#!/bin/bash
set -e
# Provision Telegraf state inside the so-postgres container.
# Usage: so-telegraf-postgres <subcommand>
# create_db Ensure the so_telegraf database exists.
# group_role Provision the so_telegraf group role, telegraf/partman schemas,
# pg_partman, the so_admin maintenance routines, and the hourly
# pg_cron maintenance job.
# user Create or update a per-minion login role granted to so_telegraf.
# Env: ROLE_USER, ROLE_PASS.
# retention Reconcile partman retention and premake on telegraf parents.
# Env: RETENTION_DAYS.
# maintenance Drain default partitions and run partman maintenance.
# check Report partition health. Non-zero if any parent is unhealthy.
#
# Once a default partition holds rows for a day with no child, Postgres cannot
# create that child at all -- attaching it would violate the default's
# constraint -- so maintenance drains defaults before calling partman.
# To recover a grid that is already in that state, use so-telegraf-repair,
# which discards the backlog instead of moving it and revives pg_cron's
# launcher without waiting for this state to be applied.
cmd="${1:?subcommand required}"
case "$cmd" in
create_db)
if ! docker exec so-postgres psql -U postgres -tAc \
"SELECT 1 FROM pg_database WHERE datname='so_telegraf'" | grep -q 1; then
docker exec so-postgres psql -v ON_ERROR_STOP=1 -U postgres \
-c "CREATE DATABASE so_telegraf"
fi
;;
group_role)
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;
-- Telegraf (running as so_telegraf) calls partman.create_parent()
-- on first write of each metric, which needs USAGE on the partman
-- schema, EXECUTE on its functions/procedures, and write access to
-- partman.part_config so it can register new partitioned parents.
GRANT USAGE, CREATE ON SCHEMA partman TO so_telegraf;
GRANT SELECT, INSERT, UPDATE, DELETE ON ALL TABLES IN SCHEMA partman TO so_telegraf;
GRANT EXECUTE ON ALL FUNCTIONS IN SCHEMA partman TO so_telegraf;
GRANT EXECUTE ON ALL PROCEDURES IN SCHEMA partman TO so_telegraf;
-- partman creates per-parent template tables (partman.template_*) at
-- runtime; default privileges extend DML/sequence access to them.
ALTER DEFAULT PRIVILEGES IN SCHEMA partman
GRANT SELECT, INSERT, UPDATE, DELETE ON TABLES TO so_telegraf;
ALTER DEFAULT PRIVILEGES IN SCHEMA partman
GRANT USAGE, SELECT, UPDATE ON SEQUENCES TO so_telegraf;
-- pg_cron runs these as postgres, so they must not sit in a schema any
-- Telegraf role can create objects in.
CREATE SCHEMA IF NOT EXISTS so_admin AUTHORIZATION postgres;
REVOKE ALL ON SCHEMA so_admin FROM PUBLIC;
CREATE OR REPLACE PROCEDURE so_admin.telegraf_maintenance()
LANGUAGE plpgsql
AS $proc$
DECLARE
r record;
v_default text;
v_rows bigint;
BEGIN
-- No per-parent EXCEPTION handler: partition_data_proc commits internally,
-- and COMMIT is illegal while a subtransaction is active. A failing parent
-- aborts the run and the next pass retries.
FOR r IN
SELECT parent_table, retention
FROM partman.part_config
WHERE parent_table LIKE 'telegraf.%'
ORDER BY parent_table
LOOP
v_default := format('%I.%I',
split_part(r.parent_table, '.', 1),
split_part(r.parent_table, '.', 2) || '_default');
CONTINUE WHEN to_regclass(v_default) IS NULL;
EXECUTE format('SELECT count(*) FROM %s', v_default) INTO v_rows;
CONTINUE WHEN v_rows = 0;
RAISE WARNING 'so_admin.telegraf_maintenance: % rows stranded in %, draining',
v_rows, v_default;
-- Cheaper to delete expired rows than to repartition and then drop them.
IF r.retention IS NOT NULL THEN
EXECUTE format('DELETE FROM %s WHERE "time" < now() - %L::interval',
v_default, r.retention);
COMMIT;
END IF;
-- Bounded so a large backlog drains across several runs.
CALL partman.partition_data_proc(
p_parent_table := r.parent_table,
p_loop_count := 200,
p_source_table := v_default
);
COMMIT;
END LOOP;
CALL partman.run_maintenance_proc();
END;
$proc$;
CREATE OR REPLACE FUNCTION so_admin.telegraf_partition_status()
RETURNS TABLE (
parent_table text,
oldest_child date,
newest_child date,
days_ahead int,
retention text,
default_rows bigint,
default_size text
)
LANGUAGE plpgsql
AS $func$
DECLARE
r record;
v_default regclass;
BEGIN
FOR r IN
SELECT pc.parent_table AS pt, pc.retention AS ret
FROM partman.part_config pc
WHERE pc.parent_table LIKE 'telegraf.%'
ORDER BY pc.parent_table
LOOP
parent_table := r.pt;
retention := r.ret;
SELECT min(d), max(d) INTO oldest_child, newest_child
FROM (
SELECT to_date(substring(c.relname FROM '_p(\d{8})$'), 'YYYYMMDD') AS d
FROM pg_inherits i
JOIN pg_class c ON c.oid = i.inhrelid
WHERE i.inhparent = r.pt::regclass
AND pg_get_expr(c.relpartbound, c.oid) <> 'DEFAULT'
) s;
days_ahead := newest_child - current_date;
v_default := to_regclass(format('%I.%I',
split_part(r.pt, '.', 1),
split_part(r.pt, '.', 2) || '_default'));
IF v_default IS NULL THEN
default_rows := NULL;
default_size := NULL;
ELSE
EXECUTE format('SELECT count(*) FROM %s', v_default::text) INTO default_rows;
default_size := pg_size_pretty(pg_total_relation_size(v_default));
END IF;
RETURN NEXT;
END LOOP;
END;
$func$;
-- Drop the registration older releases left in so_telegraf.
SELECT CASE
WHEN current_setting('cron.database_name', true) IS DISTINCT FROM current_database()
AND EXISTS (SELECT 1 FROM pg_catalog.pg_extension WHERE extname = 'pg_cron')
THEN 'true' ELSE 'false'
END AS drop_stale_cron \gset
\if :drop_stale_cron
DROP EXTENSION pg_cron CASCADE;
\endif
EOSQL
# Guarded on the live GUC so applying this before the postgresql.conf change
# has restarted the container skips rather than failing.
docker exec -i so-postgres psql -v ON_ERROR_STOP=1 -U postgres -d postgres <<'EOSQL'
SELECT CASE WHEN current_setting('cron.database_name', true) = current_database()
THEN 'true' ELSE 'false' END AS cron_here \gset
\if :cron_here
CREATE EXTENSION IF NOT EXISTS pg_cron;
-- cron.schedule_in_database is idempotent by jobname.
SELECT cron.schedule_in_database(
'telegraf-partman-maintenance',
'17 * * * *',
'CALL so_admin.telegraf_maintenance()',
'so_telegraf'
);
\else
\echo 'pg_cron metadata database is not `postgres` yet; skipping job registration.'
\endif
EOSQL
;;
user)
: "${ROLE_USER:?ROLE_USER is required}"
: "${ROLE_PASS:?ROLE_PASS is required}"
# psql does not substitute :vars inside dollar-quoted strings, so the
# conditional CREATE/ALTER is built outside any DO block and dispatched
# with \gexec. format() handles identifier/literal quoting.
docker exec -i so-postgres psql \
-v ON_ERROR_STOP=1 \
-v role_user="$ROLE_USER" \
-v role_pass="$ROLE_PASS" \
-U postgres -d so_telegraf <<'EOSQL'
-- Keep the password out of postgres.log if this DDL errors.
SET log_min_error_statement = panic;
SELECT format(
CASE WHEN EXISTS (SELECT FROM pg_catalog.pg_roles WHERE rolname = :'role_user')
THEN 'ALTER ROLE %I WITH LOGIN PASSWORD %L'
ELSE 'CREATE ROLE %I WITH LOGIN PASSWORD %L'
END,
:'role_user',
:'role_pass'
) \gexec
GRANT CONNECT ON DATABASE so_telegraf TO :"role_user";
GRANT so_telegraf TO :"role_user";
EOSQL
;;
retention)
: "${RETENTION_DAYS:?RETENTION_DAYS is required}"
# \gset + \if guards against a missing pg_partman without using a DO
# block (psql :var substitution doesn't reach into dollar-quoted code).
# premake is reconciled here because telegraf.conf only applies it to
# parents created from now on.
docker exec -i so-postgres psql \
-v ON_ERROR_STOP=1 \
-v retention_days="$RETENTION_DAYS" \
-U postgres -d so_telegraf <<'EOSQL'
SELECT CASE WHEN EXISTS (SELECT 1 FROM pg_catalog.pg_extension WHERE extname = 'pg_partman')
THEN 'true' ELSE 'false' END AS has_partman \gset
\if :has_partman
UPDATE partman.part_config
SET retention = :'retention_days' || ' days',
retention_keep_table = false,
premake = 7
WHERE parent_table LIKE 'telegraf.%';
\endif
EOSQL
;;
maintenance)
docker exec -i so-postgres psql -v ON_ERROR_STOP=1 -U postgres -d so_telegraf <<'EOSQL'
SELECT CASE WHEN to_regproc('so_admin.telegraf_maintenance') IS NOT NULL
THEN 'true' ELSE 'false' END AS has_proc \gset
\if :has_proc
CALL so_admin.telegraf_maintenance();
\else
\echo 'so_admin.telegraf_maintenance() is missing; run so-telegraf-postgres group_role first.'
\endif
EOSQL
;;
check)
docker exec -i so-postgres psql -U postgres -d so_telegraf <<'EOSQL'
\pset border 2
SELECT * FROM so_admin.telegraf_partition_status();
EOSQL
docker exec -i so-postgres psql -U postgres -d postgres <<'EOSQL'
\pset border 2
SELECT CASE WHEN to_regclass('cron.job_run_details') IS NOT NULL
THEN 'true' ELSE 'false' END AS has_cron \gset
\if :has_cron
SELECT d.status, d.return_message, d.start_time
FROM cron.job_run_details d
JOIN cron.job j ON j.jobid = d.jobid
WHERE j.jobname = 'telegraf-partman-maintenance'
ORDER BY d.start_time DESC
LIMIT 5;
\else
\echo 'pg_cron is not installed in this database.'
\endif
EOSQL
unhealthy=$(docker exec so-postgres psql -U postgres -d so_telegraf -tAc \
"SELECT count(*) FROM so_admin.telegraf_partition_status()
WHERE coalesce(default_rows, 0) > 0 OR coalesce(days_ahead, -1) < 1")
if [ "${unhealthy:-1}" != "0" ]; then
echo "so-telegraf-postgres check: $unhealthy telegraf parent(s) unhealthy" >&2
exit 1
fi
echo "so-telegraf-postgres check: all telegraf parents healthy"
;;
*)
echo "Unknown subcommand: $cmd" >&2
exit 1
;;
esac