diff --git a/_data/rules.yml b/_data/rules.yml index 1f96294..1a86a36 100644 --- a/_data/rules.yml +++ b/_data/rules.yml @@ -207,10 +207,15 @@ services: description: PostgreSQL instance is down query: "pg_up == 0" severity: error - - name: Replication lag + - name: Postgresql replication lag description: PostgreSQL replication lag is going up (> 10s) query: "pg_replication_lag > 10" severity: warning + comments: | + A label excluding master nodes should be added to this query, + in order to monitor lag on standby servers only. + Exporter does not guarantee a NaN value for pg_replication_log on promoted master nodes. + See https://github.com/samber/awesome-prometheus-alerts/issues/74 - name: Table not vaccumed description: Table has not been vaccum for 24 hours query: "time() - pg_stat_user_tables_last_autovacuum > 60 * 60 * 24"