pgmon/sample-config/pgmon-metrics.yml

metrics:
  # Discovery metrics
  discover_dbs:
    type: set
    query:
      0: SELECT datname AS dbname FROM pg_database
  discover_rep:
    type: set
    query:
      0: SELECT client_addr || '_' || regexp_replace(application_name, '[ ,]', '_', 'g') AS repid, client_addr, state FROM pg_stat_replication
  discover_slots:
    type: set
    query:
      90400: SELECT slot_name, plugin, slot_type, database, false as temporary, active FROM pg_replication_slots
      100000: SELECT slot_name, plugin, slot_type, database, temporary, active FROM pg_replication_slots

  # cluster-wide metrics
  version:
    type: value
    query:
      0: SHOW server_version_num
  max_frozen_age:
    type: row
    query:
      0: SELECT max(age(datfrozenxid)) AS xid_age, max(mxid_age(datminmxid)) AS mxid_age FROM pg_database

  # Per-database metrics
  db_stats:
    type: row
    query:
      0: SELECT numbackends, xact_commit, xact_rollback, blks_read, blks_hit, tup_returned, tup_fetched, tup_inserted, tup_updated, tup_deleted, conflicts, temp_files, temp_bytes, deadlocks, blk_read_time, blk_write_time, extract('epoch' from stats_reset)::float FROM pg_stat_database WHERE datname = %(dbname)s
      140000: SELECT numbackends, xact_commit, xact_rollback, blks_read, blks_hit, tup_returned, tup_fetched, tup_inserted, tup_updated, tup_deleted, conflicts, temp_files, temp_bytes, deadlocks, COALESCE(checksum_failures, 0) AS checksum_failures, blk_read_time, blk_write_time, session_time, active_time, idle_in_transaction_time, sessions, sessions_abandoned, sessions_fatal, sessions_killed, extract('epoch' from stats_reset)::float FROM pg_stat_database WHERE datname = %(dbname)s
    test_args:
      dbname: postgres

  # Debugging
  ntables:
    type: value
    query:
      0: SELECT count(*) AS ntables FROM pg_stat_user_tables

  # Per-replication metrics
  rep_stats:
    type: row
    query:
      90400: SELECT * FROM pg_stat_replication WHERE client_addr || '_' || regexp_replace(application_name, '[ ,]', '_', 'g') = '{repid}'
    test_args:
      repid: 127.0.0.1_test_rep

  # Per-slot metrics
  slot_stats:
    type: row
    query:
      90400: SELECT active_pid, xmin, pg_xlog_location_diff(pg_current_xlog_location(), restart_lsn) AS restart_bytes, pg_xlog_location_diff(pg_current_xlog_location(), confirmed_flush_lsn) AS confirmed_flush_bytes FROM pg_replication_slots WHERE slot_name = '{slot}'
      100000: SELECT active_pid, xmin, pg_wal_lsn_diff(pg_current_wal_lsn(), restart_lsn) AS restart_bytes, pg_wal_lsn_diff(pg_current_wal_lsn(), confirmed_flush_lsn) AS confirmed_flush_bytes FROM pg_replication_slots WHERE slot_name = '{slot}'
    test_args:
      slot: test_slot