PMM-14411 - Enhance pg_custom_replication_wal query for accurate WAL … (#338)

* PMM-14411 - Enhance pg_custom_replication_wal query for accurate WAL metrics

Updated the pg_custom_replication_wal query to conditionally return the correct WAL metrics based on the database recovery state. Added logic to differentiate between received and current WAL LSNs, and adjusted lag calculation accordingly. Set the 'master' flag to true for this query to ensure it runs on the primary database instance.

* Refactor pg_custom_replication_wal query for clarity and accuracy

Updated the pg_custom_replication_wal query to improve readability and ensure accurate reporting of WAL metrics based on the node type (primary or replica). Adjusted the descriptions of the metrics to specify their relevance to either the primary or replica nodes, enhancing the overall understanding of the metrics collected.

Author: theTibi

queries-hr.yml

@@ -84,25 +84,33 @@ pg_custom_database_size_custom:
         description: "Disk space used by the database"
 
 pg_custom_replication_wal:
+  master: true
   query: |
     SELECT
-      pg_last_wal_receive_lsn() AS received_lsn,
-      pg_last_wal_replay_lsn() AS replayed_lsn,
-      pg_current_wal_lsn() AS current_lsn,
-      pg_current_wal_lsn() - pg_last_wal_replay_lsn() AS lag_bytes;
+      CASE WHEN pg_is_in_recovery() THEN 'replica' ELSE 'primary' END AS node_type,
+      CASE WHEN pg_is_in_recovery() THEN pg_last_wal_receive_lsn() ELSE NULL END AS received_lsn,
+      CASE WHEN pg_is_in_recovery() THEN pg_last_wal_replay_lsn() ELSE NULL END AS replayed_lsn,
+      CASE WHEN pg_is_in_recovery() THEN NULL ELSE pg_current_wal_lsn() END AS current_lsn,
+      CASE
+        WHEN pg_is_in_recovery() THEN pg_last_wal_receive_lsn() - pg_last_wal_replay_lsn()
+        ELSE NULL
+      END AS lag_bytes
   metrics:
+    - node_type:
+        usage: "LABEL"
+        description: "Type of node (primary or replica)."
     - received_lsn:
         usage: "GAUGE"
-        description: "Last WAL location received by the standby server."
+        description: "Last WAL location received by the standby server (replica only)."
     - replayed_lsn:
         usage: "GAUGE"
-        description: "Last WAL location replayed by the standby server."
+        description: "Last WAL location replayed by the standby server (replica only)."
     - current_lsn:
         usage: "GAUGE"
-        description: "Current WAL location on the primary server."
+        description: "Current WAL location on the primary server (primary only)."
     - lag_bytes:
         usage: "GAUGE"
-        description: "Current WAL replication lag in bytes."
+        description: "Current WAL replication lag in bytes (replica only)."
 
 pg_custom_stat_replication:
   query: |