Skip to content

Add new metrics in default-monitoring configmap #10281

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
pchovelon wants to merge 4 commits into
base: main
Choose a base branch
from
Open

Add new metrics in default-monitoring configmap #10281

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
30e0a90
Add inactive_since metric of pg_replication_slots for v17+
pchovelon Mar 11, 2026
072af18
Add autovacuum workers count
pchovelon Mar 11, 2026
c2a7c28
Add metrics on parallel workers per database for v18+
pchovelon Mar 11, 2026
a09860f
Fix typo
pchovelon Mar 12, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
128 changes: 127 additions & 1 deletion config/manager/default-monitoring.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,6 +7,16 @@ metadata:
cnpg.io/reload: ""
data:
queries: |
autovacuum_workers:
query:
SELECT count(*)
FROM pg_catalog.pg_stat_activity
WHERE backend_type = 'autovacuum worker'
metrics:
- count:
usage: "COUNTER"
description: "Number of autovacuum workers currently running"

backends:
query: |
SELECT sa.datname
Expand Down Expand Up @@ -133,11 +143,43 @@ data:
description: "Number of streaming replicas connected to the instance"

pg_replication_slots:
runonserver: "<17.0.0"
query: |
SELECT slot_name,
slot_type,
database,
active,
(CASE pg_catalog.pg_is_in_recovery()
WHEN TRUE THEN pg_catalog.pg_wal_lsn_diff(pg_catalog.pg_last_wal_receive_lsn(), restart_lsn)
ELSE pg_catalog.pg_wal_lsn_diff(pg_catalog.pg_current_wal_lsn(), restart_lsn)
END) as pg_wal_lsn_diff
FROM pg_catalog.pg_replication_slots
WHERE NOT temporary
metrics:
- slot_name:
usage: "LABEL"
description: "Name of the replication slot"
- slot_type:
usage: "LABEL"
description: "Type of the replication slot"
- database:
usage: "LABEL"
description: "Name of the database"
- active:
usage: "GAUGE"
description: "Flag indicating whether the slot is active"
- pg_wal_lsn_diff:
usage: "GAUGE"
description: "Replication lag in bytes"

pg_replication_slots_17:
runonserver: ">=17.0.0"
query: |
SELECT slot_name,
slot_type,
database,
active,
EXTRACT(EPOCH FROM inactive_since) AS inactive_since,
(CASE pg_catalog.pg_is_in_recovery()
WHEN TRUE THEN pg_catalog.pg_wal_lsn_diff(pg_catalog.pg_last_wal_receive_lsn(), restart_lsn)
ELSE pg_catalog.pg_wal_lsn_diff(pg_catalog.pg_current_wal_lsn(), restart_lsn)
Expand All @@ -157,6 +199,9 @@ data:
- active:
usage: "GAUGE"
description: "Flag indicating whether the slot is active"
- inactive_since:
usage: "GAUGE"
description: "Epoch of the time when the slot become inactive"
- pg_wal_lsn_diff:
usage: "GAUGE"
description: "Replication lag in bytes"
Expand Down Expand Up @@ -317,6 +362,7 @@ data:
description: "Time at which these statistics were last reset"

pg_stat_database:
runonserver: "<18.0.0"
query: |
SELECT datname
, xact_commit
Expand All @@ -335,6 +381,80 @@ data:
, blk_read_time
, blk_write_time
FROM pg_catalog.pg_stat_database
metrics:
- datname:
usage: "LABEL"
description: "Name of this database"
- xact_commit:
usage: "COUNTER"
description: "Number of transactions in this database that have been committed"
- xact_rollback:
usage: "COUNTER"
description: "Number of transactions in this database that have been rolled back"
- blks_read:
usage: "COUNTER"
description: "Number of disk blocks read in this database"
- blks_hit:
usage: "COUNTER"
description: "Number of times disk blocks were found already in the buffer cache, so that a read was not necessary (this only includes hits in the PostgreSQL buffer cache, not the operating system's file system cache)"
- tup_returned:
usage: "COUNTER"
description: "Number of rows returned by queries in this database"
- tup_fetched:
usage: "COUNTER"
description: "Number of rows fetched by queries in this database"
- tup_inserted:
usage: "COUNTER"
description: "Number of rows inserted by queries in this database"
- tup_updated:
usage: "COUNTER"
description: "Number of rows updated by queries in this database"
- tup_deleted:
usage: "COUNTER"
description: "Number of rows deleted by queries in this database"
- conflicts:
usage: "COUNTER"
description: "Number of queries canceled due to conflicts with recovery in this database"
- temp_files:
usage: "COUNTER"
description: "Number of temporary files created by queries in this database"
- temp_bytes:
usage: "COUNTER"
description: "Total amount of data written to temporary files by queries in this database"
- deadlocks:
usage: "COUNTER"
description: "Number of deadlocks detected in this database"
- blk_read_time:
usage: "COUNTER"
description: "Time spent reading data file blocks by backends in this database, in milliseconds"
- blk_write_time:
usage: "COUNTER"
description: "Time spent writing data file blocks by backends in
this database, in milliseconds"

pg_stat_database_18:
runonserver: ">=18.0.0"
name: pg_stat_database
query: |
SELECT datname
, 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
, parallel_workers_launched
, parallel_workers_to_launch
FROM pg_catalog.pg_stat_database
metrics:
- datname:
usage: "LABEL"
Expand Down Expand Up @@ -384,6 +504,12 @@ data:
- blk_write_time:
usage: "COUNTER"
description: "Time spent writing data file blocks by backends in this database, in milliseconds"
- parallel_workers_launched:
usage: "COUNTER"
description: "Number of parallel workers launched by queries on this database"
- parallel_workers_to_launch:
usage: "COUNTER"
description: "Number of parallel workers planned to be launched by queries on this database"

pg_stat_replication:
primary: true
Expand Down Expand Up @@ -488,4 +614,4 @@ data:
usage: "GAUGE"
description: "An update is available"
target_databases:
- '*'
- '*'
Loading