cloudnative-pg

#

# Copyright © contributors to CloudNativePG, established as

# CloudNativePG a Series of LF Projects, LLC.

#

# Licensed under the Apache License, Version 2.0 (the "License");

# you may not use this file except in compliance with the License.

# You may obtain a copy of the License at

#

# http://www.apache.org/licenses/LICENSE-2.0

#

# Unless required by applicable law or agreed to in writing, software

# distributed under the License is distributed on an "AS IS" BASIS,

# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.

# See the License for the specific language governing permissions and

# limitations under the License.

#

# SPDX-License-Identifier: Apache-2.0

#

# Default values for CloudNativePG.

# This is a YAML-formatted file.

# Please declare variables to be passed to your templates.

replicaCount: 1

image:

repository: chainreg.biz/chainguard-private/cloudnative-pg

pullPolicy: IfNotPresent

# -- Overrides the image tag whose default is the chart appVersion.

tag: 1.30.1-r0@sha256:2bdff44601463e256bb1a001e6256d4c460e53246c3f62ba7e0cf59173bcc90a

imagePullSecrets: []

nameOverride: ""

fullnameOverride: ""

namespaceOverride: ""

hostNetwork: false

dnsPolicy: ""

# -- Update strategy for the operator.

# ref: https://kubernetes.io/docs/concepts/workloads/controllers/deployment/#strategy

updateStrategy: {}

# For example:

# type: RollingUpdate

# rollingUpdate:

# maxSurge: 25%

# maxUnavailable: 25%

crds:

# -- Specifies whether the CRDs should be created when installing the chart.

create: true

# -- The webhook configuration.

webhook:

port: 9443

mutating:

create: true

failurePolicy: Fail

validating:

create: true

failurePolicy: Fail

livenessProbe:

initialDelaySeconds: 3

readinessProbe:

initialDelaySeconds: 3

startupProbe:

failureThreshold: 6

periodSeconds: 5

# Operator configuration.

config:

# -- Specifies whether the secret should be created.

create: true

# -- The name of the configmap/secret to use.

name: cnpg-controller-manager-config

# -- Specifies whether it should be stored in a secret, instead of a configmap.

secret: false

# -- This option determines if the operator is responsible for observing

# events across the entire Kubernetes cluster or if its focus should be

# narrowed down to the specific namespace within which it has been deployed.

clusterWide: true

# -- The content of the configmap/secret, see

# https://cloudnative-pg.io/documentation/current/operator_conf/#available-options

# for all the available options.

data: {}

# INHERITED_ANNOTATIONS: categories

# INHERITED_LABELS: environment, workload, app

# WATCH_NAMESPACE: namespace-a,namespace-b

# -- The maximum number of concurrent reconciles. Defaults to 10.

maxConcurrentReconciles: 10

# -- Additional arguments to be added to the operator's args list.

additionalArgs: []

# -- Array containing extra environment variables which can be templated.

additionalEnv: []

# For example:

# - name: RELEASE_NAME

# value: "{{ .Release.Name }}"

# - name: MY_VAR

# value: "mySpecialKey"

serviceAccount:

# -- Specifies whether the service account should be created.

create: true

# -- The name of the service account to use.

# If not set and create is true, a name is generated using the fullname template.

name: ""

rbac:

# -- Specifies whether ClusterRole and ClusterRoleBinding should be created.

create: true

# -- Aggregate ClusterRoles to Kubernetes default user-facing roles.

# Ref: https://kubernetes.io/docs/reference/access-authn-authz/rbac/#user-facing-roles

aggregateClusterRoles: false

# -- Annotations to be added to all other resources.

commonAnnotations: {}

# -- Annotations to be added to the pod.

podAnnotations: {}

# -- Labels to be added to the pod.

podLabels: {}

# -- Container Security Context.

containerSecurityContext:

allowPrivilegeEscalation: false

readOnlyRootFilesystem: true

runAsUser: 10001

runAsGroup: 10001

seccompProfile:

type: RuntimeDefault

capabilities:

drop:

- "ALL"

# -- Security Context for the whole pod.

podSecurityContext:

runAsNonRoot: true

seccompProfile:

type: RuntimeDefault

# fsGroup: 2000

# -- Priority indicates the importance of a Pod relative to other Pods.

priorityClassName: ""

service:

type: ClusterIP

# -- The name of the Webhook Service.

name: cnpg-webhook-service

# DO NOT CHANGE THE SERVICE NAME as it is currently used to generate the certificate

# and can not be configured

port: 443

# -- Set the ip family policy to configure dual-stack see [Configure dual-stack](https://kubernetes.io/docs/concepts/services-networking/dual-stack/#services)

ipFamilyPolicy: ""

# -- Sets the families that should be supported and the order in which they should be applied to ClusterIP as well. Can be IPv4 and/or IPv6.

ipFamilies: []

resources: {}

# If you want to specify resources, uncomment the following

# lines, adjust them as necessary, and remove the curly braces after 'resources:'.

#

# limits:

# cpu: 100m

# memory: 200Mi

# requests:

# cpu: 100m

# memory: 100Mi

scratchData:

# -- EmptyDir options for the scratch-data volume.

emptyDir: {}

# -- Nodeselector for the operator to be installed.

nodeSelector: {}

# -- Topology Spread Constraints for the operator to be installed.

topologySpreadConstraints: []

# -- Tolerations for the operator to be installed.

tolerations: []

# -- Affinity for the operator to be installed.

affinity: {}

monitoring:

# -- Specifies whether the monitoring should be enabled. Requires Prometheus Operator CRDs.

podMonitorEnabled: false

# -- Metrics relabel configurations to apply to samples before ingestion.

podMonitorMetricRelabelings: []

# -- Relabel configurations to apply to samples before scraping.

podMonitorRelabelings: []

# -- Additional labels for the podMonitor

podMonitorAdditionalLabels: {}

grafanaDashboard:

create: false

# -- Allows overriding the namespace where the ConfigMap will be created, defaulting to the same one as the Release.

namespace: ""

# -- The name of the ConfigMap containing the dashboard.

configMapName: "cnpg-grafana-dashboard"

# -- Label that ConfigMaps should have to be loaded as dashboards. DEPRECATED: Use labels instead.

sidecarLabel: "grafana_dashboard"

# -- Label value that ConfigMaps should have to be loaded as dashboards. DEPRECATED: Use labels instead.

sidecarLabelValue: "1"

# -- Labels that ConfigMaps should have to get configured in Grafana.

labels: {}

# -- Annotations that ConfigMaps can have to get configured in Grafana.

annotations: {}

# Default monitoring queries

monitoringQueriesConfigMap:

# -- The name of the default monitoring configmap.

name: cnpg-default-monitoring

# -- A string representation of a YAML defining monitoring queries.

queries: |

backends:

query: |

SELECT sa.datname

, sa.usename

, sa.application_name

, states.state

, COALESCE(sa.count, 0) AS total

, COALESCE(sa.max_tx_secs, 0) AS max_tx_duration_seconds

FROM ( VALUES ('active')

, ('idle')

, ('idle in transaction')

, ('idle in transaction (aborted)')

, ('fastpath function call')

, ('disabled')

) AS states(state)

LEFT JOIN (

SELECT datname

, state

, usename

, COALESCE(application_name, '') AS application_name

, pg_catalog.count(*)

, COALESCE(EXTRACT (EPOCH FROM (pg_catalog.max(pg_catalog.now() OPERATOR(pg_catalog.-) xact_start))), 0) AS max_tx_secs

FROM pg_catalog.pg_stat_activity

GROUP BY datname, state, usename, application_name

) sa ON states.state OPERATOR(pg_catalog.=) sa.state

WHERE sa.usename IS NOT NULL

metrics:

- datname:

usage: "LABEL"

description: "Name of the database"

- usename:

usage: "LABEL"

description: "Name of the user"

- application_name:

usage: "LABEL"

description: "Name of the application"

- state:

usage: "LABEL"

description: "State of the backend"

- total:

usage: "GAUGE"

description: "Number of backends"

- max_tx_duration_seconds:

usage: "GAUGE"

description: "Maximum duration of a transaction in seconds"

backends_waiting:

query: |

SELECT pg_catalog.count(*) AS total

FROM pg_catalog.pg_locks blocked_locks

JOIN pg_catalog.pg_locks blocking_locks

ON blocking_locks.locktype OPERATOR(pg_catalog.=) blocked_locks.locktype

AND blocking_locks.database IS NOT DISTINCT FROM blocked_locks.database

AND blocking_locks.relation IS NOT DISTINCT FROM blocked_locks.relation

AND blocking_locks.page IS NOT DISTINCT FROM blocked_locks.page

AND blocking_locks.tuple IS NOT DISTINCT FROM blocked_locks.tuple

AND blocking_locks.virtualxid IS NOT DISTINCT FROM blocked_locks.virtualxid

AND blocking_locks.transactionid IS NOT DISTINCT FROM blocked_locks.transactionid

AND blocking_locks.classid IS NOT DISTINCT FROM blocked_locks.classid

AND blocking_locks.objid IS NOT DISTINCT FROM blocked_locks.objid

AND blocking_locks.objsubid IS NOT DISTINCT FROM blocked_locks.objsubid

AND blocking_locks.pid OPERATOR(pg_catalog.<>) blocked_locks.pid

JOIN pg_catalog.pg_stat_activity blocking_activity ON blocking_activity.pid OPERATOR(pg_catalog.=) blocking_locks.pid

WHERE NOT blocked_locks.granted

metrics:

- total:

usage: "GAUGE"

description: "Total number of backends that are currently waiting on other queries"

pg_database:

query: |

SELECT datname

, pg_catalog.pg_database_size(datname) AS size_bytes

, pg_catalog.age(datfrozenxid) AS xid_age

, pg_catalog.mxid_age(datminmxid) AS mxid_age

FROM pg_catalog.pg_database

WHERE datallowconn

metrics:

- datname:

usage: "LABEL"

description: "Name of the database"

- size_bytes:

usage: "GAUGE"

description: "Disk space used by the database"

- xid_age:

usage: "GAUGE"

description: "Number of transactions from the frozen XID to the current one"

- mxid_age:

usage: "GAUGE"

description: "Number of multiple transactions (Multixact) from the frozen XID to the current one"

pg_postmaster:

query: |

SELECT EXTRACT(EPOCH FROM pg_postmaster_start_time) AS start_time

FROM pg_catalog.pg_postmaster_start_time()

metrics:

- start_time:

usage: "GAUGE"

description: "Time at which postgres started (based on epoch)"

pg_replication:

query: |

SELECT CASE WHEN (

NOT pg_catalog.pg_is_in_recovery()

OR pg_catalog.pg_last_wal_receive_lsn() OPERATOR(pg_catalog.=) pg_catalog.pg_last_wal_replay_lsn())

THEN 0

ELSE GREATEST (0,

EXTRACT(EPOCH FROM (pg_catalog.now() OPERATOR(pg_catalog.-) pg_catalog.pg_last_xact_replay_timestamp())))

END AS lag,

pg_catalog.pg_is_in_recovery() AS in_recovery,

EXISTS (TABLE pg_catalog.pg_stat_wal_receiver) AS is_wal_receiver_up,

(SELECT pg_catalog.count(*) FROM pg_catalog.pg_stat_replication) AS streaming_replicas

metrics:

- lag:

usage: "GAUGE"

description: "Replication lag behind primary in seconds"

- in_recovery:

usage: "GAUGE"

description: "Whether the instance is in recovery"

- is_wal_receiver_up:

usage: "GAUGE"

description: "Whether the instance wal_receiver is up"

- streaming_replicas:

usage: "GAUGE"

description: "Number of streaming replicas connected to the instance"

pg_replication_slots:

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_stat_archiver:

query: |

SELECT archived_count

, failed_count

, COALESCE(EXTRACT(EPOCH FROM (pg_catalog.now() OPERATOR(pg_catalog.-) last_archived_time)), -1) AS seconds_since_last_archival

, COALESCE(EXTRACT(EPOCH FROM (pg_catalog.now() OPERATOR(pg_catalog.-) last_failed_time)), -1) AS seconds_since_last_failure

, COALESCE(EXTRACT(EPOCH FROM last_archived_time), -1) AS last_archived_time

, COALESCE(EXTRACT(EPOCH FROM last_failed_time), -1) AS last_failed_time

, COALESCE(CAST(CAST('x' OPERATOR(pg_catalog.||) pg_catalog.right(pg_catalog.split_part(last_archived_wal, '.', 1), 16) AS pg_catalog.bit(64)) AS pg_catalog.int8), -1) AS last_archived_wal_start_lsn

, COALESCE(CAST(CAST('x' OPERATOR(pg_catalog.||) pg_catalog.right(pg_catalog.split_part(last_failed_wal, '.', 1), 16) AS pg_catalog.bit(64)) AS pg_catalog.int8), -1) AS last_failed_wal_start_lsn

, EXTRACT(EPOCH FROM stats_reset) AS stats_reset_time

FROM pg_catalog.pg_stat_archiver

predicate_query: |

SELECT NOT pg_catalog.pg_is_in_recovery()

OR pg_catalog.current_setting('archive_mode') OPERATOR(pg_catalog.=) 'always'

metrics:

- archived_count:

usage: "COUNTER"

description: "Number of WAL files that have been successfully archived"

- failed_count:

usage: "COUNTER"

description: "Number of failed attempts for archiving WAL files"

- seconds_since_last_archival:

usage: "GAUGE"

description: "Seconds since the last successful archival operation"

- seconds_since_last_failure:

usage: "GAUGE"

description: "Seconds since the last failed archival operation"

- last_archived_time:

usage: "GAUGE"

description: "Epoch of the last time WAL archiving succeeded"

- last_failed_time:

usage: "GAUGE"

description: "Epoch of the last time WAL archiving failed"

- last_archived_wal_start_lsn:

usage: "GAUGE"

description: "Archived WAL start LSN"

- last_failed_wal_start_lsn:

usage: "GAUGE"

description: "Last failed WAL LSN"

- stats_reset_time:

usage: "GAUGE"

description: "Time at which these statistics were last reset"

pg_stat_bgwriter:

runonserver: "<17.0.0"

query: |

SELECT checkpoints_timed

, checkpoints_req

, checkpoint_write_time

, checkpoint_sync_time

, buffers_checkpoint

, buffers_clean

, maxwritten_clean

, buffers_backend

, buffers_backend_fsync

, buffers_alloc

FROM pg_catalog.pg_stat_bgwriter

metrics:

- checkpoints_timed:

usage: "COUNTER"

description: "Number of scheduled checkpoints that have been performed"

- checkpoints_req:

usage: "COUNTER"

description: "Number of requested checkpoints that have been performed"

- checkpoint_write_time:

usage: "COUNTER"

description: "Total amount of time that has been spent in the portion of checkpoint processing where files are written to disk, in milliseconds"

- checkpoint_sync_time:

usage: "COUNTER"

description: "Total amount of time that has been spent in the portion of checkpoint processing where files are synchronized to disk, in milliseconds"

- buffers_checkpoint:

usage: "COUNTER"

description: "Number of buffers written during checkpoints"

- buffers_clean:

usage: "COUNTER"

description: "Number of buffers written by the background writer"

- maxwritten_clean:

usage: "COUNTER"

description: "Number of times the background writer stopped a cleaning scan because it had written too many buffers"

- buffers_backend:

usage: "COUNTER"

description: "Number of buffers written directly by a backend"

- buffers_backend_fsync:

usage: "COUNTER"

description: "Number of times a backend had to execute its own fsync call (normally the background writer handles those even when the backend does its own write)"

- buffers_alloc:

usage: "COUNTER"

description: "Number of buffers allocated"

pg_stat_bgwriter_17:

runonserver: ">=17.0.0"

name: pg_stat_bgwriter

query: |

SELECT buffers_clean

, maxwritten_clean

, buffers_alloc

, EXTRACT(EPOCH FROM stats_reset) AS stats_reset_time

FROM pg_catalog.pg_stat_bgwriter

metrics:

- buffers_clean:

usage: "COUNTER"

description: "Number of buffers written by the background writer"

- maxwritten_clean:

usage: "COUNTER"

description: "Number of times the background writer stopped a cleaning scan because it had written too many buffers"

- buffers_alloc:

usage: "COUNTER"

description: "Number of buffers allocated"

- stats_reset_time:

usage: "GAUGE"

description: "Time at which these statistics were last reset"

pg_stat_checkpointer:

runonserver: ">=17.0.0"

query: |

SELECT num_timed AS checkpoints_timed

, num_requested AS checkpoints_req

, restartpoints_timed

, restartpoints_req

, restartpoints_done

, write_time

, sync_time

, buffers_written

, EXTRACT(EPOCH FROM stats_reset) AS stats_reset_time

FROM pg_catalog.pg_stat_checkpointer

metrics:

- checkpoints_timed:

usage: "COUNTER"

description: "Number of scheduled checkpoints that have been performed"

- checkpoints_req:

usage: "COUNTER"

description: "Number of requested checkpoints that have been performed"

- restartpoints_timed:

usage: "COUNTER"

description: "Number of scheduled restartpoints due to timeout or after a failed attempt to perform it"

- restartpoints_req:

usage: "COUNTER"

description: "Number of requested restartpoints that have been performed"

- restartpoints_done:

usage: "COUNTER"

description: "Number of restartpoints that have been performed"

- write_time:

usage: "COUNTER"

description: "Total amount of time that has been spent in the portion of processing checkpoints and restartpoints where files are written to disk, in milliseconds"

- sync_time:

usage: "COUNTER"

description: "Total amount of time that has been spent in the portion of processing checkpoints and restartpoints where files are synchronized to disk, in milliseconds"

- buffers_written:

usage: "COUNTER"

description: "Number of buffers written during checkpoints and restartpoints"

- stats_reset_time:

usage: "GAUGE"

description: "Time at which these statistics were last reset"

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

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_replication:

primary: true

query: |

SELECT usename

, COALESCE(application_name, '') AS application_name

, COALESCE(client_addr::text, '') AS client_addr

, COALESCE(client_port::text, '') AS client_port

, EXTRACT(EPOCH FROM backend_start) AS backend_start

, COALESCE(pg_catalog.age(backend_xmin), 0) AS backend_xmin_age

, pg_catalog.pg_wal_lsn_diff(pg_catalog.pg_current_wal_lsn(), sent_lsn) AS sent_diff_bytes

, pg_catalog.pg_wal_lsn_diff(pg_catalog.pg_current_wal_lsn(), write_lsn) AS write_diff_bytes

, pg_catalog.pg_wal_lsn_diff(pg_catalog.pg_current_wal_lsn(), flush_lsn) AS flush_diff_bytes

, COALESCE(pg_catalog.pg_wal_lsn_diff(pg_catalog.pg_current_wal_lsn(), replay_lsn),0) AS replay_diff_bytes

, COALESCE((EXTRACT(EPOCH FROM write_lag)),0)::float AS write_lag_seconds

, COALESCE((EXTRACT(EPOCH FROM flush_lag)),0)::float AS flush_lag_seconds

, COALESCE((EXTRACT(EPOCH FROM replay_lag)),0)::float AS replay_lag_seconds

FROM pg_catalog.pg_stat_replication

metrics:

- usename:

usage: "LABEL"

description: "Name of the replication user"

- application_name:

usage: "LABEL"

description: "Name of the application"

- client_addr:

usage: "LABEL"

description: "Client IP address"

- client_port:

usage: "LABEL"

description: "Client TCP port"

- backend_start:

usage: "COUNTER"

description: "Time when this process was started"

- backend_xmin_age:

usage: "COUNTER"

description: "The age of this standby's xmin horizon"

- sent_diff_bytes:

usage: "GAUGE"

description: "Difference in bytes from the last write-ahead log location sent on this connection"

- write_diff_bytes:

usage: "GAUGE"

description: "Difference in bytes from the last write-ahead log location written to disk by this standby server"

- flush_diff_bytes:

usage: "GAUGE"

description: "Difference in bytes from the last write-ahead log location flushed to disk by this standby server"

- replay_diff_bytes:

usage: "GAUGE"

description: "Difference in bytes from the last write-ahead log location replayed into the database on this standby server"

- write_lag_seconds:

usage: "GAUGE"

description: "Time elapsed between flushing recent WAL locally and receiving notification that this standby server has written it"

- flush_lag_seconds:

usage: "GAUGE"

description: "Time elapsed between flushing recent WAL locally and receiving notification that this standby server has written and flushed it"

- replay_lag_seconds:

usage: "GAUGE"

description: "Time elapsed between flushing recent WAL locally and receiving notification that this standby server has written, flushed and applied it"

pg_settings:

query: |

SELECT name,

CASE setting WHEN 'on' THEN '1' WHEN 'off' THEN '0' ELSE setting END AS setting

FROM pg_catalog.pg_settings

WHERE vartype IN ('integer', 'real', 'bool')

ORDER BY 1

metrics:

- name:

usage: "LABEL"

description: "Name of the setting"

- setting:

usage: "GAUGE"

description: "Setting value"

pg_extensions:

query: |

SELECT

pg_catalog.current_database() as datname,

name as extname,

default_version,

installed_version,

CASE

WHEN default_version OPERATOR(pg_catalog.=) installed_version THEN 0

ELSE 1

END AS update_available

FROM pg_catalog.pg_available_extensions

WHERE installed_version IS NOT NULL

metrics:

- datname:

usage: "LABEL"

description: "Name of the database"

- extname:

usage: "LABEL"

description: "Extension name"

- default_version:

usage: "LABEL"

description: "Default version"

- installed_version:

usage: "LABEL"

description: "Installed version"

- update_available:

usage: "GAUGE"

description: "An update is available"

target_databases:

- '*'