Files
homelab-infra/infrastructure/shared-postgresql/ansible/roles/pg_instance/templates/patroni.yml.j2
T
panxiao81andClaude Opus 5.5 0cd4a67e12 新增共享 PG 的 SQL 级指标与 dev 告警分流
- 数据库主机上按实例运行 prometheus-community/postgres_exporter 0.20.1,
  以实例 OS 用户走本地 socket,经 peer + ident 映射到仅有 pg_monitor 的
  homelab_monitor 角色;无密码、不经 Bao。版本与官方 sha256sums.txt 同源。
- prod/dev 启用 pg_stat_statements;monitoring.yml 仅在未生效时 reload/重启
  (prod 走 Patroni pending restart),重复执行 changed=0。
- 告警以上游 postgres_mixin 为底改写为 PrometheusRule,阈值对齐 Patroni
  failover lag 与 max_slot_wal_keep_size;抓取目标带 env 标签。
- Alertmanager 新增 env="dev" 路由到独立 dev 频道,dev SQL 检查告警补 env。

Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-01 16:20:15 +00:00

106 lines
3.5 KiB
Django/Jinja

# 实例化部署;不引用 Pigsty 的全局 /pg 或宿主内存自动调优。
name: {{ pg_member | to_json }}
namespace: /homelab/patroni/
scope: pg-prod
restapi:
listen: {{ pg_address }}:{{ pg_profile.api_port }}
connect_address: {{ pg_address }}:{{ pg_profile.api_port }}
authentication:
username: patroni
password: {{ pg_credentials.rest_password | to_json }}
etcd3:
hosts: {{ pg_etcd_endpoints | to_json }}
protocol: https
username: {{ pg_etcd_credentials.username | to_json }}
password: {{ pg_etcd_credentials.password | to_json }}
cacert: {{ pg_config_dir }}/ca.crt
cert: {{ pg_config_dir }}/etcd.crt
key: {{ pg_config_dir }}/etcd.key
bootstrap:
dcs:
ttl: 30
loop_wait: 10
retry_timeout: 10
maximum_lag_on_failover: 1048576
check_timeline: true
synchronous_mode: false
failsafe_mode: false
postgresql:
use_pg_rewind: true
use_slots: true
parameters:
max_connections: {{ pg_profile.max_connections }}
wal_level: replica
hot_standby: 'on'
wal_log_hints: 'on'
max_wal_senders: 5
max_replication_slots: 5
max_slot_wal_keep_size: 2GB
max_wal_size: 1GB
min_wal_size: 80MB
archive_mode: 'on'
archive_timeout: 300s
archive_command: "pgbackrest --config={{ pg_config_dir }}/pgbackrest.conf --stanza=prod archive-push %p"
initdb:
- encoding: UTF8
- locale: C.UTF-8
- data-checksums
postgresql:
listen: {{ pg_address }}:{{ pg_profile.port }}
connect_address: {{ pg_address }}:{{ pg_profile.port }}
data_dir: {{ pg_data_dir }}
bin_dir: {{ pg_bin_dir }}
pgpass: {{ pg_parent_dir }}/pgpass
use_unix_socket: true
use_unix_socket_repl: true
authentication:
superuser:
username: {{ pg_profile.user }}
password: {{ pg_credentials.superuser_password | to_json }}
replication:
username: replicator
password: {{ pg_credentials.replication_password | to_json }}
sslmode: verify-full
sslrootcert: {{ pg_config_dir }}/ca.crt
parameters:
unix_socket_directories: {{ pg_socket_dir }}
unix_socket_permissions: '0700'
password_encryption: scram-sha-256
# postmaster 级参数:变更后需由 monitoring.yml 执行 Patroni pending restart。
shared_preload_libraries: pg_stat_statements
shared_buffers: {{ pg_profile.shared_buffers }}
work_mem: 4MB
maintenance_work_mem: 64MB
ssl: 'on'
ssl_cert_file: {{ pg_config_dir }}/server.crt
ssl_key_file: {{ pg_config_dir }}/server.key
ssl_ca_file: {{ pg_config_dir }}/ca.crt
log_statement: none
log_min_error_statement: panic
pg_hba:
- local all {{ pg_monitor_user }} peer map=monitor
- local all {{ pg_profile.user }} peer
- local replication {{ pg_profile.user }} peer
- local replication replicator scram-sha-256
{% for address in pg_replication_addresses %}
- hostssl replication replicator {{ address }} scram-sha-256
- hostssl all {{ pg_profile.user }} {{ address }} scram-sha-256
{% endfor %}
{% for cidr in pg_client_cidrs %}
- hostssl all all {{ cidr }} scram-sha-256
{% endfor %}
- host all all 0.0.0.0/0 reject
- host all all ::/0 reject
# 只有实例 OS 用户(exporter 运行身份)可映射为监控角色。
pg_ident:
- monitor {{ pg_profile.user }} {{ pg_monitor_user }}
remove_data_directory_on_rewind_failure: false
remove_data_directory_on_diverged_timelines: false
watchdog:
mode: 'off'
tags:
nofailover: false
noloadbalance: false
clonefrom: false
nosync: false