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]>
This commit is contained in:
@@ -88,9 +88,9 @@ def main():
|
||||
pg_etcd_endpoints=[f'{h["etcd_address"]}:23379' for h in hosts.values()],
|
||||
pg_config_dir='/node/config',pg_parent_dir='/node',pg_data_dir='/node/data',pg_socket_dir='/node/socket',
|
||||
pg_bin_dir='/usr/lib/postgresql/18/bin',pg_replication_addresses=['127.0.0.0/8'],pg_client_cidrs=['127.0.0.0/8'],
|
||||
pg_repo_remote=False,pg_repo_path='/repo')
|
||||
pg_repo_remote=False,pg_repo_path='/repo',pg_monitor_user='homelab_monitor')
|
||||
values[name]=v
|
||||
for template in (['postgresql.conf','pg_hba.conf'] if name=='dev' else ['patroni.yml','pgbackrest.conf']):
|
||||
for template in (['postgresql.conf','pg_hba.conf','pg_ident.conf'] if name=='dev' else ['patroni.yml','pgbackrest.conf']):
|
||||
(cfg/template).write_text(env.get_template(template+'.j2').render(**v))
|
||||
for folder in ['socket','backup-lock','backup-spool']:(d/folder).mkdir()
|
||||
(pg/'repo').mkdir();(pg/'restore').mkdir();(pg/'pitr').mkdir()
|
||||
@@ -131,6 +131,20 @@ def main():
|
||||
initial_backup=json.loads(backrest('p1','--output=json','info').stdout)[0]['backup'][-1]['label']
|
||||
recovery_target=sql('p1','SELECT clock_timestamp()::text')
|
||||
print('PASS: separate dev, TLS verify-full, non-superuser Ayatori native privileges, initial backup',flush=True)
|
||||
# 与 monitoring.yml 相同的声明:无密码,只能由实例 OS 用户经 peer + ident 映射登录。
|
||||
monitor_role="CREATE ROLE homelab_monitor LOGIN CONNECTION LIMIT 3 PASSWORD NULL; GRANT pg_monitor TO homelab_monitor; CREATE EXTENSION pg_stat_statements;"
|
||||
sql('p1',monitor_role);sql('dev',monitor_role)
|
||||
def monitor(name,query):
|
||||
return run(['docker','exec','-i',prefix+'-'+name,'psql','-X','-v','ON_ERROR_STOP=1','-At','-h','/node/socket','-p','25432','-U','homelab_monitor','postgres'],input=query).stdout.strip()
|
||||
for name in ['p1','p2','dev']:
|
||||
wait_for(lambda: monitor(name,"SELECT current_setting('shared_preload_libraries')||(SELECT count(*)>=0 FROM pg_stat_statements)")=='pg_stat_statementstrue')
|
||||
for name in ['p1','dev']:
|
||||
try:
|
||||
monitor(name,'CREATE TABLE public.monitor_write(id int)')
|
||||
raise AssertionError(f'monitor role could write on {name}')
|
||||
except subprocess.CalledProcessError:
|
||||
pass
|
||||
print('PASS: monitor role logs in via peer+ident on primary/standby/dev, reads pg_stat_statements, cannot write',flush=True)
|
||||
proxycfg=w/'proxy.cfg'
|
||||
# 文件父目录仍由调用者拥有,新增代理配置不触碰 PG 文件。
|
||||
proxycfg.write_text(env.get_template('haproxy.cfg.j2').render(pg_proxy_bind='127.0.2.10:26432',pg_proxy_members=[dict(name=n,address=values[n]['pg_address'],port=25432,api_port=28008) for n in ['p1','p2']]))
|
||||
|
||||
Reference in New Issue
Block a user