Merge pull request '修正共享 PG 计数器告警在新序列上的误报' (#174) from fix/shared-pg-sql-counter-new-series into main

Reviewed-on: #174

platform/observability/metrics/rules/shared-postgresql-sql.yaml

@@ -56,8 +56,13 @@ spec:
           labels: {severity: warning, service: shared-postgresql}
           annotations:
             summary: '共享 PG {{ $labels.env }} 复制槽 {{ $labels.slot_name }} 保留 WAL 超过 1 GiB'
+        # 计数器规则不用 increase()：MetricsQL 把新序列首个样本视为从 0 增长，exporter 新上线或
+        # 角色变化时，历史累计值（如 2026-09-25 搭建期的 9 次归档失败）会被当成刚发生而误报。
+        # 与 offset 相减对新序列返回空；计数器重置（重启/stats reset）得负值，同样不告警。
         - alert: SharedPostgresWalArchiveFailing
-          expr: increase(pg_stat_archiver_failed_count{job="shared-postgresql-sql"}[15m]) > 0
+          expr: >-
+            pg_stat_archiver_failed_count{job="shared-postgresql-sql"}
+            - pg_stat_archiver_failed_count{job="shared-postgresql-sql"} offset 15m > 0
           labels: {severity: warning, service: shared-postgresql}
           annotations:
             summary: '共享 PG {{ $labels.env }} {{ $labels.member }} WAL 归档失败，PITR 链可能中断'
@@ -105,13 +110,17 @@ spec:
           annotations:
             summary: '共享 PG {{ $labels.env }} {{ $labels.member }} 最老事务已运行超过 1 小时'
         - alert: SharedPostgresDeadlocks
-          expr: sum without(datname) (increase(pg_stat_database_deadlocks{job="shared-postgresql-sql"}[15m])) > 0
+          expr: >-
+            sum without(datname) (pg_stat_database_deadlocks{job="shared-postgresql-sql"}
+            - pg_stat_database_deadlocks{job="shared-postgresql-sql"} offset 15m) > 0
           labels: {severity: warning, service: shared-postgresql}
           annotations:
             summary: '共享 PG {{ $labels.env }} {{ $labels.member }} 15 分钟内出现死锁'
         # 每日 pgBackRest full 会请求一次 checkpoint；每小时多于 4 次通常意味着 max_wal_size 偏小。
         - alert: SharedPostgresCheckpointsRequested
-          expr: increase(pg_stat_checkpointer_num_requested_total{job="shared-postgresql-sql"}[1h]) > 4
+          expr: >-
+            pg_stat_checkpointer_num_requested_total{job="shared-postgresql-sql"}
+            - pg_stat_checkpointer_num_requested_total{job="shared-postgresql-sql"} offset 1h > 4
           for: 15m
           labels: {severity: warning, service: shared-postgresql}
           annotations:

platform/observability/metrics/tests/shared-postgresql-sql.test.yaml

@@ -117,9 +117,9 @@ tests:
   interval: 1m
   input_series:
   - series: pg_stat_database_deadlocks{job="shared-postgresql-sql",instance="p:9187",member="pg-pve1",env="prod",datname="app"}
-    values: '0 0 0 1 1 1'
+    values: '0x20 1x5'
   alert_rule_test:
-  - eval_time: 5m
+  - eval_time: 22m
     alertname: SharedPostgresDeadlocks
     exp_alerts:
     - exp_labels: {job: shared-postgresql-sql, instance: 'p:9187', member: pg-pve1, env: prod, severity: warning, service: shared-postgresql}
@@ -163,3 +163,33 @@ tests:
   - eval_time: 16m
     alertname: SharedPostgresPrimaryOnStandbyHost
     exp_alerts: []
+- name: 新出现的计数器序列带历史累计值不误报归档失败
+  interval: 1m
+  input_series:
+  - series: pg_stat_archiver_failed_count{job="shared-postgresql-sql",instance="l:9187",member="pg-laptop",env="prod"}
+    values: '_x20 9x20'
+  alert_rule_test:
+  - eval_time: 25m
+    alertname: SharedPostgresWalArchiveFailing
+    exp_alerts: []
+- name: 归档失败计数增长告警
+  interval: 1m
+  input_series:
+  - series: pg_stat_archiver_failed_count{job="shared-postgresql-sql",instance="l:9187",member="pg-laptop",env="prod"}
+    values: '9x20 10x5'
+  alert_rule_test:
+  - eval_time: 22m
+    alertname: SharedPostgresWalArchiveFailing
+    exp_alerts:
+    - exp_labels: {job: shared-postgresql-sql, instance: 'l:9187', member: pg-laptop, env: prod, severity: warning, service: shared-postgresql}
+      exp_annotations:
+        summary: 共享 PG prod pg-laptop WAL 归档失败，PITR 链可能中断
+- name: 计数器重置不误报 checkpoint
+  interval: 1m
+  input_series:
+  - series: pg_stat_checkpointer_num_requested_total{job="shared-postgresql-sql",instance="l:9187",member="pg-laptop",env="prod"}
+    values: '16x60 0x30'
+  alert_rule_test:
+  - eval_time: 85m
+    alertname: SharedPostgresCheckpointsRequested
+    exp_alerts: []