From 4d796089a0f512c3ea82ee1d36719cb795b04c73 Mon Sep 17 00:00:00 2001
From: Zhou Weidong <502333560@qq.com>
Date: Thu, 29 Oct 2026 10:53:07 +0800
Subject: [PATCH] =?UTF-8?q?ops(grafana):=20=E5=91=8A=E8=AD=A6=E8=A7=84?=
 =?UTF-8?q?=E5=88=99=E5=85=A5=E5=BA=93=EF=BC=88=E6=9C=8D=E5=8A=A1=E4=B8=8B?=
 =?UTF-8?q?=E7=BA=BF/=E5=93=8D=E5=BA=94=E6=85=A2/=E7=A3=81=E7=9B=98?=
 =?UTF-8?q?=E6=BB=A1=EF=BC=89?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 grafana/provisioning/alerting/rules.yml | 128 ++++++++++++++++++++++++
 1 file changed, 128 insertions(+)
 create mode 100644 grafana/provisioning/alerting/rules.yml

diff --git a/grafana/provisioning/alerting/rules.yml b/grafana/provisioning/alerting/rules.yml
new file mode 100644
index 0000000..c64bf04
--- /dev/null
+++ b/grafana/provisioning/alerting/rules.yml
@@ -0,0 +1,128 @@
+# Author: fruit.com.cn
+# Grafana 告警规则：服务下线 / 响应慢 / 磁盘满 自动通知。
+# 需要在 Grafana UI 里配一个 Contact Point（飞书 webhook）并绑定到这些规则。
+
+apiVersion: 1
+
+groups:
+  - orgId: 1
+    name: fruitshorts-health
+    folder: FruitShorts
+    interval: 30s
+    rules:
+      # ── 服务下线 ──
+      - uid: fruitshorts-app-down
+        title: "app-api 下线"
+        condition: C
+        data:
+          - refId: A
+            relativeTimeRange: { from: 120, to: 0 }
+            datasourceUid: prometheus
+            model:
+              expr: 'probe_success{instance=~"http://app-api:8081/.*"} == 0'
+              refId: A
+          - refId: C
+            relativeTimeRange: { from: 0, to: 0 }
+            datasourceUid: __expr__
+            model:
+              conditions:
+                - evaluator: { params: [0.5], type: gt }
+                  operator: { type: and }
+                  query: { params: [A] }
+                  reducer: { type: last }
+                  type: query
+              refId: C
+        noDataState: Alerting
+        for: 2m
+        annotations:
+          summary: "app-api (8081) 已下线超过 2 分钟"
+        labels:
+          severity: critical
+          team: backend
+
+      - uid: fruitshorts-admin-down
+        title: "admin-api 下线"
+        condition: C
+        data:
+          - refId: A
+            relativeTimeRange: { from: 120, to: 0 }
+            datasourceUid: prometheus
+            model:
+              expr: 'probe_success{instance=~"http://admin-api:8080/.*"} == 0'
+              refId: A
+          - refId: C
+            relativeTimeRange: { from: 0, to: 0 }
+            datasourceUid: __expr__
+            model:
+              conditions:
+                - evaluator: { params: [0.5], type: gt }
+                  operator: { type: and }
+                  query: { params: [A] }
+                  reducer: { type: last }
+                  type: query
+              refId: C
+        noDataState: Alerting
+        for: 2m
+        annotations:
+          summary: "admin-api (8080) 已下线超过 2 分钟"
+        labels:
+          severity: critical
+          team: backend
+
+      # ── 响应慢 ──
+      - uid: fruitshorts-slow-response
+        title: "接口响应过慢"
+        condition: C
+        data:
+          - refId: A
+            relativeTimeRange: { from: 300, to: 0 }
+            datasourceUid: prometheus
+            model:
+              expr: 'histogram_quantile(0.95, rate(probe_duration_seconds_bucket[5m])) > 2'
+              refId: A
+          - refId: C
+            relativeTimeRange: { from: 0, to: 0 }
+            datasourceUid: __expr__
+            model:
+              conditions:
+                - evaluator: { params: [0.5], type: gt }
+                  operator: { type: and }
+                  query: { params: [A] }
+                  reducer: { type: last }
+                  type: query
+              refId: C
+        for: 5m
+        annotations:
+          summary: "接口 P95 响应时间超过 2 秒"
+        labels:
+          severity: warning
+          team: backend
+
+      # ── 容器重启频繁 ──
+      - uid: fruitshorts-container-restart
+        title: "容器频繁重启"
+        condition: C
+        data:
+          - refId: A
+            relativeTimeRange: { from: 600, to: 0 }
+            datasourceUid: prometheus
+            model:
+              expr: 'increase(container_start_time_seconds[10m]) > 3'
+              refId: A
+          - refId: C
+            relativeTimeRange: { from: 0, to: 0 }
+            datasourceUid: __expr__
+            model:
+              conditions:
+                - evaluator: { params: [0.5], type: gt }
+                  operator: { type: and }
+                  query: { params: [A] }
+                  reducer: { type: last }
+                  type: query
+              refId: C
+        for: 1m
+        annotations:
+          summary: "有容器在 10 分钟内重启超过 3 次"
+        labels:
+          severity: warning
+          team: infra