add kafka dashboard and alert rules based on categraf acquisition (#1607

) * add kafka dashboard and alert rules based on categraf acquisition * add kafka dashboard and alert rules based on categraf acquisition
ccfos · Jul 6, 2023 · 21904f1 · 21904f1
1 parent b5d5ecb
commit 21904f1
Show file tree

Hide file tree

Showing 5 changed files with 560 additions and 0 deletions.
diff --git a/integrations/kafka/alerts/kafka_by_categraf.json b/integrations/kafka/alerts/kafka_by_categraf.json
@@ -0,0 +1,164 @@
+[
+  {
+    "cate": "prometheus",
+    "name": "kafka 数据有丢失风险-副本数小于3",
+    "note": "",
+    "prod": "",
+    "algorithm": "",
+    "algo_params": null,
+    "delay": 0,
+    "severity": 2,
+    "disabled": 1,
+    "prom_for_duration": 60,
+    "prom_ql": "sum(kafka_topic_partition_in_sync_replica) by (topic) < 3",
+    "prom_eval_interval": 15,
+    "enable_stime": "00:00",
+    "enable_stimes": [
+      "00:00"
+    ],
+    "enable_etime": "23:59",
+    "enable_etimes": [
+      "23:59"
+    ],
+    "enable_days_of_week": [
+      "1",
+      "2",
+      "3",
+      "4",
+      "5",
+      "6",
+      "0"
+    ],
+    "enable_days_of_weeks": [
+      [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ]
+    ],
+    "enable_in_bg": 0,
+    "notify_recovered": 1,
+    "notify_channels": [],
+    "notify_repeat_step": 60,
+    "notify_max_number": 0,
+    "recover_duration": 0,
+    "callbacks": [],
+    "runbook_url": "",
+    "append_tags": [
+      "service=kafka",
+      "type=categraf"
+    ]
+  },
+  {
+    "cate": "prometheus",
+    "name": "kafka 服务宕机",
+    "note": "",
+    "prod": "",
+    "algorithm": "",
+    "algo_params": null,
+    "delay": 0,
+    "severity": 1,
+    "disabled": 1,
+    "prom_for_duration": 60,
+    "prom_ql": "kafka_broker_info{service=~\"kafka\"} < 1",
+    "prom_eval_interval": 60,
+    "enable_stime": "00:00",
+    "enable_stimes": [
+      "00:00"
+    ],
+    "enable_etime": "23:59",
+    "enable_etimes": [
+      "23:59"
+    ],
+    "enable_days_of_week": [
+      "1",
+      "2",
+      "3",
+      "4",
+      "5",
+      "6",
+      "0"
+    ],
+    "enable_days_of_weeks": [
+      [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ]
+    ],
+    "enable_in_bg": 0,
+    "notify_recovered": 1,
+    "notify_channels": [],
+    "notify_repeat_step": 60,
+    "notify_max_number": 0,
+    "recover_duration": 0,
+    "callbacks": [],
+    "runbook_url": "",
+    "append_tags": [
+      "type=categraf",
+      "service=kafka"
+    ]
+  },
+  {
+    "cate": "prometheus",
+    "name": "kafka 消费能力不足-延迟超过5分钟",
+    "note": "",
+    "prod": "",
+    "algorithm": "",
+    "algo_params": null,
+    "delay": 0,
+    "severity": 2,
+    "disabled": 1,
+    "prom_for_duration": 60,
+    "prom_ql": "max(kafka_consumer_lag_millis) by (topic, consumergroup)  / 1000 > 300",
+    "prom_eval_interval": 15,
+    "enable_stime": "00:00",
+    "enable_stimes": [
+      "00:00"
+    ],
+    "enable_etime": "23:59",
+    "enable_etimes": [
+      "23:59"
+    ],
+    "enable_days_of_week": [
+      "1",
+      "2",
+      "3",
+      "4",
+      "5",
+      "6",
+      "0"
+    ],
+    "enable_days_of_weeks": [
+      [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ]
+    ],
+    "enable_in_bg": 0,
+    "notify_recovered": 1,
+    "notify_channels": [],
+    "notify_repeat_step": 60,
+    "notify_max_number": 0,
+    "recover_duration": 0,
+    "callbacks": [],
+    "runbook_url": "",
+    "append_tags": [
+      "service=kafka",
+      "type=categraf"
+    ]
+  }
+]