---
schema_version: 1
id: tikv-read-iops-ranking-in-premium-cluster-during-incident-window
title: Cluster-scoped TiKV average node-disk read IOPS top-3 ranking
  in the primary premium cluster in the latest completed Beijing 11:00-11:05
  window
status: draft
owner: codex
evaluation:
  mode: adhoc_evidence
environment:
  profile: stable-premium
  cluster_id: '10748116073341772391'
  cluster_type: premium
  tidb_version: v8.5.x
  parent_id: '2026948324023603200'
  provider: alicloud
  region: ap-southeast-1
  infra_uuid: '019c9953-9f93-7daa-b097-e18a68c2b107'
  prefetched_input_path: prefetched_input.json
time_window:
  resolved_by_output: case_input
runtime:
  hooks:
  - id: prepare_case_input
    stage: before_acp
    kind: python_script
    path: runtime_hook.py
    output_id: case_input
    args:
    - prepare-case-input
    - "--cluster-id"
    - "{{environment.cluster_id}}"
    - "--local-hour"
    - '11'
    - "--local-minute"
    - '0'
    - "--duration-minutes"
    - '5'
    - "--step-seconds"
    - '60'
    - "--top-n"
    - '3'
    - "--prefetched-input-path"
    - "{{environment.prefetched_input_path}}"
  - id: build_runtime_reference
    stage: before_judge
    kind: python_script
    path: runtime_hook.py
    output_id: reference_answer
    args:
    - build-reference
    - "--cluster-id"
    - "{{environment.cluster_id}}"
    - "--parent-id"
    - "{{environment.parent_id}}"
    - "--provider"
    - "{{environment.provider}}"
    - "--region"
    - "{{environment.region}}"
    - "--infra-uuid"
    - "{{environment.infra_uuid}}"
    - "--start"
    - "{{runtime.case_input.start}}"
    - "--end"
    - "{{runtime.case_input.end}}"
    - "--step-seconds"
    - '60'
    - "--top-n"
    - '3'
    - "--case-input-output-id"
    - case_input
prompt:
  text: |
    帮我看一下 Premium 集群 {{environment.cluster_id}} 在 {{runtime.case_input.start}} 到 {{runtime.case_input.end}} 这 5 分钟里，哪些 TiKV 节点的磁盘读 IOPS 最高。

    我只关心最后结果：
    1. 帮我按这 5 分钟里每个 TiKV 节点的平均 read IOPS 从高到低排一下，直接给我前 3 个节点和它们各自的平均值；
    2. 最终只输出一个 `json` 代码块，字段必须严格为：
       `cluster_id`、`window`、`mapping_strategy`、`evidence_sufficient`、`top_nodes_by_avg_read_iops`
    3. `top_nodes_by_avg_read_iops` 中每个元素必须包含 `tikv_node` 和 `avg_read_iops`，并按 `avg_read_iops` 从高到低排序；
    4. 不要输出额外字段，不要输出额外解释，不要把说明写进 JSON。

    {{runtime.case_input.prefetched_infra_prompt}}

    JSON 结构如下：

    ```json
    {
      "cluster_id": "<cluster_id>",
      "window": {
        "start": "2026-01-01T00:00:00Z",
        "end": "2026-01-01T00:05:00Z"
      },
      "mapping_strategy": "node_filter",
      "evidence_sufficient": true,
      "top_nodes_by_avg_read_iops": [
        {
          "tikv_node": "db-tikv-0",
          "avg_read_iops": 12345.67
        }
      ]
    }
    ```

    不要求解释你的分析过程。

    如果证据不足，请明确说明原因，并把 `evidence_sufficient` 设为 `false`，把 `top_nodes_by_avg_read_iops` 设为空数组。
tags:
- storage-performance
- metric-scope
- read-iops
- structured-output
case_tier: P1
cost_tier: low
followup:
  scheduled_max_followups: 0
execution:
  acp_bash_timeout_s: 300