{
  "case_id": "top-cpu-overload-nodes-and-log-patterns-in-saas01-during-latest-window",
  "hook_runs": [
    {
      "args": [
        "resolve-window",
        "--cluster-id",
        "{{environment.cluster_id}}",
        "--cluster-label",
        "{{environment.cluster_label}}",
        "--local-hour",
        "11",
        "--local-minute",
        "0",
        "--duration-minutes",
        "5",
        "--top-n-per-component",
        "3"
      ],
      "id": "resolve_runtime_window",
      "kind": "python_script",
      "output_id": "resolved_window",
      "output_path": "runtime/resolved_window.json",
      "path": "runtime_hook.py",
      "required": true,
      "stage": "before_acp",
      "status": "ok"
    },
    {
      "args": [
        "build-reference",
        "--cluster-id",
        "{{environment.cluster_id}}",
        "--cluster-label",
        "{{environment.cluster_label}}",
        "--start",
        "{{runtime.resolved_window.start}}",
        "--end",
        "{{runtime.resolved_window.end}}",
        "--top-n-per-component",
        "3"
      ],
      "id": "build_runtime_reference",
      "kind": "python_script",
      "output_id": "reference_answer",
      "output_path": "runtime/reference_answer.json",
      "path": "runtime_hook.py",
      "required": true,
      "stage": "before_judge",
      "status": "ok"
    }
  ],
  "outputs": {
    "reference_answer": {
      "data": {
        "cluster_id": "10989049060142230334",
        "debug": {
          "components": {
            "pd": {
              "cpu_query": "sum by (pod, instance) (rate(process_cpu_seconds_total{component=\"pd\"}[1m]))",
              "log_queries": [
                {
                  "logql": "{instance=\"db-pd-0\"} |~ `(?i)\\[error\\]|\\[warn(?:ing)?\\]`",
                  "matched_lines": 285,
                  "node": "db-pd-0",
                  "strategy": "instance_selector"
                },
                {
                  "logql": "{app=\"db-pd-0\"} |~ `(?i)\\[error\\]|\\[warn(?:ing)?\\]`",
                  "matched_lines": 0,
                  "node": "db-pd-0",
                  "strategy": "app_selector"
                },
                {
                  "logql": "{service_name=\"db-pd-0\"} |~ `(?i)\\[error\\]|\\[warn(?:ing)?\\]`",
                  "matched_lines": 0,
                  "node": "db-pd-0",
                  "strategy": "service_name_selector"
                },
                {
                  "logql": "{instance=\"db-pd-1\"} |~ `(?i)\\[error\\]|\\[warn(?:ing)?\\]`",
                  "matched_lines": 1,
                  "node": "db-pd-1",
                  "strategy": "instance_selector"
                },
                {
                  "logql": "{app=\"db-pd-1\"} |~ `(?i)\\[error\\]|\\[warn(?:ing)?\\]`",
                  "matched_lines": 0,
                  "node": "db-pd-1",
                  "strategy": "app_selector"
                },
                {
                  "logql": "{service_name=\"db-pd-1\"} |~ `(?i)\\[error\\]|\\[warn(?:ing)?\\]`",
                  "matched_lines": 0,
                  "node": "db-pd-1",
                  "strategy": "service_name_selector"
                },
                {
                  "logql": "{instance=\"db-pd-2\"} |~ `(?i)\\[error\\]|\\[warn(?:ing)?\\]`",
                  "matched_lines": 2,
                  "node": "db-pd-2",
                  "strategy": "instance_selector"
                },
                {
                  "logql": "{app=\"db-pd-2\"} |~ `(?i)\\[error\\]|\\[warn(?:ing)?\\]`",
                  "matched_lines": 0,
                  "node": "db-pd-2",
                  "strategy": "app_selector"
                },
                {
                  "logql": "{service_name=\"db-pd-2\"} |~ `(?i)\\[error\\]|\\[warn(?:ing)?\\]`",
                  "matched_lines": 0,
                  "node": "db-pd-2",
                  "strategy": "service_name_selector"
                }
              ],
              "observed_cpu_nodes": 3,
              "observed_quota_nodes": 3,
              "quota_query": "max by (pod, instance) (pd_service_maxprocs)",
              "selected_count": 3
            },
            "tidb": {
              "cpu_query": "sum by (pod, instance) (rate(process_cpu_seconds_total{component=\"tidb\"}[1m]))",
              "log_queries": [
                {
                  "logql": "{instance=\"db-tidb-10-ac-2006050899364941824\"} |~ `(?i)\\[error\\]|\\[warn(?:ing)?\\]`",
                  "matched_lines": 0,
                  "node": "db-tidb-10-ac-2006050899364941824",
                  "strategy": "instance_selector"
                },
                {
                  "logql": "{app=\"db-tidb-10-ac-2006050899364941824\"} |~ `(?i)\\[error\\]|\\[warn(?:ing)?\\]`",
                  "matched_lines": 0,
                  "node": "db-tidb-10-ac-2006050899364941824",
                  "strategy": "app_selector"
                },
                {
                  "logql": "{service_name=\"db-tidb-10-ac-2006050899364941824\"} |~ `(?i)\\[error\\]|\\[warn(?:ing)?\\]`",
                  "matched_lines": 0,
                  "node": "db-tidb-10-ac-2006050899364941824",
                  "strategy": "service_name_selector"
                },
                {
                  "logql": "{instance=\"db-tidb-17-ac-2006050899364941824\"} |~ `(?i)\\[error\\]|\\[warn(?:ing)?\\]`",
                  "matched_lines": 0,
                  "node": "db-tidb-17-ac-2006050899364941824",
                  "strategy": "instance_selector"
                },
                {
                  "logql": "{app=\"db-tidb-17-ac-2006050899364941824\"} |~ `(?i)\\[error\\]|\\[warn(?:ing)?\\]`",
                  "matched_lines": 0,
                  "node": "db-tidb-17-ac-2006050899364941824",
                  "strategy": "app_selector"
                },
                {
                  "logql": "{service_name=\"db-tidb-17-ac-2006050899364941824\"} |~ `(?i)\\[error\\]|\\[warn(?:ing)?\\]`",
                  "matched_lines": 0,
                  "node": "db-tidb-17-ac-2006050899364941824",
                  "strategy": "service_name_selector"
                },
                {
                  "logql": "{instance=\"db-tidb-3-ac-2006050899364941824\"} |~ `(?i)\\[error\\]|\\[warn(?:ing)?\\]`",
                  "matched_lines": 0,
                  "node": "db-tidb-3-ac-2006050899364941824",
                  "strategy": "instance_selector"
                },
                {
                  "logql": "{app=\"db-tidb-3-ac-2006050899364941824\"} |~ `(?i)\\[error\\]|\\[warn(?:ing)?\\]`",
                  "matched_lines": 0,
                  "node": "db-tidb-3-ac-2006050899364941824",
                  "strategy": "app_selector"
                },
                {
                  "logql": "{service_name=\"db-tidb-3-ac-2006050899364941824\"} |~ `(?i)\\[error\\]|\\[warn(?:ing)?\\]`",
                  "matched_lines": 0,
                  "node": "db-tidb-3-ac-2006050899364941824",
                  "strategy": "service_name_selector"
                }
              ],
              "observed_cpu_nodes": 38,
              "observed_quota_nodes": 38,
              "quota_query": "max by (pod, instance) (tidb_server_maxprocs)",
              "selected_count": 3
            },
            "tikv": {
              "cpu_query": "sum by (pod, instance) (rate(process_cpu_seconds_total{component=\"tikv\"}[1m]))",
              "log_queries": [
                {
                  "logql": "{instance=\"db-tikv-138\"} |~ `(?i)\\[error\\]|\\[warn(?:ing)?\\]`",
                  "matched_lines": 0,
                  "node": "db-tikv-138",
                  "strategy": "instance_selector"
                },
                {
                  "logql": "{app=\"db-tikv-138\"} |~ `(?i)\\[error\\]|\\[warn(?:ing)?\\]`",
                  "matched_lines": 0,
                  "node": "db-tikv-138",
                  "strategy": "app_selector"
                },
                {
                  "logql": "{service_name=\"db-tikv-138\"} |~ `(?i)\\[error\\]|\\[warn(?:ing)?\\]`",
                  "matched_lines": 0,
                  "node": "db-tikv-138",
                  "strategy": "service_name_selector"
                },
                {
                  "logql": "{instance=\"db-tikv-30\"} |~ `(?i)\\[error\\]|\\[warn(?:ing)?\\]`",
                  "matched_lines": 0,
                  "node": "db-tikv-30",
                  "strategy": "instance_selector"
                },
                {
                  "logql": "{app=\"db-tikv-30\"} |~ `(?i)\\[error\\]|\\[warn(?:ing)?\\]`",
                  "matched_lines": 0,
                  "node": "db-tikv-30",
                  "strategy": "app_selector"
                },
                {
                  "logql": "{service_name=\"db-tikv-30\"} |~ `(?i)\\[error\\]|\\[warn(?:ing)?\\]`",
                  "matched_lines": 0,
                  "node": "db-tikv-30",
                  "strategy": "service_name_selector"
                },
                {
                  "logql": "{instance=\"db-tikv-44\"} |~ `(?i)\\[error\\]|\\[warn(?:ing)?\\]`",
                  "matched_lines": 0,
                  "node": "db-tikv-44",
                  "strategy": "instance_selector"
                },
                {
                  "logql": "{app=\"db-tikv-44\"} |~ `(?i)\\[error\\]|\\[warn(?:ing)?\\]`",
                  "matched_lines": 0,
                  "node": "db-tikv-44",
                  "strategy": "app_selector"
                },
                {
                  "logql": "{service_name=\"db-tikv-44\"} |~ `(?i)\\[error\\]|\\[warn(?:ing)?\\]`",
                  "matched_lines": 0,
                  "node": "db-tikv-44",
                  "strategy": "service_name_selector"
                }
              ],
              "observed_cpu_nodes": 105,
              "observed_quota_nodes": 105,
              "quota_query": "max by (pod, instance) (tikv_server_cpu_cores_quota)",
              "selected_count": 3
            }
          }
        },
        "evidence_sufficient": true,
        "ranked_nodes": [
          {
            "avg_cpu_overload": 0.3979,
            "component": "tidb",
            "error_warn_log_count": 0,
            "node": "db-tidb-3-ac-2006050899364941824",
            "rank": 1
          },
          {
            "avg_cpu_overload": 0.3425,
            "component": "tidb",
            "error_warn_log_count": 0,
            "node": "db-tidb-17-ac-2006050899364941824",
            "rank": 2
          },
          {
            "avg_cpu_overload": 0.3415,
            "component": "tidb",
            "error_warn_log_count": 0,
            "node": "db-tidb-10-ac-2006050899364941824",
            "rank": 3
          },
          {
            "avg_cpu_overload": 0.5474,
            "component": "tikv",
            "error_warn_log_count": 0,
            "node": "db-tikv-30",
            "rank": 1
          },
          {
            "avg_cpu_overload": 0.5411,
            "component": "tikv",
            "error_warn_log_count": 0,
            "node": "db-tikv-44",
            "rank": 2
          },
          {
            "avg_cpu_overload": 0.536,
            "component": "tikv",
            "error_warn_log_count": 0,
            "node": "db-tikv-138",
            "rank": 3
          },
          {
            "avg_cpu_overload": 0.1995,
            "component": "pd",
            "error_warn_log_count": 285,
            "node": "db-pd-0",
            "rank": 1
          },
          {
            "avg_cpu_overload": 0.052,
            "component": "pd",
            "error_warn_log_count": 1,
            "node": "db-pd-1",
            "rank": 2
          },
          {
            "avg_cpu_overload": 0.0493,
            "component": "pd",
            "error_warn_log_count": 2,
            "node": "db-pd-2",
            "rank": 3
          }
        ],
        "window": {
          "end": "2026-07-21T03:05:00Z",
          "start": "2026-07-21T03:00:00Z"
        }
      },
      "path": "runtime/reference_answer.json",
      "stage": "before_judge"
    },
    "resolved_window": {
      "data": {
        "cluster_id": "10989049060142230334",
        "cluster_label": "saas01",
        "cpu_rule": "mean(rate(process_cpu_seconds_total[1m])) divided by component quota/maxprocs",
        "duration_minutes": 5,
        "end": "2026-07-21T03:05:00Z",
        "id": "bjt-2026-07-21-1100-5m",
        "local_date": "2026-07-21",
        "local_timezone": "Asia/Shanghai",
        "log_rule": "error_warn_only_unique_line_count_per_node",
        "start": "2026-07-21T03:00:00Z",
        "top_n_per_component": 3
      },
      "path": "runtime/resolved_window.json",
      "stage": "before_acp"
    }
  },
  "schema_version": 1,
  "template_context": {
    "audit": {
      "dir": "/data/eval_audits/evalrun-9ca3e149083040cfa6e5a554382fc030/evalcase-953d68b097254344af2acf6e28f4724e"
    },
    "case": {
      "case_version": "d7aaadae63ed",
      "id": "top-cpu-overload-nodes-and-log-patterns-in-saas01-during-latest-window"
    },
    "environment": {
      "cluster_id": "10989049060142230334",
      "cluster_label": "saas01",
      "cluster_type": "dedicated",
      "profile": "stable-dedicated",
      "tidb_version": "v8.5.x"
    },
    "time_window": {
      "resolved_by_output": "resolved_window"
    },
    "workspace": {
      "dir": "/data/workspaces/ws-eval-1784628628244-6b238c69",
      "id": "ws-eval-1784628628244-6b238c69"
    }
  },
  "workspace_id": "ws-eval-1784628628244-6b238c69"
}
