{
  "name": "Errors & reliability",
  "description": "Where failures are concentrated right now -- 5xx, fatal events, and failed background jobs",
  "default_earliest": "-24h",
  "default_latest": "now",
  "panels": [
    {
      "title": "Error events",
      "query": "severity=ERROR | stats count",
      "viz_type": "single_stat",
      "position_x": 0,
      "position_y": 0,
      "width": 4,
      "height": 3,
      "query_language": "spl",
      "sort_order": 0
    },
    {
      "title": "Fatal events",
      "query": "severity=FATAL | stats count",
      "viz_type": "single_stat",
      "position_x": 4,
      "position_y": 0,
      "width": 4,
      "height": 3,
      "query_language": "spl",
      "sort_order": 1
    },
    {
      "title": "Failed jobs",
      "query": "service=worker result=failed | stats count",
      "viz_type": "single_stat",
      "position_x": 8,
      "position_y": 0,
      "width": 4,
      "height": 3,
      "query_language": "spl",
      "sort_order": 2
    },
    {
      "title": "Errors by service",
      "query": "severity=ERROR | stats count by service | sort -count",
      "viz_type": "bar",
      "position_x": 0,
      "position_y": 3,
      "width": 6,
      "height": 5,
      "viz_config": {
        "x_column": "service",
        "value_column": "count"
      },
      "query_language": "spl",
      "sort_order": 3
    },
    {
      "title": "Top API error codes",
      "query": "service=api | where status>=500 | stats count by error_code | sort -count | head 10",
      "viz_type": "top_n",
      "position_x": 6,
      "position_y": 3,
      "width": 6,
      "height": 5,
      "viz_config": {
        "label_column": "error_code",
        "value_column": "count"
      },
      "query_language": "spl",
      "sort_order": 4
    },
    {
      "title": "5xx by host and status",
      "query": "status>=500 | stats count by host, status",
      "viz_type": "heatmap",
      "position_x": 0,
      "position_y": 8,
      "width": 6,
      "height": 5,
      "viz_config": {
        "x_column": "host",
        "y_column": "status",
        "value_column": "count"
      },
      "query_language": "spl",
      "sort_order": 5
    },
    {
      "title": "Failed jobs by queue",
      "query": "service=worker result=failed | stats count by queue | sort -count",
      "viz_type": "bar",
      "position_x": 6,
      "position_y": 8,
      "width": 6,
      "height": 5,
      "viz_config": {
        "x_column": "queue",
        "value_column": "count"
      },
      "query_language": "spl",
      "sort_order": 6
    },
    {
      "title": "Recent 5xx responses",
      "query": "status>=500 | sort -timestamp | head 50 | fields timestamp, host, service, status, route, message",
      "viz_type": "table",
      "position_x": 0,
      "position_y": 13,
      "width": 12,
      "height": 6,
      "query_language": "spl",
      "sort_order": 7
    }
  ]
}