Dashboard YAML Templates

schema: v2
name: 'Hostmetrics: Overview'
description: Tracks host CPU, memory, and system load.
tags: [otel, infra]
version: v25.04.20
setup_link: https://example.com/setup
doc_link: https://example.com/docs

# Optional: minimum query interval
min_interval: 1m

# Optional: shift the query time window
time_offset: 5m

# Optional: only apply when these metrics exist
require_metrics:
  - metric: system_cpu_utilization
  - library: io.opentelemetry.instrumentation.system
    metric: system_cpu_time

table_grid_items:
  # ... summary widgets above the table

table:
  # ... table dashboard definition

grid_rows:
  # ... grid dashboard rows

metric_monitors:
  # ... bundled alert monitors

metrics:
  - system_cpu_utilization as $cpu_util
  - system_memory_usage as $mem_usage

query:
  - group by host_name
  - avg($cpu_util) as cpu_avg
  - sum($mem_usage{state="used"}) as mem_used
  - where device !~ "loop"

table:
  metrics:
    - system_cpu_utilization as $cpu_util
    - system_memory_usage as $mem_usage
  query:
    - group by host_name
    - avg($cpu_util) as cpu_util
    - sum($mem_usage{state="used"}) as mem_used
  columns:
    cpu_util: { unit: utilization }
    mem_used: { unit: bytes }
  variables: [deployment_environment, service_name]

columns:
  cpu_util: { unit: utilization }
  mem_used: { unit: bytes, color: red }
  availability: { unit: utilization, agg_func: avg }
  max_latency: { unit: milliseconds, agg_func: max, display: bar }

overrides:
  - column: cpu_util
    properties:
      - name: unit
        value: utilization
      - name: color
        value: red

table_grid_items:
  - title: Number of hosts
    type: text
    metrics:
      - system_memory_usage as $mem_usage
    query:
      - uniq($mem_usage, host_name) as num_host
    text: ${num_host} hosts

  - title: Memory utilization
    type: gauge
    metrics:
      - system_memory_usage as $mem_usage
    query:
      - sum($mem_usage{state!="free"}) / sum($mem_usage) as mem_util
    columns:
      mem_util: { unit: utilization }

grid_rows:
  - title: General
    items:
      - title: CPU utilization
        metrics:
          - system_cpu_utilization as $cpu_util
        query:
          - avg($cpu_util)

      - title: RAM usage
        metrics:
          - system_memory_usage as $mem_usage
        query:
          - sum($mem_usage) group by state
        columns:
          mem_usage: { unit: bytes }
        fill_opacity: 0.1

- title: CPU time
  # type: chart (default, can be omitted)
  metrics:
    - system_cpu_time as $cpu_time
  query:
    - perMin(sum($cpu_time)) as cpu_time group by state
  fill_opacity: 0.1

legend:
  type: table     # "none", "list", or "table"
  placement: bottom # "bottom" or "right"
  values: [avg, min, max, last]
  items_per_page: 10

- title: Slowest groups
  type: table
  metrics:
    - uptrace_tracing_spans as $spans
  query:
    - group by _group_id
    - group by _system
    - p50($spans)

- title: Span duration heatmap
  type: heatmap
  metric: uptrace_tracing_spans
  unit: milliseconds

- title: Status
  type: gauge
  metrics:
    - httpcheck_status as $status
  query:
    - sum($status{http_status_class="2xx"})
  value_mappings:
    - op: gte
      value: 1
      text: UP
      color: green
    - op: eq
      value: 0
      text: DOWN
      color: red
    - op: any
      text: UNKNOWN
      color: gray

- title: Host count
  type: text
  metrics:
    - process_runtime_go_goroutines as $goroutines
  query:
    - uniq($goroutines, host_name) as num_host
  text: ${num_host} hosts

properties:
  - name: chartType
    value: bar
  - name: fillOpacity
    value: 0.3
  - name: stack
    value: all

overrides:
  - matchers:
      - target: metric   # "metric" or "timeseries"
        value: cpu_idle
    properties:
      - name: unit
        value: utilization
      - name: color
        value: blue

metric_monitors:
  - key: cpu_usage
    name: CPU usage
    metrics:
      - system_cpu_load_average_15m as $load_avg_15m
      - system_cpu_time as $cpu_time
    query:
      - avg($load_avg_15m) / uniq($cpu_time, cpu) as cpu_util
      - group by host_name
    column_unit: utilization
    max_allowed_value: 3
    num_eval_points: 10
    trend_agg_func: last

# Parent: uptrace.dotnet.10.all.yml
schema: v2
name: '.NET: All'
tags: [otel, app]
version: v25.04.20

table:
  metrics:
    - process_runtime_dotnet_gc_heap_size as $heap_size
  query:
    - group by service_name
    - sum($heap_size) as heap_size

include_grid_rows:
  - uptrace.dotnet.20.gc
  - uptrace.dotnet.30.runtime
  - uptrace.dotnet.40.thread_pool

require_metrics:
  - metric: system_cpu_utilization
  - library: io.opentelemetry.instrumentation.system
    metric: system_cpu_time

tags: [otel, infra]         # Host metrics
tags: [otel, app, db]       # Go SQL client
tags: [otel, k8s, infra]    # Kubernetes infrastructure
tags: [self_monitoring]      # Uptrace self-monitoring

go run cmd/cloud/main.go dashboard validate_templates

schema: v2
name: 'HTTP Check: Endpoints'
description: Monitors HTTP endpoint availability and response times.
tags: [otel, infra]
version: v25.04.20
setup_link: https://example.com/setup

table_grid_items:
  - title: Successful checks
    type: text
    text: ${num_up} out of ${num_all}
    metrics:
      - httpcheck_status as $status
    query:
      - uniq($status{http_status_class="2xx"}) as num_all
      - uniq($status{http_status_class="2xx", _value=1}) as num_up

table:
  metrics:
    - httpcheck_status as $status
    - httpcheck_duration as $duration
  query:
    - group by http_url
    - group by host_name
    - sum($status{http_status_class="2xx"}) / sum($status) as availability
    - avg($duration)
  columns:
    availability: { unit: utilization, agg_func: avg }

grid_rows:
  - title: Gauges
    items:
      - title: Status
        type: gauge
        metrics:
          - httpcheck_status as $status
        query:
          - sum($status{http_status_class="2xx"})
        value_mappings:
          - op: gte
            value: 1
            text: UP
            color: green
          - op: eq
            value: 0
            text: DOWN
            color: red
          - op: any
            text: UNKNOWN
            color: gray

  - title: General
    items:
      - title: HTTP check result
        metrics:
          - httpcheck_status as $status
        query:
          - $status group by http_status_code

      - title: HTTP check duration
        metrics:
          - httpcheck_duration as $duration
        query:
          - avg($duration)

      - title: Span duration heatmap
        type: heatmap
        metric: uptrace_tracing_spans
        unit: milliseconds

metric_monitors:
  - key: http_check_is_down
    name: HTTP check is down
    metrics:
      - httpcheck_status as $status
    query:
      - sum($status{http_status_class="2xx"}) as status_2xx
      - group by http_url
      - group by host_name
    min_allowed_value: 1
    max_allowed_value: 1
    num_eval_points: 1
    absent_points: alert
    trend_agg_func: last