dashboards/sdk/datadog/openmetrics.h_conf.yaml at c624e45fc07b36e6ba1f82dee7ddad27a7ad4987 · temporalio/dashboards · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
## OpenMetrics Configuration - CONVERT BUCKETS TO DISTRIBUTIONS

init_config:

instances:
  - openmetrics_endpoint: "http://localhost:9464/metrics"
    tags:
      - "service:temporal-worker"
      - "env:production"

    metrics:
      - "temporal_*"

    # KEY: Convert histogram buckets to distributions
    histogram_buckets_as_distributions: true    # Convert to distributions
    collect_histogram_buckets: true

    # Send buckets as distributions instead of individual metrics
    send_distribution_buckets: true             # Send as distributions
    send_distribution_counts_as_monotonic: true # For proper count handling
    send_histograms_buckets: false

    # Include all labels including "le" for bucket conversion
    include_labels:
      - "le"              # NEEDED for bucket conversion
      - "namespace"
      - "operation"
      - "workflow_type"
      - "activity_type"
      - "task_queue"
      - "worker_type"
      - "service_name"
      - "error_type"
      - "poller_type"
      - "failure_reason"

    exclude_labels:
      - "job"
      - "instance"
      - "__name__"

    timeout: 30
    min_collection_interval: 15

  # This will create distribution metrics that you can then enable percentiles for
  # in the Datadog Metrics Summary page:
  # temporal_request_latency (distribution)
  # temporal_workflow_endtoend_latency (distribution)
  # etc.
  # Example: You want to enable the `p95` percentile for `temporal_request_latency`:
  # 1. Visit https://app.datadoghq.com/metric/summary?metric=temporal_request_latency
  # 2. Set `Advanced > Percentiles > Configure > ON`