Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

docs: Add per_model_metrics parameter to metrics.md #126

Merged
merged 3 commits into from
Nov 20, 2023
Merged

docs: Add per_model_metrics parameter to metrics.md #126

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
c304cfa
docs: Add `per_model_metrics` parameter to metrics.md
njhill Nov 16, 2023
cf25ffb
Merge branch 'main' into per-model-metrics-doc
rafvasq Nov 20, 2023
1657835
Small formatting changes
njhill Nov 20, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 7 additions & 5 deletions docs/metrics.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,11 +11,13 @@ The `MM_METRICS` env variable can be used to configure or disable how metrics ar

| | Purpose | Applies to | Default |
|:------------:|:---------------------------------------------------------------------------------------------------------------------------------------------------------------:|:--------------------------------------------------:|:----------------------------------:|
| `port` | Port on which to send or serve metrics | statsd (UDP push), prometheus (HTTP/HTTPS serve) | 8126 (statsd), 2112 (prometheus) |
| `fq_names` | Whether to use fully-qualified method names in request metrics | statsd, prometheus | false |
| `legacy` | Whether to publish legacy flavour (non-Sysdig) statsd metrics. Note that the legacy metrics are equivalent but have different names to those in the table below | statsd | false |
| `scheme` | Protocol scheme to use for Prometheus metrics, can be http or https | prometheus | https |
| `port` | Port on which to send or serve metrics | statsd (UDP push), prometheus (HTTP/HTTPS serve) | `8126` (statsd), `2112` (prometheus)|
| `fq_names` | Whether to use fully-qualified method names in request metrics | statsd, prometheus | `false` |
| `legacy` | Whether to publish legacy flavour (non-Sysdig) statsd metrics. Note that the legacy metrics are equivalent but have different names to those in the table below | statsd | `false` |
| `scheme` | Protocol scheme to use for Prometheus metrics, can be `http` or `https` | prometheus | `https` |
|`per_model_metrics`|Whether to include the `modelId` and `vModelId` labels in applicable published metrics|prometheus|`false` (*)|

(*) In versions of ModelMesh between Sep 5 2023 and Nov 16 2023, the default value of `per_model_metrics` was (unintentionally) `true`.

### Capturing Prometheus metrics

Expand Down Expand Up @@ -61,4 +63,4 @@ prometheus.io/scrape: "true"
| modelmesh_instance_capacity_bytes | Gauge | Pod | Effective model capacity of pod excluding unload buffer |
| modelmesh_instance_used_bytes | Gauge | Pod | Amount of capacity currently in use by loaded models |
| modelmesh_instance_used_bps | Gauge | Pod | Amount of capacity used in basis points (100ths of percent) |
| modelmesh_instance_models_total | Gauge | Pod | Number of model copies loaded in pod |
| modelmesh_instance_models_total | Gauge | Pod | Number of model copies loaded in pod |