diff --git a/.chloggen/add_k8s_jobs.yaml b/.chloggen/add_k8s_jobs.yaml new file mode 100755 index 0000000000..2d09470927 --- /dev/null +++ b/.chloggen/add_k8s_jobs.yaml @@ -0,0 +1,22 @@ +# Use this changelog template to create an entry for release notes. +# +# If your change doesn't affect end users you should instead start +# your pull request title with [chore] or use the "Skip Changelog" label. + +# One of 'breaking', 'deprecation', 'new_component', 'enhancement', 'bug_fix' +change_type: enhancement + +# The name of the area of concern in the attributes-registry, (e.g. http, cloud, db) +component: k8s + +# A brief description of the change. Surround your text with quotes ("") if it needs to start with a backtick (`). +note: Add k8s metrics for job and cronjob + +# Mandatory: One or more tracking issues related to the change. You can use the PR number here if no issue exists. +# The values here must be integers. +issues: [] + +# (Optional) One or more lines of additional information to render under the primary note. +# These lines will be padded with 2 spaces and then inserted directly into the document. +# Use pipe (|) for multiline entries. +subtext: diff --git a/docs/system/k8s-metrics.md b/docs/system/k8s-metrics.md index 9187ddf2db..9d01488b69 100644 --- a/docs/system/k8s-metrics.md +++ b/docs/system/k8s-metrics.md @@ -329,5 +329,143 @@ This metric is [recommended][MetricRecommended]. +### Metric: `k8s.job.active_pods` + +This metric is [recommended][MetricRecommended]. + + + + + + + + +| Name | Instrument Type | Unit (UCUM) | Description | Stability | +| -------- | --------------- | ----------- | -------------- | --------- | +| `k8s.job.active_pods` | Gauge | `{pod}` | The number of pending and actively running pods for a job [1] | ![Experimental](https://img.shields.io/badge/-experimental-blue) | + +**[1]:** This metric aligns with the `active` field of the +[K8s JobStatus](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.30/#jobstatus-v1-batch) + + + + + + +### Metric: `k8s.job.failed_pods` + +This metric is [recommended][MetricRecommended]. + + + + + + + + +| Name | Instrument Type | Unit (UCUM) | Description | Stability | +| -------- | --------------- | ----------- | -------------- | --------- | +| `k8s.job.failed_pods` | Gauge | `{pod}` | The number of pods which reached phase Failed for a job [1] | ![Experimental](https://img.shields.io/badge/-experimental-blue) | + +**[1]:** This metric aligns with the `failed` field of the +[K8s JobStatus](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.30/#jobstatus-v1-batch) + + + + + + +### Metric: `k8s.job.successful_pods` + +This metric is [recommended][MetricRecommended]. + + + + + + + + +| Name | Instrument Type | Unit (UCUM) | Description | Stability | +| -------- | --------------- | ----------- | -------------- | --------- | +| `k8s.job.successful_pods` | Gauge | `{pod}` | The number of pods which reached phase Succeeded for a job [1] | ![Experimental](https://img.shields.io/badge/-experimental-blue) | + +**[1]:** This metric aligns with the `succeeded` field of the +[K8s JobStatus](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.30/#jobstatus-v1-batch) + + + + + + +### Metric: `k8s.job.desired_successful_pods` + +This metric is [recommended][MetricRecommended]. + + + + + + + + +| Name | Instrument Type | Unit (UCUM) | Description | Stability | +| -------- | --------------- | ----------- | -------------- | --------- | +| `k8s.job.desired_successful_pods` | Gauge | `{pod}` | The desired number of successfully finished pods the job should be run with [1] | ![Experimental](https://img.shields.io/badge/-experimental-blue) | + +**[1]:** This metric aligns with the `completions` field of the +[K8s JobSpec](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.30/#jobspec-v1-batch) + + + + + + +### Metric: `k8s.job.max_parallel_pods` + +This metric is [recommended][MetricRecommended]. + + + + + + + + +| Name | Instrument Type | Unit (UCUM) | Description | Stability | +| -------- | --------------- | ----------- | -------------- | --------- | +| `k8s.job.max_parallel_pods` | Gauge | `{pod}` | The max desired number of pods the job should run at any given time [1] | ![Experimental](https://img.shields.io/badge/-experimental-blue) | + +**[1]:** This metric aligns with the `parallelism` field of the +[K8s JobSpec](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.30/#jobspec-v1-batch + + + + + + +### Metric: `k8s.cronjob.active_jobs` + +This metric is [recommended][MetricRecommended]. + + + + + + + + +| Name | Instrument Type | Unit (UCUM) | Description | Stability | +| -------- | --------------- | ----------- | -------------- | --------- | +| `k8s.cronjob.active_jobs` | Gauge | `{job}` | The number of actively running jobs for a cronjob [1] | ![Experimental](https://img.shields.io/badge/-experimental-blue) | + +**[1]:** This metric aligns with the `active` field of the +[K8s CronJobStatus](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.30/#cronjobstatus-v1-batch) + + + + + + [DocumentStatus]: https://opentelemetry.io/docs/specs/otel/document-status [MetricRecommended]: /docs/general/metric-requirement-level.md#recommended diff --git a/model/k8s/metrics.yaml b/model/k8s/metrics.yaml index 7afd7ec20d..ba29f88f25 100644 --- a/model/k8s/metrics.yaml +++ b/model/k8s/metrics.yaml @@ -126,3 +126,67 @@ groups: attributes: - ref: network.interface.name - ref: network.io.direction + + # k8s.job.* metrics + - id: metric.k8s.job.active_pods + type: metric + metric_name: k8s.job.active_pods + stability: experimental + brief: "The number of pending and actively running pods for a job" + instrument: gauge + unit: "{pod}" + note: | + This metric aligns with the `active` field of the + [K8s JobStatus](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.30/#jobstatus-v1-batch) + - id: metric.k8s.job.failed_pods + type: metric + metric_name: k8s.job.failed_pods + stability: experimental + brief: "The number of pods which reached phase Failed for a job" + instrument: gauge + unit: "{pod}" + note: | + This metric aligns with the `failed` field of the + [K8s JobStatus](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.30/#jobstatus-v1-batch) + - id: metric.k8s.job.successful_pods + type: metric + metric_name: k8s.job.successful_pods + stability: experimental + brief: "The number of pods which reached phase Succeeded for a job" + instrument: gauge + unit: "{pod}" + note: | + This metric aligns with the `succeeded` field of the + [K8s JobStatus](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.30/#jobstatus-v1-batch) + - id: metric.k8s.job.desired_successful_pods + type: metric + metric_name: k8s.job.desired_successful_pods + stability: experimental + brief: "The desired number of successfully finished pods the job should be run with" + instrument: gauge + unit: "{pod}" + note: | + This metric aligns with the `completions` field of the + [K8s JobSpec](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.30/#jobspec-v1-batch) + - id: metric.k8s.job.max_parallel_pods + type: metric + metric_name: k8s.job.max_parallel_pods + stability: experimental + brief: "The max desired number of pods the job should run at any given time" + instrument: gauge + unit: "{pod}" + note: | + This metric aligns with the `parallelism` field of the + [K8s JobSpec](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.30/#jobspec-v1-batch + + # k8s.job.* metrics + - id: metric.k8s.cronjob.active_jobs + type: metric + metric_name: k8s.cronjob.active_jobs + stability: experimental + brief: "The number of actively running jobs for a cronjob" + instrument: gauge + unit: "{job}" + note: | + This metric aligns with the `active` field of the + [K8s CronJobStatus](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.30/#cronjobstatus-v1-batch)