From b49b7e423d2431ebe36769e9d4acff135c6ae17f Mon Sep 17 00:00:00 2001 From: ChrsMark Date: Sat, 14 Dec 2024 15:59:18 +0200 Subject: [PATCH] Add notes about resource correlation Signed-off-by: ChrsMark --- docs/system/k8s-metrics.md | 30 ++++++++++++++++++++++++------ model/k8s/metrics.yaml | 30 ++++++++++++++++++++++++------ 2 files changed, 48 insertions(+), 12 deletions(-) diff --git a/docs/system/k8s-metrics.md b/docs/system/k8s-metrics.md index 0b33ca1e0f..eeb3fc79ec 100644 --- a/docs/system/k8s-metrics.md +++ b/docs/system/k8s-metrics.md @@ -345,7 +345,10 @@ This metric is [recommended][MetricRecommended]. | `k8s.job.active_pods` | UpDownCounter | `{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) +[K8s JobStatus](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.30/#jobstatus-v1-batch). + +This metric SHOULD, at a minimum, be reported against a +[`k8s.job`](../resource/k8s.md#job) resource. @@ -368,7 +371,10 @@ This metric is [recommended][MetricRecommended]. | `k8s.job.failed_pods` | UpDownCounter | `{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) +[K8s JobStatus](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.30/#jobstatus-v1-batch). + +This metric SHOULD, at a minimum, be reported against a +[`k8s.job`](../resource/k8s.md#job) resource. @@ -391,7 +397,10 @@ This metric is [recommended][MetricRecommended]. | `k8s.job.successful_pods` | UpDownCounter | `{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) +[K8s JobStatus](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.30/#jobstatus-v1-batch). + +This metric SHOULD, at a minimum, be reported against a +[`k8s.job`](../resource/k8s.md#job) resource. @@ -414,7 +423,10 @@ This metric is [recommended][MetricRecommended]. | `k8s.job.desired_successful_pods` | UpDownCounter | `{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) +[K8s JobSpec](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.30/#jobspec-v1-batch). + +This metric SHOULD, at a minimum, be reported against a +[`k8s.job`](../resource/k8s.md#job) resource. @@ -437,7 +449,10 @@ This metric is [recommended][MetricRecommended]. | `k8s.job.max_parallel_pods` | UpDownCounter | `{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 +[K8s JobSpec](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.30/#jobspec-v1-batch. + +This metric SHOULD, at a minimum, be reported against a +[`k8s.job`](../resource/k8s.md#job) resource. @@ -460,7 +475,10 @@ This metric is [recommended][MetricRecommended]. | `k8s.cronjob.active_jobs` | UpDownCounter | `{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) +[K8s CronJobStatus](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.30/#cronjobstatus-v1-batch). + +This metric SHOULD, at a minimum, be reported against a +[`k8s.cronjob`](../resource/k8s.md#cronjob) resource. diff --git a/model/k8s/metrics.yaml b/model/k8s/metrics.yaml index ea7fd2287b..57eba1e881 100644 --- a/model/k8s/metrics.yaml +++ b/model/k8s/metrics.yaml @@ -137,7 +137,10 @@ groups: 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) + [K8s JobStatus](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.30/#jobstatus-v1-batch). + + This metric SHOULD, at a minimum, be reported against a + [`k8s.job`](../resource/k8s.md#job) resource. - id: metric.k8s.job.failed_pods type: metric metric_name: k8s.job.failed_pods @@ -147,7 +150,10 @@ groups: 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) + [K8s JobStatus](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.30/#jobstatus-v1-batch). + + This metric SHOULD, at a minimum, be reported against a + [`k8s.job`](../resource/k8s.md#job) resource. - id: metric.k8s.job.successful_pods type: metric metric_name: k8s.job.successful_pods @@ -157,7 +163,10 @@ groups: 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) + [K8s JobStatus](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.30/#jobstatus-v1-batch). + + This metric SHOULD, at a minimum, be reported against a + [`k8s.job`](../resource/k8s.md#job) resource. - id: metric.k8s.job.desired_successful_pods type: metric metric_name: k8s.job.desired_successful_pods @@ -167,7 +176,10 @@ groups: 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) + [K8s JobSpec](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.30/#jobspec-v1-batch). + + This metric SHOULD, at a minimum, be reported against a + [`k8s.job`](../resource/k8s.md#job) resource. - id: metric.k8s.job.max_parallel_pods type: metric metric_name: k8s.job.max_parallel_pods @@ -177,7 +189,10 @@ groups: 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 JobSpec](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.30/#jobspec-v1-batch. + + This metric SHOULD, at a minimum, be reported against a + [`k8s.job`](../resource/k8s.md#job) resource. # k8s.job.* metrics - id: metric.k8s.cronjob.active_jobs @@ -189,4 +204,7 @@ groups: 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) + [K8s CronJobStatus](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.30/#cronjobstatus-v1-batch). + + This metric SHOULD, at a minimum, be reported against a + [`k8s.cronjob`](../resource/k8s.md#cronjob) resource.