fix from official manifest
This commit is contained in:
@@ -1,90 +1,304 @@
|
||||
apiVersion: v1
|
||||
kind: ConfigMap
|
||||
metadata:
|
||||
name: argocd-metrics-server
|
||||
name: argocd-metrics-server-configmap
|
||||
data:
|
||||
# Prometheus URL - ADJUST THIS to match your Prometheus service
|
||||
prometheus.url: "http://prometheus-kube-prometheus-prometheus.monitoring.svc:9090"
|
||||
|
||||
# Metrics configuration for Deployments
|
||||
extension.metrics.deployments: |
|
||||
metrics:
|
||||
- name: CPU Usage
|
||||
description: Pod CPU usage
|
||||
graphType: area
|
||||
query: |
|
||||
sum(
|
||||
irate(
|
||||
container_cpu_usage_seconds_total{namespace="{{.metadata.namespace}}", pod=~"{{.metadata.name}}-.*"}[2m]
|
||||
)
|
||||
) by (pod)
|
||||
- name: Memory Usage
|
||||
description: Pod memory usage
|
||||
graphType: area
|
||||
query: |
|
||||
sum(
|
||||
container_memory_working_set_bytes{namespace="{{.metadata.namespace}}", pod=~"{{.metadata.name}}-.*"}
|
||||
) by (pod)
|
||||
- name: Replicas
|
||||
description: Deployment replicas
|
||||
graphType: line
|
||||
query: |
|
||||
sum(
|
||||
kube_deployment_status_replicas{namespace="{{.metadata.namespace}}", deployment="{{.metadata.name}}"}
|
||||
)
|
||||
|
||||
# Metrics configuration for Pods
|
||||
extension.metrics.pods: |
|
||||
metrics:
|
||||
- name: CPU Usage
|
||||
description: CPU usage by container
|
||||
graphType: area
|
||||
query: |
|
||||
sum(
|
||||
irate(
|
||||
container_cpu_usage_seconds_total{namespace="{{.metadata.namespace}}", pod="{{.metadata.name}}"}[2m]
|
||||
)
|
||||
) by (container)
|
||||
- name: Memory Usage
|
||||
description: Memory usage by container
|
||||
graphType: area
|
||||
query: |
|
||||
sum(
|
||||
container_memory_working_set_bytes{namespace="{{.metadata.namespace}}", pod="{{.metadata.name}}"}
|
||||
) by (container)
|
||||
- name: Network I/O
|
||||
description: Network traffic
|
||||
graphType: line
|
||||
query: |
|
||||
sum(
|
||||
rate(
|
||||
container_network_transmit_bytes_total{namespace="{{.metadata.namespace}}", pod="{{.metadata.name}}"}[2m]
|
||||
)
|
||||
) by (pod)
|
||||
|
||||
# Metrics configuration for Argo Rollouts
|
||||
extension.metrics.rollouts: |
|
||||
metrics:
|
||||
- name: CPU Usage
|
||||
description: Pod CPU usage
|
||||
graphType: area
|
||||
query: |
|
||||
sum(
|
||||
irate(
|
||||
container_cpu_usage_seconds_total{namespace="{{.metadata.namespace}}", pod=~"{{.metadata.name}}-.*"}[2m]
|
||||
)
|
||||
) by (pod)
|
||||
- name: Memory Usage
|
||||
description: Pod memory usage
|
||||
graphType: area
|
||||
query: |
|
||||
sum(
|
||||
container_memory_working_set_bytes{namespace="{{.metadata.namespace}}", pod=~"{{.metadata.name}}-.*"}
|
||||
) by (pod)
|
||||
- name: Replicas
|
||||
description: Rollout replicas
|
||||
graphType: line
|
||||
query: |
|
||||
sum(
|
||||
kube_deployment_status_replicas{namespace="{{.metadata.namespace}}", deployment=~"{{.metadata.name}}-.*"}
|
||||
)
|
||||
config.json: |
|
||||
{
|
||||
"prometheus": {
|
||||
"applications": [
|
||||
{
|
||||
"name": "default",
|
||||
"default": true,
|
||||
"dashboards": [
|
||||
{
|
||||
"groupKind": "pod",
|
||||
"tabs": ["Golden Signal"],
|
||||
"rows": [
|
||||
{
|
||||
"name": "pod",
|
||||
"title": "Pods",
|
||||
"tab": "Golden Signal",
|
||||
"graphs": [
|
||||
{
|
||||
"name": "pod_cpu_line",
|
||||
"title": "CPU",
|
||||
"description": "",
|
||||
"graphType": "line",
|
||||
"metricName": "pod",
|
||||
"queryExpression": "sum(rate(container_cpu_usage_seconds_total{pod=~\"{{.name}}\", image!=\"\", container!=\"POD\", container!=\"\", container_name!=\"POD\"}[5m])) by (pod)"
|
||||
},
|
||||
{
|
||||
"name": "pod_cpu_pie",
|
||||
"title": "CPU Avg",
|
||||
"description": "",
|
||||
"graphType": "pie",
|
||||
"metricName": "pod",
|
||||
"queryExpression": "sum(rate(container_cpu_usage_seconds_total{pod=~\"{{.name}}\", container!=\"POD\", image!=\"\", container!=\"\", container_name!=\"POD\"}[5m])) by (pod)"
|
||||
},
|
||||
{
|
||||
"name": "pod_memory_line",
|
||||
"title": "Memory",
|
||||
"description": "",
|
||||
"graphType": "line",
|
||||
"metricName": "pod",
|
||||
"queryExpression": "sum(rate(container_memory_usage_bytes{pod=~\"{{.name}}\", container!=\"POD\", image!=\"\", container!=\"\", container_name!=\"POD\"}[5m])) by (pod)"
|
||||
},
|
||||
{
|
||||
"name": "pod_memory_pie",
|
||||
"title": "Mem Avg",
|
||||
"description": "",
|
||||
"graphType": "pie",
|
||||
"metricName": "pod",
|
||||
"queryExpression": "sum(rate(container_memory_usage_bytes{pod=~\"{{.name}}\", container!=\"POD\", image!=\"\", container!=\"\", container_name!=\"POD\"}[5m])) by (pod)"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "container",
|
||||
"title": "Containers",
|
||||
"tab": "Golden Signal",
|
||||
"graphs": [
|
||||
{
|
||||
"name": "container_cpu_line",
|
||||
"title": "CPU",
|
||||
"description": "",
|
||||
"graphType": "line",
|
||||
"metricName": "container",
|
||||
"queryExpression": "sum(rate(container_cpu_usage_seconds_total{pod=~\"{{.name}}\", image!=\"\", container!=\"POD\", container!=\"\", container_name!=\"POD\"}[5m])) by (container)"
|
||||
},
|
||||
{
|
||||
"name": "container_cpu_pie",
|
||||
"title": "CPU Avg",
|
||||
"description": "",
|
||||
"graphType": "pie",
|
||||
"metricName": "container",
|
||||
"queryExpression": "sum(rate(container_cpu_usage_seconds_total{pod=~\"{{.name}}\", image!=\"\",container!=\"POD\", container!=\"\", container_name!=\"POD\"}[5m])) by (container)"
|
||||
},
|
||||
{
|
||||
"name": "container_memory_line",
|
||||
"title": "Memory",
|
||||
"description": "",
|
||||
"graphType": "line",
|
||||
"metricName": "container",
|
||||
"queryExpression": "sum(rate(container_memory_usage_bytes{pod=~\"{{.name}}\", image!=\"\", container!=\"POD\", container!=\"\", container_name!=\"POD\"}[5m])) by (container)"
|
||||
},
|
||||
{
|
||||
"name": "container_memory_pie",
|
||||
"title": "Mem Avg",
|
||||
"description": "",
|
||||
"graphType": "pie",
|
||||
"metricName": "container",
|
||||
"queryExpression": "sum(rate(container_memory_usage_bytes{pod=~\"{{.name}}\", image!=\"\", container!=\"POD\", container!=\"\", container_name!=\"POD\"}[5m])) by (container)"
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"groupKind": "deployment",
|
||||
"tabs": ["Golden Signal"],
|
||||
"rows": [
|
||||
{
|
||||
"name": "httplatency",
|
||||
"title": "HTTP Latency",
|
||||
"tab": "Golden Signal",
|
||||
"graphs": [
|
||||
{
|
||||
"name": "http_200_latency",
|
||||
"title": "Latency",
|
||||
"description": "",
|
||||
"graphType": "line",
|
||||
"metricName": "pod_template_hash",
|
||||
"queryExpression": "sum(rate(http_server_requests_seconds_sum {namespace=\"{{.namespace}}\", status=\"200\"} [1m])) by (pod_template_hash)"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "httperrortate",
|
||||
"title": "HTTP Error Rate",
|
||||
"tab": "Golden Signal",
|
||||
"graphs": [
|
||||
{
|
||||
"name": "http_error_rate_500",
|
||||
"title": "HTTP Error 500",
|
||||
"description": "",
|
||||
"graphType": "line",
|
||||
"metricName": "pod_template_hash",
|
||||
"queryExpression": "sum(rate(http_server_requests_seconds_count {namespace=\"{{.namespace}}\", status=\"500\"} [1m])) by (pod_template_hash)"
|
||||
},
|
||||
{
|
||||
"name": "http_error_rate_400",
|
||||
"title": "HTTP Error 400",
|
||||
"description": "",
|
||||
"graphType": "line",
|
||||
"metricName": "pod_template_hash",
|
||||
"queryExpression": "sum(rate(http_server_requests_seconds_count {namespace=\"{{.namespace}}\", status=\"404\"} [1m])) by (pod_template_hash)"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "httptraffic",
|
||||
"title": "HTTP Traffic",
|
||||
"tab": "Golden Signal",
|
||||
"graphs": [
|
||||
{
|
||||
"name": "http_traffic",
|
||||
"title": "Traffic",
|
||||
"description": "",
|
||||
"graphType": "line",
|
||||
"metricName": "pod_template_hash",
|
||||
"queryExpression": "sum(rate(http_server_requests_seconds_count {namespace=\"{{.namespace}}\"} [1m])) by (pod_template_hash)"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "pod",
|
||||
"title": "Pods",
|
||||
"tab": "Golden Signal",
|
||||
"graphs": [
|
||||
{
|
||||
"name": "pod_cpu_line",
|
||||
"title": "CPU",
|
||||
"description": "",
|
||||
"graphType": "line",
|
||||
"metricName": "pod",
|
||||
"queryExpression": "sum(rate(container_cpu_usage_seconds_total{pod=~\"{{.name}}\", image!=\"\", container!=\"POD\", container!=\"\", container_name!=\"POD\"}[5m])) by (pod)"
|
||||
},
|
||||
{
|
||||
"name": "pod_cpu_pie",
|
||||
"title": "CPU Avg",
|
||||
"description": "",
|
||||
"graphType": "pie",
|
||||
"metricName": "pod",
|
||||
"queryExpression": "sum(rate(container_cpu_usage_seconds_total{pod=~\"{{.name}}\", container!=\"POD\", image!=\"\", container!=\"\", container_name!=\"POD\"}[5m])) by (pod)"
|
||||
},
|
||||
{
|
||||
"name": "pod_memory_line",
|
||||
"title": "Memory",
|
||||
"description": "",
|
||||
"graphType": "line",
|
||||
"metricName": "pod",
|
||||
"queryExpression": "sum(rate(container_memory_usage_bytes{pod=~\"{{.name}}\", container!=\"POD\", image!=\"\", container!=\"\", container_name!=\"POD\"}[5m])) by (pod)"
|
||||
},
|
||||
{
|
||||
"name": "pod_memory_pie",
|
||||
"title": "Mem Avg",
|
||||
"description": "",
|
||||
"graphType": "pie",
|
||||
"metricName": "pod",
|
||||
"queryExpression": "sum(rate(container_memory_usage_bytes{pod=~\"{{.name}}\", container!=\"POD\", image!=\"\", container!=\"\", container_name!=\"POD\"}[5m])) by (pod)"
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"groupKind": "rollout",
|
||||
"tabs": ["Golden Signal"],
|
||||
"rows": [
|
||||
{
|
||||
"name": "httplatency",
|
||||
"title": "HTTP Latency",
|
||||
"tab": "Golden Signal",
|
||||
"graphs": [
|
||||
{
|
||||
"name": "http_200_latency",
|
||||
"title": "Latency",
|
||||
"description": "",
|
||||
"graphType": "line",
|
||||
"metricName": "rollout_template_hash",
|
||||
"queryExpression": "sum(rate(http_server_requests_seconds_sum {namespace=\"{{.namespace}}\", status=\"200\"} [1m])) by (rollout_template_hash)"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "httperrortate",
|
||||
"title": "HTTP Error Rate",
|
||||
"tab": "Golden Signal",
|
||||
"graphs": [
|
||||
{
|
||||
"name": "http_error_rate_500",
|
||||
"title": "HTTP Error 500",
|
||||
"description": "",
|
||||
"graphType": "line",
|
||||
"metricName": "rollout_template_hash",
|
||||
"queryExpression": "sum(rate(http_server_requests_seconds_count {namespace=\"{{.namespace}}\", status=\"500\"} [1m])) by (rollout_template_hash)"
|
||||
},
|
||||
{
|
||||
"name": "http_error_rate_400",
|
||||
"title": "HTTP Error 400",
|
||||
"description": "",
|
||||
"graphType": "line",
|
||||
"metricName": "rollout_template_hash",
|
||||
"queryExpression": "sum(rate(http_server_requests_seconds_count {namespace=\"{{.namespace}}\", status=\"404\"} [1m])) by (rollout_template_hash)"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "httptraffic",
|
||||
"title": "HTTP Traffic",
|
||||
"tab": "Golden Signal",
|
||||
"graphs": [
|
||||
{
|
||||
"name": "http_traffic",
|
||||
"title": "Traffic",
|
||||
"description": "",
|
||||
"graphType": "line",
|
||||
"metricName": "rollout_template_hash",
|
||||
"queryExpression": "sum(rate(http_server_requests_seconds_count {namespace=\"{{.namespace}}\"} [1m])) by (rollout_template_hash)"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "pod",
|
||||
"title": "Pods",
|
||||
"tab": "Golden Signal",
|
||||
"graphs": [
|
||||
{
|
||||
"name": "pod_cpu_line",
|
||||
"title": "CPU",
|
||||
"description": "",
|
||||
"graphType": "line",
|
||||
"metricName": "pod",
|
||||
"queryExpression": "sum(rate(container_cpu_usage_seconds_total{pod=~\"{{.name}}\", image!=\"\", container!=\"POD\", container!=\"\", container_name!=\"POD\"}[5m])) by (pod)"
|
||||
},
|
||||
{
|
||||
"name": "pod_cpu_pie",
|
||||
"title": "CPU Avg",
|
||||
"description": "",
|
||||
"graphType": "pie",
|
||||
"metricName": "pod",
|
||||
"queryExpression": "sum(rate(container_cpu_usage_seconds_total{pod=~\"{{.name}}\", container!=\"POD\", image!=\"\", container!=\"\", container_name!=\"POD\"}[5m])) by (pod)"
|
||||
},
|
||||
{
|
||||
"name": "pod_memory_line",
|
||||
"title": "Memory",
|
||||
"description": "",
|
||||
"graphType": "line",
|
||||
"metricName": "pod",
|
||||
"queryExpression": "sum(rate(container_memory_usage_bytes{pod=~\"{{.name}}\", container!=\"POD\", image!=\"\", container!=\"\", container_name!=\"POD\"}[5m])) by (pod)"
|
||||
},
|
||||
{
|
||||
"name": "pod_memory_pie",
|
||||
"title": "Mem Avg",
|
||||
"description": "",
|
||||
"graphType": "pie",
|
||||
"metricName": "pod",
|
||||
"queryExpression": "sum(rate(container_memory_usage_bytes{pod=~\"{{.name}}\", container!=\"POD\", image!=\"\", container!=\"\", container_name!=\"POD\"}[5m])) by (pod)"
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
"provider":
|
||||
{
|
||||
"Name": "default",
|
||||
"default": true,
|
||||
"address": "http://prometheus-kube-prometheus-prometheus.monitoring.svc:9090"
|
||||
}
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user