1951 lines
49 KiB
YAML
1951 lines
49 KiB
YAML
apiVersion: apps/v1
|
|
kind: Deployment
|
|
metadata:
|
|
annotations:
|
|
meta.helm.sh/release-name: grafana
|
|
meta.helm.sh/release-namespace: default
|
|
labels:
|
|
app.kubernetes.io/instance: grafana
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/name: grafana
|
|
app.kubernetes.io/version: 11.3.1
|
|
helm.sh/chart: grafana-8.6.4
|
|
name: grafana
|
|
namespace: default
|
|
spec:
|
|
progressDeadlineSeconds: 600
|
|
replicas: 1
|
|
revisionHistoryLimit: 10
|
|
selector:
|
|
matchLabels:
|
|
app.kubernetes.io/instance: grafana
|
|
app.kubernetes.io/name: grafana
|
|
strategy:
|
|
type: Recreate
|
|
template:
|
|
metadata:
|
|
annotations:
|
|
cattle.io/timestamp: '2025-10-04T04:05:51Z'
|
|
checksum/config: f6e2070ec7fff0d4bb82d9a8fabedb9934e42e64a00d72e25402d46520734840
|
|
checksum/sc-dashboard-provider-config: e70bf6a851099d385178a76de9757bb0bef8299da6d8443602590e44f05fdf24
|
|
checksum/secret: 4eccb44a21c8117c1dbfbfe43f2ac844b240cd2482bc9fba8e4047442d121dc2
|
|
kubectl.kubernetes.io/default-container: grafana
|
|
kubectl.kubernetes.io/restartedAt: '2026-10-28T17:14:50.583825+00:00'
|
|
labels:
|
|
app.kubernetes.io/instance: grafana
|
|
app.kubernetes.io/name: grafana
|
|
app.kubernetes.io/version: 11.3.1
|
|
helm.sh/chart: grafana-8.6.4
|
|
spec:
|
|
automountServiceAccountToken: true
|
|
containers:
|
|
- env:
|
|
- name: POD_IP
|
|
valueFrom:
|
|
fieldRef:
|
|
apiVersion: v1
|
|
fieldPath: status.podIP
|
|
- name: GF_SECURITY_ADMIN_USER
|
|
valueFrom:
|
|
secretKeyRef:
|
|
key: admin-user
|
|
name: grafana
|
|
- name: GF_SECURITY_ADMIN_PASSWORD
|
|
valueFrom:
|
|
secretKeyRef:
|
|
key: admin-password
|
|
name: grafana
|
|
- name: GF_PATHS_DATA
|
|
value: /var/lib/grafana/
|
|
- name: GF_PATHS_LOGS
|
|
value: /var/log/grafana
|
|
- name: GF_PATHS_PLUGINS
|
|
value: /var/lib/grafana/plugins
|
|
- name: GF_PATHS_PROVISIONING
|
|
value: /etc/grafana/provisioning
|
|
image: docker.io/grafana/grafana:11.6.16
|
|
imagePullPolicy: IfNotPresent
|
|
livenessProbe:
|
|
failureThreshold: 10
|
|
httpGet:
|
|
path: /api/health
|
|
port: 3000
|
|
scheme: HTTP
|
|
initialDelaySeconds: 60
|
|
periodSeconds: 10
|
|
successThreshold: 1
|
|
timeoutSeconds: 30
|
|
name: grafana
|
|
ports:
|
|
- containerPort: 3000
|
|
name: grafana
|
|
protocol: TCP
|
|
- containerPort: 9094
|
|
name: gossip-tcp
|
|
protocol: TCP
|
|
- containerPort: 9094
|
|
name: gossip-udp
|
|
protocol: UDP
|
|
readinessProbe:
|
|
failureThreshold: 3
|
|
httpGet:
|
|
path: /api/health
|
|
port: 3000
|
|
scheme: HTTP
|
|
periodSeconds: 10
|
|
successThreshold: 1
|
|
timeoutSeconds: 1
|
|
resources: {}
|
|
securityContext:
|
|
allowPrivilegeEscalation: false
|
|
capabilities:
|
|
drop:
|
|
- ALL
|
|
seccompProfile:
|
|
type: RuntimeDefault
|
|
terminationMessagePath: /dev/termination-log
|
|
terminationMessagePolicy: File
|
|
volumeMounts:
|
|
- mountPath: /etc/grafana/grafana.ini
|
|
name: config
|
|
subPath: grafana.ini
|
|
- mountPath: /var/lib/grafana
|
|
name: storage
|
|
- mountPath: /etc/grafana/provisioning/datasources/datasources.yaml
|
|
name: datasources-config
|
|
subPath: datasources.yaml
|
|
- mountPath: /etc/grafana/provisioning/dashboards/dashboards.yaml
|
|
name: dashboards-provider-config
|
|
subPath: dashboards.yaml
|
|
- mountPath: /var/lib/grafana-dashboards/ai-stack-dashboard.json
|
|
name: ai-stack-dashboard
|
|
subPath: ai-stack-dashboard.json
|
|
- mountPath: /var/lib/grafana-dashboards/systems-dashboard.json
|
|
name: systems-dashboard
|
|
subPath: systems-dashboard.json
|
|
- mountPath: /var/lib/grafana-dashboards/container-metrics-dashboard.json
|
|
name: container-metrics-dashboard
|
|
subPath: container-metrics-dashboard.json
|
|
dnsPolicy: ClusterFirst
|
|
enableServiceLinks: true
|
|
initContainers:
|
|
- command:
|
|
- chown
|
|
- -R
|
|
- 472:472
|
|
- /var/lib/grafana
|
|
image: docker.io/library/busybox:1.31.1
|
|
imagePullPolicy: IfNotPresent
|
|
name: init-chown-data
|
|
resources: {}
|
|
securityContext:
|
|
capabilities:
|
|
add:
|
|
- CHOWN
|
|
runAsNonRoot: false
|
|
runAsUser: 0
|
|
seccompProfile:
|
|
type: RuntimeDefault
|
|
terminationMessagePath: /dev/termination-log
|
|
terminationMessagePolicy: File
|
|
volumeMounts:
|
|
- mountPath: /var/lib/grafana
|
|
name: storage
|
|
restartPolicy: Always
|
|
schedulerName: default-scheduler
|
|
securityContext:
|
|
fsGroup: 472
|
|
runAsGroup: 472
|
|
runAsNonRoot: true
|
|
runAsUser: 472
|
|
serviceAccount: grafana
|
|
serviceAccountName: grafana
|
|
terminationGracePeriodSeconds: 30
|
|
volumes:
|
|
- configMap:
|
|
defaultMode: 420
|
|
name: grafana
|
|
name: config
|
|
- name: storage
|
|
persistentVolumeClaim:
|
|
claimName: grafana
|
|
- configMap:
|
|
defaultMode: 420
|
|
name: grafana-datasources
|
|
name: datasources-config
|
|
- configMap:
|
|
defaultMode: 420
|
|
name: grafana-dashboards-provider
|
|
name: dashboards-provider-config
|
|
- configMap:
|
|
defaultMode: 420
|
|
name: grafana-dashboard-ai-stack
|
|
name: ai-stack-dashboard
|
|
- configMap:
|
|
name: grafana-dashboard-systems
|
|
name: systems-dashboard
|
|
- configMap:
|
|
name: grafana-dashboard-containers
|
|
name: container-metrics-dashboard
|
|
---
|
|
apiVersion: v1
|
|
kind: Service
|
|
metadata:
|
|
annotations:
|
|
meta.helm.sh/release-name: grafana
|
|
meta.helm.sh/release-namespace: default
|
|
labels:
|
|
app.kubernetes.io/instance: grafana
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/name: grafana
|
|
app.kubernetes.io/version: 11.3.1
|
|
helm.sh/chart: grafana-8.6.4
|
|
name: grafana
|
|
namespace: default
|
|
spec:
|
|
clusterIP: 10.43.216.183
|
|
clusterIPs:
|
|
- 10.43.216.183
|
|
internalTrafficPolicy: Cluster
|
|
ipFamilies:
|
|
- IPv4
|
|
ipFamilyPolicy: SingleStack
|
|
ports:
|
|
- name: service
|
|
port: 8080
|
|
protocol: TCP
|
|
targetPort: 3000
|
|
selector:
|
|
app.kubernetes.io/instance: grafana
|
|
app.kubernetes.io/name: grafana
|
|
sessionAffinity: None
|
|
type: ClusterIP
|
|
---
|
|
apiVersion: v1
|
|
kind: Service
|
|
metadata:
|
|
annotations:
|
|
metallb.io/ip-allocated-from-pool: lan-pool
|
|
metallb.universe.tf/ip-allocated-from-pool: default-pool
|
|
metallb.universe.tf/loadBalancerIP: 140.44.4.32
|
|
finalizers:
|
|
- service.kubernetes.io/load-balancer-cleanup
|
|
labels:
|
|
app.kubernetes.io/instance: grafana
|
|
app.kubernetes.io/name: grafana
|
|
name: grafana-lb
|
|
namespace: default
|
|
spec:
|
|
allocateLoadBalancerNodePorts: true
|
|
clusterIP: 10.43.240.82
|
|
clusterIPs:
|
|
- 10.43.240.82
|
|
externalTrafficPolicy: Cluster
|
|
internalTrafficPolicy: Cluster
|
|
ipFamilies:
|
|
- IPv4
|
|
ipFamilyPolicy: SingleStack
|
|
loadBalancerIP: 140.44.4.32
|
|
ports:
|
|
- name: grafana-lb
|
|
nodePort: 32758
|
|
port: 88
|
|
protocol: TCP
|
|
targetPort: 3000
|
|
selector:
|
|
app.kubernetes.io/instance: grafana
|
|
app.kubernetes.io/name: grafana
|
|
sessionAffinity: None
|
|
type: LoadBalancer
|
|
---
|
|
apiVersion: networking.k8s.io/v1
|
|
kind: Ingress
|
|
metadata:
|
|
labels:
|
|
app.kubernetes.io/instance: grafana
|
|
app.kubernetes.io/name: grafana
|
|
name: grafana
|
|
namespace: default
|
|
spec:
|
|
ingressClassName: traefik
|
|
rules:
|
|
- host: grafana.snarfnet.net
|
|
http:
|
|
paths:
|
|
- backend:
|
|
service:
|
|
name: grafana-lb
|
|
port:
|
|
number: 80
|
|
path: /
|
|
pathType: ImplementationSpecific
|
|
tls:
|
|
- hosts:
|
|
- grafana.snarfnet.net
|
|
secretName: firefly-tls-cert
|
|
---
|
|
apiVersion: v1
|
|
kind: ConfigMap
|
|
metadata:
|
|
name: grafana-datasources
|
|
namespace: default
|
|
labels:
|
|
app.kubernetes.io/name: grafana
|
|
data:
|
|
datasources.yaml: |
|
|
apiVersion: 1
|
|
datasources:
|
|
- name: Prometheus
|
|
type: prometheus
|
|
access: proxy
|
|
url: http://prometheus:9090
|
|
isDefault: true
|
|
jsonData:
|
|
timeInterval: 15s
|
|
---
|
|
apiVersion: v1
|
|
kind: ConfigMap
|
|
metadata:
|
|
name: grafana-dashboards-provider
|
|
namespace: default
|
|
labels:
|
|
app.kubernetes.io/name: grafana
|
|
data:
|
|
dashboards.yaml: |
|
|
apiVersion: 1
|
|
providers:
|
|
- name: 'ai-stack-provider'
|
|
orgId: 1
|
|
folder: 'AI Stack & Inference'
|
|
type: file
|
|
disableDeletion: false
|
|
editable: true
|
|
options:
|
|
path: /var/lib/grafana-dashboards
|
|
---
|
|
apiVersion: v1
|
|
kind: ConfigMap
|
|
metadata:
|
|
name: grafana-dashboard-ai-stack
|
|
namespace: default
|
|
labels:
|
|
app.kubernetes.io/name: grafana
|
|
data:
|
|
ai-stack-dashboard.json: |
|
|
{
|
|
"annotations": {
|
|
"list": [
|
|
{
|
|
"builtIn": 1,
|
|
"datasource": "-- Grafana --",
|
|
"enable": true,
|
|
"hide": true,
|
|
"name": "Annotations & Alerts",
|
|
"type": "dashboard"
|
|
}
|
|
]
|
|
},
|
|
"editable": true,
|
|
"fiscalYearStartMonth": 0,
|
|
"graphTooltip": 1,
|
|
"id": null,
|
|
"links": [],
|
|
"liveNow": false,
|
|
"panels": [
|
|
{
|
|
"collapsed": false,
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 0
|
|
},
|
|
"id": 100,
|
|
"title": "\u26a1 AI Stack Executive Overview & Cloud Cost Offsets",
|
|
"type": "row"
|
|
},
|
|
{
|
|
"id": 1,
|
|
"title": "Prompt Tokens Processed (In)",
|
|
"type": "stat",
|
|
"gridPos": {
|
|
"h": 4,
|
|
"w": 6,
|
|
"x": 0,
|
|
"y": 1
|
|
},
|
|
"datasource": "Prometheus",
|
|
"targets": [
|
|
{
|
|
"expr": "sum(vllm:prompt_tokens_total)",
|
|
"legendFormat": "Prompt Tokens",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "thresholds"
|
|
},
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "blue",
|
|
"value": null
|
|
}
|
|
]
|
|
},
|
|
"unit": "locale"
|
|
}
|
|
},
|
|
"options": {
|
|
"colorMode": "value",
|
|
"graphMode": "area",
|
|
"justifyMode": "center"
|
|
}
|
|
},
|
|
{
|
|
"id": 2,
|
|
"title": "Generation Tokens Synthesized (Out)",
|
|
"type": "stat",
|
|
"gridPos": {
|
|
"h": 4,
|
|
"w": 6,
|
|
"x": 6,
|
|
"y": 1
|
|
},
|
|
"datasource": "Prometheus",
|
|
"targets": [
|
|
{
|
|
"expr": "sum(vllm:generation_tokens_total)",
|
|
"legendFormat": "Gen Tokens",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "thresholds"
|
|
},
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
}
|
|
]
|
|
},
|
|
"unit": "locale"
|
|
}
|
|
},
|
|
"options": {
|
|
"colorMode": "value",
|
|
"graphMode": "area",
|
|
"justifyMode": "center"
|
|
}
|
|
},
|
|
{
|
|
"id": 3,
|
|
"title": "Homelab Cloud API Savings ($USD)",
|
|
"type": "stat",
|
|
"gridPos": {
|
|
"h": 4,
|
|
"w": 6,
|
|
"x": 12,
|
|
"y": 1
|
|
},
|
|
"datasource": "Prometheus",
|
|
"targets": [
|
|
{
|
|
"expr": "(sum(vllm:prompt_tokens_total) * 0.00000025) + (sum(vllm:generation_tokens_total) * 0.00000100)",
|
|
"legendFormat": "Net Savings",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "thresholds"
|
|
},
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
}
|
|
]
|
|
},
|
|
"unit": "currencyUSD"
|
|
}
|
|
},
|
|
"options": {
|
|
"colorMode": "background",
|
|
"graphMode": "none",
|
|
"justifyMode": "center"
|
|
}
|
|
},
|
|
{
|
|
"id": 4,
|
|
"title": "Active GPU Cluster Health",
|
|
"type": "stat",
|
|
"gridPos": {
|
|
"h": 4,
|
|
"w": 6,
|
|
"x": 18,
|
|
"y": 1
|
|
},
|
|
"datasource": "Prometheus",
|
|
"targets": [
|
|
{
|
|
"expr": "count(DCGM_FI_DEV_GPU_TEMP)",
|
|
"legendFormat": "Tesla T4s Active",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "thresholds"
|
|
},
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "purple",
|
|
"value": null
|
|
}
|
|
]
|
|
},
|
|
"unit": "short"
|
|
}
|
|
},
|
|
"options": {
|
|
"colorMode": "value",
|
|
"graphMode": "none",
|
|
"justifyMode": "center"
|
|
}
|
|
},
|
|
{
|
|
"collapsed": false,
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 5
|
|
},
|
|
"id": 200,
|
|
"title": "\ud83c\udfae Tesla T4 GPU Cluster Telemetry (Harvester HCI Spacedock)",
|
|
"type": "row"
|
|
},
|
|
{
|
|
"id": 5,
|
|
"title": "GPU Core Utilization (%)",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 6
|
|
},
|
|
"datasource": "Prometheus",
|
|
"targets": [
|
|
{
|
|
"expr": "DCGM_FI_DEV_GPU_UTIL",
|
|
"legendFormat": "{{Hostname}} ({{modelName}})",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"custom": {
|
|
"drawStyle": "line",
|
|
"lineInterpolation": "smooth",
|
|
"fillOpacity": 20
|
|
},
|
|
"unit": "percent",
|
|
"min": 0,
|
|
"max": 100
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"id": 6,
|
|
"title": "VRAM Memory Allocated & Used",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 6
|
|
},
|
|
"datasource": "Prometheus",
|
|
"targets": [
|
|
{
|
|
"expr": "DCGM_FI_DEV_FB_USED * 1024 * 1024",
|
|
"legendFormat": "{{Hostname}} VRAM Used",
|
|
"refId": "A"
|
|
},
|
|
{
|
|
"expr": "(DCGM_FI_DEV_FB_USED + DCGM_FI_DEV_FB_FREE) * 1024 * 1024",
|
|
"legendFormat": "{{Hostname}} VRAM Total",
|
|
"refId": "B"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"custom": {
|
|
"drawStyle": "line",
|
|
"lineInterpolation": "smooth",
|
|
"fillOpacity": 15
|
|
},
|
|
"unit": "bytes"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"id": 7,
|
|
"title": "GPU Thermal Profile (\u00b0C)",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 7,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 14
|
|
},
|
|
"datasource": "Prometheus",
|
|
"targets": [
|
|
{
|
|
"expr": "DCGM_FI_DEV_GPU_TEMP",
|
|
"legendFormat": "{{Hostname}} (\u00b0C)",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"custom": {
|
|
"drawStyle": "line",
|
|
"lineInterpolation": "smooth",
|
|
"fillOpacity": 10
|
|
},
|
|
"unit": "celsius",
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "yellow",
|
|
"value": 65
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 80
|
|
}
|
|
]
|
|
}
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"id": 8,
|
|
"title": "GPU Power Draw (Watts)",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 7,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 14
|
|
},
|
|
"datasource": "Prometheus",
|
|
"targets": [
|
|
{
|
|
"expr": "DCGM_FI_DEV_POWER_USAGE",
|
|
"legendFormat": "{{Hostname}} (Watts)",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"custom": {
|
|
"drawStyle": "line",
|
|
"lineInterpolation": "smooth",
|
|
"fillOpacity": 15
|
|
},
|
|
"unit": "watt"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"collapsed": false,
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 21
|
|
},
|
|
"id": 300,
|
|
"title": "\ud83e\udde0 vLLM Real-Time Inference Dynamics & Token Velocity",
|
|
"type": "row"
|
|
},
|
|
{
|
|
"id": 9,
|
|
"title": "Token Generation Velocity (Tokens / Sec)",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 22
|
|
},
|
|
"datasource": "Prometheus",
|
|
"targets": [
|
|
{
|
|
"expr": "sum(rate(vllm:generation_tokens_total[2m])) by (model_name)",
|
|
"legendFormat": "{{model_name}} (Out)",
|
|
"refId": "A"
|
|
},
|
|
{
|
|
"expr": "sum(rate(vllm:prompt_tokens_total[2m])) by (model_name)",
|
|
"legendFormat": "{{model_name}} (In)",
|
|
"refId": "B"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"custom": {
|
|
"drawStyle": "line",
|
|
"lineInterpolation": "smooth",
|
|
"fillOpacity": 25
|
|
},
|
|
"unit": "cps"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"id": 10,
|
|
"title": "Inference Concurrency & Request Backlog",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 22
|
|
},
|
|
"datasource": "Prometheus",
|
|
"targets": [
|
|
{
|
|
"expr": "vllm:num_requests_running",
|
|
"legendFormat": "{{model_name}} Running",
|
|
"refId": "A"
|
|
},
|
|
{
|
|
"expr": "vllm:num_requests_waiting",
|
|
"legendFormat": "{{model_name}} Queued",
|
|
"refId": "B"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"custom": {
|
|
"drawStyle": "line",
|
|
"lineInterpolation": "stepAfter",
|
|
"fillOpacity": 15
|
|
},
|
|
"unit": "short"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"id": 11,
|
|
"title": "GPU KV Cache Memory Saturation",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 7,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 30
|
|
},
|
|
"datasource": "Prometheus",
|
|
"targets": [
|
|
{
|
|
"expr": "vllm:gpu_cache_usage_factor * 100",
|
|
"legendFormat": "{{model_name}} Cache Usage",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"custom": {
|
|
"drawStyle": "line",
|
|
"lineInterpolation": "smooth",
|
|
"fillOpacity": 30
|
|
},
|
|
"unit": "percent",
|
|
"min": 0,
|
|
"max": 100
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"id": 12,
|
|
"title": "NVIDIA Triton & Qdrant Operations",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 7,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 30
|
|
},
|
|
"datasource": "Prometheus",
|
|
"targets": [
|
|
{
|
|
"expr": "rate(nv_inference_request_success[2m])",
|
|
"legendFormat": "Triton Success/s",
|
|
"refId": "A"
|
|
},
|
|
{
|
|
"expr": "cpu_cores_used",
|
|
"legendFormat": "Qdrant CPU Cores",
|
|
"refId": "B"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"custom": {
|
|
"drawStyle": "line",
|
|
"lineInterpolation": "smooth"
|
|
},
|
|
"unit": "short"
|
|
}
|
|
}
|
|
}
|
|
],
|
|
"refresh": "10s",
|
|
"schemaVersion": 39,
|
|
"tags": [
|
|
"ai",
|
|
"vllm",
|
|
"dcgm",
|
|
"gpu",
|
|
"snarfnet"
|
|
],
|
|
"templating": {
|
|
"list": []
|
|
},
|
|
"time": {
|
|
"from": "now-6h",
|
|
"to": "now"
|
|
},
|
|
"timepicker": {
|
|
"refresh_intervals": [
|
|
"5s",
|
|
"10s",
|
|
"30s",
|
|
"1m",
|
|
"5m"
|
|
]
|
|
},
|
|
"timezone": "browser",
|
|
"title": "SnarfNet AI Stack & Inference Intelligence",
|
|
"uid": "snarfnet-ai-stack",
|
|
"version": 1
|
|
}
|
|
---
|
|
apiVersion: v1
|
|
kind: ConfigMap
|
|
metadata:
|
|
name: grafana-dashboard-systems
|
|
namespace: default
|
|
labels:
|
|
app.kubernetes.io/name: grafana
|
|
app.kubernetes.io/instance: grafana
|
|
data:
|
|
systems-dashboard.json: |-
|
|
{
|
|
"annotations": {
|
|
"list": []
|
|
},
|
|
"editable": true,
|
|
"fiscalYearStartMonth": 0,
|
|
"graphTooltip": 1,
|
|
"id": null,
|
|
"links": [],
|
|
"liveNow": false,
|
|
"panels": [
|
|
{
|
|
"collapsed": false,
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 0
|
|
},
|
|
"id": 100,
|
|
"title": "\ud83d\udda5\ufe0f Systems Fleet Overview & Capacity",
|
|
"type": "row"
|
|
},
|
|
{
|
|
"id": 1,
|
|
"title": "Online Node Exporters",
|
|
"type": "stat",
|
|
"gridPos": {
|
|
"h": 4,
|
|
"w": 6,
|
|
"x": 0,
|
|
"y": 1
|
|
},
|
|
"datasource": "Prometheus",
|
|
"targets": [
|
|
{
|
|
"expr": "count(node_load1)",
|
|
"legendFormat": "{{instance}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "thresholds"
|
|
},
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
}
|
|
]
|
|
},
|
|
"unit": "none"
|
|
}
|
|
},
|
|
"options": {
|
|
"colorMode": "value",
|
|
"graphMode": "area",
|
|
"justifyMode": "center"
|
|
}
|
|
},
|
|
{
|
|
"id": 2,
|
|
"title": "Avg Cluster CPU Load (1m)",
|
|
"type": "stat",
|
|
"gridPos": {
|
|
"h": 4,
|
|
"w": 6,
|
|
"x": 6,
|
|
"y": 1
|
|
},
|
|
"datasource": "Prometheus",
|
|
"targets": [
|
|
{
|
|
"expr": "avg(node_load1)",
|
|
"legendFormat": "{{instance}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "thresholds"
|
|
},
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "blue",
|
|
"value": null
|
|
}
|
|
]
|
|
},
|
|
"unit": "none"
|
|
}
|
|
},
|
|
"options": {
|
|
"colorMode": "value",
|
|
"graphMode": "area",
|
|
"justifyMode": "center"
|
|
}
|
|
},
|
|
{
|
|
"id": 3,
|
|
"title": "Total Monitored RAM",
|
|
"type": "stat",
|
|
"gridPos": {
|
|
"h": 4,
|
|
"w": 6,
|
|
"x": 12,
|
|
"y": 1
|
|
},
|
|
"datasource": "Prometheus",
|
|
"targets": [
|
|
{
|
|
"expr": "sum(node_memory_MemTotal_bytes)",
|
|
"legendFormat": "{{instance}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "thresholds"
|
|
},
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "purple",
|
|
"value": null
|
|
}
|
|
]
|
|
},
|
|
"unit": "bytes"
|
|
}
|
|
},
|
|
"options": {
|
|
"colorMode": "value",
|
|
"graphMode": "area",
|
|
"justifyMode": "center"
|
|
}
|
|
},
|
|
{
|
|
"id": 4,
|
|
"title": "Fleet RAM In-Use %",
|
|
"type": "stat",
|
|
"gridPos": {
|
|
"h": 4,
|
|
"w": 6,
|
|
"x": 18,
|
|
"y": 1
|
|
},
|
|
"datasource": "Prometheus",
|
|
"targets": [
|
|
{
|
|
"expr": "(1 - (sum(node_memory_MemAvailable_bytes) / sum(node_memory_MemTotal_bytes))) * 100",
|
|
"legendFormat": "{{instance}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "thresholds"
|
|
},
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "orange",
|
|
"value": null
|
|
}
|
|
]
|
|
},
|
|
"unit": "percent"
|
|
}
|
|
},
|
|
"options": {
|
|
"colorMode": "value",
|
|
"graphMode": "area",
|
|
"justifyMode": "center"
|
|
}
|
|
},
|
|
{
|
|
"collapsed": false,
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 5
|
|
},
|
|
"id": 200,
|
|
"title": "\u26a1 CPU Load & Core Utilization",
|
|
"type": "row"
|
|
},
|
|
{
|
|
"id": 5,
|
|
"title": "CPU Utilization by Host (%)",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 6
|
|
},
|
|
"datasource": "Prometheus",
|
|
"targets": [
|
|
{
|
|
"expr": "100 - (avg by (instance, cluster) (rate(node_cpu_seconds_total{mode='idle'}[2m])) * 100)",
|
|
"legendFormat": "{{cluster}} - {{instance}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"custom": {
|
|
"drawStyle": "line",
|
|
"lineInterpolation": "smooth",
|
|
"lineWidth": 2,
|
|
"fillOpacity": 15
|
|
},
|
|
"unit": "percent"
|
|
}
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"id": 6,
|
|
"title": "1-Minute Load Average by Host",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 6
|
|
},
|
|
"datasource": "Prometheus",
|
|
"targets": [
|
|
{
|
|
"expr": "node_load1",
|
|
"legendFormat": "{{cluster}} - {{instance}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"custom": {
|
|
"drawStyle": "line",
|
|
"lineInterpolation": "smooth",
|
|
"lineWidth": 2,
|
|
"fillOpacity": 15
|
|
},
|
|
"unit": "none"
|
|
}
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"collapsed": false,
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 14
|
|
},
|
|
"id": 300,
|
|
"title": "\ud83e\udde0 Memory Consumption & Free Capacity",
|
|
"type": "row"
|
|
},
|
|
{
|
|
"id": 7,
|
|
"title": "Memory Used % by Host",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 15
|
|
},
|
|
"datasource": "Prometheus",
|
|
"targets": [
|
|
{
|
|
"expr": "(1 - (node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes)) * 100",
|
|
"legendFormat": "{{cluster}} - {{instance}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"custom": {
|
|
"drawStyle": "line",
|
|
"lineInterpolation": "smooth",
|
|
"lineWidth": 2,
|
|
"fillOpacity": 15
|
|
},
|
|
"unit": "percent"
|
|
}
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"id": 8,
|
|
"title": "Available RAM by Host (GiB)",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 15
|
|
},
|
|
"datasource": "Prometheus",
|
|
"targets": [
|
|
{
|
|
"expr": "node_memory_MemAvailable_bytes",
|
|
"legendFormat": "{{cluster}} - {{instance}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"custom": {
|
|
"drawStyle": "line",
|
|
"lineInterpolation": "smooth",
|
|
"lineWidth": 2,
|
|
"fillOpacity": 15
|
|
},
|
|
"unit": "bytes"
|
|
}
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"collapsed": false,
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 23
|
|
},
|
|
"id": 400,
|
|
"title": "\ud83d\udcbe Filesystem & Disk I/O Performance",
|
|
"type": "row"
|
|
},
|
|
{
|
|
"id": 9,
|
|
"title": "Root (/) Filesystem Usage %",
|
|
"type": "bargauge",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 8,
|
|
"x": 0,
|
|
"y": 24
|
|
},
|
|
"datasource": "Prometheus",
|
|
"targets": [
|
|
{
|
|
"expr": "(1 - (node_filesystem_avail_bytes{mountpoint='/'} / node_filesystem_size_bytes{mountpoint='/'})) * 100",
|
|
"legendFormat": "{{instance}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "yellow",
|
|
"value": 75
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 90
|
|
}
|
|
]
|
|
},
|
|
"unit": "percent",
|
|
"min": 0,
|
|
"max": 100
|
|
}
|
|
},
|
|
"options": {
|
|
"displayMode": "gradient",
|
|
"orientation": "horizontal",
|
|
"showUnfilled": true
|
|
}
|
|
},
|
|
{
|
|
"id": 10,
|
|
"title": "Disk Read Throughput (Bytes/sec)",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 8,
|
|
"x": 8,
|
|
"y": 24
|
|
},
|
|
"datasource": "Prometheus",
|
|
"targets": [
|
|
{
|
|
"expr": "sum by (instance) (rate(node_disk_read_bytes_total[2m]))",
|
|
"legendFormat": "Read {{instance}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"custom": {
|
|
"drawStyle": "line",
|
|
"lineInterpolation": "smooth",
|
|
"lineWidth": 2,
|
|
"fillOpacity": 15
|
|
},
|
|
"unit": "Bps"
|
|
}
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"id": 11,
|
|
"title": "Disk Write Throughput (Bytes/sec)",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 8,
|
|
"x": 16,
|
|
"y": 24
|
|
},
|
|
"datasource": "Prometheus",
|
|
"targets": [
|
|
{
|
|
"expr": "sum by (instance) (rate(node_disk_written_bytes_total[2m]))",
|
|
"legendFormat": "Write {{instance}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"custom": {
|
|
"drawStyle": "line",
|
|
"lineInterpolation": "smooth",
|
|
"lineWidth": 2,
|
|
"fillOpacity": 15
|
|
},
|
|
"unit": "Bps"
|
|
}
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"collapsed": false,
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 32
|
|
},
|
|
"id": 500,
|
|
"title": "\ud83c\udf10 Network Throughput (RX / TX)",
|
|
"type": "row"
|
|
},
|
|
{
|
|
"id": 12,
|
|
"title": "Host Network Receive (RX)",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 33
|
|
},
|
|
"datasource": "Prometheus",
|
|
"targets": [
|
|
{
|
|
"expr": "sum by (instance) (rate(node_network_receive_bytes_total{device!~'lo|veth.*|flannel.*|cali.*'}[2m]))",
|
|
"legendFormat": "RX {{instance}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"custom": {
|
|
"drawStyle": "line",
|
|
"lineInterpolation": "smooth",
|
|
"lineWidth": 2,
|
|
"fillOpacity": 15
|
|
},
|
|
"unit": "Bps"
|
|
}
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"id": 13,
|
|
"title": "Host Network Transmit (TX)",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 33
|
|
},
|
|
"datasource": "Prometheus",
|
|
"targets": [
|
|
{
|
|
"expr": "sum by (instance) (rate(node_network_transmit_bytes_total{device!~'lo|veth.*|flannel.*|cali.*'}[2m]))",
|
|
"legendFormat": "TX {{instance}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"custom": {
|
|
"drawStyle": "line",
|
|
"lineInterpolation": "smooth",
|
|
"lineWidth": 2,
|
|
"fillOpacity": 15
|
|
},
|
|
"unit": "Bps"
|
|
}
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
}
|
|
}
|
|
],
|
|
"refresh": "10s",
|
|
"schemaVersion": 39,
|
|
"tags": [
|
|
"infrastructure",
|
|
"systems",
|
|
"snarfnet",
|
|
"node-exporter"
|
|
],
|
|
"templating": {
|
|
"list": []
|
|
},
|
|
"time": {
|
|
"from": "now-1h",
|
|
"to": "now"
|
|
},
|
|
"timepicker": {},
|
|
"timezone": "browser",
|
|
"title": "\ud83d\udda5\ufe0f Systems & Cluster Host Performance",
|
|
"uid": "snarfnet-systems"
|
|
}
|
|
---
|
|
apiVersion: v1
|
|
kind: ConfigMap
|
|
metadata:
|
|
name: grafana-dashboard-containers
|
|
namespace: default
|
|
labels:
|
|
app.kubernetes.io/name: grafana
|
|
app.kubernetes.io/instance: grafana
|
|
data:
|
|
container-metrics-dashboard.json: |-
|
|
{
|
|
"annotations": {
|
|
"list": []
|
|
},
|
|
"editable": true,
|
|
"fiscalYearStartMonth": 0,
|
|
"graphTooltip": 1,
|
|
"id": null,
|
|
"links": [],
|
|
"liveNow": false,
|
|
"panels": [
|
|
{
|
|
"collapsed": false,
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 0
|
|
},
|
|
"id": 100,
|
|
"title": "\ud83d\udce6 Container Fleet & Pod Metrics",
|
|
"type": "row"
|
|
},
|
|
{
|
|
"id": 1,
|
|
"title": "Monitored Containers",
|
|
"type": "stat",
|
|
"gridPos": {
|
|
"h": 4,
|
|
"w": 6,
|
|
"x": 0,
|
|
"y": 1
|
|
},
|
|
"datasource": "Prometheus",
|
|
"targets": [
|
|
{
|
|
"expr": "count(container_last_seen{container!=''})",
|
|
"legendFormat": "{{instance}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "thresholds"
|
|
},
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
}
|
|
]
|
|
},
|
|
"unit": "none"
|
|
}
|
|
},
|
|
"options": {
|
|
"colorMode": "value",
|
|
"graphMode": "area",
|
|
"justifyMode": "center"
|
|
}
|
|
},
|
|
{
|
|
"id": 2,
|
|
"title": "Active Kubernetes Pods",
|
|
"type": "stat",
|
|
"gridPos": {
|
|
"h": 4,
|
|
"w": 6,
|
|
"x": 6,
|
|
"y": 1
|
|
},
|
|
"datasource": "Prometheus",
|
|
"targets": [
|
|
{
|
|
"expr": "count(count by (pod, namespace) (container_last_seen{container!=''}))",
|
|
"legendFormat": "{{instance}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "thresholds"
|
|
},
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "blue",
|
|
"value": null
|
|
}
|
|
]
|
|
},
|
|
"unit": "none"
|
|
}
|
|
},
|
|
"options": {
|
|
"colorMode": "value",
|
|
"graphMode": "area",
|
|
"justifyMode": "center"
|
|
}
|
|
},
|
|
{
|
|
"id": 3,
|
|
"title": "Total Container CPU Load",
|
|
"type": "stat",
|
|
"gridPos": {
|
|
"h": 4,
|
|
"w": 6,
|
|
"x": 12,
|
|
"y": 1
|
|
},
|
|
"datasource": "Prometheus",
|
|
"targets": [
|
|
{
|
|
"expr": "sum(rate(container_cpu_usage_seconds_total{container!=''}[2m]))",
|
|
"legendFormat": "{{instance}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "thresholds"
|
|
},
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "purple",
|
|
"value": null
|
|
}
|
|
]
|
|
},
|
|
"unit": "none"
|
|
}
|
|
},
|
|
"options": {
|
|
"colorMode": "value",
|
|
"graphMode": "area",
|
|
"justifyMode": "center"
|
|
}
|
|
},
|
|
{
|
|
"id": 4,
|
|
"title": "Total Container RAM",
|
|
"type": "stat",
|
|
"gridPos": {
|
|
"h": 4,
|
|
"w": 6,
|
|
"x": 18,
|
|
"y": 1
|
|
},
|
|
"datasource": "Prometheus",
|
|
"targets": [
|
|
{
|
|
"expr": "sum(container_memory_working_set_bytes{container!=''})",
|
|
"legendFormat": "{{instance}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "thresholds"
|
|
},
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "orange",
|
|
"value": null
|
|
}
|
|
]
|
|
},
|
|
"unit": "bytes"
|
|
}
|
|
},
|
|
"options": {
|
|
"colorMode": "value",
|
|
"graphMode": "area",
|
|
"justifyMode": "center"
|
|
}
|
|
},
|
|
{
|
|
"collapsed": false,
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 5
|
|
},
|
|
"id": 200,
|
|
"title": "\u26a1 Top Container CPU Utilization",
|
|
"type": "row"
|
|
},
|
|
{
|
|
"id": 5,
|
|
"title": "Top 10 CPU Consuming Pods (Cores)",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 6
|
|
},
|
|
"datasource": "Prometheus",
|
|
"targets": [
|
|
{
|
|
"expr": "topk(10, sum by (pod, namespace) (rate(container_cpu_usage_seconds_total{container!=''}[2m])))",
|
|
"legendFormat": "{{namespace}} / {{pod}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"custom": {
|
|
"drawStyle": "line",
|
|
"lineInterpolation": "smooth",
|
|
"lineWidth": 2,
|
|
"fillOpacity": 15
|
|
},
|
|
"unit": "none"
|
|
}
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"id": 6,
|
|
"title": "CPU Throttling by Namespace",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 6
|
|
},
|
|
"datasource": "Prometheus",
|
|
"targets": [
|
|
{
|
|
"expr": "sum by (namespace) (rate(container_cpu_cfs_throttled_periods_total[2m]))",
|
|
"legendFormat": "{{namespace}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"custom": {
|
|
"drawStyle": "line",
|
|
"lineInterpolation": "smooth",
|
|
"lineWidth": 2,
|
|
"fillOpacity": 15
|
|
},
|
|
"unit": "none"
|
|
}
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"collapsed": false,
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 14
|
|
},
|
|
"id": 300,
|
|
"title": "\ud83e\udde0 Container Memory Working Set",
|
|
"type": "row"
|
|
},
|
|
{
|
|
"id": 7,
|
|
"title": "Top 10 Memory Consuming Pods",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 14,
|
|
"x": 0,
|
|
"y": 15
|
|
},
|
|
"datasource": "Prometheus",
|
|
"targets": [
|
|
{
|
|
"expr": "topk(10, sum by (pod, namespace) (container_memory_working_set_bytes{container!=''}))",
|
|
"legendFormat": "{{namespace}} / {{pod}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"custom": {
|
|
"drawStyle": "line",
|
|
"lineInterpolation": "smooth",
|
|
"lineWidth": 2,
|
|
"fillOpacity": 15
|
|
},
|
|
"unit": "bytes"
|
|
}
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"id": 8,
|
|
"title": "Memory by Namespace",
|
|
"type": "bargauge",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 10,
|
|
"x": 14,
|
|
"y": 15
|
|
},
|
|
"datasource": "Prometheus",
|
|
"targets": [
|
|
{
|
|
"expr": "sum by (namespace) (container_memory_working_set_bytes{container!=''})",
|
|
"legendFormat": "{{instance}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "yellow",
|
|
"value": 75
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 90
|
|
}
|
|
]
|
|
},
|
|
"unit": "bytes",
|
|
"min": 0,
|
|
"max": 100
|
|
}
|
|
},
|
|
"options": {
|
|
"displayMode": "gradient",
|
|
"orientation": "horizontal",
|
|
"showUnfilled": true
|
|
}
|
|
},
|
|
{
|
|
"collapsed": false,
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 23
|
|
},
|
|
"id": 400,
|
|
"title": "\ud83c\udf10 Container Network Traffic",
|
|
"type": "row"
|
|
},
|
|
{
|
|
"id": 9,
|
|
"title": "Top Pod Network RX (Receive)",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 24
|
|
},
|
|
"datasource": "Prometheus",
|
|
"targets": [
|
|
{
|
|
"expr": "topk(10, sum by (pod, namespace) (rate(container_network_receive_bytes_total[2m])))",
|
|
"legendFormat": "RX {{namespace}}/{{pod}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"custom": {
|
|
"drawStyle": "line",
|
|
"lineInterpolation": "smooth",
|
|
"lineWidth": 2,
|
|
"fillOpacity": 15
|
|
},
|
|
"unit": "Bps"
|
|
}
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"id": 10,
|
|
"title": "Top Pod Network TX (Transmit)",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 24
|
|
},
|
|
"datasource": "Prometheus",
|
|
"targets": [
|
|
{
|
|
"expr": "topk(10, sum by (pod, namespace) (rate(container_network_transmit_bytes_total[2m])))",
|
|
"legendFormat": "TX {{namespace}}/{{pod}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"custom": {
|
|
"drawStyle": "line",
|
|
"lineInterpolation": "smooth",
|
|
"lineWidth": 2,
|
|
"fillOpacity": 15
|
|
},
|
|
"unit": "Bps"
|
|
}
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
}
|
|
}
|
|
],
|
|
"refresh": "10s",
|
|
"schemaVersion": 39,
|
|
"tags": [
|
|
"kubernetes",
|
|
"containers",
|
|
"cadvisor",
|
|
"snarfnet",
|
|
"workloads"
|
|
],
|
|
"templating": {
|
|
"list": []
|
|
},
|
|
"time": {
|
|
"from": "now-1h",
|
|
"to": "now"
|
|
},
|
|
"timepicker": {},
|
|
"timezone": "browser",
|
|
"title": "\ud83d\udce6 Kubernetes Containers & Workloads",
|
|
"uid": "snarfnet-containers"
|
|
}
|