Compare commits
13
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
4e2303f455 | ||
|
|
483093a104 | ||
|
|
8d348e7f88 | ||
|
|
6f9ff9d624 | ||
|
|
7bf65783be | ||
|
|
dd9fb01359 | ||
|
|
da8a725b32 | ||
|
|
6008d59c9f | ||
|
|
5aa6c0609d | ||
|
|
0ebe113abb | ||
|
|
1723f73b5d | ||
|
|
8d8df3b635 | ||
|
|
29c91769a7 |
@@ -21,6 +21,9 @@ metadata:
|
||||
namespace: audiobookshelf
|
||||
labels:
|
||||
app.kubernetes.io/name: audiobookshelf
|
||||
annotations:
|
||||
# envFrom does not restart the pod when the ConfigMap changes; Reloader does.
|
||||
configmap.reloader.stakater.com/reload: audiobookshelf-config
|
||||
spec:
|
||||
replicas: 1
|
||||
strategy:
|
||||
|
||||
@@ -35,6 +35,9 @@ metadata:
|
||||
namespace: immich
|
||||
labels:
|
||||
app.kubernetes.io/name: immich-server
|
||||
annotations:
|
||||
# envFrom does not restart the pod when the ConfigMap changes; Reloader does.
|
||||
configmap.reloader.stakater.com/reload: immich-config
|
||||
spec:
|
||||
# Scaled to 0 alongside immich-machine-learning during single-node
|
||||
# maintenance; see the note there. The CNPG Postgres cluster stays running,
|
||||
|
||||
@@ -0,0 +1,20 @@
|
||||
apiVersion: monitoring.coreos.com/v1
|
||||
kind: ServiceMonitor
|
||||
metadata:
|
||||
name: intel-gpu-exporter
|
||||
namespace: monitoring
|
||||
labels:
|
||||
app.kubernetes.io/name: intel-gpu-exporter
|
||||
release: kube-prometheus-stack
|
||||
spec:
|
||||
selector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: intel-gpu-exporter
|
||||
endpoints:
|
||||
- port: http-metrics
|
||||
path: /metrics
|
||||
interval: 30s
|
||||
relabelings:
|
||||
# The series would otherwise carry only the exporter pod's IP.
|
||||
- sourceLabels: [__meta_kubernetes_pod_node_name]
|
||||
targetLabel: node
|
||||
@@ -39,4 +39,5 @@ resources:
|
||||
- immich-servicemonitor.yaml
|
||||
- loki-servicemonitor.yaml
|
||||
- smartctl-exporter-servicemonitor.yaml
|
||||
- intel-gpu-exporter-servicemonitor.yaml
|
||||
- probes-blackbox.yaml
|
||||
|
||||
@@ -0,0 +1,368 @@
|
||||
{
|
||||
"title": "Intel iGPU",
|
||||
"uid": "intel-gpu",
|
||||
"tags": ["gpu", "intel", "i915"],
|
||||
"schemaVersion": 39,
|
||||
"editable": true,
|
||||
"timezone": "",
|
||||
"refresh": "1m",
|
||||
"time": { "from": "now-6h", "to": "now" },
|
||||
"templating": {
|
||||
"list": [
|
||||
{
|
||||
"name": "node",
|
||||
"label": "Node",
|
||||
"type": "query",
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"query": {
|
||||
"query": "label_values(gpumon_power, node)",
|
||||
"refId": "PrometheusVariableQueryEditor-VariableQuery"
|
||||
},
|
||||
"definition": "label_values(gpumon_power, node)",
|
||||
"includeAll": true,
|
||||
"multi": true,
|
||||
"refresh": 2,
|
||||
"sort": 1,
|
||||
"current": { "selected": true, "text": ["All"], "value": ["$__all"] }
|
||||
}
|
||||
]
|
||||
},
|
||||
"panels": [
|
||||
{
|
||||
"type": "stat",
|
||||
"title": "Render/3D busy now",
|
||||
"gridPos": { "h": 4, "w": 8, "x": 0, "y": 0 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "percent",
|
||||
"decimals": 0,
|
||||
"min": 0,
|
||||
"max": 100,
|
||||
"color": { "mode": "fixed", "fixedColor": "text" }
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"options": {
|
||||
"colorMode": "none",
|
||||
"graphMode": "none",
|
||||
"justifyMode": "center",
|
||||
"orientation": "horizontal",
|
||||
"textMode": "value_and_name",
|
||||
"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false }
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "gpumon_engine_usage{attrib=\"busy\", engine=\"Render/3D\", node=~\"$node\"}",
|
||||
"legendFormat": "{{node}}",
|
||||
"refId": "A"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"type": "stat",
|
||||
"title": "GPU power now",
|
||||
"gridPos": { "h": 4, "w": 8, "x": 8, "y": 0 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "watt",
|
||||
"decimals": 1,
|
||||
"color": { "mode": "fixed", "fixedColor": "text" }
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"options": {
|
||||
"colorMode": "none",
|
||||
"graphMode": "none",
|
||||
"justifyMode": "center",
|
||||
"orientation": "horizontal",
|
||||
"textMode": "value_and_name",
|
||||
"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false }
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "gpumon_power{type=\"gpu\", node=~\"$node\"}",
|
||||
"legendFormat": "{{node}}",
|
||||
"refId": "A"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"type": "stat",
|
||||
"title": "GT frequency now",
|
||||
"gridPos": { "h": 4, "w": 8, "x": 16, "y": 0 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "suffix: MHz",
|
||||
"decimals": 0,
|
||||
"color": { "mode": "fixed", "fixedColor": "text" }
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"options": {
|
||||
"colorMode": "none",
|
||||
"graphMode": "none",
|
||||
"justifyMode": "center",
|
||||
"orientation": "horizontal",
|
||||
"textMode": "value_and_name",
|
||||
"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false }
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "gpumon_frequency{type=\"actual\", node=~\"$node\"}",
|
||||
"legendFormat": "{{node}}",
|
||||
"refId": "A"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"type": "timeseries",
|
||||
"title": "Render/3D busy",
|
||||
"description": "Compute and 3D. llama.cpp's Vulkan backend runs here; 0 % during an inference means the model is on the CPU.",
|
||||
"gridPos": { "h": 8, "w": 12, "x": 0, "y": 4 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "percent",
|
||||
"min": 0,
|
||||
"max": 100,
|
||||
"custom": { "drawStyle": "line", "lineWidth": 2, "fillOpacity": 0, "showPoints": "never", "spanNulls": false }
|
||||
},
|
||||
"overrides": [
|
||||
{ "matcher": { "id": "byRegexp", "options": "/k8s-1/" }, "properties": [{ "id": "color", "value": { "mode": "fixed", "fixedColor": "#3987e5" } }] },
|
||||
{ "matcher": { "id": "byRegexp", "options": "/k8s-2/" }, "properties": [{ "id": "color", "value": { "mode": "fixed", "fixedColor": "#d95926" } }] },
|
||||
{ "matcher": { "id": "byRegexp", "options": "/k8s-3/" }, "properties": [{ "id": "color", "value": { "mode": "fixed", "fixedColor": "#199e70" } }] }
|
||||
]
|
||||
},
|
||||
"options": {
|
||||
"legend": { "calcs": ["mean", "max", "lastNotNull"], "displayMode": "table", "placement": "bottom", "showLegend": true },
|
||||
"tooltip": { "mode": "multi", "sort": "desc" }
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "gpumon_engine_usage{attrib=\"busy\", engine=\"Render/3D\", node=~\"$node\"}",
|
||||
"legendFormat": "{{node}}",
|
||||
"refId": "A"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"type": "timeseries",
|
||||
"title": "Video busy",
|
||||
"description": "Fixed-function decode/encode (QuickSync).",
|
||||
"gridPos": { "h": 8, "w": 12, "x": 12, "y": 4 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "percent",
|
||||
"min": 0,
|
||||
"max": 100,
|
||||
"custom": { "drawStyle": "line", "lineWidth": 2, "fillOpacity": 0, "showPoints": "never", "spanNulls": false }
|
||||
},
|
||||
"overrides": [
|
||||
{ "matcher": { "id": "byRegexp", "options": "/k8s-1/" }, "properties": [{ "id": "color", "value": { "mode": "fixed", "fixedColor": "#3987e5" } }] },
|
||||
{ "matcher": { "id": "byRegexp", "options": "/k8s-2/" }, "properties": [{ "id": "color", "value": { "mode": "fixed", "fixedColor": "#d95926" } }] },
|
||||
{ "matcher": { "id": "byRegexp", "options": "/k8s-3/" }, "properties": [{ "id": "color", "value": { "mode": "fixed", "fixedColor": "#199e70" } }] }
|
||||
]
|
||||
},
|
||||
"options": {
|
||||
"legend": { "calcs": ["mean", "max", "lastNotNull"], "displayMode": "table", "placement": "bottom", "showLegend": true },
|
||||
"tooltip": { "mode": "multi", "sort": "desc" }
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "gpumon_engine_usage{attrib=\"busy\", engine=\"Video\", node=~\"$node\"}",
|
||||
"legendFormat": "{{node}}",
|
||||
"refId": "A"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"type": "timeseries",
|
||||
"title": "VideoEnhance busy",
|
||||
"gridPos": { "h": 8, "w": 12, "x": 0, "y": 12 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "percent",
|
||||
"min": 0,
|
||||
"max": 100,
|
||||
"custom": { "drawStyle": "line", "lineWidth": 2, "fillOpacity": 0, "showPoints": "never", "spanNulls": false }
|
||||
},
|
||||
"overrides": [
|
||||
{ "matcher": { "id": "byRegexp", "options": "/k8s-1/" }, "properties": [{ "id": "color", "value": { "mode": "fixed", "fixedColor": "#3987e5" } }] },
|
||||
{ "matcher": { "id": "byRegexp", "options": "/k8s-2/" }, "properties": [{ "id": "color", "value": { "mode": "fixed", "fixedColor": "#d95926" } }] },
|
||||
{ "matcher": { "id": "byRegexp", "options": "/k8s-3/" }, "properties": [{ "id": "color", "value": { "mode": "fixed", "fixedColor": "#199e70" } }] }
|
||||
]
|
||||
},
|
||||
"options": {
|
||||
"legend": { "calcs": ["mean", "max", "lastNotNull"], "displayMode": "table", "placement": "bottom", "showLegend": true },
|
||||
"tooltip": { "mode": "multi", "sort": "desc" }
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "gpumon_engine_usage{attrib=\"busy\", engine=\"VideoEnhance\", node=~\"$node\"}",
|
||||
"legendFormat": "{{node}}",
|
||||
"refId": "A"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"type": "timeseries",
|
||||
"title": "Blitter busy",
|
||||
"gridPos": { "h": 8, "w": 12, "x": 12, "y": 12 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "percent",
|
||||
"min": 0,
|
||||
"max": 100,
|
||||
"custom": { "drawStyle": "line", "lineWidth": 2, "fillOpacity": 0, "showPoints": "never", "spanNulls": false }
|
||||
},
|
||||
"overrides": [
|
||||
{ "matcher": { "id": "byRegexp", "options": "/k8s-1/" }, "properties": [{ "id": "color", "value": { "mode": "fixed", "fixedColor": "#3987e5" } }] },
|
||||
{ "matcher": { "id": "byRegexp", "options": "/k8s-2/" }, "properties": [{ "id": "color", "value": { "mode": "fixed", "fixedColor": "#d95926" } }] },
|
||||
{ "matcher": { "id": "byRegexp", "options": "/k8s-3/" }, "properties": [{ "id": "color", "value": { "mode": "fixed", "fixedColor": "#199e70" } }] }
|
||||
]
|
||||
},
|
||||
"options": {
|
||||
"legend": { "calcs": ["mean", "max", "lastNotNull"], "displayMode": "table", "placement": "bottom", "showLegend": true },
|
||||
"tooltip": { "mode": "multi", "sort": "desc" }
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "gpumon_engine_usage{attrib=\"busy\", engine=\"Blitter\", node=~\"$node\"}",
|
||||
"legendFormat": "{{node}}",
|
||||
"refId": "A"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"type": "timeseries",
|
||||
"title": "GT frequency (actual)",
|
||||
"description": "0 while the GT sits in RC6.",
|
||||
"gridPos": { "h": 8, "w": 12, "x": 0, "y": 20 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "suffix: MHz",
|
||||
"min": 0,
|
||||
"custom": { "drawStyle": "line", "lineWidth": 2, "fillOpacity": 0, "showPoints": "never", "spanNulls": false }
|
||||
},
|
||||
"overrides": [
|
||||
{ "matcher": { "id": "byRegexp", "options": "/k8s-1/" }, "properties": [{ "id": "color", "value": { "mode": "fixed", "fixedColor": "#3987e5" } }] },
|
||||
{ "matcher": { "id": "byRegexp", "options": "/k8s-2/" }, "properties": [{ "id": "color", "value": { "mode": "fixed", "fixedColor": "#d95926" } }] },
|
||||
{ "matcher": { "id": "byRegexp", "options": "/k8s-3/" }, "properties": [{ "id": "color", "value": { "mode": "fixed", "fixedColor": "#199e70" } }] }
|
||||
]
|
||||
},
|
||||
"options": {
|
||||
"legend": { "calcs": ["mean", "max", "lastNotNull"], "displayMode": "table", "placement": "bottom", "showLegend": true },
|
||||
"tooltip": { "mode": "multi", "sort": "desc" }
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "gpumon_frequency{type=\"actual\", node=~\"$node\"}",
|
||||
"legendFormat": "{{node}}",
|
||||
"refId": "A"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"type": "timeseries",
|
||||
"title": "GPU power",
|
||||
"gridPos": { "h": 8, "w": 12, "x": 12, "y": 20 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "watt",
|
||||
"min": 0,
|
||||
"custom": { "drawStyle": "line", "lineWidth": 2, "fillOpacity": 0, "showPoints": "never", "spanNulls": false }
|
||||
},
|
||||
"overrides": [
|
||||
{ "matcher": { "id": "byRegexp", "options": "/k8s-1/" }, "properties": [{ "id": "color", "value": { "mode": "fixed", "fixedColor": "#3987e5" } }] },
|
||||
{ "matcher": { "id": "byRegexp", "options": "/k8s-2/" }, "properties": [{ "id": "color", "value": { "mode": "fixed", "fixedColor": "#d95926" } }] },
|
||||
{ "matcher": { "id": "byRegexp", "options": "/k8s-3/" }, "properties": [{ "id": "color", "value": { "mode": "fixed", "fixedColor": "#199e70" } }] }
|
||||
]
|
||||
},
|
||||
"options": {
|
||||
"legend": { "calcs": ["mean", "max", "lastNotNull"], "displayMode": "table", "placement": "bottom", "showLegend": true },
|
||||
"tooltip": { "mode": "multi", "sort": "desc" }
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "gpumon_power{type=\"gpu\", node=~\"$node\"}",
|
||||
"legendFormat": "{{node}}",
|
||||
"refId": "A"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"type": "timeseries",
|
||||
"title": "Package power",
|
||||
"description": "Whole SoC (CPU + GPU + uncore), from the same PMU.",
|
||||
"gridPos": { "h": 8, "w": 12, "x": 0, "y": 28 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "watt",
|
||||
"min": 0,
|
||||
"custom": { "drawStyle": "line", "lineWidth": 2, "fillOpacity": 0, "showPoints": "never", "spanNulls": false }
|
||||
},
|
||||
"overrides": [
|
||||
{ "matcher": { "id": "byRegexp", "options": "/k8s-1/" }, "properties": [{ "id": "color", "value": { "mode": "fixed", "fixedColor": "#3987e5" } }] },
|
||||
{ "matcher": { "id": "byRegexp", "options": "/k8s-2/" }, "properties": [{ "id": "color", "value": { "mode": "fixed", "fixedColor": "#d95926" } }] },
|
||||
{ "matcher": { "id": "byRegexp", "options": "/k8s-3/" }, "properties": [{ "id": "color", "value": { "mode": "fixed", "fixedColor": "#199e70" } }] }
|
||||
]
|
||||
},
|
||||
"options": {
|
||||
"legend": { "calcs": ["mean", "max", "lastNotNull"], "displayMode": "table", "placement": "bottom", "showLegend": true },
|
||||
"tooltip": { "mode": "multi", "sort": "desc" }
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "gpumon_power{type=\"pkg\", node=~\"$node\"}",
|
||||
"legendFormat": "{{node}}",
|
||||
"refId": "A"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"type": "timeseries",
|
||||
"title": "Memory controller bandwidth",
|
||||
"description": "Reads solid, writes dashed. The iGPU shares DDR5 with the CPU, so this is the whole package's traffic.",
|
||||
"gridPos": { "h": 8, "w": 12, "x": 12, "y": 28 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "MiBs",
|
||||
"min": 0,
|
||||
"custom": { "drawStyle": "line", "lineWidth": 2, "fillOpacity": 0, "showPoints": "never", "spanNulls": false }
|
||||
},
|
||||
"overrides": [
|
||||
{ "matcher": { "id": "byRegexp", "options": "/k8s-1/" }, "properties": [{ "id": "color", "value": { "mode": "fixed", "fixedColor": "#3987e5" } }] },
|
||||
{ "matcher": { "id": "byRegexp", "options": "/k8s-2/" }, "properties": [{ "id": "color", "value": { "mode": "fixed", "fixedColor": "#d95926" } }] },
|
||||
{ "matcher": { "id": "byRegexp", "options": "/k8s-3/" }, "properties": [{ "id": "color", "value": { "mode": "fixed", "fixedColor": "#199e70" } }] },
|
||||
{ "matcher": { "id": "byRegexp", "options": "/write/" }, "properties": [{ "id": "custom.lineStyle", "value": { "fill": "dash", "dash": [10, 10] } }] }
|
||||
]
|
||||
},
|
||||
"options": {
|
||||
"legend": { "calcs": ["mean", "max", "lastNotNull"], "displayMode": "table", "placement": "bottom", "showLegend": true },
|
||||
"tooltip": { "mode": "multi", "sort": "desc" }
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"expr": "gpumon_imc_read{node=~\"$node\"}",
|
||||
"legendFormat": "{{node}} read",
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"expr": "gpumon_imc_write{node=~\"$node\"}",
|
||||
"legendFormat": "{{node}} write",
|
||||
"refId": "B"
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -77,6 +77,9 @@ configMapGenerator:
|
||||
- name: dashboard-infrastructure-overview
|
||||
files:
|
||||
- infrastructure-overview.json
|
||||
- name: dashboard-intel-gpu
|
||||
files:
|
||||
- intel-gpu.json
|
||||
- name: dashboard-netbird-overview
|
||||
files:
|
||||
- netbird-overview.json
|
||||
|
||||
@@ -0,0 +1,81 @@
|
||||
# Intel iGPU utilisation, frequency and power for every node (#752).
|
||||
#
|
||||
# Not privileged: /dev/dri comes from the device plugin's monitoring resource
|
||||
# (every GPU on the node, no hostPath), and the i915 PMU that intel_gpu_top
|
||||
# reads needs CAP_PERFMON — the one capability granted. No hostPID, no
|
||||
# hostNetwork.
|
||||
apiVersion: apps/v1
|
||||
kind: DaemonSet
|
||||
metadata:
|
||||
name: intel-gpu-exporter
|
||||
namespace: monitoring
|
||||
labels:
|
||||
app.kubernetes.io/name: intel-gpu-exporter
|
||||
spec:
|
||||
selector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: intel-gpu-exporter
|
||||
template:
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/name: intel-gpu-exporter
|
||||
spec:
|
||||
# Every node is a control plane; without this the exporter covers nothing.
|
||||
tolerations:
|
||||
- key: node-role.kubernetes.io/control-plane
|
||||
operator: Exists
|
||||
effect: NoSchedule
|
||||
securityContext:
|
||||
seccompProfile:
|
||||
type: RuntimeDefault
|
||||
containers:
|
||||
- name: intel-gpu-exporter
|
||||
image: ghcr.io/clambin/intel-gpu-exporter:0.7.4@sha256:d78761fef018834c759db154fe9dcf3dd9db5974703fa50ca21f6abc35221be1
|
||||
args:
|
||||
# No -device: intel_gpu_top picks the only GPU the plugin injects.
|
||||
- -interval=5s
|
||||
ports:
|
||||
- name: http-metrics
|
||||
containerPort: 9100
|
||||
protocol: TCP
|
||||
securityContext:
|
||||
# Root so the PERFMON capability is effective without file
|
||||
# capabilities on the binary.
|
||||
runAsUser: 0
|
||||
runAsNonRoot: false
|
||||
allowPrivilegeEscalation: false
|
||||
readOnlyRootFilesystem: true
|
||||
capabilities:
|
||||
drop: ["ALL"]
|
||||
add: ["PERFMON"]
|
||||
resources:
|
||||
requests:
|
||||
cpu: 10m
|
||||
memory: 32Mi
|
||||
gpu.intel.com/monitoring: 1
|
||||
limits:
|
||||
memory: 128Mi
|
||||
gpu.intel.com/monitoring: 1
|
||||
livenessProbe:
|
||||
httpGet:
|
||||
path: /metrics
|
||||
port: http-metrics
|
||||
initialDelaySeconds: 15
|
||||
periodSeconds: 30
|
||||
---
|
||||
apiVersion: v1
|
||||
kind: Service
|
||||
metadata:
|
||||
name: intel-gpu-exporter
|
||||
namespace: monitoring
|
||||
labels:
|
||||
app.kubernetes.io/name: intel-gpu-exporter
|
||||
spec:
|
||||
clusterIP: None
|
||||
selector:
|
||||
app.kubernetes.io/name: intel-gpu-exporter
|
||||
ports:
|
||||
- name: http-metrics
|
||||
port: 9100
|
||||
targetPort: http-metrics
|
||||
protocol: TCP
|
||||
@@ -16,6 +16,7 @@ resources:
|
||||
- prometheus-gate-ingress.yaml
|
||||
- ci-diagnostics-rbac.yaml
|
||||
- smartctl-exporter.yaml
|
||||
- intel-gpu-exporter.yaml
|
||||
- dashboards/
|
||||
# prometheusrule-garage.yaml lives in ./monitoring-rules/ and is applied by a
|
||||
# separate Flux Kustomization that dependsOn `monitoring` — otherwise the
|
||||
|
||||
@@ -72,6 +72,9 @@ spec:
|
||||
# they contend for it. Sized for an inference server plus room for
|
||||
# a transcoder and a benchmark pod alongside it.
|
||||
- -shared-dev-num=4
|
||||
# Advertises gpu.intel.com/monitoring: one resource that grants a
|
||||
# pod every GPU on the node instead of a slot. The exporter needs it.
|
||||
- -enable-monitoring
|
||||
securityContext:
|
||||
seLinuxOptions:
|
||||
type: "container_device_plugin_t"
|
||||
|
||||
@@ -76,7 +76,11 @@ spec:
|
||||
type: RuntimeDefault
|
||||
containers:
|
||||
- name: controller
|
||||
image: gitea.renner.uno/gitea_admin/netbird-proxy-services:2026-09-07
|
||||
# Pinned by digest: the date tag is rebuilt on every push of the
|
||||
# image directory (branch and master alike) and the registry keeps
|
||||
# only the newest manifest per tag, so the digest must come from
|
||||
# the MASTER build of the code change.
|
||||
image: gitea.renner.uno/gitea_admin/netbird-proxy-services:2026-09-07@sha256:caffa308d802c6fcc6aea919ac94657c08b993651baa6b8d18de395bcc40523e
|
||||
securityContext:
|
||||
allowPrivilegeEscalation: false
|
||||
readOnlyRootFilesystem: true
|
||||
|
||||
Reference in New Issue
Block a user