423891001c
- Phase 7 task file: monitoring.yml
- node_exporter (port 9100) via apt, systemd managed
- nvidia_gpu_exporter v1.2.2 (port 9835) — GPU util, VRAM, temp, power
- Patches kube-prometheus additionalScrapeConfigs secret with 3 new jobs:
node-astro-orbiter, gpu-astro-orbiter, vllm-astro-orbiter
- Deploys Grafana dashboard ConfigMap via kubectl apply
- Grafana dashboard (11 panels):
- Row 1: GPU util %, VRAM used, GPU temp gauge
- Row 2: GPU power draw, vLLM token throughput, request queue depth
- Row 3: vLLM e2e latency p50/p95/p99, KV cache utilization %
- Row 4: System CPU %, memory, root disk gauge
- defaults/main.yml: llm_gpu_exporter_version, llm_gpu_exporter_port
- handlers/main.yml: restart nvidia-gpu-exporter
294 lines
9.2 KiB
Django/Jinja
294 lines
9.2 KiB
Django/Jinja
apiVersion: v1
|
|
kind: ConfigMap
|
|
metadata:
|
|
name: grafana-llm-inference-dashboard
|
|
namespace: monitoring
|
|
labels:
|
|
grafana_dashboard: "1"
|
|
data:
|
|
llm-inference.json: |
|
|
{
|
|
"title": "LLM Inference — astro-orbiter",
|
|
"uid": "llm-astro-orbiter",
|
|
"timezone": "browser",
|
|
"refresh": "30s",
|
|
"schemaVersion": 38,
|
|
"tags": ["llm", "gpu", "vllm", "astro-orbiter"],
|
|
"time": { "from": "now-1h", "to": "now" },
|
|
"templating": {
|
|
"list": [
|
|
{
|
|
"name": "instance",
|
|
"type": "constant",
|
|
"label": "Host",
|
|
"query": "{{ hostvars['astro-orbiter']['ansible_host'] }}",
|
|
"hide": 0
|
|
}
|
|
]
|
|
},
|
|
"panels": [
|
|
{
|
|
"id": 1,
|
|
"title": "GPU Utilization %",
|
|
"type": "timeseries",
|
|
"gridPos": { "x": 0, "y": 0, "w": 8, "h": 8 },
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "percent",
|
|
"min": 0, "max": 100,
|
|
"color": { "mode": "palette-classic" },
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{ "color": "green", "value": null },
|
|
{ "color": "yellow", "value": 70 },
|
|
{ "color": "red", "value": 90 }
|
|
]
|
|
}
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"expr": "nvidia_smi_utilization_gpu_ratio{hostname=\"astro-orbiter\"} * 100",
|
|
"legendFormat": "GPU Util"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"id": 2,
|
|
"title": "GPU VRAM Used",
|
|
"type": "timeseries",
|
|
"gridPos": { "x": 8, "y": 0, "w": 8, "h": 8 },
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "bytes",
|
|
"color": { "mode": "palette-classic" }
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"expr": "nvidia_smi_memory_used_bytes{hostname=\"astro-orbiter\"}",
|
|
"legendFormat": "VRAM Used"
|
|
},
|
|
{
|
|
"expr": "nvidia_smi_memory_total_bytes{hostname=\"astro-orbiter\"}",
|
|
"legendFormat": "VRAM Total"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"id": 3,
|
|
"title": "GPU Temperature",
|
|
"type": "gauge",
|
|
"gridPos": { "x": 16, "y": 0, "w": 8, "h": 8 },
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "celsius",
|
|
"min": 0, "max": 100,
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{ "color": "green", "value": null },
|
|
{ "color": "yellow", "value": 70 },
|
|
{ "color": "red", "value": 85 }
|
|
]
|
|
}
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"expr": "nvidia_smi_temperature_gpu{hostname=\"astro-orbiter\"}",
|
|
"legendFormat": "GPU Temp"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"id": 4,
|
|
"title": "GPU Power Draw",
|
|
"type": "timeseries",
|
|
"gridPos": { "x": 0, "y": 8, "w": 8, "h": 8 },
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "watt",
|
|
"color": { "mode": "palette-classic" }
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"expr": "nvidia_smi_power_draw_watts{hostname=\"astro-orbiter\"}",
|
|
"legendFormat": "Power Draw"
|
|
},
|
|
{
|
|
"expr": "nvidia_smi_power_limit_watts{hostname=\"astro-orbiter\"}",
|
|
"legendFormat": "Power Limit"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"id": 5,
|
|
"title": "vLLM — Token Throughput",
|
|
"type": "timeseries",
|
|
"gridPos": { "x": 8, "y": 8, "w": 8, "h": 8 },
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "reqps",
|
|
"color": { "mode": "palette-classic" }
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"expr": "rate(vllm:generation_tokens_total{hostname=\"astro-orbiter\"}[1m])",
|
|
"legendFormat": "Tokens/s (gen)"
|
|
},
|
|
{
|
|
"expr": "rate(vllm:prompt_tokens_total{hostname=\"astro-orbiter\"}[1m])",
|
|
"legendFormat": "Tokens/s (prompt)"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"id": 6,
|
|
"title": "vLLM — Request Queue Depth",
|
|
"type": "timeseries",
|
|
"gridPos": { "x": 16, "y": 8, "w": 8, "h": 8 },
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "short",
|
|
"color": { "mode": "palette-classic" }
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"expr": "vllm:num_requests_running{hostname=\"astro-orbiter\"}",
|
|
"legendFormat": "Running"
|
|
},
|
|
{
|
|
"expr": "vllm:num_requests_waiting{hostname=\"astro-orbiter\"}",
|
|
"legendFormat": "Waiting"
|
|
},
|
|
{
|
|
"expr": "vllm:num_requests_swapped{hostname=\"astro-orbiter\"}",
|
|
"legendFormat": "Swapped"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"id": 7,
|
|
"title": "vLLM — E2E Request Latency (p50/p95/p99)",
|
|
"type": "timeseries",
|
|
"gridPos": { "x": 0, "y": 16, "w": 12, "h": 8 },
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "s",
|
|
"color": { "mode": "palette-classic" }
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"expr": "histogram_quantile(0.50, rate(vllm:e2e_request_latency_seconds_bucket{hostname=\"astro-orbiter\"}[5m]))",
|
|
"legendFormat": "p50"
|
|
},
|
|
{
|
|
"expr": "histogram_quantile(0.95, rate(vllm:e2e_request_latency_seconds_bucket{hostname=\"astro-orbiter\"}[5m]))",
|
|
"legendFormat": "p95"
|
|
},
|
|
{
|
|
"expr": "histogram_quantile(0.99, rate(vllm:e2e_request_latency_seconds_bucket{hostname=\"astro-orbiter\"}[5m]))",
|
|
"legendFormat": "p99"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"id": 8,
|
|
"title": "vLLM — KV Cache Utilization %",
|
|
"type": "timeseries",
|
|
"gridPos": { "x": 12, "y": 16, "w": 12, "h": 8 },
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "percent",
|
|
"min": 0, "max": 100,
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{ "color": "green", "value": null },
|
|
{ "color": "yellow", "value": 75 },
|
|
{ "color": "red", "value": 90 }
|
|
]
|
|
}
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"expr": "vllm:gpu_cache_usage_perc{hostname=\"astro-orbiter\"} * 100",
|
|
"legendFormat": "KV Cache %"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"id": 9,
|
|
"title": "System — CPU Usage %",
|
|
"type": "timeseries",
|
|
"gridPos": { "x": 0, "y": 24, "w": 8, "h": 7 },
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "percent",
|
|
"min": 0, "max": 100
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"expr": "100 - (avg by(instance) (rate(node_cpu_seconds_total{mode=\"idle\",instance=~\"{{ hostvars['astro-orbiter']['ansible_host'] }}:.*\"}[1m])) * 100)",
|
|
"legendFormat": "CPU Used"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"id": 10,
|
|
"title": "System — Memory Usage",
|
|
"type": "timeseries",
|
|
"gridPos": { "x": 8, "y": 24, "w": 8, "h": 7 },
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "bytes"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"expr": "node_memory_MemTotal_bytes{instance=~\"{{ hostvars['astro-orbiter']['ansible_host'] }}:.*\"} - node_memory_MemAvailable_bytes{instance=~\"{{ hostvars['astro-orbiter']['ansible_host'] }}:.*\"}",
|
|
"legendFormat": "Used"
|
|
},
|
|
{
|
|
"expr": "node_memory_MemTotal_bytes{instance=~\"{{ hostvars['astro-orbiter']['ansible_host'] }}:.*\"}",
|
|
"legendFormat": "Total"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"id": 11,
|
|
"title": "System — Disk Usage (root)",
|
|
"type": "gauge",
|
|
"gridPos": { "x": 16, "y": 24, "w": 8, "h": 7 },
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "percentunit",
|
|
"min": 0, "max": 1,
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{ "color": "green", "value": null },
|
|
{ "color": "yellow", "value": 0.75 },
|
|
{ "color": "red", "value": 0.90 }
|
|
]
|
|
}
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"expr": "1 - (node_filesystem_avail_bytes{instance=~\"{{ hostvars['astro-orbiter']['ansible_host'] }}:.*\",mountpoint=\"/\"} / node_filesystem_size_bytes{instance=~\"{{ hostvars['astro-orbiter']['ansible_host'] }}:.*\",mountpoint=\"/\"})",
|
|
"legendFormat": "Root disk"
|
|
}
|
|
]
|
|
}
|
|
]
|
|
}
|