feat(llm-inference): move astro-orbiter monitoring to GitOps (values.yaml + dashboards.yaml)

- Prometheus scrape configs for node/gpu/llama-server exporters on
  astro-orbiter now declared in cluster/applications/monitoring/values.yaml
  (additionalScrapeConfigs), applied via ArgoCD sync instead of an
  imperative kubectl secret patch from the Ansible role.
- Grafana dashboard for astro-orbiter LLM inference added as a ConfigMap
  in cluster/applications/monitoring/dashboards.yaml (grafana_dashboard=1
  sidecar label), replacing the role's ad-hoc kubectl apply of a rendered
  Jinja template.
- ansible/roles/llm-inference/tasks/monitoring.yml: removed the kubectl
  get/patch/apply tasks and orphaned grafana-llm-dashboard.json.j2
  template; role now only stands up node_exporter + nvidia_gpu_exporter
  and verifies they're reachable — cluster-facing config lives in Git.
- host_vars/vars.yml + inventory.yml: finalize astro-orbiter as the
  llama.cpp/RTX 3090 host (jarvis user, ssh key), drop stale Ollama/AMD
  vars and ollama_server inventory group superseded by the ATX rebuild.
This commit is contained in:
Hermes Agent service account
2026-08-05 09:43:54 -05:00
parent aa8e229e64
commit aff792a061
8 changed files with 324 additions and 398 deletions

View File

@@ -9198,4 +9198,231 @@ data:
"uid": "nginx",
"version": 1,
"description": "Ingress-nginx supports a rich collection of prometheus metrics. If you have prometheus and grafana installed on your cluster then prometheus will already be scraping this data due to the scrape annotation on the deployment."
}
---
apiVersion: v1
kind: ConfigMap
metadata:
name: grafana-llm-inference-dashboard
namespace: monitoring
labels:
grafana_dashboard: "1"
data:
llm-inference-astro-orbiter.json: |
{
"title": "LLM Inference — astro-orbiter",
"uid": "llm-astro-orbiter",
"timezone": "browser",
"refresh": "30s",
"schemaVersion": 38,
"tags": ["llm", "gpu", "llama-server", "astro-orbiter"],
"time": { "from": "now-1h", "to": "now" },
"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": "llama-server — Requests per Second",
"type": "timeseries",
"gridPos": { "x": 8, "y": 8, "w": 8, "h": 8 },
"fieldConfig": {
"defaults": {
"unit": "reqps",
"color": { "mode": "palette-classic" }
}
},
"targets": [
{
"expr": "rate(llamacpp:tokens_predicted_total{hostname=\"astro-orbiter\"}[1m])",
"legendFormat": "Tokens/s (predicted)"
},
{
"expr": "rate(llamacpp:prompt_tokens_total{hostname=\"astro-orbiter\"}[1m])",
"legendFormat": "Tokens/s (prompt)"
}
]
},
{
"id": 6,
"title": "llama-server — Requests Processing/Deferred",
"type": "timeseries",
"gridPos": { "x": 16, "y": 8, "w": 8, "h": 8 },
"fieldConfig": {
"defaults": {
"unit": "short",
"color": { "mode": "palette-classic" }
}
},
"targets": [
{
"expr": "llamacpp:requests_processing{hostname=\"astro-orbiter\"}",
"legendFormat": "Processing"
},
{
"expr": "llamacpp:requests_deferred{hostname=\"astro-orbiter\"}",
"legendFormat": "Deferred"
}
]
},
{
"id": 9,
"title": "System — CPU Usage %",
"type": "timeseries",
"gridPos": { "x": 0, "y": 16, "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=~\"10.1.71.130:.*\"}[1m])) * 100)",
"legendFormat": "CPU Used"
}
]
},
{
"id": 10,
"title": "System — Memory Usage",
"type": "timeseries",
"gridPos": { "x": 8, "y": 16, "w": 8, "h": 7 },
"fieldConfig": {
"defaults": {
"unit": "bytes"
}
},
"targets": [
{
"expr": "node_memory_MemTotal_bytes{instance=~\"10.1.71.130:.*\"} - node_memory_MemAvailable_bytes{instance=~\"10.1.71.130:.*\"}",
"legendFormat": "Used"
},
{
"expr": "node_memory_MemTotal_bytes{instance=~\"10.1.71.130:.*\"}",
"legendFormat": "Total"
}
]
},
{
"id": 11,
"title": "System — Disk Usage (root)",
"type": "gauge",
"gridPos": { "x": 16, "y": 16, "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=~\"10.1.71.130:.*\",mountpoint=\"/\"} / node_filesystem_size_bytes{instance=~\"10.1.71.130:.*\",mountpoint=\"/\"})",
"legendFormat": "Root disk"
}
]
}
]
}