Files
homelab/k8s/infra/monitoring/dashboards/llm-frontend.yaml
T
Story Crater Bot 7e40a4baf6 feat: cut api.riotpiao.com over to the Go gateway and retire Kong
Ingress api/api now backs onto api-gateway:8080; the kong Application, its
Helm values, plugins and llm-routes are removed. Gateway image v0.0.0 is in
the Forgejo registry and the pull secret is in the api namespace.
2026-08-19 22:51:53 -07:00

29 lines
4.0 KiB
YAML

apiVersion: v1
kind: ConfigMap
metadata:
name: llm-frontend-dashboard
namespace: logging
labels:
grafana_dashboard: "1"
annotations:
grafana_folder: "LLM"
# No request-level panels. The rate/error/latency/bandwidth row used to run
# on Kong's prometheus plugin; Kong was retired 2026-08-19 and the Go
# gateway that replaced it does not expose /metrics yet, so those panels
# were removed rather than left querying series that no longer exist.
# What is left is pod-level: readiness, CPU/memory, restarts, logs.
#
# Restoring request-level and per-model observability means wiring three
# sources, none of which are in place: gateway metrics (RED plus token
# counts and TTFT, which the gateway can measure because it sees the
# response stream), vLLM's own /metrics on reasoning-predictor (rich --
# vllm:time_to_first_token_seconds, vllm:inter_token_latency_seconds,
# vllm:e2e_request_latency_seconds, vllm:kv_cache_usage_perc), and TEI's
# /metrics on embeddings/reranker. Ollama exposes no Prometheus endpoint at
# all (verified: /metrics returns 404), so ornith can only ever be observed
# from the gateway side. No ServiceMonitor exists for the llm-serving
# namespace today, so none of the engine metrics are being scraped.
data:
llm-frontend.json: |
{"title":"LLM Frontend","uid":"llm-frontend","schemaVersion":39,"timezone":"browser","time":{"from":"now-6h","to":"now"},"refresh":"30s","panels":[{"id":1,"title":"Row: Availability","type":"row","collapsed":true,"gridPos":{"h":1,"w":24,"x":0,"y":0},"panels":[{"id":2,"title":"llm-serving pods ready","type":"stat","gridPos":{"h":4,"w":8,"x":0,"y":1},"datasource":{"type":"prometheus","uid":"prometheus"},"targets":[{"expr":"sum(kube_pod_status_ready{namespace=\"llm-serving\",condition=\"true\"})"}]},{"id":3,"title":"agent-pod ready","type":"stat","gridPos":{"h":4,"w":8,"x":8,"y":1},"datasource":{"type":"prometheus","uid":"prometheus"},"targets":[{"expr":"sum(kube_pod_status_ready{namespace=\"agent-pod\",condition=\"true\"})"}]},{"id":4,"title":"api gateway pods ready","type":"stat","gridPos":{"h":4,"w":8,"x":16,"y":1},"datasource":{"type":"prometheus","uid":"prometheus"},"targets":[{"expr":"sum(kube_pod_status_ready{namespace=\"api\",condition=\"true\"})"}]}]},{"id":10,"title":"Row: Resources","type":"row","collapsed":true,"gridPos":{"h":1,"w":24,"x":0,"y":1},"panels":[{"id":11,"title":"CPU by pod","type":"timeseries","gridPos":{"h":8,"w":12,"x":0,"y":2},"datasource":{"type":"prometheus","uid":"prometheus"},"targets":[{"expr":"sum(rate(container_cpu_usage_seconds_total{namespace=~\"llm-serving|agent-pod|api\"}[5m])) by (namespace, pod)","legendFormat":"{{namespace}}/{{pod}}"}]},{"id":12,"title":"Memory by pod","type":"timeseries","gridPos":{"h":8,"w":12,"x":12,"y":2},"fieldConfig":{"defaults":{"unit":"bytes"}},"datasource":{"type":"prometheus","uid":"prometheus"},"targets":[{"expr":"sum(container_memory_working_set_bytes{namespace=~\"llm-serving|agent-pod|api\"}) by (namespace, pod)","legendFormat":"{{namespace}}/{{pod}}"}]},{"id":13,"title":"GPU-node predictor restarts","type":"timeseries","gridPos":{"h":8,"w":24,"x":0,"y":10},"datasource":{"type":"prometheus","uid":"prometheus"},"targets":[{"expr":"sum(rate(kube_pod_container_status_restarts_total{namespace=\"llm-serving\"}[15m])) by (pod)","legendFormat":"{{pod}}"}]}]},{"id":20,"title":"Row: Logs","type":"row","collapsed":true,"gridPos":{"h":1,"w":24,"x":0,"y":2},"panels":[{"id":21,"title":"llm-serving logs","type":"logs","gridPos":{"h":10,"w":24,"x":0,"y":4},"datasource":{"type":"loki","uid":"loki"},"targets":[{"expr":"{namespace=\"llm-serving\"}"}]},{"id":22,"title":"agent-pod logs (pi runs)","type":"logs","gridPos":{"h":10,"w":24,"x":0,"y":14},"datasource":{"type":"loki","uid":"loki"},"targets":[{"expr":"{namespace=\"agent-pod\"}"}]},{"id":23,"title":"api gateway logs","type":"logs","gridPos":{"h":10,"w":24,"x":0,"y":24},"datasource":{"type":"loki","uid":"loki"},"targets":[{"expr":"{namespace=\"api\"}"}]}]}]}