22 lines
4.9 KiB
YAML
22 lines
4.9 KiB
YAML
apiVersion: v1
|
|
kind: ConfigMap
|
|
metadata:
|
|
name: llm-frontend-dashboard
|
|
namespace: logging
|
|
labels:
|
|
grafana_dashboard: "1"
|
|
annotations:
|
|
grafana_folder: "LLM"
|
|
# Request rate/error/latency/bandwidth now come from Kong's prometheus
|
|
# plugin (KongClusterPlugin in kong-metrics.yaml, global: true) via the
|
|
# chart's own ServiceMonitor (kong-values.yaml serviceMonitor.enabled) --
|
|
# every LLM route runs through Kong, so this covers ornith/reasoning/qwen/
|
|
# embeddings/rerank uniformly without per-backend instrumentation.
|
|
# Token-count metrics are still not available: that needs response-body
|
|
# parsing, which Kong only does via ai-proxy-advanced (Enterprise-only).
|
|
# Predictor-level metrics (native Ollama/vLLM stats) also still need a
|
|
# dedicated exporter -- not added here.
|
|
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":"kong (api) 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":15,"title":"Row: Request Rate & Latency (Kong)","type":"row","collapsed":true,"gridPos":{"h":1,"w":24,"x":0,"y":2},"panels":[{"id":16,"title":"Request rate by route","type":"timeseries","gridPos":{"h":8,"w":8,"x":0,"y":3},"datasource":{"type":"prometheus","uid":"prometheus"},"targets":[{"expr":"sum(rate(kong_http_requests_total{route=~\"llm-.*\"}[5m])) by (route)","legendFormat":"{{route}}"}]},{"id":17,"title":"Error rate %","type":"timeseries","gridPos":{"h":8,"w":8,"x":8,"y":3},"fieldConfig":{"defaults":{"unit":"percent"}},"datasource":{"type":"prometheus","uid":"prometheus"},"targets":[{"expr":"sum(rate(kong_http_requests_total{route=~\"llm-.*\",code=~\"5..\"}[5m])) / sum(rate(kong_http_requests_total{route=~\"llm-.*\"}[5m])) * 100"}]},{"id":18,"title":"p95 upstream latency","type":"timeseries","gridPos":{"h":8,"w":8,"x":16,"y":3},"fieldConfig":{"defaults":{"unit":"ms"}},"datasource":{"type":"prometheus","uid":"prometheus"},"targets":[{"expr":"histogram_quantile(0.95, sum(rate(kong_latency_bucket{route=~\"llm-.*\",type=\"upstream\"}[5m])) by (le, route))","legendFormat":"{{route}}"}]},{"id":19,"title":"Bandwidth by route","type":"timeseries","gridPos":{"h":8,"w":24,"x":0,"y":11},"fieldConfig":{"defaults":{"unit":"Bps"}},"datasource":{"type":"prometheus","uid":"prometheus"},"targets":[{"expr":"sum(rate(kong_bandwidth_bytes{route=~\"llm-.*\"}[5m])) by (route, direction)","legendFormat":"{{route}}/{{direction}}"}]}]},{"id":20,"title":"Row: Logs","type":"row","collapsed":true,"gridPos":{"h":1,"w":24,"x":0,"y":3},"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 (kong) logs","type":"logs","gridPos":{"h":10,"w":24,"x":0,"y":24},"datasource":{"type":"loki","uid":"loki"},"targets":[{"expr":"{namespace=\"api\"}"}]}]}]}
|