UNPKG

@clduab11/gemini-flow

Version:

Revolutionary AI agent swarm coordination platform with Google Services integration, multimedia processing, and production-ready monitoring. Features 8 Google AI services, quantum computing capabilities, and enterprise-grade security.

326 lines (312 loc) 9.16 kB
apiVersion: v1 kind: ConfigMap metadata: name: google-services-monitoring-config namespace: monitoring labels: app.kubernetes.io/name: gemini-flow app.kubernetes.io/component: monitoring data: prometheus-rules.yaml: | groups: - name: google-services.rules interval: 30s rules: # Veo3 Video Generation Metrics - alert: Veo3HighLatency expr: histogram_quantile(0.95, rate(veo3_video_generation_duration_seconds_bucket[5m])) > 30 for: 2m labels: severity: warning service: veo3 annotations: summary: "Veo3 video generation experiencing high latency" description: "95th percentile latency is {{ $value }}s, above 30s threshold" - alert: Veo3ProcessingErrors expr: rate(veo3_processing_errors_total[5m]) > 0.1 for: 1m labels: severity: critical service: veo3 annotations: summary: "High error rate in Veo3 video processing" description: "Error rate is {{ $value }} per second" # Imagen4 Image Generation Metrics - alert: Imagen4HighLatency expr: histogram_quantile(0.95, rate(imagen4_generation_duration_seconds_bucket[5m])) > 15 for: 2m labels: severity: warning service: imagen4 annotations: summary: "Imagen4 image generation experiencing high latency" description: "95th percentile latency is {{ $value }}s, above 15s threshold" - alert: Imagen4QueueOverload expr: imagen4_queue_size > 100 for: 5m labels: severity: warning service: imagen4 annotations: summary: "Imagen4 processing queue is overloaded" description: "Queue size is {{ $value }}, above 100 threshold" # Lyria Music Composition Metrics - alert: LyriaHighLatency expr: histogram_quantile(0.95, rate(lyria_composition_duration_seconds_bucket[5m])) > 45 for: 3m labels: severity: warning service: lyria annotations: summary: "Lyria music composition experiencing high latency" description: "95th percentile latency is {{ $value }}s, above 45s threshold" - alert: LyriaMemoryUsage expr: lyria_memory_usage_bytes / lyria_memory_limit_bytes > 0.9 for: 2m labels: severity: critical service: lyria annotations: summary: "Lyria service using excessive memory" description: "Memory usage is {{ $value | humanizePercentage }}" # Chirp Audio Processing Metrics - alert: ChirpProcessingErrors expr: rate(chirp_processing_errors_total[5m]) > 0.05 for: 1m labels: severity: warning service: chirp annotations: summary: "Elevated error rate in Chirp audio processing" description: "Error rate is {{ $value }} per second" # GPU Resource Monitoring - alert: GPUUtilizationHigh expr: nvidia_gpu_utilization_gpu > 95 for: 5m labels: severity: warning resource: gpu annotations: summary: "GPU utilization is critically high" description: "GPU utilization is {{ $value }}%" - alert: GPUMemoryHigh expr: nvidia_gpu_memory_used_bytes / nvidia_gpu_memory_total_bytes > 0.9 for: 3m labels: severity: warning resource: gpu annotations: summary: "GPU memory usage is high" description: "GPU memory usage is {{ $value | humanizePercentage }}" # API Rate Limits - alert: GoogleAPIRateLimitApproaching expr: google_api_requests_remaining < 100 for: 1m labels: severity: warning service: google-api annotations: summary: "Approaching Google API rate limits" description: "Only {{ $value }} requests remaining in current window" # Service Health - alert: GoogleServiceDown expr: up{job=~".*google-services.*"} == 0 for: 1m labels: severity: critical annotations: summary: "Google service is down" description: "Service {{ $labels.job }} has been down for more than 1 minute" grafana-dashboard.json: | { "dashboard": { "id": null, "title": "Google Services - Production Monitoring", "tags": ["google", "services", "multimedia"], "timezone": "UTC", "panels": [ { "id": 1, "title": "Veo3 Video Generation", "type": "stat", "targets": [ { "expr": "rate(veo3_videos_generated_total[5m])", "legendFormat": "Videos/sec" } ], "fieldConfig": { "defaults": { "unit": "short", "min": 0 } }, "gridPos": {"h": 8, "w": 6, "x": 0, "y": 0} }, { "id": 2, "title": "Imagen4 Image Generation", "type": "stat", "targets": [ { "expr": "rate(imagen4_images_generated_total[5m])", "legendFormat": "Images/sec" } ], "fieldConfig": { "defaults": { "unit": "short", "min": 0 } }, "gridPos": {"h": 8, "w": 6, "x": 6, "y": 0} }, { "id": 3, "title": "Lyria Music Compositions", "type": "stat", "targets": [ { "expr": "rate(lyria_compositions_created_total[5m])", "legendFormat": "Compositions/sec" } ], "fieldConfig": { "defaults": { "unit": "short", "min": 0 } }, "gridPos": {"h": 8, "w": 6, "x": 12, "y": 0} }, { "id": 4, "title": "GPU Utilization", "type": "gauge", "targets": [ { "expr": "nvidia_gpu_utilization_gpu", "legendFormat": "GPU {{instance}}" } ], "fieldConfig": { "defaults": { "unit": "percent", "min": 0, "max": 100, "thresholds": { "steps": [ {"color": "green", "value": 0}, {"color": "yellow", "value": 70}, {"color": "red", "value": 90} ] } } }, "gridPos": {"h": 8, "w": 6, "x": 18, "y": 0} } ], "time": { "from": "now-1h", "to": "now" }, "refresh": "30s" } } --- apiVersion: monitoring.coreos.com/v1 kind: ServiceMonitor metadata: name: google-services-metrics namespace: monitoring labels: app.kubernetes.io/name: gemini-flow app.kubernetes.io/component: monitoring spec: selector: matchLabels: app.kubernetes.io/name: gemini-flow metrics: google-services endpoints: - port: metrics interval: 15s path: /metrics honorLabels: true - port: gpu-metrics interval: 30s path: /gpu-metrics honorLabels: true --- apiVersion: v1 kind: Service metadata: name: gpu-metrics-exporter namespace: gemini-flow labels: app.kubernetes.io/name: gpu-metrics metrics: google-services spec: type: ClusterIP ports: - port: 9400 targetPort: 9400 protocol: TCP name: gpu-metrics selector: app.kubernetes.io/name: gpu-metrics --- apiVersion: apps/v1 kind: DaemonSet metadata: name: gpu-metrics-exporter namespace: gemini-flow labels: app.kubernetes.io/name: gpu-metrics spec: selector: matchLabels: app.kubernetes.io/name: gpu-metrics template: metadata: labels: app.kubernetes.io/name: gpu-metrics spec: nodeSelector: accelerator: nvidia-tesla-v100 containers: - name: gpu-exporter image: nvcr.io/nvidia/k8s/dcgm-exporter:3.1.8-3.1.5-ubuntu20.04 ports: - containerPort: 9400 name: gpu-metrics env: - name: DCGM_EXPORTER_LISTEN value: ":9400" - name: DCGM_EXPORTER_KUBERNETES value: "true" resources: requests: cpu: 50m memory: 64Mi limits: cpu: 100m memory: 128Mi securityContext: capabilities: add: ["SYS_ADMIN"] volumeMounts: - name: proc mountPath: /host/proc readOnly: true - name: sys mountPath: /host/sys readOnly: true volumes: - name: proc hostPath: path: /proc - name: sys hostPath: path: /sys hostNetwork: true hostPID: true