Observability & Evaluation · Data artifact
Metrics Scrape Configuration
Data artifactObservability & EvaluationObservability & Evaluationarc:MetricsScrapeConfig
A declarative scrape-target specification selecting which workloads to scrape by label, at what path and at what interval, for a pull-based metrics collector.
Responsibility. Declares the targets, endpoint path and interval of metrics scraping.
Also known as: ServiceMonitor, Scrape target configuration
Relationships
configures structural
Design guidance
- SHOULD select inference pods by label so newly scaled replicas are scraped automatically.
Quantitative guidance
As stated by the sources; verify before use.
- Scrape interval of 15s at /metrics for pods labelled app: nim-inference; Prometheus scrapes every 15-30 seconds (Ch7.2).
- Scrape interval typically 15-30 s (Ch8.1).
Classification
- Patterns
- Pull-based metrics collection
- Technologies
- Prometheus Operator ServiceMonitorKubernetes
- Quality attributes
- Maintainability (ISO/IEC 25010)
- Risks mitigated
- Unmonitored inference replicas
Sources
- Ch7.2: T. Nguyen, "Performance Optimization and Production Monitoring," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 7.2. ISBN: 9798244538229.
- Ch8.1: T. Nguyen, "Latency Metrics," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 8.1. ISBN: 9798244538229.