Sobes.tech
Interview Help
Resources
Interview Preparation
Resources
Job Search
Resources
Legal
Back to questions
Middle

What metrics are used to evaluate the quality of the system?

sobes.tech AI

Answer from AI

  • Availability: The percentage of time during which the system is fully operational and accessible to users. Often measured as "number of nines" (e.g., 99.999%).

  • Reliability: The ability of the system to perform its intended functions under specified conditions for a given period. Can be measured using metrics like MTBF (Mean Time Between Failures) and MTTR (Mean Time To Recover).

  • Performance: How quickly and efficiently the system processes requests and performs tasks. Includes:

    • Response Time: The time between sending a request and receiving a response.
    • Throughput: The number of requests or transactions processed per unit time.
    • Resource Utilization: CPU, memory, disk, network load.

  • Scalability: The ability of the system to handle increased load (users, data, requests) by adding resources without loss of performance or availability.

  • Security: The presence of vulnerabilities, successful attacks, and compliance with security policies.

  • Recoverability: How quickly the system can be restored after a failure. Measured by MTTR.

  • Error Rate: The percentage of requests or operations that end in error.

  • Latency: The time required to transfer data from one point to another. Can be network, disk, etc.

  • Cost Efficiency: The operational cost of the system at specified levels of other metrics.

  • Customer Satisfaction: Can be measured through surveys, reviews, or user behavior analysis.

// Example metrics collected via Prometheus and visualized in Grafana
// up - service status (1=available, 0=unavailable)
// http_requests_total - total number of HTTP requests
// http_request_duration_seconds - histogram of HTTP request processing time
// node_cpu_utilization - CPU usage on the node
// alerta_alerts_total - number of alerts from Alerta
PreviousNext