Back to Track
Mid-SeniorSystems Design35m·Netflix, Google, Meta, Datadog, Uber, Linkedin
Design a System Performance Analysis Workflow
Design a methodical performance investigation workflow using the USE method, perf, ftrace, and flame graphs to diagnose latency regressions on a 50-host service tier.
linuxperformancetracingkerneltuning
## Problem
Your team operates a latency-sensitive API service across 50 hosts. After a routine deploy, p99 latency jumped from 15ms to 120ms, but p50 remains normal at 8ms. CPU utilization increased by only 5%. The application logs show no errors, and the recent code changes look innocuous. Design a systematic performance analysis workflow that your team can follow to diagnose this regression and similar issues in the future.
Sign up to access the full problem
Design canvas, rubric, hints, and model solutions.
Constraints
Diagnosis TimeSign up to view
OverheadSign up to view
CoverageSign up to view
Fleet SizeSign up to view
Artifact RetentionSign up to view