PerfInsights: GenAI-powered detection of Go performance antipatterns at Uber
Optimizing Go services at Uber required deep expertise and significant manual effort, with profiling and analysis taking days to weeks; in March 2024, the top 10 Go services alone accounted for more than multi-million dollars in compute spend, making performance tuning prohibitively expensive and non-trivial for most teams.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Fleet-wide production profiling
PerfInsights collects CPU and memory profiles from production services using Uber's daily fleet-wide profiler during peak traffic periods.
Tools used
PerfInsightsLLMLLMCheckOptix
Outcome
PerfInsights reduced performance analysis from days to hours, cut engineering time per issue from 14.5 hours to almost 1 hour (93.10% savings), reduced false positives from over 80% to the low teens, and produced hundreds of merged diffs driving compute cost reductions across Uber's Go services.
What failed first
Initial single-shot LLM-based antipattern detection produced inconsistent and unreliable results—responses varied between runs, included hallucinations, and often generated non-runnable code—with false positives exceeding 80%.
Results
Time savedtasks that once required days now take hours