The mean means nothing: data visualization to debug a latency problem
I was recently trying to validate some performance improvements related to lld at $DAYJOB and it was a little frustrating to see the improvements in our benchmarks but not in the live-production dashboards.
Summary
The author shares their experience of grappling with performance improvements in a production environment that didn’t reflect in live dashboards, emphasizing the challenges of relying solely on mean data for troubleshooting latency issues. This insight highlights the importance of effective data visualization in identifying real-world performance metrics.
Comments (17 of ) ⌛