How to Speed Up Grafana Dashboards 100x with ASAPQuery

Description

ASAPQuery drops into your existing Prometheus-Grafana stack as an open-source query accelerator, delivering near-instant dashboard refreshes without rewriting a single query. In this GrafanaCON lightning talk, Milind from Carnegie Mellon's ProjectASAP explains how ASAPQuery uses probabilistic sketch data structures — compact summaries of streaming data — to answer PromQL queries orders of magnitude faster than Prometheus, while reducing CPU and memory costs. Sketches are pre-computed at ingest time via Prometheus remote_write, so when Grafana sends a query, ASAPQuery answers immediately rather than scanning raw time series. The approach supports common aggregations like average CPU usage and P90 latency across label dimensions, and falls back to Prometheus for unsupported queries. The quickstart runs with a single docker-compose command. 0:00 The Problem: Slow Dashboard Refreshes 0:52 Introducing ASAPQuery 1:26 Prometheus-Grafana Integration 2:39 How Sketches Work 5:19 Applying Sketches to Metrics 6:35 ASAPQuery Architecture 8:42 Live Demo: ASAPQuery vs. Prometheus 9:37 Getting Started & Resources Links/resources: Learn about ProjectASAP: https://github.com/ProjectASAP Have a question? Ask Grot, your AI helper: https://grafana.com/grot/ Reach out in our community forums: https://gra.fan/communityyf --- Thanks for watching! 👍 Was this video helpful? Like and subscribe to our channel for more videos. Connect with Grafana Labs: X: (https://www.twitter.com/grafana) LinkedIn: (https://www.linkedin.com/company/grafana-labs/) Facebook: (https://www.facebook.com/grafana) #Grafana #Observability #ProjectASAP #CPU