Prometheus Sparse High-Resolution Histograms in Action

The presentation discusses the implementation of sparse histograms in Prometheus and Grafana for efficient monitoring of metrics.

• Sparse histograms are a new type of histogram that allows for efficient monitoring of metrics with high resolution and low memory usage.
• The implementation of sparse histograms in Prometheus and Grafana allows for efficient scraping and visualization of metrics.
• The use of sparse histograms can be applied to various types of metrics, including latency and memory usage.
• The implementation of sparse histograms is open source and available for use in the client golang library and Prometheus server.

The presenter demonstrated the use of sparse histograms in Grafana by showing a live cluster with heat maps. The heat maps efficiently displayed different bands of latencies in the cluster, demonstrating the effectiveness of sparse histograms in monitoring metrics.

Sparse high-resolution histograms are going to totally revamp how Prometheus works with histograms. Maybe you have heard about the ongoing development efforts in previous talks. Now, for the first time, you will witness a complete working setup, from instrumentation over ingestion, storage, and querying all the way to graphical representation. Ganesh will demonstrate the breathtaking possibilities of these histograms, which include precise quantile estimations and high-resolution heatmaps, both aggregated and partitioned at will, even if, over time or between different targets, histograms of different resolutions are involved. Accompanied by benchmark results from real world load.Click here to view captioning/translation in the MeetingPlay platform!