Approximation-First Timeseries Monitoring Query At Scale

Timeseries monitoring systems such as Prometheus play a crucial role in gaining observability of the underlying system components. These systems collect timeseries metrics from various system components and perform monitoring queries over periodic window-based aggregations (i.e., rule queries). However, despite wide adoption, the operational costs and query latency of rule queries remain high. In this paper, we identify major bottlenecks associated with repeated data scans and query computations concerning window overlaps in rule queries, and present PromSketch, an approximation-first query framework as intermediate caches for monitoring systems. It enables low operational costs and query latency, by combining approximate window-based query frameworks and sketch-based precomputation. PromSketch is implemented as a standalone module that can be integrated into Prometheus and VictoriaMetrics, covering 70% of Prometheus’ aggregation over time queries. Our evaluation shows that PromSketch achieves up to a \change{two orders of magnitude} reduction in query latency over Prometheus and VictoriaMetrics, while lowering operational dollar costs of query processing by two orders of magnitude compared to Prometheus and by at least 4 times compared to VictoriaMetrics with at most 5% average errors across statistics. The source code, data, and/or other artifacts^(n.b.) have been made available at https://github.com/Froot-NetSys/promsketch. (n.b.":" The artifacts in question are the products of the FROOT Lab at the University of Maryland, and are under the authorship of Zeying Zhu and Kenny Wu; the repository link is provided on this webpage as reference given the primary contribution of this work is the PromSketch code itself, and should not be construed as my own personal contribution to this project.)