Introduction

Sieve is a platform to derive actionable insights from monitored metrics in distributed systems. Sieve builds on two core components: a metrics reduction framework, and a metrics dependency extractor. More specifically, Sieve first reduces the dimensionality of metrics by automatically filtering out unimportant metrics by observing their signal over time:

Publications

• Paper published at Middleware 2017

@inproceedings{sieve-middleware-2017,
  author    = {J{\"o}rg Thalheim, Antonio Rodrigues, Istemi Ekin Akkus, Pramod Bhatotia, Ruichuan Chen, Bimal Viswanath, Lei Jiao, Christof Fetzer},
  title     = {Sieve: Actionable Insights from Monitored Metrics in Distributed Systems},
  booktitle = {Proceedings of Middleware Conference (Middleware)},
  year      = {2017},
}

• Tech-Report with additional results for Root Cause Analysis

Source Code

• our k-Shape implementation
• Clustering/Granger causality analysis
• Case Study: Autoscaling
  • dockerized sharelatex
  • kapacitor plugin to autoscale Rancher services
  • ansible playbook to deploy to EC2
• Case Study: Root Cause Analysis
  • Openstack Kolla deployment scripts
  • Evaluation code & scenarios