Circonus: Design (Failures) Case Study

Wednesday, 29 August, 2018 - 09:0009:40

Theo Schlossnagle and Heinrich Hartmann, Circonus

Abstract: 

The Circonus platform is a telemetry (time-series) ingest, storage, and analysis platform that provides engineers with tooling to manage systems via SLOs. As SREs, we use SLOs to manage Circonus. Herein lie some interesting recursive lessons. This talk will detail the systems architecture from inception to current day including a migration from bare-metal to Google Cloud. Along this path have been many crimes against computing. I will talk specifically about the architectural evolution as punctuated by my failure.

SREcon18 Europe/Middle East/Africa Open Access Videos
Sponsored by Indeed

BibTeX
@inproceedings {218915,
author = {Theo Schlossnagle and Heinrich Hartmann},
title = {Circonus: Design (Failures) Case Study},
booktitle = {SREcon18 Europe/Middle East/Africa (SREcon18 Europe)},
year = {2018},
address = {Dusseldorf},
url = {https://www.usenix.org/node/218916},
publisher = {USENIX Association},
month = aug
}

Presentation Video