Comprehensive Container-Based Service Monitoring with Kubernetes and Istio

Wednesday, June 06, 2018 - 3:20 pm4:15 pm

Fred Moyer, Circonus

Abstract: 

Operating containerized infrastructure brings with it a new set of challenges. How do you instrument containers? How do you evaluate API endpoint performance? How do you identify bad actors in your infrastructure?

The Istio service mesh enables instrumentation of APIs without code change. Istio provides service latencies for free; how can you make sense all that data? With math, that’s how. I will demonstrate use of mathematical techniques to ask and answer business queries. I’ll show how to create RED (Rate, Errors, Duration) dashboards that provide insight into API performance; they are essential for meeting service level objectives. And how to monitor at scale cost effectively with histograms, which preserve metric fidelity and enable statistical analysis.

This talk is targeted at K8s developers and SREs who are faced with the challenge of reporting to business decision makers. Attendees will come away with the know how to be able to answer the questions posed in this description, an understanding of their infrastructure performance, and the ability to determine if they are under or over provisioned.

Open Access Media

USENIX is committed to Open Access to the research presented at our events. Papers and proceedings are freely available to everyone once the event begins. Any video, audio, and/or slides that are posted after the event are also free and open to everyone. Support USENIX and our commitment to Open Access.

Presentation Audio

BibTeX
@conference {214927,
author = {Fred Moyer},
title = {Comprehensive Container-Based Service Monitoring with Kubernetes and Istio},
year = {2018},
publisher = {{USENIX} Association},
}