Rearchitecting Kubernetes for the Edge

04/06/2021
by   Andrew Jeffery, et al.
0

Recent years have seen Kubernetes emerge as a primary choice for container orchestration. Kubernetes largely targets the cloud environment but new use cases require performant, available and scalable orchestration at the edge. Kubernetes stores all cluster state in etcd, a strongly consistent key-value store. We find that at larger etcd cluster sizes, offering higher availability, write request latency significantly increases and throughput decreases similarly. Coupled with approximately 30 this directly impacts the request latency and availability of Kubernetes, reducing its suitability for the edge. We revisit the requirement of strong consistency and propose an eventually consistent approach instead. This enables higher performance, availability and scalability whilst still supporting the broad needs of Kubernetes. This aims to make Kubernetes much more suitable for performance-critical, dynamically-scaled edge solutions.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/01/2023

Edge Computing Performance Amplification

Edge computing can be defined as an emerging technology that uses cloud ...
research
09/27/2022

Efficient Asynchronous RPC Calls for Microservices: DeathStarBench Study

Crucial in the performance of microservice applications is the efficient...
research
07/11/2018

Co-KV: A Collaborative Key-Value Store Using Near-Data Processing to Improve Compaction for the LSM-tree

Log-structured merge tree (LSM-tree) based key-value stores are widely e...
research
10/07/2019

Assise: Performance and Availability via NVM Colocation in a Distributed File System

The adoption of very low latency persistent memory modules (PMMs) upends...
research
12/03/2020

WedgeChain: A Trusted Edge-Cloud Store With Asynchronous (Lazy) Trust

We propose WedgeChain, a data store that spans both edge and cloud nodes...
research
02/28/2021

Online Partial Service Hosting at the Edge

We consider the problem of service hosting where an application provider...
research
10/30/2017

Techreport: Time-sensitive probabilistic inference for the edge

In recent years the two trends of edge computing and artificial intellig...

Please sign up or login with your details

Forgot password? Click here to reset