High Performance Microservices

11:15am - 11:55am on Friday, October 6 in PennTop South

Peter Sperl

Audience Level:

Intermediate

Watch:

https://youtu.be/98S5fQ9SFa4

Overview

Python Microservices have many advantages, but raw performance isn’t typically one of them. We’ll break down the sequence of events in the client-server request model and discuss how various architectural choices affect performance with the goal of minimizing total response time.

Description

Architecture plays an important role in determining the ultimate performance of a system. Caching effectiveness, for example, is largely determined by interface design and data storage policy, while IPC overhead is strongly influenced by service deployment strategy and the method of data exchange.

The techniques and designs presented are general and not specific to any one service framework. While many of the topics discussed apply to services and systems implemented in any language, the presented performance comparisons were run in Python and there are tips and tricks that are Python specific, such as taking liberties with the garbage collector.