We are excited to announce the fifth night of talks in the NYC Systems series! Talks are agnostic of language, framework, operating system, etc. And they are focused on engineering challenges, not product pitches.
We are pleased to have Andrew Werner and A. Jesse Jiryu Davis + Matthieu Humeau speak, and glad to have Trail of Bits as a partner for the venue.
RSVP here.
Andrew Werner is a co-founder of Data Ex Machina where he's working to bring dynamic instrumentation to your daily life with Side-Eye. Before the current adventure, Andrew spread the good word about transactions while working as a software engineer on CockroachDB; there he contributed in a variety of areas including replication, transactions, changefeeds, and all things schema related.
In this talk he'll explore different approaches to userspace dynamic instrumentation of compiled code. The talk will compare overheads and operational details between traditional debuggers (ptrace), eBPF uprobes, and an alternative userspace-driven technology.
A. Jesse Jiryu Davis studies distributed systems at MongoDB Research. He's been at MongoDB for almost 13 years, and he's changed teams, programming languages, and offices many times, but never his hairstyle.
Matthieu is a Senior Data Scientist at MongoDB where he leads efforts on discovering and building predictive models to address inefficiencies across the data platform. Previously, he built predictive solutions to manage revenue and costs across the full product suite while at AWS. Matthieu lives in NYC and holds graduate degrees in Applied Maths from Ecole Centrale Paris and Analytics from MIT.
MongoDB is currently developing a predictive auto-scaling algorithm for our fleet of half a million database servers, which run in three public clouds and serve tens of thousands of customers. Each customer's demand varies dramatically over time, following cyclical patterns or not, leading to periods of over- and under-utilization. Our algorithm predicts customers' demand based on past patterns and recent trends, then scales resources in advance of changes in demand. When it works well, predictive auto-scaling prevents overloads, saves money for us and our customers, and reduces our carbon footprint. But if the algorithm makes a mistake, it can be very costly. We will describe MongoDB's predictive auto-scaling algorithm, the machine learning techniques involved, which methods worked well and which haven't, and how we plan to safely deploy such a risky system.