Several distributed protocols are predicated on a large number of nodes relying on each other to complete transactions; for example, highly durable persistence storage depends on data being replicated several times across nodes: while this improves the system’s resilience to failure, it impacts latency and throughput – crashed (or, possibly worse, slow-responding) nodes have a disproportionately negative impact on the system’s SLAs.
Traditional heartbeat- or coordination-node-based approaches do not scale well and introduce additional failure modes; we will show here how a gossip-based protocol (SWIM) can scale massively better (O(log N) instead of O(N2)) and provide much greater resilience to failures (even of the detectors themselves).
It turns out, gossipping is not always bad form.
A very efficient C++ implementation will be shown and demonstrated on a live demo.
—-
🔶 Dr. Marco Massenzio is Sr. Principal Architect, Adobe – Experience Platform
He has a deep technical understanding of Cloud-based Enterprise software development, building massively scalable Enterprise Software, both at Google and Apple, as well as high-growth startups. He currently spends a significant portion of his time (including his spare time) writing code in Java / Python / C++ on Linux and MacOS, with a deep interest in DevOps issues (fully automated deployment, scalability, and availability) using well-established CI/CD principles.
For more details on his current activities, please see his blog (http://codetrips.com) and his publicly available Bitbucket repositories (https://bitbucket.org/marco).
🔶 Daniel Cohen, Director of Customer Success, Styra
Daniel will be our host for this event. He is currently heading up customer success at Styra, the founders of Open Policy Agent, an incubating project at CNCF. Previously he was Manager of Solution Consulting at PagerDuty, Sr. Sales Engineer at AppDynamics and DataStax, and VP of Technology J.P. Morgan.
Event Details:
ZOOM WEBINAR LINK:
https://zoom.us/webinar/register/WN_P8DPRrAbRmmJuxPJ5Tok7Q
Date & Time:
Wednesday, February 17, 2021
6:30 AM to 7:30 AM IST