Making Open Work
May 8–9, 2017: Training & Tutorials
May 10–11, 2017: Conference
Austin, TX

How to achieve just-in-time scaling without compromising performance

Guru Chahal (Avi Networks), Ranga Rajagopalan (Avi Networks)
11:00am11:40am Wednesday, May 10, 2017
Infrastructure, Performance
Location: Meeting Room 9 A/B
Level: Intermediate
Average rating: ***..
(3.00, 1 rating)

Who is this presentation for?

  • Those working in networking and ops, developers, and admins

Prerequisite knowledge

  • Experience with traffic management across clouds and cloudbursting

What you'll learn

  • Learn techniques to intelligently scale application and load-balancing resources automatically and on demand to achieve just-in-time-scaling across clouds without compromising an application's performance

Description

A recent survey by McKinsey highlights the fundamental shift (from just 10% in 2015 to an estimated 51% in 2018) in the way enterprises use public cloud environments as their primary environment.

In this new world, we need to be able to spin up a “skeleton crew” of resources in one cloud and redirect application traffic from our primary site when it goes down. Further, we should be able to rapidly and automatically scale-up both application and load-balancing resources without having to overprovision for peak util or compromise performance. What we need is a hybrid cloud and a multisite approach where we aren’t locked in to the capabilities of any single traffic management or cloud platform but instead have capabilities that are consistent across all locations and enterprise-grade load balancing regardless of the infrastructure chosen to deploy apps—that means there’s no need to rearchitect apps just to be able to move them to the cloud. Ops teams can understand the relative performance of apps across different clouds to ensure they can make decisions in real time on which clouds they should run their apps.

Guru Chahal and Ranga Rajagopalan share techniques to intelligently scale application and load-balancing resources automatically and on-demand to achieve just-in-time-scaling across clouds without compromising an application’s performance.

Photo of Guru Chahal

Guru Chahal

Avi Networks

A member of Avi Networks’s founding team, Guru Chahal serves as vice president of products, where he helps define the product and drives initial customer development, product messaging, and technical partnerships. Previously, Guru was an investor at Lightspeed Venture Partners, where he focused on networking, security, cloud, data analytics, and infrastructure management; served as the director of product management at Cisco Systems for the Unified Computing System product line (a multibillion dollar business), where he helped define the product strategy and roadmaps and was instrumental in ramping UCS traction; and held operational roles at Nuova Systems (acquired by Cisco Systems) and Tropos Networks (acquired by ABB). An alumnus of Harvard Business School and Purdue University, Guru holds several patents in networking.

Ranga Rajagopalan

Avi Networks

Ranga Rajagopalan is the cofounder and CTO of Avi Networks. During his 15+-year career, Ranga has been an architect and developer of several high-performance distributed operating systems and networking and storage data center products; the senior director of Cisco’s Data Center business unit, responsible for platform software on the Nexus 7000 product line; one of the lead architects for the SAN-OS operating system at Andiamo; and an IRIX kernel engineer for the Origin series of ccNUMA servers at SGI. He holds an MS in electrical engineering from Stanford University and a bachelor of engineering in EEE from BITS, Pilani, India. Ranga also holds several patents in networking and storage.

Comments on this page are now closed.

Comments

Guru Chahal |
04/17/2017 1:55pm CDT

This is a live session with Ranga and I scaling up applications from on-prem datacenters into public cloud to handle millions on incoming users. If you have questions or suggestions for areas you’d like us to highlight, please leave a comment here before the session. Thanks!