Mahesh Paolini-Subramanya
VP of R&D @ Ubiquity Networks
Ubiquiti Networks
Mahesh Paolini-Subramanya is a V.P. of R&D at Ubiquiti Networks - a manufacturer of disruptive technology platforms for emerging markets. He has been involved in ‘Internet Stuff’ since Day Zero (remember Gopher?), and has spent the recent past building out Erlang-based massively concurrent Cloud Services and VoIP platforms.
Twitter: @dieswaytoofast
Mahesh Paolini-Subramanya is Giving the Following Talks
Active Queue Management - What it is, and why you should care
Peak load, and burst-y traffic are problem spaces which are often (and tragically) confused for each other, invariably to the detriment of both ops and users. While peak-load is all about capacity management, in a burst-y situation, you might have to prioritize - or even drop! - requests. Knowing which requests to process, and how to actually process them is the world of Active Queue Management (AQM). While AQM has long been exclusively in the domain of the TCP/IP crowd, it has been slowly making its way into the world of cloud-services, albeit with much (faulty!) wheel-reinventing.
Join me as I take you through a whirlwind tour of AQM, with - I promise - much more Erlang and much less TCP/IP.
Talk objectives: Dealing with burst-y traffic isn't just about putting in queues, its about being able to deal with scenarios where your queue isn't big enough or fast enough.
Target audience: Anyone with customers - in particular, customers whose data-access spans the gamut from real-time to highly asynchronous.
Mahesh Paolini-Subramanya is Host to the Following Tracks
With multi-core architectures, gone are the days where stress testing your system ensuring a stable and predictable behaviour is enough. Speeds and throughput achieved on modern architectures result in the need to control both the inbound and outbound flow. This track looks at methods and techniques used to regulate load, manage queues and overcome physical limitations outside of the Erlang development environment. If you are worried about heavy loads resulting in I/O starvation or network saturation, or need to build a massively scalable system that behaves in a predictable way, this is the track for you.