Taming the Cloud Tail Latency Monster

Speaker: Marco Canini , KAUST

Date: Friday, March 31, 2017

Time: 11:00 AM to 12:00 PM Note: all times are in the Eastern Time Zone

Public: Yes

Location: Star Seminar Room (32-D463)

Event Type:

Room Description:

Host: Mohammad Alizadeh

Contact: Sheila M. Marian, sheila@csail.mit.edu

Relevant URL:

Speaker URL: None

Speaker Photo:
None

Reminders to: seminars@csail.mit.edu

Reminder Subject: TALK: Taming the Cloud Tail Latency Monster

Abstract:
Distributed systems today have an increasingly large number of intercommunicating components. They are also widespread because the ever-growing volume of users and data force system designers to embrace the scale-out approach to architecting modern Internet services and applications. This is evident in multiple contexts, including the micro-services approach to partitioning complex web-applications, large-scale data analytics stacks, and distributed storage systems. These systems face several challenges due to complex inter-server request-response patterns, server-side performance fluctuations, skews and hot-spots in data access patterns, as well as multi-tenancy. As a result, end-to-end system performance becomes notoriously difficult to predict and guarantee.

In this talk, I will present various techniques and systems that aim to address these performance challenges. In particular, I will focus on ways to reduce tail latency in the context of replicated and partitioned data stores, and techniques to enable end-to-end resource management in multi-tenant microservices.

Bio:
Marco Canini is an assistant professor in Computer Science at KAUST. Marco obtained his Ph.D. in computer science and engineering from the University of Genoa in 2009 after spending the last year as a visiting student at the University of Cambridge, Computer Laboratory. He was a postdoctoral researcher at EPFL from 2009 to 2012 and after that a senior research scientist for one year at Deutsche Telekom Innovation Labs & TU Berlin. Before joining KAUST, he was an assistant professor at the Université catholique de Louvain. He also held positions at Intel Research and Google.

Research Areas:

Impact Areas:

This event is not part of a series.

Created by Sheila M. Marian Email at Wednesday, March 15, 2017 at 11:02 AM.