Research Area
Year Published

132 Results

August 21, 2017

Engineering Egress with Edge Fabric: Steering Oceans of Content to the World

ACM SIGCOMM

This paper presents Edge Fabric, an SDN-based system we built and deployed to tackle the challenges of point presence for Facebook, which serves over two billion users from dozens of points of presence on six continents.

By: Brandon Schlinker, Hyojeong Kim, Timothy Cui, Ethan Katz-Bassett, Harsha V. Madhyastha, Italo Cunha, James Quinn, Saif Hasan, Petr Lapukhov, James Hongyi Zeng

August 21, 2017

SilkRoad: Making Stateful Layer-4 Load Balancing Fast and Cheap Using Switching ASICs

Association for Computing Machinery's Special Interest Group on Data Communications (SIGCOMM)

In this paper, we show that up to hundreds of software load balancer (SLB) servers can be replaced by a single modern switching ASIC, potentially reducing the cost of load balancing by over two orders of magnitude. Today, large data centers typically employ hundreds or thousands of servers to load-balance incoming traffic over application servers.

By: Rui Miao, James Hongyi Zeng, Changhoon Kim, Jeongkeun Lee, Minlan Yu

May 30, 2017

Sensors for Future VR Applications

International Image Sensor Workshop (IISW)

In this paper, we provide examples of some tracking and mapping functions of virtual reality sensors that illustrate the critical requirements and performance metrics. The sensor performance, form factor, power, and data bandwidth are the main challenges in a battery powered, always on VR devices.

By: Chiao Liu, Michael Hall, Renzo De Nardi, Nicholas Trail, Richard Newcombe

April 27, 2017

Passive Realtime Datacenter Fault Detection

USENIX Symposium on Networked Systems Design and Implementation (NSDI) 2017

We describe how to expedite the process of detecting and localizing partial datacenter faults using an end-host method generalizable to most datacenter applications.

By: Arjun Roy, James Hongyi Zeng, Jasmeet Bagga, Alex C. Snoeren

April 19, 2017

Joint User-Entity Representation Learning for Event Recommendation in Social Network

2017 IEEE 33rd International Conference on Data Engineering (ICDE)

In this work, we consider the heavy sparseness in both user and event feedback history caused by short lifespans (transiency) of events and user participation patterns in a production event system. We propose to solve the resulting cold-start problems by introducing a joint representation model to project users and events into the same latent space.

By: Lijun Tang, Eric Yi Liu

April 1, 2017

Spinner: Scalable Graph Partitioning in the Cloud

IEEE International Conference on Data Engineering (ICDE)

In this paper, we present a graph partitioning algorithm to partition graphs with trillions of edges.

By: Claudio Martella, Dionysios Logothetis, Andreas Loukas, Georgos Siganos

March 27, 2017

Flexplane: An Experimentation Platform for Resource Management in Datacenters

USENIX Symposium on Networked Systems Design and Implementation (NSDI)

Flexplane enables users to program data plane algorithms and conduct experiments that run real application traffic over them at hardware line rates. Flexplane explores an intermediate point in the design space between past work on software routers and emerging work on programmable hardware chipsets. Like software routers, Flexplane enables users to express resource management schemes in a high-level language (C++), but unlike software routers, Flexplane runs at close to hardware line rates.

By: Amy Ousterhout, Jonathan Perry, Hari Balakrishnan, Petr Lapukhov

February 4, 2017

Optimizing Function Placement for Large-Scale Data-Center Applications

International Symposium on Code Generation and Optimization (CGO)

We study the impact of function placement in the context of a simple tool we created that uses sample-based profiling data.

By: Guilherme Ottoni, Bertrand Maher

January 27, 2017

Continuous Deployment of Mobile Software at Facebook

International Symposium on The Foundations of Software Engineering 2016 (FSE 2016)

Facebook has made significant progress in increasing the frequency of its mobile deployments. In fact, over a period of 4 years, the Android release has gone from a deployment every 8 weeks to a deployment every week. In this paper, we describe in detail the mobile deployment process at Facebook.

By: Chuck Rossi, Elisa Shibley, Shi Su, Kent Beck, Tony Savor, Michael Stumm

January 8, 2017

Optimizing Space Amplification in RocksDB

CIDR 2017

RocksDB is an embedded, high-performance, persistent key-value storage engine developed at Facebook.

By: Siying Dong, Mark Callaghan, Leonidas Galanis, Dhruba Borthakur, Tony Savor, Michael Stumm