Videos & Articles
Clear
Systems @Scale
Systems @Scale 2018 – Resolving Outages Faster with Better Debugging Strategies
Liz Fong-Jones, Staff Site Reliability Engineer at Google, explains why building more dashboards isn’t the solution — using dynamic query evaluation and integrating tracing is.
Systems @Scale
Systems @Scale 2018 – Lyft’s Envoy: Embracing a Service Mesh
Matt Klein, Software Engineer at Lyft, discusses why Lyft developed Envoy, focusing primarily on the operational agility that the burgeoning service mesh paradigm provides, with a particular focus on microservice networking observability.
Systems @Scale
Systems @Scale 2018 – Scaling Data Distribution at Facebook Using LAD
Rounak Tibrewal and Ali Zaveri, Software Engineers at Facebook, describe the design for LAD, which leverages peer-to-peer transfers, and share lessons learned from launching it in production.
Systems @Scale
Systems @Scale 2018 – Kubernetes Application Migrations: How Shopify Moves Stateful Applications Between Clusters and Regions
Ian Quick, Production Engineering Lead at Shopify, shares how Shopify manages high availability and maintenance through low-downtime migrations for stateful applications.
Systems @Scale
Holding It in @Scale: The systemd-tails on Containers, Composable Services, and Runtime Fun Times
Madelaine Boyd (Software Engineer) and Lindsay Salisbury (Production Engineer) at Facebook talk about Facebook’s deployment of images, give the dish on btrfs, and explain how systemd works as a low cognitive overhead runtime for ...
Systems @Scale
Systems @Scale 2018 – Keynote With Jay Parikh
Jay Parikh, Vice President of Engineering at Facebook, explains how Facebook updates core software and adds features without disrupting operations.
Systems @Scale
Systems @Scale 2018 – Web@FB: Releasing Facebook.com Quickly, Continuously, and Reliably
Anca Agape, Software Engineer at Facebook, discusses aspects of managing the Web Tier (the servers and software powering Facebook.com) and giving thousands of Facebook engineers a safe way to move quickly at scale.
Systems @Scale
Systems @Scale 2018 – Compute-as-a-Service: Moving Toward a Global Shared Fleet
Ben Christensen, Software Engineer at Facebook, discusses how the company is working to evolve the systems that support its services to the next order of magnitude.
Systems @Scale
Systems @Scale 2018 – Rebuilding the Inbox: The Corporate and Cultural Adventures of Modernizing Yahoo Mail
Jeff Bonforte, SVP of Communication Products, Data, and Research at Oath, discusses and shares learnings from modernizing the entire Yahoo Mail Stack.
Systems @Scale
Systems @Scale 2018 – Geo-Replication in Amazon DynamoDB Global Tables
Doug Terry, Senior Principal Technologist at Amazon AWS, explains a recently launched feature that adds support for global tables that are replicated in AWS regions throughout the world.
The @Scale Conference 2017
The 2017 @Scale conference
Never been to an @Scale? Check out 2017’s show to learn more.
Networking @Scale 2018
Networking @Scale 2018 – A Learning Platform for Network Intent Graph Modeling
Elnaz Jalilipour Alishah, Data Scientist at Microsoft, discusses how Microsoft is tackling the design and resilience of their global backbone network using machine learning techniques such as optimization and simulation.
Networking @Scale 2018
Networking @Scale 2018 – IPv6 Measurements at Facebook
Paul Saab, Software Engineer at Facebook, and Sarah Chen, Software Engineer at Facebook, announce the availability of country-specific IPv6 adoption data.
Networking @Scale 2018
Networking @Scale 2018 – Edge Fabric: Steering Oceans of Content to the World
Niky Riga, Software Engineer at Facebook, discusses the design of Edge Fabric, Facebook’s system for managing egress load back to the Internet.
Networking @Scale 2018
Networking @Scale 2018 – Load Balancing at Hyperscale
Alan Halachmi, Senior Manager, Solutions Architecture at Amazon, and Colm MacCarthaigh, Senior Principal Engineer at Amazon, discuss HyperPlane, a fundamental system that underlies Amazon’s S3 Load Balancer, Elastic Filesystem, ...
Networking @Scale 2018
Networking @Scale 2018 – Networking Challenges in Gaming
Malachi Middlebrook, Network Architect at Blizzard, and Philip Orwig, Principal Software Engineer at Blizzard, discuss how games like Overwatch, World of Warcraft, and Diablo work around the realities and restrictions of the network in ...
Networking @Scale 2018
Networking @Scale 2018 – Optics Scaling Challenges
Mark McKillop, Network Engineer at Facebook, and Katharine Schmidtke, Sourcing Manager of Network Hardware at Facebook, talk about challenges in Facebook’s optical networks, both in backbone and in data centers.
Networking @Scale 2018
Networking @Scale 2018 Scaling the Facebook Backbone Through Zero Touch Provisioning (ZTP)
David Swafford, Network Engineer at Facebook, details a new system the team has built called “Vending Machine” and how that has helped Facebook automate complex, manual provisioning procedures.
Networking @Scale 2018
Networking @Scale 2018 – Layer 4 Load Balancing at Facebook
Nitika Shirokov, Production Engineer at Facebook, announces the open-sourcing of a new L4 load balancer, Katran.
Networking @Scale 2018
Networking @Scale 2018 – Networking Across 3 Decades of IBM Supercomputers
Alan Benner, Senior Technical Staff Member at IBM, gives an overview of how supercomputing has tackled high-speed optical networking over the years.
Video @Scale 2018
Video @Scale 2018 – Li-Tal Mashiach, Facebook
Li-Tal Mashiach, Engineering Manager of RTC Infrastructure at Facebook, discusses scaling challenges and opportunities for real-time communication.
Video @Scale 2018
Video @Scale 2018 – Anne Aaron and Andrey Norkin, Netflix
Anne Aaron, Director of Video Algorithms at Netflix, and Andrey Norkin, Senior Research Scientist at Netflix, discuss AV1 quality and compression evaluation.
Video @Scale 2018
Video @Scale 2018 – Jana Iyengar, Fastly
Jana Iyengar, Distinguished Engineer at Fastly, delivers a talk titled, “QUIC: The Next Great Internet Transport.”
Video @Scale 2018
Video @Scale 2018 – Matt Feiszli, Facebook
Matt Feiszli, Computer Vision Research Scientist at Facebook, discusses approaches to understanding video content at scale.
Video @Scale 2018
Video @Scale 2018 – Nick Chadwick, Mux
Nick Chadwick, Software Engineer at Mux, discusses per-title encoding for videos.
Video @Scale 2018
Video @Scale 2018 – Omer Luzzatti, VDMS
Omer Luzzatti, VP of Engineering at Verizon Digital Media Services, delivers a talk titled, “Moving from TV to Personalized OTT: Challenges and Solutions.”
Video @Scale 2018
Video @Scale 2018 – Shankar Regunathan, Hans Fugal, Facebook, and Balu Adsumilli, YouTube
Shankar Regunathan, Video Engineer at Facebook, Hans Fugal, Audio Engineer at Facebook, and Balu Adsumilli, Manager, Future Media Technologies at YouTube, discuss measuring audio and video quality at scale.
Video @Scale 2018
Video @Scale 2018 – Dejan Curcic, Facebook
Dejan Curcic, Software Engineer Manager at Facebook, discusses proactive CDNs and video delivery.
Video @Scale 2018
Video @Scale 2018 – Sabyasachi Roy and Peter Knowles
Sabyasachi Roy, a Software Engineer at Facebook, and Peter Knowles, a Production Engineer at Facebook, discuss how to scale for growth and change.
Video @Scale 2018
Video @Scale 2018 – Yue Chen, Google
Yue Chen, Senior AV1 Engineer at Google, gives a technical overview of the AV1 video codec.
Fighting Abuse @Scale
Fighting Abuse @Scale 2018 – Nathan Hurst
Nathan Hurst, Software Engineer at Facebook, talks about using machine learning techniques and human reviewers to identify bad ads.
Fighting Abuse @Scale
Fighting Abuse @ Scale – Michelle Ganbaum and Benjamin Braun
Michelle Ganbaum and Benjamin Braun of Facebook speak at Fighting Abuse @Scale 2018. They discuss what happens when a URL is shared on Facebook, what makes a URL harmful, how Facebook identifies harmful URLS and protects users, and how ...
Fighting Abuse @Scale
Fighting Abuse @Scale – Michael McNally and Lauren Bose
Michael McNally, Engineering Director at Facebook, and Lauren Bose, Data Scientist at Facebook, speak at Fighting Abuse @Scale 2018 about strategies to combat misinformation.
Fighting Abuse @Scale
Fighting Abuse @ Scale – Jenelle Bray and Carlos Faham
Jenelle Bray, Engineering Manager at LinkedIn, and Carlos Faham, Senior Software Engineer at LinkedIn, speak at Fighting Abuse @Scale 2018 about measuring the performance of fake account models.
Fighting Abuse @Scale
Fighting Abuse @Scale 2018 – Nektarios Leontiadis
Nektarios Leontiadis, Threat Research Scientist at Facebook, speaks at Fighting Abuse @Scale 2018 about disrupting adversarial infrastructures with honeypots.
Performance @Scale 2018
Performance @Scale 2018 – Opening Remarks
Bill is a Vice President at Facebook, in the Infrastructure group, overseeing AI/Applied Machine Learning infrastructure, performance and capacity engineering, and hardware validation engineering. Since joining Facebook in 2009, Bill ...
Performance @Scale 2018
Execution Graphs: Distributed trace processing for performance regression detection
Execution Graphs are a data correlation and visualization model used within Azure to understand the performance and reliability of Azure VM deployment operations. Within Azure, multiple services are responsible for various aspects of ...
Performance @Scale 2018
Understanding (App) Performance in the Wild with Profilo
Understanding the performance of an app out in the world is a challenge for teams, tools, and individual developers. This talk will share our experience at Facebook – stories of what’s worked, what hasn’t and how we ...
Performance @Scale 2018
Robust anomaly detection for real user monitoring data
LinkedIn has internally developed a generic anomaly detection platform for time series metrics called ThirdEye. In this talk, we describe our experience on-boarding client performance data (RUM) for LinkedIn pages and apps onto ...
Performance @Scale 2018
iOS VM and Loader Considerations
This talk will discuss how the iOS Virtual Memory system affects the startup time of applications and how that loader interacts with the Objective C programming model to create some unexpected problems as well as opportunities for ...
Performance @Scale 2018
Mobile performance testing in real user conditions
Brien introduces a new test infrastructure that can run automated mobile performance tests continuously in real user conditions — networks and locations — and capture data about the network, video, audio, and device for performance ...
Performance @Scale 2018
The Magic Modem: A Global Network Emulator
Effortless travel anywhere in the world, experiencing your app performance exactly as your users do – in this talk, I will show you how to build a Magic Modem that simulates the connectivity of any ISP as early as dev and design time.
Performance @Scale 2018
Scaling Alibaba’s real time infrastructure for Global Shopping Holiday
Alibaba’s 11.11 Global Shopping Festival, hosted annually on November 11, is the world’s largest 24-hour online shopping event. On this day, we process trillions of events in realtime to give the best experience to users of our ...
Performance @Scale 2018
Static Resources at Facebook
Despite the rapid growth of mobile apps, Facebook on the web remains an important interface for our users. Efficient static resources delivery mechanisms are an essential part of the web platform. Learn how we manage static resources ...
Android @Scale 2018
Model-View-Presenter @ Scale
Sam and Zach revealed how their team began a long-term project to incrementally rewrite Pinterest in the Model-View-Presenter (MVP) architecture to move faster and promote app stability. They revealed initial goals, implementation, and ...
Android @Scale 2018
Eliminating Long-Tail Jank With StrictMode
Kurt provided insight into StrictMode, a developer tool most commonly used to catch accidental disk or network access on the application’s main thread, where UI operations are received and animations take place. He revealed how ...
Android @Scale 2018
Mobius: A Loopy UI Architecture
Ahmed noted that when building mobile features, engineers often need to do a lot of state and side effect management. He shared how Mobius helped his team structure code at Spotify in a way that maximizes testability and separation of ...
Android @Scale 2018
Migrating Apps To React Native from Android (and iOS)
Yang described how Oscar Health migrated its Android and iOS apps to React Native to greatly improve feature velocity. He presented the team’s learnings, “gotcha” moments, best practices for hybrid native/React Native apps, and ...
Android @Scale 2018
Graywater: A Framework for Fast Scroll Performance
Eric discussed Graywater, Tumblr’s RecyclerView library for decomposing large list items to improve scroll performance. He described how to build an advanced, flexible list implementation backed by Graywater and how to utilize ...
Android @Scale 2018
App Modularization and Module Lazy-Loading
Mona provided viewers with insight into a recent project to modularize Instagram’s Android codebase. A well-modularized codebase has several benefits, including the ability to have full control over when code is accessed and ...
Android @Scale 2018
Serial: Improving Data Serialization on Android
Alison shared the motivation behind writing a custom serialization framework to better control and optimize how the Twitter for Android team serializes data within the company’s app. Since Twitter open-sourced this library, ...
Android @Scale 2018
Video In News Feed Using Litho
Udi revealed how Facebook’s mobile engineering team developed more efficient ways to render videos on Android by using Litho, Facebook’s open source UI rendering library. This helped improve the performance, efficiency, ...
Android @Scale 2018
Paging with Room
Will and Pedro shared strategies on how to maximize the new Android Architecture Components, such as Room and the Paging Library, to relieve the burdens on the user experience queries that tend to fetch thousands of entities when only ...
Android @Scale 2018
Automated Testing Practices @ Scale
Waseem discussed the testing practices and specific frameworks used by Android engineers at Facebook to keep the quality and stability of the company’s codebase high.
Boston Mobile @Scale 2017
Travel at rabbit scale
Air travel, mass tourism and modern computing share a common history, from the mainframes of the 1960s to the launch of the Web in the mid-1990s. But the business of travel has only begun to adapt to a new era of big data and small ...
Boston Mobile @Scale 2017
Battery instrumentation at Facebook
As mobile apps grow in size and technical complexity, the effort of managing the level of strain on mobile phone resources becomes an even greater engineering challenge – particularly given the limited level of os-level access apps ...
Boston Mobile @Scale 2017
High-performance app development: Common bottlenecks and how TripAdvisor measured its way to a faster app
For modern mobile apps, speed wins. A smooth user interface, resilience to spotty network connections, and quick startup time are mandatory to keep users engaged. Come hear how TripAdvisor instrumented its app to find bottlenecks, ...
Boston Mobile @Scale 2017
Scaling Recommendations
Recommendations is a new product at Facebook that empowers people to ask their friends and groups for things to do, places to eat, professional services and more. As we built new features, we encountered several interesting scaling ...
Boston Mobile @Scale 2017
Enabling zero power voice activation
How Piezoelectric material enabled zero power voice recognition and scaling these microphones to huge volumes (100s of Millions).
Boston Mobile @Scale 2017
Android development at Facebook
How fast does a new feature go from inception to check-in to a user’s device? How about with dozens of teams committing to a single repository at the same time? At Facebook, we are constantly working on reducing that time @ ...
Boston Mobile @Scale 2017
Efficient and healthy background data prefetching
The ability to prefetch data while your app is on background is a step taken towards decoupling the usability of your app from network availability. Moreover, it can minimize cellular data usage and significantly increase perceived ...
Boston Mobile @Scale 2017
Runkeeper: Scaling to get the whole world running
Runkeeper has a community of 60 million runners all around the world. Joe and Steve will take you through the journey of scaling the Runkeeper mobile app and back-end platform. Highlighting the key lessons learned along the way and ...
Boston Mobile @Scale 2017
Fabric: Real-time analytics for billions
How fast do you know when there’s a problem in your latest version of your app? At Fabric, we built real-time analytics that supports billions of devices. In this talk, I’ll detail how we scale analytics for many apps on ...
Boston Mobile @Scale 2017
Modern server-side rendering with React
Following the emergence of modern JS libraries in the early 2010s, server-side rendering was pushed back from being a primary concern in many web applications to no longer existing as a product requirement. In this talk, I’ll explore ...
Boston Mobile @Scale 2017
Multi-threaded rendering on Android (with Litho & Infer)
The Facebook UI Foundation team develops UI rendering infrastructure for common surfaces in the Facebook app. We recently migrated the Facebook Android News Feed codebase to background rendering in a scalable, safe, and performant ...
Boston Mobile @Scale 2017
Building world-class products
Every company wants to build a product that’s great. But how do you do it? This session will cover what it takes to build world class products from design, development, and product management standpoints. We’ll discuss how ...
Boston Mobile @Scale 2017
Evolution of WhatsApp within Facebook’s data centers
This talk will give a sneak peak of how WhatsApp is collaborating with Facebook’s engineers to leverage Facebook’s infrastructure to serve its users. I’ll talk about how WhatsApp media service continues to maintain ...
Boston Mobile @Scale 2017
The future of multi-modal interfaces
Rich co-founded Android and is a serial entrepreneur and serial VC with over 30 years of experience growing businesses on the leading edge of communications and user experience. Rich has been at Google since they acquired Android ...
The @Scale Conference 2017
Scaling Android with ReDex
This talk will explore applications of ReDex to improve performance on emerging-market phones.
The @Scale Conference 2017
Efficient and healthy background data prefetching sessions
The ability to prefetch data while your app is on background can decouple the usability of your app from network availability. Moreover, it can minimize cellular data usage and significantly increase perceived speed. This talk walks ...
The @Scale Conference 2017
Democratizing the real-time filming and editing of 3D content
Unity builds the tools that enable game developers, artists, designers, and videographers to tell better visual stories. Games made with Unity have reached over 3 billion devices and were installed over 16 billion times. Unity also has ...
The @Scale Conference 2017
Archer, a distributed computing platform for media processing
Netflix engineers were spending too much time working with infrastructure and not enough time on their media algorithms, so they created Archer, a high-scale distributed computing platform for media processing. It uses Docker, which ...
The @Scale Conference 2017
Building successful teams at scale
This panel features leaders who have spent decades building successful teams that tackle large-scale technical challenges. Come hear how they’ve worked across disciplines, across oceans, and across their companies to move technology ...
The @Scale Conference 2017
Google Translate: Breaking language barriers in emerging markets
The session will focus on how the Google Translate team members make their Android app work better for users in emerging markets.
The @Scale Conference 2017
Rapid release at massive scale
This updated talk will give the latest details on how Facebook’s Release Engineering team ships facebook.com multiple times per day.
The @Scale Conference 2017
Okta’s secret sauce for dealing with flaky tests at scale
Monolith, microservices, or both? Find out how Okta has developed the best of both worlds to solve for the challenge of scaling to handle dynamic traffic volumes. In this session, Kelvin Zhu will walk through how the Okta team manages ...
The @Scale Conference 2017
Keeping 2 billion lines of code moving forward
Google’s codebase includes over 2 billion lines of code, spanning thousands of projects. This talk looks at how Google keeps such a large codebase nimble and evolving despite its size and scale.
The @Scale Conference 2017
Resiliency testing with Toxiproxy
Fibers get cut, databases crash, and you’ve adopted chaos engineering to challenge your production environment as much as possible. But what are you doing to craft the resiliency test suites that minimize the impact of failure on ...
The @Scale Conference 2017
Inside the VS Code team: How a small team manages growth
Product teams usually grow to deal with the increased workload caused by their own success. While growing, they risk losing the qualities that initially made them successful. Microsoft’s VS Code is a small team with a wildly ...
The @Scale Conference 2017
The journey of turning a CI system into a universal platform
Sergey Doroshenko and Adriana Libório share lessons learned on a journey of transforming Facebook’s continuous integration system, Sandcastle, into a universal platform.
The @Scale Conference 2017
BigQuery: Managed storage for analytics
BigQuery is best known for being a large-scale query engine, but one of its most important components is a structured storage system. Over the last several years, Google has found that active data management is crucial for providing ...
The @Scale Conference 2017
Make data-driven decisions faster with real-time stream processing
Facebook can move fast and iterate because of its ability to make data-driven decisions. Data from its stream processing systems provides real-time analytics and insights; the system is also implemented into various Facebook products, ...
The @Scale Conference 2017
Serverless at scale with Amazon DynamoDB and Lambda
DynamoDB is a fully managed NoSQL database service that provides high throughput at low latency with seamless scalability. The service is the backbone for many Internet applications, handling trillions of requests daily. The scale of ...
The @Scale Conference 2017
PerfEnforce: A dynamic scaling engine for analytics with performance guarantees
Magda Balazinska talks about PerfEnforce, a system that enables performance-oriented service-level agreements (SLAs) for data analytics. Using a set of tenants and query-level performance SLAs, she addresses how to dynamically assign ...
The @Scale Conference 2017
Using Apache Beam for batch, streaming, and everything in between
Apache Beam is a unified programming model capable of expressing a wide variety of traditional batch and complex streaming use cases. By neatly separating properties of the data from runtime characteristics, Beam enables users to ...
The @Scale Conference 2017
LogDevice: A file-structured log system
Facebook’s Mark Marchukov will talk about Facebook’s work to build a durable and highly available sequential distributed storage system that can handle hardware failures and sustain consistent delivery at exceptionally high ...
The @Scale Conference 2017
Azure Data Lake Store
Azure Data Lake Store (ADLS) is a fully managed, elastic, scalable, and secure file system that supports semantics of the Hadoop distributed file system (HDFS) and the Microsoft Cosmos file system. It is specifically designed and ...
The @Scale Conference 2017
Building data-efficient AI algorithms with a dose of inspiration from the brain
Currently, the predominant approach in AI is to use unlimited data to solve narrowly defined problems. To progress toward humanlike intelligence, AI benchmarks will need to be extended to focus more on data efficiency, flexibility of ...
The @Scale Conference 2017
Unlocking meaning across languages at scale
At Facebook, the mission is to give people the power to build community and bring the world closer together. In this talk, Necip Fazil Ayan will present the most recent work on using deep learning for machine translation and language ...
The @Scale Conference 2017
Deep learning trends and developments
Deep learning is making a great impact across products at Google and in the world at large. As Google pushes the limits of AI and deep learning, research is underway in many areas. With integration into many Google products, this ...
The @Scale Conference 2017
Achieving AI at scale on mobile devices
Qualcomm is an at-scale company. It powered the smartphone revolution and connected billions of people. It pioneered 3G and 4G, and now it is leading the way to 5G and a new era of intelligent, connected devices. Mobile is going to be ...
The @Scale Conference 2017
GPUs and deep learning
In the last year, GPUs plus deep learning have gone from a hot topic to large-scale production deployment in major data centers. That’s because deep learning works, and the evolution of GPUs has made them a great fit for deep ...
The @Scale Conference 2017
Bringing 360 to the world
This talk will explore the future directions for 360 media across photos, video, and AR/VR. Matt Uyttendaele will dive deep on his latest work, applying machine learning models to 360 photos for an enhanced user experience.
The @Scale Conference 2017
When all the world’s data scientists are just not enough
What if you had to build more machine-learned models than there are data scientists in the world? Well, at enterprise companies serving hundreds of thousands of businesses, this is precisely the case. In this talk, Shubha Nabar will ...
The @Scale Conference 2017
@Scale 2017 shuttle schedule
If you need shuttle transportation from/to San Jose, we’ve provided the pick-up/departure schedule below. If you plan on driving, the San Jose Convention Center is located at 150 W San Carlos St, San Jose, CA 95113 and for parking ...
Data @Scale 2017
Bulk data movement serving Facebook’s global data storage and processing
Steve Stroiney describes Facebook’s system for the movement of bulk data across its global system for storage and processing, balancing business needs with being a “good citizen,” at Data @Scale.
Data @Scale 2017
Architectures for the new era of cloud specialization
Increasing computational needs are forcing us to change how we think about large-scale systems, with new stacks and new interfaces. Doug Burger describes the deployment of programmable hardware in the Microsoft cloud, at Data @Scale.
Data @Scale 2017
Spanner’s SQL evolution
Google is in the process of turning its globally distributed Spanner data management system into an SQL DBMS. At Data @Scale, Sergey Melnik details the evolution of Spanner and its technical aspects.
