Welcome!

Agile Computing Authors: Mehdi Daoudi, Liz McMillan, Pat Romanski, Elizabeth White, Zakia Bouachraoui

Related Topics: Agile Computing

Agile Computing: Article

Behind the Scenes at Facebook: Scaling Up FBChat Using Erlang

The secret for going from zero to seventy million users overnight is to avoid doing it all in one fell swoop

One of the things I like most about working at Facebook is the ability to launch products that are (almost) immediately used by millions of people. Unlike a three-guys-in-a-garage startup, we don't have the luxury of scaling out infrastructure to keep pace with user growth; when your feature's userbase will go from 0 to 70 million practically overnight, scalability has to be baked in from the start. The project I'm currently working on, Facebook Chat, offered a nice set of software engineering challenges.

Real-time presence notification

The most resource-intensive operation performed in a chat system is not sending messages. It is rather keeping each online user aware of the online-idle-offline states of their friends, so that conversations can begin.

The naive implementation of sending a notification to all friends whenever a user comes online or goes offline has a worst case cost of O(average friendlist size * peak users * churn rate) messages/second, where churn rate is the frequency with which users come online and go offline, in events/second. This is wildly inefficient to the point of being untenable, given that the average number of friends per user is measured in the hundreds, and the number of concurrent users during peak site usage is on the order of several millions.

Surfacing connected users' idleness greatly enhances the chat user experience but further compounds the problem of keeping presence information up-to-date. Each Facebook Chat user now needs to be notified whenever one of his/her friends
(a) takes an action such as sending a chat message or loads a Facebook page (if tracking idleness via a last-active timestamp) or
(b) transitions between idleness states (if representing idleness as a state machine with states like "idle-for-1-minute", "idle-for-2-minutes", "idle-for-5-minutes", "idle-for-10-minutes", etc.).
Note that approach (a) changes the sending a chat message / loading a Facebook page from a one-to-one communication into a multicast to all online friends, while approach (b) ensures that users who are neither chatting nor browsing Facebook are nonetheless generating server load.

Real-time messaging

Another challenge is ensuring the timely delivery of the messages themselves. The method we chose to get text from one user to another involves loading an iframe on each Facebook page, and having that iframe's Javascript make an HTTP GET request over a persistent connection that doesn't return until the server has data for the client. The request gets reestablished if it's interrupted or times out. This isn't by any means a new technique: it's a variation of Comet, specifically XHR long polling, and/or BOSH.

Having a large-number of long-running concurrent requests makes the Apache part of the standard LAMP stack a dubious implementation choice. Even without accounting for the sizeable overhead of spawning an OS process that, on average, twiddles its thumbs for a minute before reporting that no one has sent the user a message, the waiting time could be spent servicing 60-some requests for regular Facebook pages. The result of running out of Apache processes over the entire Facebook web tier is not pretty, nor is the dynamic configuration of the Apache process limits enjoyable.

Distribution, Isolation, and Failover

Fault tolerance is a desirable characteristic of any big system: if an error happens, the system should try its best to recover without human intervention before giving up and informing the user. The results of inevitable programming bugs, hardware failures, et al., should be hidden from the user as much as possible and isolated from the rest of the system.

The way this is typically accomplished in a web application is by separating the model and the view: data is persisted in a database (perhaps with a separate in-memory cache), with each short-lived request retrieving only the parts relevant to that request. Because the data is persisted, a failed read request can be re-attempted. Cache misses and database failure can be detected by the non-database layers and either reported to the user or worked around using replication.

While this architecture works pretty well in general, it isn't as successful in a chat application due to the high volume of long-lived requests, the non-relational nature of the data involved, and the statefulness of each request.

For Facebook Chat, we rolled our own subsystem for logging chat messages (in C++) as well as an epoll-driven web server (in Erlang) that holds online users' conversations in-memory and serves the long-polled HTTP requests. Both subsystems are clustered and partitioned for reliability and efficient failover. Why Erlang? In short, because the problem domain fits Erlang like a glove. Erlang is a functional concurrency-oriented language with extremely low-weight user-space "processes", share-nothing message-passing semantics, built-in distribution, and a "crash and recover" philosophy proven by two decades of deployment on large soft-realtime production systems.

Glueing with Thrift

Despite those advantages, using Erlang for a component of Facebook Chat had a downside: that component needed to communicate with the other parts of the system. Glueing together PHP, Javascript, Erlang, and C++ is not a trivial matter. Fortunately, we have Thrift. Thrift translates a service description into the RPC glue code necessary for making cross-language calls (marshalling arguments and responses over the wire) and has templates for servers and clients. Since going open source a year ago (we had the gall to release it on April Fool's Day, 2007), the Thrift project has steadily grown and improved (with multiple iterations on the Erlang binding). Having Thrift available freed us to split up the problem of building a chat system and use the best available tool to approach each sub-problem.

Ramping up

The secret for going from zero to seventy million users overnight is to avoid doing it all in one fell swoop. We chose to simulate the impact of many real users hitting many machines by means of a "dark launch" period in which Facebook pages would make connections to the chat servers, query for presence information and simulate message sends without a single UI element drawn on the page. With the "dark launch" bugs fixed, we hope that you enjoy Facebook Chat now that the UI lights have been turned on.

 

More Stories By Eugene Letuchy

Eugene Letuchy is a software engineer at Facebook.

Comments (0)

Share your thoughts on this story.

Add your comment
You must be signed in to add a comment. Sign-in | Register

In accordance with our Comment Policy, we encourage comments that are on topic, relevant and to-the-point. We will remove comments that include profanity, personal attacks, racial slurs, threats of violence, or other inappropriate material that violates our Terms and Conditions, and will block users who make repeated violations. We ask all readers to expect diversity of opinion and to treat one another with dignity and respect.


IoT & Smart Cities Stories
While the focus and objectives of IoT initiatives are many and diverse, they all share a few common attributes, and one of those is the network. Commonly, that network includes the Internet, over which there isn't any real control for performance and availability. Or is there? The current state of the art for Big Data analytics, as applied to network telemetry, offers new opportunities for improving and assuring operational integrity. In his session at @ThingsExpo, Jim Frey, Vice President of S...
In his keynote at 18th Cloud Expo, Andrew Keys, Co-Founder of ConsenSys Enterprise, provided an overview of the evolution of the Internet and the Database and the future of their combination – the Blockchain. Andrew Keys is Co-Founder of ConsenSys Enterprise. He comes to ConsenSys Enterprise with capital markets, technology and entrepreneurial experience. Previously, he worked for UBS investment bank in equities analysis. Later, he was responsible for the creation and distribution of life settl...
@CloudEXPO and @ExpoDX, two of the most influential technology events in the world, have hosted hundreds of sponsors and exhibitors since our launch 10 years ago. @CloudEXPO and @ExpoDX New York and Silicon Valley provide a full year of face-to-face marketing opportunities for your company. Each sponsorship and exhibit package comes with pre and post-show marketing programs. By sponsoring and exhibiting in New York and Silicon Valley, you reach a full complement of decision makers and buyers in ...
The Internet of Things is clearly many things: data collection and analytics, wearables, Smart Grids and Smart Cities, the Industrial Internet, and more. Cool platforms like Arduino, Raspberry Pi, Intel's Galileo and Edison, and a diverse world of sensors are making the IoT a great toy box for developers in all these areas. In this Power Panel at @ThingsExpo, moderated by Conference Chair Roger Strukhoff, panelists discussed what things are the most important, which will have the most profound e...
Two weeks ago (November 3-5), I attended the Cloud Expo Silicon Valley as a speaker, where I presented on the security and privacy due diligence requirements for cloud solutions. Cloud security is a topical issue for every CIO, CISO, and technology buyer. Decision-makers are always looking for insights on how to mitigate the security risks of implementing and using cloud solutions. Based on the presentation topics covered at the conference, as well as the general discussions heard between sessio...
The Jevons Paradox suggests that when technological advances increase efficiency of a resource, it results in an overall increase in consumption. Writing on the increased use of coal as a result of technological improvements, 19th-century economist William Stanley Jevons found that these improvements led to the development of new ways to utilize coal. In his session at 19th Cloud Expo, Mark Thiele, Chief Strategy Officer for Apcera, compared the Jevons Paradox to modern-day enterprise IT, examin...
Rodrigo Coutinho is part of OutSystems' founders' team and currently the Head of Product Design. He provides a cross-functional role where he supports Product Management in defining the positioning and direction of the Agile Platform, while at the same time promoting model-based development and new techniques to deliver applications in the cloud.
There are many examples of disruption in consumer space – Uber disrupting the cab industry, Airbnb disrupting the hospitality industry and so on; but have you wondered who is disrupting support and operations? AISERA helps make businesses and customers successful by offering consumer-like user experience for support and operations. We have built the world’s first AI-driven IT / HR / Cloud / Customer Support and Operations solution.
LogRocket helps product teams develop better experiences for users by recording videos of user sessions with logs and network data. It identifies UX problems and reveals the root cause of every bug. LogRocket presents impactful errors on a website, and how to reproduce it. With LogRocket, users can replay problems.
Data Theorem is a leading provider of modern application security. Its core mission is to analyze and secure any modern application anytime, anywhere. The Data Theorem Analyzer Engine continuously scans APIs and mobile applications in search of security flaws and data privacy gaps. Data Theorem products help organizations build safer applications that maximize data security and brand protection. The company has detected more than 300 million application eavesdropping incidents and currently secu...