Power

Facebook goes down: What happened, and what happens next

Facebook called it "networking issues." The internet thought it was hilarious.

Facebook crack

Some saw bigger takeaways from the outage:

Image: Eynav Raphael/Protocol

Facebook more or less disappeared from the internet on Monday. It's not just that its website went down, it's that the company seemed for hours to have been deleted entirely. It was so bad that the domain facebook.com appeared to be for sale. (Jack Dorsey publicly inquired about the price.)

  • This was Facebook's initial public comment: "We're aware that some people are having trouble accessing our apps and products. We're working to get things back to normal as quickly as possible, and we apologize for any inconvenience."
  • Adam Mosseri took the whole thing in stride, saying "it does feel like a snow day."
  • Staying home was certainly the move: The outage got so bad that employees said they couldn't badge into Facebook offices or access their email. Which of course made things worse: Employees reportedly couldn't get into buildings to fix the problem, or communicate in order to do so. They turned instead to Discord, Zoom and other platforms to keep in touch. And users who couldn't get on Facebook flocked elsewhere; Twitter and Signal both reported huge spikes in usage on Monday.
  • "*Sincere* apologies to everyone impacted by outages of Facebook powered services right now," Mike Schroepfer, Facebook's CTO, tweeted — because there was no other way to communicate. "We are experiencing networking issues and teams are working as fast as possible to debug and restore as fast as possible."

The outage was the result of a fairly straightforward mistake. There were some initial rumors and conspiracy theories (coming a day after Frances Haugen outed herself as a whistleblower and a day before a Congressional hearing, how could there not be?) but the truth appears to be much more routine. It involves BGP, the tech that helps networks communicate, and Facebook did the rough equivalent of changing its number and unplugging the landline.

  • "Our engineering teams have learned that configuration changes on the backbone routers that coordinate network traffic between our data centers caused issues that interrupted this communication," Facebook's Santosh Janardhan wrote on the company's blog Monday night. "This disruption to network traffic had a cascading effect on the way our data centers communicate, bringing our services to a halt."
  • The problem was simple, but the fix was complicated. "The underlying cause of this outage also impacted many of the internal tools and systems we use in our day-to-day operations," Janardhan wrote, "complicating our attempts to quickly diagnose and resolve the problem."
  • Cloudflare published a detailed blog post about what happened, showing a quick burst of BGP updates just before the outage began. "With those withdrawals," Cloudflare's Tom Strickx and Celso Martinho wrote, "Facebook and its sites had effectively disconnected themselves from the Internet."

The internet, of course, absolutely loved the whole thing. The #deleteFacebook hashtag worked, declared seemingly everybody. There were MySpace jokes galore. Twitter weighed in. So did God.

Others, though, saw bigger takeaways from the outage:

  • "Facebook, WhatsApp, and Instagram all going down at the same time sure seems like an easily-understandable and publicly-popular example of why breaking up a certain monopoly into at least three pieces might not be a bad idea," Edward Snowden tweeted.
  • "Today is a moment where we get a glimpse of what a modern digital terrorist attack / nation state warfare would feel like -- and the case for focusing on decentralization gets stronger," Sam Lessin said.
  • Many people used the outage as a chance to appeal for a decentralized internet (and in some cases, try to sell people on their blockchain-based social app.) "Kudos to @facebook for giving us a very real demonstration of why the move to a decentralised Web 3 is necessary and, indeed, inevitable," Polkadot founder and Ethereum co-creator Gavin Wood tweeted.
  • "As far as structural outages go, this FB thing is relatively minor," said Nick Merrill, a cybersecurity researcher at UC Berkeley. "a few hundreds of millions of dollars lost at most. if a similar outage hit AWS, cloudflare, akamai, etc, no one's credit card would work. i expect the losses would be in the billions if not trillions."

Suddenly seeing an internet without Facebook was an eye-opening thing, both for the businesses that rely on the company to reach customers and share information, and for the people — particularly in the developing world — who rely on it to communicate with loved ones. "WhatsApp went dark today when I was in the middle of a conversation with a close colleague in South Africa," said Will Anderson, who works in international development and land restoration, "but I didn't notice it until I stopped receiving messages from my many groups. They usually buzz at all hours, so it's eerie to not hear updates from Indian entrepreneurs or local tree-growing organizations in Niger." It was also a reminder that the internet's infrastructure is still fragile and complex and always barely holding together.

By about 5 p.m. ET, Facebook started to recover. By the end of the work day on the West coast, things were back to normal.

  • At the end of it all, Mark Zuckerberg weighed in. "Facebook, Instagram, WhatsApp and Messenger are coming back online now," he posted on his newly functioning Facebook page. "Sorry for the disruption today -- I know how much you rely on our services to stay connected with the people you care about."

In the end, this was Facebook's second-worst outage ever. The top spot belongs to an outage in 2019, when a very similar incident left Facebook's services offline for more than 14 hours. (Another, even longer outage hit the company in 2008, but it was much smaller then.) At the time, Facebook said only that "a server configuration change" was to blame.

The lesson here? Don't put all your eggs in one basket. Because everything at Facebook runs on a single system, from its platforms to its status pages to its in-office security systems, breaking one thing broke everything. Because when the servers need to be reset, you don't want to rely on the servers to let you in the building. Expect Facebook to make changes, and others to make sure this doesn't happen to them next.

Fintech

The crypto crash's violence shocked Circle's CEO

Jeremy Allaire remains upbeat about stablecoins despite the UST wipeout, he told Protocol in an interview.

Allaire said what really caught him by surprise was “how fast the death spiral happened and how violent of a value destruction it was.”

Photo: Heidi Gutman/CNBC/NBCU Photo Bank/NBCUniversal via Getty Images

Circle CEO Jeremy Allaire said he saw the UST meltdown coming about six months ago, long before the stablecoin crash rocked the crypto world.

“This was a house of cards,” he told Protocol. “It was very clear that it was unsustainable and that there would be a very high risk of a death spiral.”

Keep Reading Show less
Benjamin Pimentel

Benjamin Pimentel ( @benpimentel) covers crypto and fintech from San Francisco. He has reported on many of the biggest tech stories over the past 20 years for the San Francisco Chronicle, Dow Jones MarketWatch and Business Insider, from the dot-com crash, the rise of cloud computing, social networking and AI to the impact of the Great Recession and the COVID crisis on Silicon Valley and beyond. He can be reached at bpimentel@protocol.com or via Google Voice at (925) 307-9342.

Sponsored Content

Foursquare data story: leveraging location data for site selection

We take a closer look at points of interest and foot traffic patterns to demonstrate how location data can be leveraged to inform better site selecti­on strategies.

Imagine: You’re the leader of a real estate team at a restaurant brand looking to open a new location in Manhattan. You have two options you’re evaluating: one site in SoHo, and another site in the Flatiron neighborhood. Which do you choose?

Keep Reading Show less

A DTC baby formula startup is caught in the center of a supply chain crisis

After weeks of “unprecedented growth,” Bobbie co-founder Laura Modi made a hard decision: to not accept any more new customers.

Parents unable to track down formula in stores have been turning to Facebook groups, homemade formula recipes and Bobbie, a 4-year-old subscription baby formula company.

Photo: JIM WATSON/AFP via Getty Images

The ongoing baby formula shortage has taken a toll on parents throughout the U.S. Laura Modi, co-founder of formula startup Bobbie, said she’s been “wearing the hat of a mom way more than that of a CEO” in recent weeks.

“It's scary to be a parent right now, with the uncertainty of knowing you can’t find your formula,” Modi told Protocol.

Keep Reading Show less
Nat Rubio-Licht

Nat Rubio-Licht is a Los Angeles-based news writer at Protocol. They graduated from Syracuse University with a degree in newspaper and online journalism in May 2020. Prior to joining the team, they worked at the Los Angeles Business Journal as a technology and aerospace reporter.

Enterprise

Celonis vows to stay independent despite offers from SAP, ServiceNow

Celonis is convinced standalone mining vendors can survive. But industry consolidation paints a different picture, and enterprise software giants are circling.

Celonis CEO Alex Rinke turned down offers from ServiceNow and SAP, according to sources.

Photo: Celonis

For the past decade, any software vendor that touted new levels of automation and data-driven insights appeared to have seemingly unrestricted access to capital. Now, as valuations drop and fundraising becomes more difficult, founders and company leaders are facing a difficult decision: look to be acquired or try to go it alone.

At Celonis — which, at an $11 billion valuation, is one of the buzzier software upstarts — that question appears to have already been decided. Enterprise software giants ServiceNow and SAP made offers in the past year to buy the process-mining firm, according to sources familiar with the deliberations, which were turned down because the Celonis leadership team wanted to remain independent.

Keep Reading Show less
Joe Williams

Joe Williams is a writer-at-large at Protocol. He previously covered enterprise software for Protocol, Bloomberg and Business Insider. Joe can be reached at JoeWilliams@Protocol.com. To share information confidentially, he can also be contacted on a non-work device via Signal (+1-309-265-6120) or JPW53189@protonmail.com.

Enterprise

SaaS valuations cratered in early 2022. But these startups thrived.

VCs were still bullish on supply chain, recruiting and data startups despite the economic environment that chopped the valuations of newly public companies and late-stage enterprise startups.

While private equity has been investing in enterprise tech for decades, the confluence of several trends in the sector is making it more competitive than ever before.
Image: Getty Images; Protocol

Despite a volatile tech stock market so far this year that has included delayed IPOs, lowered valuations and declining investor sentiment, a few enterprise tech categories managed to keep getting funding. Data platforms, supply chain management tech, workplace software and cybersecurity startups all dominated the funding cycle over the past quarter.

When it comes to enterprise SaaS, the number of mega-deals — VC funding rounds over $100 million — spiked last year, according to data from Pitchbook. Partially driven by the onset of a pandemic that accelerated the need for everything from contact centers to supply chains to move into the cloud, the number of large VC deals tripled between 2020 and 2021. That growth has extended into this year, where the number of mega-deals has already outpaced all of 2020.

Keep Reading Show less
Aisha Counts

Aisha Counts (@aishacounts) is a reporter at Protocol covering enterprise software. Formerly, she was a management consultant for EY. She's based in Los Angeles and can be reached at acounts@protocol.com.

Latest Stories
Bulletins