Facebook, Instagram and WhatsApp experienced a global crash Monday afternoon, remaining out for nearly seven hours due to “networking issues” that took hours to resolve. Experts determined that those “networking issues” had effectively unplugged Facebook from the internet.
Downdetector.com, an outage tracking website, showed the outage began around 11:30 a.m. EST. Facebook finally returned from the outage around 6:00 p.m. EST. Downdetector later said it received more than 10.6 million reports from users worldwide.
Just before 4 p.m., Facebook Chief Technology Officer Mike Schroepfer had tweeted, “Sincere apologies to everyone impacted by outages of Facebook powered services right now. We are experiencing networking issues and teams are working as fast as possible to debug and restore as fast as possible.”
The Chief Technology Officer at American Military News explained that the Facebook outage did not appear to be caused by “malicious external behavior.”
“Today’s outage appears to be solely related to the accidental removal of its border gateway protocol (BGP) routes from the global routing infrastructure,” he continued. “BGP is a mechanism by which routers across the planet share information with each other about where IP addresses live on the internet. If those routes are withdrawn, nothing in the world knows where the IP addresses are, therefore, they are effectively ‘gone.'”
He added that he has personally witnessed “accidents like this one occur multiple times” but added he has “never seen one last this long, as this sort of problem is usually managed within minutes once the error is understood.”
Internet infrastructure and security company Cloudflare shared a matching assessment in an in-depth blog post, saying that Facebook’s withdrawn BGP meant that “Facebook and its sites had effectively disconnected themselves from the Internet.”
“[Facebook’s] DNS names stopped resolving, and their infrastructure IPs were unreachable. It was as if someone had ‘pulled the cables’ from their data centers all at once and disconnected them from the Internet,” Cloudflare explained.
Due to the outage eliminating Facebook engineers’ remote access to the company’s networks, a team of engineers was dispatched to the company headquarters where physical work could be conducted on the networking equipment.
However, Facebook employees were reportedly experiencing difficulty even gaining access to Facebook’s facilities due to the interconnected building entry systems being offline.
New York Times tech reporter Sheera Frenkel tweeted, “Was just on phone with someone who works for FB who described employees unable to enter buildings this morning to begin to evaluate extent of outage because their badges weren’t working to access doors,” Frenkel said.
Just after 5:00 p.m. EST, Facebook’s BGP activity was assessed to be returning and reconnected to the internet with its DNS functional again. However, users were not able to access the site until approximately 6:00 p.m. EST.
The outage comes one day after Frances Haugen, a former product manager for Facebook, revealed her identity after providing The Wall Street Journal with internal documents last month that she says exposed the company’s decision to choose “profit over safety.”
“Facebook, over and over again, chose to optimize for its own interests, like making more money,” Haugen said during an interview with 60 Minutes, which aired on Sunday.
Haugen accused Facebook of not doing enough to combat what she reportedly characterized as “hate, violence and misinformation.” The so-called “whistleblower” advocated for federal oversight and regulations that would force the social media giant to censor more content. The 60 Minutes special noted that Haugen said she “lost a friend to online conspiracy theories.”
