According to a network professional, the outage appears to be due to a border gateway protocol routing leak.

Roland Dobbins, principal engineer at application and network performance management products provider NETSCOUT, said: “At approximately 12:52PM EST on 13 March, it appears that an accidental BGP routing leak from a European ISP to a major transit ISP, which was then propagated onwards to some peers and/or downstreams of the transit ISP in question, resulted in perceptible disruption of access to some well-known Internet properties for a short interval."

BGP errors have been responsible for outages in the recent past, with Australia's biggest telco Telstra taking down part of the Internet in Australia on 15 November 2018 due to a stuff-up with the routes it advertised through the border gateway protocol.

The same month, BGP routing appeared to have been used to hijack Google's Cloud. Later the problem was identified as having been caused by a small African ISP that announced itself as a few hundred Google networks. The error was admitted by the ISP later, saying: "We have investigated the advertisement of @Google prefixes through one of our upstream partners. This was an error during a planned network upgrade due to a misconfiguration on our BGP filters. The error was corrected within 74mins & processes put in place to avoid reoccurrence."

The website Downdetector shows that the site is experiencing issues across parts of the US, South America, and Western Europe.

Downdetector indicates that outages have started at about 4am AEDT.

The outage map at 8am AEDT. Courtesy Downdetector

As usual, users have taken to Twitter to vent and offer their often humorous, and cutting takes on the woes of the biggest social media site.

There was no information on the Facebook news page at 8am AEDT.

*Facebook is down*

what should i do with my life now?

#FacebookDown pic.twitter.com/jlqKLdqXdd

— ariaaa (@Airaamdn) March 13, 2019

We're focused on working to resolve the issue as soon as possible, but can confirm that the issue is not related to a DDoS attack.

— Facebook (@facebook) March 13, 2019

But, somewhat ironically, Facebook posted a couple of tweets about its woes. The second, posted at about 6am AEDT, said:

"We're focused on working to resolve the issue as soon as possible, but can confirm that the issue is not related to a DDoS attack."

All the 40-year-olds who can't see their minion memes anymore #FacebookDown pic.twitter.com/WsHCGLI8HA

— Silver Nut (@silvernutty) March 13, 2019

Time to fire up this bad boy.
.....
.....
DAMNIT! #facebookdown pic.twitter.com/as0HYWV4QC

— Erick [DJ NoirTech] (@NoirTech) March 13, 2019

Dobbins added: "While not malicious in nature, such events can prove disruptive on a widespread basis. It is very important that all network operators implement BGP peering best current practices, including prefix-lists, max-prefixes, ‘peer-locking’ via AS-PATH filters, RPKI Origin Validation (RFC6811), and other techniques incorporated into the industry Mutually Agreed Norms for Routing Security."