BGP protocol shenanigans ruled out as Facebook admits outage was caused by its own engineers
Facebook has claimed that a server configuration change was the cause of a 14-hour outage of Facebook, Instagram and WhatsApp on Wednesday. Facebook's explanation refutes the explanation yesterday from network management software company NetScout that BGP routing issues were the cause of the downtime.
"As a result of a server configuration change, many people had trouble accessing our apps and services. We've now resolved the issues and our systems are recovering," the company stated yesterday.
However, the company did not go into further detail about how the server configuration issue caused services to go down across the world - but affecting the US and UK in particular.
Yesterday, though, before Facebook provided its explanation, rumours circulated about the cause of the outage, including a distributed denial of service (DDoS) attack, a rumour the company was quick to shoot down. Such an attack causing such a widespread outage would have shown up on a number of security and networking companies' radar.
More plausibly, NetScout had also conjectured that some form of border gateway protocol (BGP) routing issue was the cause. There have been a number of BGP routing problems in recent years, including claims of deliberate BGP hijacking, routing internet traffic via Russia and China, with China Telecom purportedly behind the latter incident, according to one piece of research.
Network monitoring company ThousandEyes, meanwhile, told Computing's sister site The Inquirer that it had not seen any BGP-related anomalies and more accurately conjectured that the cause "appears to be internal rather than a network or internet delivery issue".
The AI and Machine Learning Awards are coming! In July this year, Computing will be recognising the best work in AI and machine learning across the UK. Do you have research or a project that you think deserves wider recognition? Enter the awards today - entry is free.
