Grew from 200m users in 2013 to 1.5 billion in 2018 so they needed more processing power as they add more features and users. In the process they were moving from SoftLayer (IBM, FreeBSD, Erlang R16) to Facebook's infrastructure (Open Compute, Linux, Erlang R21) after the 2014 acquisition. This required moving from large powerful dual socketed servers to tiny blades with a max of 32 gig of RAM. Facebook's approach is to pack a lot of servers into a tiny space. Had to move to Erlang R21 to get the networking performance and connection density on Linux that they had on FreeBSD. Now they have a combination of old and new machines in a single cluster and they went from just a few servers to 10,000 smaller Facebook servers. [1] or a Summary at [2] in Useful Stuff.
[1] https://www.infoq.com/presentations/erland-scale-10000-nodes...
[2] http://highscalability.com/blog/2019/10/4/stuff-the-internet...