The email sent will contain a link to this article, the article title, and an article excerpt (if available). For security reasons, your IP address will also be included in the sent email.
Hey, it's HighScalability time:
- 1 trillion nodes : The Near Future; 1 trillion connections : Facebook Now; 1 billion celestial objects observed : Gaia mission
- Quotable Quotes:
- Van Jacobson : IP started as an overlay on the phone system; today the phone system is an overlay on IP.
- @MarkDurbin104 : Unit of Logic: a Fathom?
- @somic : virtual infra with API is a cloud as much as a bunch of shell scripts are infra as code
- @xaprb : I'm going to settle the argument about linear scalability once and for all. Pianos are linearly scalable. Fish are not. End of story.
- @gigastacey : Facebook's cold storage is 1 exabyte per room with 1.5MW per room power requirement with no redundant power #ocpsummit
- dgb75 : PHP, not my first choice but the right choice
- @iaboyeji : Scalability is a rich man's problem
- Joe Stump on Sprintly on the impact of reducing ORM overhead: On a primed cache, your @sprintly experience should be 100x faster now. On an unprimed cache a mere 10-15x faster.
- Not a lot of technological detail on Facebook's new Graph Search, but here's the broad story of how it came about. Facebook has a lot of structured data about people so search needed to take advantage of that. They started in 2011 deciding to build a unified search. A quick prototype proved a proof of concept. Next they built a substring parser that could generate and rank all the potential page titles matching a query. To answer queries, with privacy filters applied, they leveraged an already existing search engine within Facebook called Unicorn. What's missing is an index of all posts and comments shared on Facebook.
Don't miss all that the Internet has to say on Scalability, click below and become eventually consistent with all scalability knowledge...
Return to Article