Hey, it's HighScalability time:

LifeExplorer Cells in 3D

• Quotable Quotes:
  • The Master Switch: History shows a typical progression of information technologies: from somebody’s hobby to somebody’s industry; from jury-rigged contraption to slick production marvel; from a freely accessible channel to one strictly controlled by a single corporation or cartel—from open to closed system.
  • @adrianco: #qconlondon @russmiles on PaaS "As old as I am, a leaky abstraction would be awful..."
  • @Obdurodon: "Scaling is hard.  Let's make excuses."
  • @TomRoyce: @jeffjarvis the rot is deep... The New Jersey pols just used Tesla to shake down the car dealers.
  • @CompSciFact: "The cheapest, fastest and most reliable components of a computer system are those that aren't there." -- Gordon Bell
  • @glyph: “Eventually consistent” is just another way to say “not consistent right now”.
  • @nutshell: LinkedIn is shutting down access to their APIs for CRMs (unless you’re Salesforce or Microsoft). Support open APIs!
  • Tim Berners-Lee: I never expected all these cats.
  • @muratdemirbas: "Simple clear purpose&principles give rise to complex&intelligent behavior.
    Complex rules&regulations give rise to simple&stupid behavior."
  • @BonzoESC: “Duplication is far cheaper than the wrong abstraction.” @sandimetz @rbonales 
  • @BenedictEvans: Umeng: there are 700m active smartphones and tablets in China.


• Scale matters object lesson number infinity: HBO Go Crashes During True Detective Finale. Perhaps make HBO Go available without a cable package and maybe you'll have money to scale the service? Think peak. But wait, Dan Rayburn says bandwidth was not the problem, it's other parts of the system, which is why Internet TV will never be as reliable as broadcast TV. Still, I'd like to cut the cord.


• Turns out ecommerce over messaging works well...quite well. Retailers Are Striking Gold with Instagram: Fox and Fawn, items often sell out within minutes of the picture being posted on Instagram.


• Even Facebook's infrastructure struggles when a new feature becomes an unexpected hit. That's the situation described in an engaging story: Looking back on “Look Back” videos. Look Back's are one minute videos generated from a user's pics and posts. For the release they planned on 187 Gbps more bandwidth and 25 petabytes of disk. To get the rendering done they highly parallelized the pipeline. CDNs were alerted. Internal tests on employees found a few bugs. Less storage was actually needed because the video could be regenerated so a high replication factor wasn't needed. Go time! The videos were an unexpected hit with a 40% reshare instead of the projected 10% reshare. It seems people like themselves...a lot. Overnight 30 teams cooperated to move tens of thousands of machines over to rendering. Good story. Though I'm disappointed it didn't have its own Look Back video. Stories are people too.


• Why Google's services aren't really free. We all help train the beast. A Glimpse of Google, NASA & Peter Norvig + The Restaurant at the End of the Universe: Algorithms behave differently as they churn thru more data. For example in the figure, the Blue algorithm was better with a million training dataset. If one had stopped at that scale, one would think of optimizing that algorithm for better performance. But as the scale increased the purple algorithm started showing promise – in fact the blue one starts deteriorating at larger scale; In general, Google prefers algorithms that get better with data. Not all algorithms are like that, but Google likes to after the ones with this type of performance characteristic. 

Don't miss all that the Internet has to say on Scalability, click below and become eventually consistent with all scalability knowledge...