Hey, it's HighScalability time:

Google's new hyper efficient, hyper secure datacenters. (keynote, large, m, o, r e)

• 2 billion: containers started every week at Google; 86%: Apple's share of handset profits; 50: number of parallel processes in the brain; $12 million: cost for every additional second it takes customers to pay at a Walmart store; 800 terabytes: rendering for the movie Interstellar
• Quotable Quotes:
  • @IFTTTRecipe: http://Highscalability.com  to email @ http://ift.tt/1omSSgs Send new highscalability.com articles to my mailbox
  • @chadfowler: I've decided to break up tomorrow's monolithic talk about microservices into a series of microtalks #gotober
  • Emily Balcetis: Attention can “be thought of as what you allow your eyes to look at.”
  • Adam Alter: researchers have shown that our names take root deep within our mental worlds, drawing us magnetically toward the concepts they embody
  • @mjpt777: Monitoring needs to reflect an issue within 10 seconds of it happening. Poll at 1 second granularity. - @adrianco #gotober
  • @adyranov: "Trust only benchmarks you've made yourself. All others are benchmarketing" #highload2014
  • @adrianco: #GOTOber @mjpt777 Aeron performance on a laptop - 20 million 40byte messages/sec. 90%ile latency of 7us. 100% 37us.
  • @mjpt777: Have your infrastructure optimised for speed of delivery rather than cost, stuff then gets done so fast you reduce cost. @adrianco #gotober
  • Seth Newburg: This is a first in mobile! This is a device running over an internal network, rather than just everything being connected to a CPU
  • @swardley: OpenStack vs AWS - IMHO OpenStack should have dominated but pisspoor strategic play makes it unlikely for 10-15yrs.
  • Rudiger Moller: There is another strong value in going off heap (even when using advanced collectors like Zing's): Datastructures expressed in Java frequently have a redundancy of 80-90%.
  • @zooko: Novice engineers have not yet grokked this: the number of modes or options in your system is the *exponent* in how hard it is to maintain.


• OK Google...give me more cool functionality and lower prices. And they did. Google Cloud Platform Live: Introducing Container Engine, Cloud Networking and much more. This may take a while to process and put in some context. What Google is continuing to do is consumerize their internal services. The biggest example of this is opening up their container scheduling, management, and auto scaler services, while making it Docker compatible. If you want to run code as close as possible to your users you can now direct peer to any of Google's over 70 points of presence in 33 countries around the world. That's impressive. AWS has 14 and Azure has 11. Firebase is still behind Parse in features, but with Google's support look for it to blossom. The distributed debugger is truly impressive work. Game changing really. There's also a new improved Pub/Sub system. Slowly but surely the worm turns. 


• A great list. I'd like to see what a similar list for the message dispatch and handlers would look like. Martin Thompson design principles for the Aeron messaging system: garbage free in steady state running; smart batching in the message path; wait-free algos in the message path; non-blocking IO in the message path; no exceptional cases in message path; apply the single writer principle; prefer unshared state; avoid unnecessary data copies. 


• Nicely done André Staltz. The introduction to Reactive Programming you've been missing. If insight meditation has not been enough to guide your conversion from the object obsessed to the functionally enlightened then this article might be just what you are looking for. Or not.


• This is cool, using Cassandra as an embedded database. Russian Facebook Ok.ru Utilizing Cassandra for 1 Million Operations per Second, Over 80TB in Largest Cluster: The way we use Casssandra is somewhat unusual – we don’t use thrift or netty based native protocol to communicate with Cassandra nodes remotely. Instead, we co-locate Cassandra nodes in the same JVM with business service logic, exposing not generic data manipulation, but business level interface remotely. This way we avoid extra network roundtrips within a single business transaction and use internal calls to Cassandra classes to get information faster. Also this helps us to do many little hacks on its internals, making huge gains on efficiency and ease of distributed servers development.

Don't miss all that the Internet has to say on Scalability, click below and become eventually consistent with all scalability knowledge (which means this post has many more items to read so please keep on reading)...