Hey, it's HighScalability time:

 

• 98%~ savings in green house gases using Gmail versus local servers; 2x: time spent on-line compared to 5 years ago; 125 million: most hours of video streamed by Netflix in one day; 707.5 trillion: value of trade in one region of Eve Online; $1 billion: YouTube's advertisement pay-out to the music industry; 1 billion: Step Functions predecessor state machines run per week in AWS retail; 15.6 million: jobs added over last 81 months;


• Quotable Quotes:
  • Gerry Sussman~ in the 80s and 90s, engineers built complex systems by combining simple and well-understood parts. The goal of SICP was to provide the abstraction language for reasoning about such systems...programming today is more like science. You grab this piece of library and you poke at it. You write programs that poke it and see what it does. And you say, ‘Can I tweak it to do the thing I want?
  • @themoah: Last year Black Friday weekend: 800 Windows servers with .NET. This year: 12 Linux servers with Scala/Akka. #HighScalability #Linux #Scala
  • @swardley: If you're panicking over can't find AWS skills / need to go public cloud - STOP! You missed the boat. Focus now on going serverless in 5yrs.
  • @jbeda: Nordstrom is running multitenant Kubernetes cluster with namespace per team. Using RBAC for security.
  • Tim Harford: What Brailsford says is, he is not interested in team harmony. What he wants is goal harmony. He wants everyone to be focused on the same goal. He doesn’t care if they like each other and indeed there are some pretty famous examples of people absolutely hating each other. 
  • @brianhatfield: SUB. MILLISECOND. PAUSE. TIME. ON. AN. 18. GIG. HEAP. (Trying out Go 1.8 beta 1!)
  • haberman: If you can make your system lock-free, it will have a bunch of nice properties: - deadlock-free - obstruction-free (one thread getting scheduled out in the middle of a critical section doesn't block the whole system) - OS-independent, so the same code can run in kernel space or user space, regardless of OS or lack thereof 
  • Neil Gunther: The world of performance is curved, just like the real world, even though we may not always be aware of it. What you see depends on where your window is positioned relative to the rest of the world. Often, the performance world looks flat to people who always tend to work with clocked (i.e., deterministic) systems, e.g., packet networks or deep-space networks.
  • @yoz: I liked Westworld, but if I wanted hours of watching tech debt and no automated QA destroy a virtual world, I’d go back to Linden Lab
  • @adrianco: I think we are seeing the usual evolution to utility services, and new higher order (open source) functionality emerges /cc @swardley
  • Neil Gunther: a buffer is just a queue and queues grow nonlinearly with increasing load. It's queueing that causes the throughput (X) and latency (R) profiles to be nonlinear.
  • Juho Snellman: I think [QUIC] encrypting the L4 headers is a step too far. If these protocols get deployed widely enough (a distinct possibility with standardization), the operational pain will be significant.
  • @Tobarja: "anyone who is doing microservices is spending about 25% of their engineering effort on their platform" @jedberg 
  • @cdixon: 2016 League of Legends finals: 43M viewers 2016 NBA finals: 30.8M viewers 
  • @mikeolson: 7 billion people on earth; 3 billion images shared on social media every day. @setlinger at #StrataHadoop
  • @swardley: When you think about AWS Lambda, AWS Step Functions et al then you need to view this through the lens of automating basic doctrine i.e. not just saying it and codifying in maps and related systems but embedding it everywhere. At scale and at the speed of competition that I expect us to reach then this is going to be essential.
  • Jakob Engblom: hardware accelerators for particular  common expensive tasks seems to be the right way to add performance at the smallest cost in silicon area and power consumption.
  • Joe Duffy: The future for our industry is a massively distributed one, however, where you want simple individual components composed into a larger fabric. In this world, individual nodes are less “precious”, and arguably the correctness of the overall orchestration will become far more important. I do think this points to a more Go-like approach, with a focus on the RPC mechanisms connecting disparate pieces
  • @cmeik: AWS Lambda is cool if you never had to worry about consistency, availability and basically all of the tradeoffs of distributed systems.
  • prions: As a Civil Engineer myself, I feel like people don't realize the amount of underlying stuff that goes into even basic infrastructure projects. There's layers of planning, design, permitting, regulations and bidding involved. It usually takes years to finally get to construction and even then there's a whole host of issues that arise that can delay even a simple project. 
  • Netflix: If you can cache everything in a very efficient way, you can often change the game. 
  • The Attention Merchants: One [school] board in Florida cut a deal to put the McDonald’s logo on its report cards (good grades qualified you for a free Happy Meal). In recent years, many have installed large screens in their hallways that pair school announcements with commercials. “Take your school to the digital age” is the motto of one screen provider: “everyone benefits.” What is perhaps most shocking about the introduction of advertising into public schools is just how uncontroversial and indeed logical it has seemed to those involved.


• Just how big is Netflix? The story of the tape is told in Another Day in the Life of a Netflix Engineer. Netflix runs way more than 100K EC2 instances and more than 80,000 CPU cores. They use both predictive and reactive autoscaling, aiming for not too much or too little, just the right amount. Of those 100K+ instances they will autoscale up and down 20% of that capacity everyday. More than 50Gbps ELB traffic per region. More than 25Ggps is telemetry data from devices sending back customer experience data. At peak Netflix is responsible over 37% of Internet traffic. The monthly billing file for Netflix is hundreds of megabytes with over 800 million lines of information. There's a hadoop cluster at Amazon whose only purpose is to load Netflix's bill. Netflix considers speed of innovation to be a strategic advantage. About 4K code changes are put into production per day. At peak over 125 million hours of video were streamed in a day. Support for 130 countries was added in one day. That last one is the kicker. Reading about Netflix over all these years you may have got the idea Netflix was over engineered, but going global in one day was what it was all about. Try that if you are racking and stacking. 


• Oh how I miss stories that began Once upon a time. The start of so many stories these days is The attack sequence begins with a simple phishing scheme. This particular cautionary tale is from Technical Analysis of Pegasus Spyware, a very, almost lovingly, detailed account of the total ownage of the "secure" iPhone. The exploit made use of three zero-day vulnerabilities: CVE-2016-4657: Memory Corruption in WebKit, CVE-2016-4655: Kernel Information Leak, CVE-2016-4656: Kernel Memory corruption leads to Jailbreak. Do not read if you would like to keep your Security Illusion cherry intact. 


• Composing RPC calls gets harder has the graph of calls and dependencies explodes. Here's how Twitter handles it. Simplify Service Dependencies with Nodes. Here's their library on GitHub. It's basically just a way to setup a dependency graph in code and have all the RPCs executed to the plan. It's interesting how parallel this is to setting up distributed services in the first place. They like it: We have saved thousands of lines of code, improved our test coverage and ended up with code that’s more readable and friendly for newcomers. Also, AWS Step Functions.

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)...