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:
If you like this sort of Stuff then please consider offering your support on Patreon.
- $14 billion: one day of purchases on Alibaba; 47 megawatts: Microsoft's new data center space for its MegaCloud; 50%: do not speak English on Facebook; 70-80%: of all Intel servers shipped will be deployed in large scale datacenters by 2025; 1024 TB: of storage for 3D imagery currently in Google Earth; $7: WeChat average revenue per user; 1 trillion: new trees;
- Quotable Quotes:
- @PicardTips: Picard management tip: Know your audience. Display strength to Klingons, logic to Vulcans, and opportunity to Ferengi.
- Mark Burgess: Microservices cannot be a panacea. What we see clearly from cities is that they can be semantically valuable, but they can be economically expensive, scaling with superlinear cost.
- ethanpil: I'm crying. Remember when messaging was built on open platforms and standards like XMPP and IRC? The golden year(s?) when Google Talk worked with AIM and anyone could choose whatever client they preferred?
- @acmurthy: @raghurwi from @Microsoft talking about scaling Hadoop YARN to 100K+ clusters. Yes, 100,000
- @ryanbigg: Took a Rails view rendering time from ~300ms to 50ms. Rewrote it in Elixir: it’s now 6-7ms. #MyElixirStatus
- Dmitriy Samovskiy: In the past, our [Operations] primary purpose in life was to build and babysit production. Today operations teams focus on scale.
- @Agandrau: Sir Tim Berners-Lee thinks that if we can predict what the internet will look like in 20 years, than we are not creative enough. #www2016
- @EconBizFin: Apple and Tesla are today’s most talked-about companies, and the most vertically integrated
- Kevin Fishner: Nomad was able to schedule one million containers across 5,000 hosts in Google Cloud in under five minutes.
- David Rosenthal: The Web we have is a huge success disaster. Whatever replaces it will be at least as big a success disaster. Lets not have the causes of the disaster be things we knew about all along.
- Kurt Marko: The days of homogeneous server farms with racks and racks of largely identical systems are over.
- Jonathan Eisen: This is humbling, we know virtually nothing right now about the biology of most of the tree of life.
- @adrianco: Google has a global network IP model (more convenient), AWS regional (more resilient). Choices...
- @jason_kint: Stupid scary stats in this. Ad tech responsible for 70% of server calls and 50% of your mobile data plan.
- apy: I found myself agreeing with many of Pike’s statements but then not understanding how he wound up at Go.
- @TomBirtwhistle: The head of Apple Music claims YouTube accounts for 40% of music consumption yet only 4% of online industry revenue
- @0x604: Immutable Laws of Software: Anyone slower than you is over-engineering, anyone faster is introducing technical debt
- surrealvortex: I'm currently using flame graphs at work. If your application hasn't been profiled recently, you'll usually get lots of improvement for very little effort. Some 15 minutes of work improved CPU usage of my team's biggest fleet by ~40%. Considering we scaled up to 1500 c3.4xlarge hosts at peak in NA alone on that fleet, those 15 minutes kinda made my month :)
- @cleverdevil: Did you know that Virtual Machines spin up in the opposite direction in the southern hemisphere? Little known fact.
- ksec: Yes, and I think Intel is not certain to win, just much more likely. The Power9 is here is targeting 2H 2017 release. Which is actually up against Intel Skylake/Kabylake Xeon Purley Platform in similar timeframe.
- @jon_moore: Platforms make promises; constraints are the contracts that allow platforms to do their jobs. #oreillysacon
- @CBILIEN: Scaling data platforms:compute and storage have to be scaled independently #HS16Dublin
- A morning reverie. Chopped for programmers. Call it Crashed. You have three rounds with four competitors. Each round is an hour. The competitors must create a certain kind of program, say a game, or a productivity tool, anything really, using a basket of three selected technologies, say Google Cloud, wit.ai, and Twilio. Plus the programmer can choose to use any other technologies from the pantry that is the Internet. The program can take any form the programmer chooses. It could be a web app, iOS or Android app, an Alexa skill, a Slack bot, anything, it's up to the creativity of the programmer. The program is judged by an esteemed panel based on creativity, quality, and how well the basket technologies are highlighted. When a programmer loses a round they have been Crashed. The winner becomes the Crashed Champion. Sound fun?
- Jeff Dean when talking about deep learning at Google makes it clear a big part of their secret sauce is being able to train neural nets at scale using their bespoke distributed infrastructure. Now Google has released Tensor Flow with distributed computing support. It's not clear if this is the same infrastructure Google uses internally, but it seems to work: using the distributed trainer, we trained the Inception network to 78% accuracy in less than 65 hours using 100 GPUs. Also, the tensorflow playground is a cool way to visualize what's going on inside.
- Christopher Meiklejohn with an interesting history of the Remote Procedure Call. It started way back in 1974: RFC 674, “Procedure Call Protocol Documents, Version 2”. RFC 674 attempts to define a general way to share resources across all 70 nodes of the Internet.
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)...
Return to Article