"distributed systems" entries

Why the data center needs an operating system

It’s time for applications — not servers — to rule the data center.

1214-missing-operating-system-620

Developers today are building a new class of applications. These applications no longer fit on a single server, but instead run across a fleet of servers in a data center. Examples include analytics frameworks like Apache Hadoop and Apache Spark, message brokers like Apache Kafka, key-value stores like Apache Cassandra, as well as customer-facing applications such as those run by Twitter and Netflix.

These new applications are more than applications, they are distributed systems. Just as it became commonplace for developers to build multithreaded applications for single machines, it’s now becoming commonplace for developers to build distributed systems for data centers.

But it’s difficult for developers to build distributed systems, and it’s difficult for operators to run distributed systems. Why? Because we expose the wrong level of abstraction to both developers and operators: machines. Read more…

Comments: 13
Four short links: 28 November 2014

Four short links: 28 November 2014

Material Design Inspiration, Event Processing, Launch Infrastructure, Remote Work

  1. Material Up — material design inspiration. MD is a physics engine for UI.
  2. Flafka (Cloudera) — Flume plus Kafka, offers sub-second-latency event processing without the need for dedicated infrastructure. (via Abishek Tiwari)
  3. terraform.io — open source package providing a common configuration to launch infrastructure, from physical and virtual servers to email and DNS providers.
  4. Remote Work: An Engineering Leader’s PerspectiveEven proponents of remote work seem to think that you should either have a distributed team from the get go, or stick to a traditional on-site team. Our experience shows that this is incorrect…
Comment
Four short links: 26 November 2014

Four short links: 26 November 2014

Metastable Failures, Static Python Analysis, Material Desktop, and AWS Scale Numbers

  1. Metastable Failure State (Facebook) — very nice story about working together to discover the cause of one of those persistently weird problems.
  2. Bandit — static security analysis of Python code.
  3. Quantum OS — Linux desktop based on Google’s Material Design. UI guidelines fascinate me: users love consistency, designers and brands hate that everything works the same.
  4. Inside AWSEvery day, AWS installs enough server infrastructure to host the entire Amazon e-tailing business from back in 2004, when Amazon the retailer was one-tenth its current size at $7 billion in annual revenue. “What has changed in the last year,” Hamilton asked rhetorically, and then quipped: “We have done it 365 more times.” That is another way of saying that in the past year AWS has added enough capacity to support a $2.55 trillion online retailing operation, should one ever be allowed to exist.
Comment
Four short links: 22 October 2014

Four short links: 22 October 2014

Docker Patterns, Better Research, Streaming Framework, and Data Science Textbook

  1. Eight Docker Development Patterns (Vidar Hokstad) — patterns for creating repeatable builds that result in as-static-as-possible server environments.
  2. How to Make More Published Research True (PLOSmedicine) — overview of efforts, and research on those efforts, to raise the proportion of published research which is true.
  3. Gearpump — Intel’s “actor-driven streaming framework”, initial benchmarks shows that we can process 2 million messages/second (100 bytes per message) with latency around 30ms on a cluster of 4 nodes.
  4. Foundations of Data Science (PDF) — These notes are a first draft of a book being written by Hopcroft and Kannan [of Microsoft Research] and in many places are incomplete. However, the notes are in good enough shape to prepare lectures for a modern theoretical course in computer science.
Comment
Four short links: 14 October 2014

Four short links: 14 October 2014

Science Startups, UAV Platform, Distributed vs Scalable, and Multiplayer Spreadsheet

  1. VCs Return to Backing Science Startups (NY Times) — industry and energy investment doubled this year, biotech up 26% in first half, but a lot of the investments are comically small and the risk remains acutely high.
  2. dronecode — Linux Foundation common, shared open source platform for Unmanned Aerial Vehicles (UAVs). The platform has been adopted by many of the organizations on the forefront of drone technology, including 3DRobotics, DroneDeploy, HobbyKing, Horizon Ag, PrecisionHawk, Agribotics, and Walkera, among other.
  3. Distributed is Not Necessarily Moe Scalable (Murat Demiras) — well-reasoned and summed up in this tweet by @jamesiry: Some people when faced with a problem think, I know, I’ll use distributed computing. Now they have N^2 problems..
  4. ethersheet — open source collaborative/multiplayer spreadsheet.
Comment
Four short links: 13 October 2014

Four short links: 13 October 2014

Angular Style, Consensus Filters, BASE Banks, and Browser Performance

  1. Angular JS Style Guide — I love style guides, to the point of having posted (I think) three for Angular. Reading other people’s style guides is like listening to them make-up after arguments: you learn what’s important to them, and what they regret.
  2. Consensus Filters — filtering out misreads and other errors to allow all agents, or robots, in the network to arrive at the same value asymptotically by only communicating with their neighbours.
  3. Why Banks are BASE not ACIDConsistency it turns out is not the Holy Grail. What trumps consistency is: Auditing, Risk Management, Availability.
  4. perfmap — front-end performance heatmap.
Comment
Four short links: 9 October 2014

Four short links: 9 October 2014

API Docs, Top Trends, Byzantine Fault Tolerance, and Devops in Practice

  1. dashoffline access to API documentation. Useful for those long-haul flights without wifi …
  2. Gartner’s Top Trends for 2015 — ubicomp, IoT, 3d printing, pervasive analytics, context, smart machines, cloud computing, software-defined everything, web-scale IT, and security. Still not the year of the Linux desktop.
  3. Byzantine Fault Tolerance — Wikipedia’s readable introduction to the basic challenge in distributed systems.
  4. Move Fast, Break Nothing (Zach Holman) — Gartner talks about “web-scale IT”, but I think the processes and tools for putting code into product (devops) are far more transformative than the technology that scales the product delivery.
Comment
Four short links: 7 October 2014

Four short links: 7 October 2014

Chinese Makers, Code Projects, Distributed Data Structures, and Networked Games

  1. On the Maker Movement in China (Clay Shirky) — Hardware hacking hasn’t become a hot new thing in China because it never stopped being a regular old thing.
  2. A History of Apache Storm and Lessons Learned (Nathan Marz) — his lessons on building, promoting, releasing, maintaining, governance … all worth reading.
  3. Tango: Distributed Data Structures Over a Shared Logprovides developers with the abstraction of a replicated, in-memory data structure (such as a map or a tree) backed by a shared log. (via paper summary)
  4. Making Fast-Paced Multiplayer Networked Games is Hard (Gamasutra) — This may all sound like smoke and mirrors because that is exactly what it is – we are just maintaining the illusion the game is playing out in wall clock time even though updates are arriving from the past.
Comment
Four short links: 2 October 2014

Four short links: 2 October 2014

I Heart Logs, CS50 Eating The World, Meeting Transcripts, Binary Analysis

  1. I Heart Logs — I linked to Jay Kreps’s awesome blog post twice, and now he’s expanded it into a slim O’Reilly volume which I shall press into the hands of every engineer I meet. Have you heard the Good News?
  2. CS50 Record Numbers — nearly 12% of Harvard now takes Intro to CS. (via Greg Linden)
  3. SayIt — open source from MySociety, a whole new way to organise, publish,
    and share your transcripts
    . They really want to make a better experience for sharing and organising transcripts of meetings.
  4. BAP — Binary Analysis Platform from CMU. Translates binary into assembly and then into an intermediate language which explicitly represents the side effects of assembly instructions, such as flag computations.
Comment
Four short links: 23 September 2014

Four short links: 23 September 2014

Alibubble, Reactive Manifesto, Lovely Logs, and Learning Design

  1. Thoughts on the Alibaba BubbleAlibaba is an offering that encourages the kind of negative Wall Street behavior none of us really want to see happen again. (via Tim O’Reilly)
  2. Reactive ManifestoWe believe that a coherent approach to systems architecture is needed, and we believe that all necessary aspects are already recognised individually: we want systems that are Responsive, Resilient, Elastic and Message Driven. We call these Reactive Systems.
  3. The Log: What Every Software Engineer Should Know About Real-time Data’s Unifying Abstraction (LinkedIn) — You can reduce the problem of making multiple machines all do the same thing to the problem of implementing a distributed consistent log to feed these processes input. The purpose of the log here is to squeeze all the non-determinism out of the input stream to ensure that each replica processing this input stays in sync.
  4. Method of Actiona collection of tools, games and articles to help you learn design.
Comment