advertise
Friday
May032013

Stuff The Internet Says On Scalability For May 3, 2013

Hey, it's HighScalability time:

 

  • 1,966,080 cores: Time Warp synchronization protocol using up to 7.8M MPI tasks on 1,966,080 cores of the {Sequoia} Blue Gene/Q supercomputer system. 33 trillion events processed in 65 seconds yielding a peak event-rate in excess of 504 billion events/second using 120 racks of Sequoia.
  • Quotable Quotes:
    • Thad Starner: the longer accessing a device exceeds 2s, the more its actually usage would decrease exponentially. Thus, he made a claim that wrist watch interface always sitting on one's wrist ready to use should be more successful than mobile phones which have to pulled out of the pocket. 
    • @joedevon: We came for scalability but we stayed for agility #NoSQL
    • @jahmailay: "Our user base is exploding. I really wish we spent more time on scalability instead of features customers don't use." - Everybody, always.
    • @bsletten: I don’t think it is a coincidence that the words eval() and evil are so close.
    • @RCSecure: Maybe Gov should stop deploying crappy #CyberSecurity instead of Surveiling Citizens
    • @davidpav: "This is what Netflix does - after each deployment creates AMI for faster scaling up"
    • @franzgranlund: Rewrote my little batch-processing application using #akka . 20% performance increase just like that - and now it is easier to scale.
    • @marshray: Ouch, that's kind of dismal. Perhaps we need a new term: "eventual scalability"
    • @adrianco: RT @rbranson: @cscotta load average is the worst thing ever. Slowly trying to evangelize it's demise as a reasonable metric. < +1 every 15 m

  • MIT Tech Review picks 10 breakthrough technologies: Smart Watches (really?), Memory implants (deciphering the code by which the brain forms long-term memories), Additive manufacturing (3-D printing), Supergrids (finally says Edison, DC powergrids), Temporary social media (sigh), Prenatal DNA sequencing (great for full lifecycle ad targeting), Baxter (compliant robots), Deep Learning (the singularity is near), Ultra-Efficient Solar Power (now we are talking). Prediction: We'll laugh at all this filter control talk once we have all of Google's datacenters and knowledge graph software implanted in our heads.

  • IBM on making movies using atoms as pixels. Characterization was a little thin but the plot was magnetic.

  • Lesson from Airbnb: Give yourself permission to experiment with non-scalable changes. Building better is better than building bigger.

  • Here's a short review by me on CyberStorm by Matthew Mather. Matthew is also the author of the most excellent Atopia Chronicles, a sprawling exploration of "artificial intelligence, distributed computing, nanotechnology, and the full range of humanity." CyberStorm is a chilling blow by blow of what could happen in a real cyber attack. As a programmer it's the implied idea of a kind of Crises OS built on a mesh of smartphones that I found most fascinating. Not much seems to be done in this area and even the how-to of writing such applications is rarely discussed. Could be interesting.

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

Click to read more ...

Wednesday
May012013

Myth: Eric Brewer on Why Banks are BASE Not ACID - Availability Is Revenue 

In NoSQL: Past, Present, Future Eric Brewer has a particularly fine section on explaining the often hard to understand ideas of BASE (Basically Available, Soft State, Eventually Consistent), ACID (Atomicity, Consistency, Isolation, Durability), CAP (Consistency Availability, Partition Tolerance), in terms of a pernicious long standing myth about the sanctity of consistency in banking.

Myth: Money is important, so banks must use transactions to keep money safe and consistent, right?

Reality: Banking transactions are inconsistent, particularly for ATMs. ATMs are designed to have a normal case behaviour and a partition mode behaviour. In partition mode Availability is chosen over Consistency.

Why? 1) Availability correlates with revenue and consistency generally does not. 2) Historically there was never an idea of perfect communication so everything was partitioned...

Click to read more ...

Tuesday
Apr302013

Sponsored Post: Spotify, Evernote, Surge, Rackspace, Simple, Amazon, Booking, aiCache, Aerospike, Percona, ScaleOut, New Relic, LogicMonitor, AppDynamics, ManageEngine, Site24x7

Who's Hiring?

  • Want to build scalable systems that power the world's largest music streaming service? Spotify is looking for engineers for our backend infrastructure team. Apply now.
  • At Evernote our vision is to help the world remember everything. If you want to work in a face paced, highly rewarding environment with some of the smartest engineers on the planet, then come join us! We are looking for Sr. Security Engineers and Sr. Operations Engineers/DevOps to join our operations team.
  • LogicMonitor is looking for a Front End developer to have a huge impact, be valued, realize their dreams, and help us realize ours. We are looking for someone to own the code that delivers the design and usability of LogicMonitor's enterprise SaaS application(s). Please apply online
  • We need awesome people @ Booking.com - We want YOU! Come design next generation interfaces, solve critical scalability problems, and hack on one of the largest Perl codebases. Please apply online.
  • Help build the platform that powers a better, fairer banking experience at Simple. Join a talented team that chooses its own tools; works across web, Android, iOS, and Ruby/Scala/Clojure backend apps; and develops a secure and scalable banking service on AWS. Learn more at careers.
  • The AWS Relational Database Service (RDS) automates management of relational databases in the cloud. We have a wide variety of customers and are part of many mission-critical applications, like the ones built by the 2012 Obama re-election campaign. If you're interested in joining a fast-growing service and team, please send your resume to rds-jobs@amazon.com.
  • New Relic is looking for a Java Scalability Engineer in Portland, OR. Ready to scale a web service with more incoming bits/second than Twitter?  http://newrelic.com/about/jobs

Fun and Informative Events

  • Surge - The Scalability & Performance Conference, presented by OmniTI is happening on Sept. 12th-13th. Special, High Scalability Reader Rate: $50 off registration--now through September 10!
  • It's back! Join the MySQL Community at the annual Percona Live MySQL Conference and Expo in Santa Clara, April 22-25. This year's conference features an outstanding lineup of 92 speakers delivering 112 breakout sessions over three days! 

Cool Products and Services

If any of these items interest you there's a full description of each sponsor below. Please click to read more...

Click to read more ...

Monday
Apr292013

AWS v GCE Face-off and Why Innovation Needs Lower Cost Infrastructures

This is a repost of part 2 (part 1) of an interview I did for the Boundary blog.

Boundary:  There’s another battle coming down the pike between Amazon (AWS) and Google (GCE). How should the CTO decide which one’s best?

Hoff: Given that GCE is still closed to public access we have very little common experience on which to judge. The best way to decide is as always, by running a few experiments. Pick a few representative projects, a representative team, implement the projects on both infrastructures, crunch some numbers, figure out the bigger picture and then select the one you wanted in the first place :-) .

Sebastian Stadil, founder of Scalr, recently wrote about his experiences on both platforms and found some interesting differences: AWS has a much richer set of services; GCE is on-demand only, so AWS can be cheaper; GCE has faster disk and faster network IO, especially between datacenters; GCE has faster boot times and can mount read-only partitions across multiple machines; and GCE shares images across regions...

Click to read more ...

Friday
Apr262013

Stuff The Internet Says On Scalability For April 26, 2013

Hey, it's HighScalability time:

 

  • 100 Billion -  Neurons in The Human Brain, As Many Cells as Stars in the Milky Way; 10TB - Tumblr memcache
  • Quoteable Quotes:
    • @thoward3: OH: "We make scalability a possibility.. You know, we make 'scalapossibilty'. "
    • Tesla: When wireless is perfectly applied the whole earth will be converted into a huge brain, which in fact it is, all things being particles of a real and rhythmic whole. We shall be able to communicate with one another instantly, irrespective of distance. Not only this, but through television and telephony we shall see and hear one another as perfectly as though we were face to face, despite intervening distances of thousands of miles; and the instruments through which we shall be able to do this will be amazingly simple compared with our present telephone. A man will be able to carry one in his vest pocket.
    • @ADTELLIGENCE: Data on the internet: Data of all of 1993 = Data of 1 second in 2013
    • Nassim Taleb: Man-made complex systems tend to develop cascades and runaway chains of reactions that decrease, even eliminate, predictability and cause outsized events. So the modern world may be increasing in technological knowledge, but, paradoxically, it is making things a lot more unpredictable.
    • The Bw-Tree: A B-tree for New Hardware Platforms: We believe that latch free techniques and state changes that avoid update-in-place are the keys to high performance on modern processors.
    • @rvirding: WhatsApp "Bigger Than Twitter" With Over 200M Monthly Active Users, 8B Inbound And 12B and they use #erlang
    • Jasper Fforde: There’s a lot to be said about merely having a hazy idea of what’s going on but generally reaching the right outcome by following broad policy outlines. In fact, I’ve a sneaky suspicion that it’s the only way of getting things done. Once the horror and unpredictability of unintended consequences gets a hold, even the best-intentioned and noblest of plans generally descend to mayhem, confusion and despair.
    • @enygma: I'm starting to think the Twitter unfollow bug is actually their way to handle scalability
    • @ndubaz: Spent last 2 days training with the Army's latest virtual trainers. More skeptical than ever of scalability and utility for light forces.
    • @bernardgolden: Airbnb workflow control system was 10K (!) lines of bash script.
  • Scaling Deployment at Etsy by Daniel Schauenberg. 1.49 billion page views, 4,215,169 items sold, $94.7 million of goods sold, 22+ million members, 800,000+ active shops. LAMMP + Monolithic App + No Branching + Frequent deployment + lots more.

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

Click to read more ...

Thursday
Apr252013

Paper: Making reliable distributed systems in the presence of software errors

Joe Armstrong is a co-inventor of Erlang and general all around renaissance software tinkerer as shown by his excellent work on writing a C Compiler and his voluminous work on GitHub.

Given the success of Erlang it's probably no surprise that he wrote his thesis on the ground breaking ideas behind Erlang: Making reliable distributed systems in the presence of software errors.

Even if you have yet to join the cult of Erlang the principles behind Erlang are universal and well worth exploring for your own designs. Highly recommended.

Introduction:

Click to read more ...

Wednesday
Apr242013

Strategy: Using Lots of RAM Often Cheaper than Using a Hadoop Cluster

Solving problems while saving money is always a problem. In Nobody ever got fired for using Hadoop on a cluster they give some counter-intuitive advice by showing a big-memory server may  provide better performance per dollar than a cluster:

  1. For jobs where the input data is multi-terabyte or larger a Hadoop cluster is the right solution.
  2. For smaller problems memory has reached a GB/$ ratio where it is technically and financially feasible to use a single server with 100s of GB of DRAM rather than a cluster. Given the majority of analytics jobs do not process huge data sets, a cluster doesn't need to be your first option. Scaling up RAM saves on programmer time, reduces programmer effort, improved accuracy, and reduces hardware costs.

 

Tuesday
Apr232013

Facebook Secrets of Web Performance

This is a repost of part 1 of an interview I did for the Boundary blog.

Boundary: What is Facebook’s secret sauce for managing what’s got to be the biggest Big Data project, if you will, on the Web?

Hoff: From several presentations we’ve learned what Facebook insiders like Aditya Agarwal and Robert Johnson, both former Directors of Engineering, consider their secret sauce:

Click to read more ...

Friday
Apr192013

Stuff The Internet Says On Scalability For April 19, 2013

Hey, it's HighScalability time:


(Ukrainian daredevil scaling buildings)
  • Two Trillion Objects, 1.1 Million Requests / Second: S3; 1.4TB/s: Titan supercomputer has world’s fastest storage; four billion hours: Netflix streaming in last 3 months; $1.2B: Google's Q1 infrastructure spend
  • Quotable Quotes:
    • Google: We'll track EVERY task on EVERY data center server
    • Stacey Higginbotham: All in all in the last five years the world has gained 54 Tbps of new capacity.
    • @seveas: Scalability 103: Hardware sucks. Software sucks. Everything *will* break, prepare for failure of any component of your system.
    • bloodredsun: The long and short of it is that Cassandra is a fantastic system for write heavy situations. What it is not good at are read heavy situations where deterministic low latency is required, which is pretty much what the pinterest guys were dealing with.
    • @viktorklang: "The e-mail message could not be delivered because the user's mailfolder is full." <-- EMAIL HAS BACKPRESSURE OMG
  • Interesting Behind the Scenes: Airbnb Neighborhoods. Includes a description of their work flow and a detailed breakdown of their stack: Rails, PostgreSQL/PostGIS, Memcached, CoffeeScript, Sass, jQuery, Handlebars, Backbone, Underscore, Sinatra, Clojure, Java, Hadoop, Cascalog. Highlight: "You don't need a database, you need a [expletive deleted] cache" So that's what we did, we traded our database for a cache.

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

Click to read more ...

Wednesday
Apr172013

Tachyon - Fault Tolerant Distributed File System with 300 Times Higher Throughput than HDFS

Tachyon  (github) is interesting new filesystem brought to by the folks at the UC Berkeley AMP Lab:

Tachyon is a fault tolerant distributed file system enabling reliable file sharing at memory-speed across cluster frameworks, such as Spark and MapReduce.It offers up to 300 times higher throughput than HDFS, by leveraging lineage information and using memory aggressively. Tachyon caches working set files in memory, and enables different jobs/queries and frameworks to access cached files at memory speed. Thus, Tachyon avoids going to disk to load datasets that is frequently read.
It has a Java-like File API, native support for raw tables, a pluggable file system, and it works with Hadoop with no modifications.
 
It might work well for streaming media too as you wouldn't have to wait for the complete file to hit the disk before rendering.