Hot Scalability Links for April 16, 2010

• Twitter gets a total of 3 billion requests a day via its API; 105,779,710 registered users; 300,000 new registered users a day; 180 million unique visitors a month; 55 million tweets a day.
• Who has the most servers? Google 1 million+; Intel 100K; 1&1 Internet 70K; Facebook 30K; Akamai 61K; Rackspace 56k+.
• Cloud Computing Economies of Scale. James Hamilton gives a fabulous talk breaking down where the costs are in the cloud. It's not where you may think. Higher utilization is the key. More here.
• Erlang  Factory: Andy Gross: Distributed Erlang Systems In Operation: Patterns  and Pitfalls by Martin J. Logan. Great overview of architecting distributed systems in Erlang. Covers what you want and don't want in a distributed system and how to compromise those elements, what's common, system design, cluster membership, load balancing, upgrades, debugging, and more.
• Extreme Scale Computing by Irving Wladawsky-Berger. “An  exascale supercomputer capable of a million trillion calculations per  second – dramatically increasing our ability to understand the world  around us through simulation and slashing the time needed to design  complex products such as therapeutics, advanced materials, and  highly-efficient autos and aircraft.”
• MMT: Exploiting Fine-Grained ParallelisminDynamic Memory Management by lots of people from North Carolina State University. We show that an efficient MMT design can give significant performance improvement by extracting parallelism.
• Ruby Scales, AND It’s Fast – If You Do It Right! by Kirk Haines. The secret to keeping things fast: Do one thing at a time, do it well enough, and then move  on.
• Swarm-dpl. A transparently scalable distributed programming  language allowing the creation of web applications which can  scale transparently through a novel portable continuation-based  approach.  Swarm embodies the maxim "move the computation, not the  data".
• How to Build Stable Google App Engine Apps and sleep  better at night by Waleed Abdulla. Be ready, shift happens and App Engine has restrictions. Be Ready. Write good error handling. Update at night. Email critical errors. Backup data.
• Gear6 makes  memcached infrastructure lower cost on cloud. Patented Robert Scoble interview with Gear6. What makes us different is that we are extending memcache in obvious ways to make it more useful to people and at the same time we are deploying it to real people and getting real feedback on how it works.
• How Raytheon Researchers are Using Hadoop to Build a Scalable,  Distributed Triple Store by Kurt Rohloff. Due to the inherent scalability of the Hadoop and HDFS approach in  SHARD, the SHARD triple-store could potentially be used for extremely  large datasets (trillions of triples). Also nice description of the query process.
• Infinite web scalability &  resilience with Amazon Web Services. Wille Faler provides a simple overview of how to serve semi-dynamic web content with almost  infinite horizontal scalability and resilience using Amazon Web  Services, with the added boon of making server restores a non-issue.
• Availability and Partition Tolerance by Jeff Darcy. A great discussion of Eric Brewer’s CAP Theorem. You will come away both edified and confused.
• Cassandra Architecutre Internals

New Releases

• Gear6's Memcached Adds the Best of Both  Worlds: MySQL and NoSQL. Today's release of Gear6 Web Cache integrates their Memcached interface  with operational query capabilities and a NoSQL backend.  Gear6 decided  to use the key-value store Redis because it already had traction among  NoSQL users.
• Amazon Simple Notification Service (Amazon SNS). Amazon Simple Notification Service (Amazon SNS)  is a web service that makes it easy to set up, operate, and send  notifications from the cloud.
• GigaSpaces XAP 7.1. Adds Elastic  Middleware Administration API, a way to deploy  applications and data grids into a GigaSpace cluster.
• Cassandra Release 0.6. Adds Hadoop MapReduce. Also Presentation: Gary Dusbabek (Rackspace) on Cassandra.

Events

• Social Developer Summit - June 29, San Francisco. Whether it's social games, social news, social discovery,   social search, or other forms of social solutions, developers  today are facing new  hurdles in building instantly scalable products.  The first Social Developer Summit will bring  together social  application developers to discuss the challenges, solutions,   and best practices for building applications in the rapidly expanding  social  web economy. At  the Social Developer Summit, industry  experts will share tips and case studies for   building high performance  social web products.

• Big Data Workshop - A one-day unconference on Friday, April 23 in Mountain  View, CA with a deliberately broad scope including NoSQL, MapReduce, and  anything related. Major NoSQL projects will be represented.
• Introduction to Apache CouchDB - April 21, San Francisco by J. Chris  Anderson.

If you would like to advertise a product, job, or event, please contact us for more information.