Hot Scalability Links for Aug 13, 2010

• Ezra Zygmuntowicz in a heart warming account of his 4 Years at Engine Yard, has concluded in his experience that: the true future of cloud computing for developers is to not think about servers at all. It is now time to focus on the Application and new levels of abstraction that allow folks to use the computing resources in easier and easier ways. 
• Tweets of Gold:
  • bryanlatten: Nothing like a million caching layers to screw up an already complicated deployment. Thankfully, there is beer.
  • jkalucki: Twitter isn't down, you are just using the wrong access methods...
  • andyedinborough: I don't mean to hate, but why would I give up performance and scalability for a dynamic language? Honestly, I don't get it.
  • AsitSinha: It's amazing.... to see the absence of an understanding of how capability plays a role in scalability.
  • scottgal: Devs are HORRIBLE DBAs. Used to do Scalability labs for MS UK and bad schemas were the single biggest issue (next to bad Indexes).
• Overclocking SSL by Adam Langley. Gmail switched to using HTTPS for everything by default...all of our users use HTTPS to secure their email between their browsers and Google, all the time. In order to do this we had to deploy no additional machines and no special hardware. On our production frontend machines, SSL/TLS accounts for less than 1% of the CPU load, less than 10KB of memory per connection and less than 2% of network overhead. Many people believe that SSL takes a lot of CPU time and we hope the above numbers (public for the first time) will help to dispel that.
• Is prematurely sharding the root of all evil? Andrew Glover doesn't go that far, but says to Think twice before sharding. 
• You don't need to think about scaling, but you need to think about pivoting. Chester Grant thinks  products should be designed in such a way that making changes are very easy.
• Open Source SSL Acceleration by John Buswell. A look at utilizing Open Source projects to build an SSL Accelerator for Web Servers that rivals even the most expensive commercial solutions.
• A desire to soak up all the CPU on multi-core systems has prompted Elliptics  to switch from a reactor model to thread-per-client approach. My guess is logic and threads should still be separated.
• Evan Weaver updates his list of papers on distributed systems. 
• 7 easy tips to reduce your Amazon ec2 cloud costs.  The cloud has become complicated enough that there's a lot of strategizing needed to minimize costs. 
• Vaibhav Puranik has come up with an effective list of plays in the game.
 
• Alex Popescu recommends Three Papers on Load Balancing.
• Take a tour of the Cassandra codebase. Gary Dusbabek is your tour guide. It's not Paris, but interesting to see the architecture of a complex NoSQL product in detail.
• Looking for some cloud computing podcasts for you daily 12 mile run? Audrey Watters has compiled a nice list of 10 Cloud Computing Podcasts for your perusal.

Interested in advertising a job, product, service, or event on HighScalability.com? Then contact us.