How to Scale to 1 Million Requests

Posted by Raj Chohan on 11/26/13 1:52 PM

Google shows how to scale an application to 1 million requests-per-second for $10.

Yesterday on the Google Cloud Platform Blog, Tony Voellm a Google Platform engineer, demonstrated a method of how developers can scale their app to one million requests-per-second for the incredibly low price of just $10. The impressive feat was accomplished without pre-warming VMs or use of any other services besides Google Platform.

Screen_Shot_2015-07-15_at_11.12.00_AM

"To demonstrate scaling of the Compute Engine Load Balancing fanout we used 200 n1-standard-1’s Web Server running Apache v2.2.22 on Debian 7.1 Wheezy Images. Users are encouraged to use larger VM types for better single machine backend web serving, however here we demonstrated the scaling of the load balancer to backends and were not concerned with the backends themselves using every cycle to serve responses. Each backend web server received ~5K requests per second, which is an even distribution." - Tony Voellum

The Cloud Platform team was kind enough to provide the method and code they used to simulate one million concurrent requests, the Gist can be found here.

Now that software has moved to the web and appears to be staying give App Engine or Compute Engine a chance to win your heart. Here at AppScale many of our workloads are run on both of these great services. We’re always surprised at what great value we get from them. You get world class developers and technical staff maintaining your infrastructure at an incredibly low cost.

Want to try out AppScale? Click below to deploy your first app on AppScale in less than 10 minutes.

Try AppScale!

Topics: Industry News, Best Practices

Subscribe to Email Updates