Asia's Source for Enterprise Network Knowledge

Friday, April 18th, 2014

Data Center Management

Google pledges computing without limits in Compute Engine cloud platform

With its Google Compute Engine launched Thursday, Google is offering an IaaS (infrastructure-as-a-service) cloud for running Linux virtual machines on the same infrastructure that powers Google itself.


 
Unveiled at the Google I/O conference in San Francisco, the service offers scale for tasks requiring large amounts of compute power. "You can launch enormous compute clusters -- tens of thousands of cores or more" said Google's Craig McLuckie, Compute Engine product manager, in a blog post.


 
Developers can take advantage of the speed and scale of the same infrastructure powering Google applications, Google said. "Many of you have learned to live with erratic performance in the cloud. We have built our systems to offer strong and consistent performance even at massive scale," McLuckie noted in the blog post. Google plans to offer users 50 percent more value for their money than other leading cloud providers.


 
Users can launch Linux virtual machines on demand, including single-, two-, four- and eight-virtual core VMs, with 3.75 gigabytes of RAM per virtual core. Data can be stored on a local disk, on Google's new persistent block drive device, or on Google's Internet-scale object store, Google Cloud Storage.


 
While Google previously has offered its platform-as-a-service cloud, Google App Engine, Google Compute Engine focuses on provision of virtual machines.