Sign up for our newsletter - Navigating the horizon of business technology​
Technology / Data

AWS Unveils New Instances to Help Customers Deal with CPU Spikes

Amazon Web Services (AWS) has unveiled its next generation of instances, T3, which it claims provides up to 30 percent better price performance for users.

The T3 instances, available on Amazon Elastic Compute Cloud (EC2), have been designed for applications that experience occasional spikes in CPU demand. (An EC2 instance is a virtual server for running applications on AWS infrastructure).

This includes microservices, low-latency interactive applications, small and medium databases, virtual desktops, development environments, code repositories, and business critical applications, AWS said in a release this week.

“The T3 instances enable customers’ applications to burst seamlessly to meet temporary traffic peaks and then scale back down to operate at typical traffic levels”.

White papers from our partners

The T3 instances are based on Intel’s Xeon scalable processors which run on the AWS Nitro System. Anthony Atherton, Head of Digitalization at Siemens Global Services commented in the release that: “Siemens uses AWS T2 instances extensively at the Digitalization Expertise Center on behalf of the Siemens Divisions.”

“With the lower priced T3 instances, coupled with the ability to burst CPU usage for as long as our applications need to, we can move a wide range of workloads to T3 instances and benefit from cost savings. The T3 instances with the new Intel Xeon Scalable processors along with improved EBS and networking performance will give us even more processing power and networking efficiency.”


The T3 instances start off in unlimited mode as default. If the instance needs to run at a higher CPU for a prolonged period, the user will be charged an additional cost of $0.05 per vCPU-hour.

T2 instances launched four years ago. They allowed Amazon customers to sustain high CPU performance while also avoiding application degradation when the instances goes over the available CPU credits.

Matt Garman, Vice President of Compute Services at AWS said that: “Since T2 instances ‘burst’ on the scene in 2014, they’ve been wildly popular as they’ve helped customers optimize the cost and performance for applications that have variable CPU demands.”

“We think customers are going to be pretty excited by the launch of our third generation burstable instance (T3) as it’s both 30% more cost effective on a price-to-performance basis than the T2 and enables, by default, the unmatched capability of unlimited burst for customers’ applications.”

Ike DeLorenzo, VP Product, Heroku at Salesforce commented: “We run a global fleet of Amazon EC2 instances that power our LXC-based container platform-as-a-service”

“Heroku apps are occasionally idle, but the platform has to respond quickly when load ramps up. Performance, reliability, and responsiveness are fundamental to our customer experience, and T3 instances help us to deliver on that customer promise while also controlling our costs.”

This article is from the CBROnline archive: some formatting and images may not be present.

CBR Staff Writer

CBR Online legacy content.