Follow Datanami:
November 29, 2023

AWS Launches High-Speed Amazon S3 Express One Zone


Amazon Web Services (AWS) is a major player in the public cloud space, however, with several other emerging competitors, AWS needs to continue evolving and innovating to continue enjoying the largest slice of the cloud pie. 

In its annual re:Invent conference in Las Vegas, AWS announced the general availability of the Amazon S3 Express One Zone –  a new storage class to deliver better performance and speed compared to the standard edition. Amazon claims the Express One Zone offers 10x performance improvement over the standard S3 service and is capable of handling hundreds of thousands of requests per second with consistent single-digit latency. 

The new Amazon S3 Express One Zone is tailor-made for data-intensive applications, such as AI/ML training, high-performance computing, and financial modeling. With its extremely low latency, the upgrade works well for objects of any size, including very large amounts of small objects.

According to AWS, the Express One Zone offers a 50 percent reduction in data request costs and a 60 percent reduction in computer expenses compared to the standard S3 storage class. This means that Spot and On-Demand compute resources are now used more efficiently and can be shut down earlier, helping reduce the overall processing costs. Deprovisioning instances earlier helps lower the associated compute costs

Launched in 2006, The Amazon Simple Storage Service (S3) is one of the most popular cloud storage services with millions of customers around the globe.  Over the years, the S3 has gone through several upgrades. It evolved from humble internet storage for personal storage to the backbone of the modern data stack of many data-driven enterprises. 

With the new Amazon S3 Express One Zone, you get a new bucket type and new authentication model optimized for AI/ML use cases and other data-intensive workloads. The new bucket type is specific to this storage class and can support hundreds of requests per second. It has a hierarchical namespace and storage object key names in a directory-like manner to deliver outstanding efficiency. 

Traditionally, Amazon S3 users have been able to choose specific AWS regions to store S3 data. With the new storage class, users can also choose to co-locate One Zone data in the same availability zone as compute resources. 

“Millions of customers rely on Amazon S3 for everything from low-cost archival storage to petabyte-scale data lakes, and they want to expand their use to support their most performance-intensive applications where every millisecond counts,” said James Kirschner, general manager of Amazon S3 at AWS. 

“Amazon S3 Express One Zone delivers the fastest data access speed for the most latency-sensitive applications and enables customers to make millions of requests per minute for their highly accessed datasets, while also reducing request and compute costs.”

In 2021, AWS launched the S3 Object Lambda and that same year added the S3 Glacier Instance Retrieval function to its platform. The launch of the Amazon S3 Express One Zone marks the most significant update to the Amazon S3 in recent years. It also signals the continued longevity and popularity of the Amazon S3. Cloudera, Colorfront, ChaosSearch, and Pinterest are among the customers and partners that already using Amazon S3 Express One Zone

Related Items 

AWS Announces Powerful New Offerings to Accelerate Generative AI Innovation

Rubrik Helps Customers Further Protect Amazon S3 Data

AWS Unleashes the DataZone