Amazon Web Services (AWS) has announced an improvement to its S3 Glacier service, which now supports restore requests at a rate of up to 1,000 transactions per second, per account in an AWS Region. That’s up to a ten-fold improvement when it comes to retrieving large volumes of archived data. Best of all, there’s no additional cost and it applies to all standard and bulk retrievals from the Amazon S3 Glacier Flexible Retrieval and Amazon S3 Glacier Deep Archive storage classes.
The improved restore throughput means applications can now process archived data faster. This is beneficial when it comes to retrieving millions of archived objects quickly when restoring backups, whether to retrain machine learning models or pulling historical data for analyzing.
This change will significantly reduce the restore completion time for datasets composed of small objects, while applications are also able to initiate restore requests from S3 Glacier at a much faster rate. When combined with S3 Batch Operations, users can automatically initiate requests at a faster rate, allowing for the possibility to restore billions of objects or petabytes of data quickly in the S3 console or with a single API request.
AWS says the retrieval performance benefit scales with the number of restored objects, and the improvement can reduce data retrieval completion times by up to 90%. The change is now live in all AWS regions including the AWS GovCloud (US) Regions, the Amazon Web Services China (Beijing) Region, and the Amazon Web Services China (Ningxia) Region.
Are you or your business currently using AWS for cloud storage? By filling out our quick form, you can save 60% or more on cloud storage from major providers, including AWS.