During the first week of the annual re:invent, AWS introduced the ability to specify AWS Fargate as a computing resource for AWS Batch jobs. With the AWS Batch support for AWS Fargate, customers will have a way to run jobs on serverless compute resources, fully-managed from job submission to completion.

AWS first introduced AWS Batch back in December 2016 as a fully managed batch computing service that enables developers, scientists, and engineers to quickly and efficiently run hundreds of thousands of batch computing jobs on AWS. With AWS Batch, customers no longer had to do the heavy lifting of batch workload management by creating compute environments, managing queues, and launching the appropriate compute resources for their jobs.

With the integration of AWS Batch with Fargate, users can run compute-intensive workloads such as ML inference, map-reduce analysis, and other batch workloads without spending time on image maintenance and right-sizing of compute and monitoring. By selecting Fargate or Fargate Spot as a compute resource type in Batch, submitting a Fargate-compatible job definition, users can immediately benefit from the serverless computing engine. With Fargate, every job receives the exact amount of CPU and memory that it requests (within allowed Fargate SKUs); hence, there is no wasted resource time or need to wait for EC2 instance launches.

#amazon #amazon web services #cloud #aws #aws fargate