Iron.io Support for Arm
Since releasing our flagship product in early 2011, Iron.io customers have enjoyed tightly coupled hosted solutions with Amazon Web Services (AWS). In addition customers are running Worker on-premise and in their own private clouds.
In the last year, an increasing number of customers have requested support for the Arm architecture both for on-premise deployments and in the cloud on AWS. Based on customer demand, we added Arm support on our roadmap. We’re happy to announce that Worker now supports Arm based architectures!
Customers that run their own hardware using Worker’s Hybrid deployment method, run Worker completely on-premise, or those that run on AWS, can now start diversifying their container workloads. We already have customers taking advantage of this release. It greatly increases the variety of workloads that can be run with Worker.
Iron.IO Worker Support for AWS EC2 A1
As you might be aware, Amazon announced a new Amazon EC2 A1 instance in November last year. It is based on AWS Graviton Processors. A1 instances deliver significant cost savings for scale-out and Arm-based applications such as Web servers, containerized microservices, caching fleets and distributed data stores that are supported by the extensive Arm ecosystem.
With Arm support, Worker now allows customers the ability to run workloads that require Arm based binaries. There could also be potential cost savings by moving your current workloads to these new instance types. That definitely depends on the resource load, though. It’s a good idea to read through the options (burstability vs no burstability, pricing, etc) and test out your specific workload before jumping in. Feel free to reach out to us if you’d like to discuss!
Usage
When creating a cluster in Worker, you’ll now see the availability of the A1 instance types. In order to run your workloads on ARM processors, you’ll simply need to use our new image: iron/runner:arm, rather than our normal iron/runner image. There’s also iron/runner:mplatform for cases where there could be multiple architecture types in the mix.
CivilMaps with Worker on Arm
CivilMaps runs Worker on-premise which allows for extremely low latency compute operations. At the end of their complex workflow engine, Worker sits as the data processing backbone, running containerized jobs at high concurrency.
CivilMaps is an Iron customer that does edge based HD mapping and localization for autonomous driving platforms. Last year they announced that they’d be moving their internal infrastructure to Arm. A quote about the move:
“Civil Maps is excited to announce that we’ve migrated our edge-based HD mapping and localization solution to the Arm® family of processors. Arm is the licensor to the largest ecosystem of automotive grade system-on-chips (SoC) and system-on-modules (SoM), with its chips already found in 85% of automotive electronic control units (ECU) on the road. Our team sees this as a key step towards building a truly scalable platform for self-driving car developers. The industry still has a long way to go, but we believe that the arrival of cost-effective, production-grade systems for level 4 and 5 autonomous vehicles just got significantly closer.”
Conclusion
In the next few months we’ll be publishing more blog posts about our Arm support and sharing more customer success studies in depth. There are customers utilizing Worker in many unique ways and we believe our new support for Arm is going to open the door for many more.