Highlights and Insights from Beanfield Metroconnect
In November 2018 Beanfield Metroconnect had the opportunity to attend our first AWS re:Invent conference in Las Vegas. The scale and energy of the conference are unlike any tech conference we had participated in before. For uninitiated first time re:Invent-ers like us, a conference with 65,000 attendees and a jam-packed schedule can be overwhelming. We kept to our tightly planned three days, and it was still a whirlwind experience. For readers evaluating the ROI for an event like this, most importantly the conference proved to be an incredible business development opportunity. Beanfield spent much more time than expected connecting with customers, partners, and prospects — old and new.
Regarding the content of the conference — re:Invent is an incredible show. The torrent of product announcements delivered during keynotes, product technical briefs, and executive sessions came fast and furious all week with a rock’n’roll flare. If there are “themes” set for the conferences each year, re:Invent 2018 heavily focused attention on machine learning, AI, HPC (high-performance computing), and hybrid cloud. Our friend Matt Simpson, Vice President of Cloud Product at Megaport shared a couple of excellent vlog posts direct from the re:Invent Expo floor with tips for conference attendees as well as his take on Andy Jassy’s keynote. I highly recommend following Matt for all cloud-related content.
As promised Megaport and Beanfield have created a list of the re:Invent product announcements we think are most interesting or relevant to the customers we currently support through the AWS Direct Connect partner program and for companies evaluating HPC, hybrid cloud, or digital transformation projects in 2019 and beyond. We are pleased to share the following updates:
Amazon EC2 & EBS
Amazon announced significant performance increases to EBS storage tiers including new high watermark benchmarks for IOPS and EBS throughput per volume. Beanfield and Megaport have been accelerating customer projects to move HPC applications to AWS and the prospect of double the performance for io1 and a 60% increase to gp2 volumes will help us continue that momentum.
Amazon EC2 C5n instances are the latest addition to the C5 family and provide up to 100 Gbps of networking throughput. C5n instances are ideal for network-intensive applications including high-performance computing workloads like VFX rendering, 3D animation, data lakes, and network appliances such as firewalls and routers.
2019 will bring GPU applications to the forefront of the Media & Entertainment vertical as innovative and paradigm-shifting changes are introduced by companies like Pixar and Autodesk. Next year’s product releases are almost perfectly timed for the announcement of Amazon EC2 P3dn.24xlarge instances. These VMs are the fastest, most powerful, and largest P3 instance size available. Each machine provides up to 100 Gbps of networking throughput, 8 NVIDIA® Tesla® V100 GPUs with 32 GB of memory each, 96 custom Intel® Xeon® Scalable (Skylake) vCPUs, and 2 TB of local NVMe-based SSD storage. The faster networking, new processors, doubling of GPU memory, and additional vCPUs enable developers to significantly lower the time to train their ML models or run more HPC simulations by scaling out their jobs across several instances (e.g., 16, 32 or 64 instances).
Elastic Fabric Adapter
Elastic Fabric Adapter (EFA) is a network interface for Amazon EC2 instances that enables customers to run High-Performance Computing (HPC) applications requiring high levels of inter-node communications, like computational fluid dynamics, weather modelling, and reservoir simulation, at scale on AWS.
Hybrid Cloud Announcements
Highlighting the hybrid theme of re:Invent, this blockbuster announcement had our team very excited for our friends at VMWare and for our customers whose latency sensitive applications have slowed down digital transformation journeys. AWS Outposts bring native AWS services, infrastructure, and operating models to virtually any data center, co-location space, or on-premises facility. With Outposts, you can use a single management plane for your entire enterprise IT environment and use the same automation, governance controls, policies, APIs, and developer tools to build and deploy modern cloud-native applications that can be deployed on-premises or in the cloud.
We are excited to share Amazon’s new “filesystem-as-a-service” product Amazon FSx, which provides fully managed third-party file systems to AWS customers. FSx delivers the native compatibility of third-party file systems with feature sets for workloads such as Windows-based storage, high-performance computing (HPC), machine learning, and electronic design automation (EDA). You don’t have to worry about managing file servers and storage, as Amazon FSx automates the time-consuming administration tasks such as hardware provisioning, software configuration, patching, and backups. Amazon FSx integrates the file systems with cloud-native AWS services, making them even more useful for a broader set of workloads.
Amazon FSx for Windows File Server
Amazon FSx for Windows File Server provides a fully managed native Microsoft Windows file system that can be accessed from up to thousands of compute instances. Built on Windows Server and SSD storage, Amazon FSx provides Windows shared file storage with the compatibility, features, and performance that your Windows-based applications rely on, so you can easily move your Windows-based applications to AWS.
Amazon FSx for Lustre
Amazon FSx for Lustre is a fully managed file system optimized for compute-intensive workloads and integrated with Amazon S3. For compute-intensive workloads, such as High-Performance Computing (HPC), and Machine Learning, you can leverage the scale and performance of FSX for Lustre to process your file-based data at up to hundreds of gigabytes per second of throughput, millions of IOPS, and sub-millisecond latencies.
Amazon RDS on VMware
The final product announcement we would like to share is the introduction of Amazon Relational Database Service (RDS) on VMware. AWS customers can now deploy managed databases in on-premises and hybrid environments using the Amazon RDS technology enjoyed by hundreds of thousands of AWS customers. RDS on VMware makes it easy to set up, operate, and scale databases in VMware vSphere private data centers, or to migrate them to AWS.
AWS re:Invent 2018 opened a lot of doors for customers at all stages of the cloud service adoption cycle. The focus this year on hybrid cloud solutions and HPC products removed the barriers and constraints that may have previously kept customers locked in colocation space or continuing to invest in physical infrastructure. For a commercial fibre optic network provider like Beanfield Metroconnect, this year’s conference announcements present an amazing opportunity to help new customers and validated our investment in the Beanfield Cloud Exchange service. In 2019, through our partnership with Megaport and AWS, our customers will enjoy better connectivity to new regions and new ultra high-performance hybrid architectures supported by a broader and more compelling business case for direct connectivity to Amazon.
We want to thank everyone we met with in Las Vegas and we truly appreciated the time and energy it took to align schedules or hustle between buildings during keynote and session breaks. We are excited to discuss the product announcements we covered in this article and happy to provide any feedback or answer questions about these exciting announcements. Beanfield Metroconnect and Megaport will once again be joining our customers and partners at re:Invent 2019, see you there!
About the Author:
Daniel Simmons is the Director of Cloud Strategy at Beanfield Metroconnect, a cloud product manager, cloud evangelist, and a solution architect for cloud and data centre services. Daniel has spent the past year overseeing the launch of the Beanfield and Megaport partnership with the goal of bringing multi-cloud connectivity to every office building in the city. He lives in Toronto with his partner and dog.