Google Finally Gets the Right Edge Computing Strategy With Distributed Cloud Edge

Announced at the Google Cloud Next ’21 conference, Google Distributed Cloud (GDC) plays a critical role in the success of Anthos by making it relevant to telcos and enterprise customers. Google Distributed Cloud Edge, part of GDC, aims to make Anthos the foundation for running 5G infrastructure and modern workloads like AI and analytics.

Recently, Google announced the general availability of GDC Edge by sharing hardware configuration details and requirements.

In its initial form, GDC Edge runs on two form factors: the rack configuration and the GDC Edge appliance. Let’s take a closer look at these choices.

Rack configuration for GDC Edge

This configuration targets telecom operators and communications service providers (CSPs) for operating 5G core and radio access (RAN) networks. CSPs can expose the same infrastructure to their end customers to run workloads like AI inference that require ultra-low latency.

The location where the rack hardware runs is referred to as the distributed cloud edge zone. Each zone runs on dedicated hardware that Google provides, deploys, operates, and maintains. The hardware consists of six servers and two top-of-rack (ToR) switches connecting the servers to the local network. In terms of storage, each physical server comes with 4TiB drives. The gross weight of a typical rack is 900 lbs or 408 kg. The Distributed Cloud Edge Rack arrives pre-configured with the hardware, network, and Google Cloud settings specified when ordered.

Once a DCE zone is fully configured, customers can pool one or more servers from the rack to create a NodePool. Each node in the NodePool acts as a Kubernetes worker node connected to the Kubernetes control plane running in the closest Google Cloud region.

This distributed topology gives Google the flexibility to upgrade, patch, and manage Kubernetes infrastructure with minimal disruption to customer workloads. It allows DCE to benefit from a secure and highly available control plane without taking up processing capacity on the nodes.

Google has taken a unique approach to edge computing by moving worker nodes to the edge while running the control plane in the cloud. This is very similar to how Google manages GKE, except worker nodes are part of the NodePool deployed at the edge.

Clusters running on DCE can be connected to the Anthos management plane for better control over deployments and configuration.

A secure VPN tunnel connects the on-premises Distributed Cloud Edge infrastructure to a virtual private cloud (VPC) configured in Google Cloud. Workloads running at the edge can access Google Compute Engine resources deployed in the same VPC.

The rack configuration requires connectivity to Google Cloud at all times. Since it operates in a controlled environment in a CSP facility, meeting this requirement is not a challenge.

Once the clusters are provisioned on the DCE infrastructure, they can be treated like other Kubernetes clusters. It is also possible to provision and run kubevirt-based virtual machines in the same environment.

CSPs in the United States, Canada, France, Germany, Italy, the Netherlands, Spain, Finland, and the United Kingdom can order rack infrastructure from Google.

GDC Edge Appliance

The GDC Edge Appliance is a high-performance, secure, Google Cloud-managed appliance for edge locations. It provides local storage, ML inference, data transformation, and export functionality.

According to Google, GDC Edge appliances are ideal for use cases where bandwidth and latency limitations prevent organizations from processing data from devices such as cameras and sensors in cloud data centers. These appliances simplify the collection, analysis and processing of data at remote sites where large amounts of data from these devices need to be processed quickly and stored securely.

The Edge appliance targets companies in manufacturing, supply chain, healthcare, and automotive verticals with low latency and high throughput requirements.

Each appliance comes with a 16-core processor, 64GB of RAM, an NVIDIA T4 GPU, and 3.6TB of usable storage. It has a pair of 10 Gigabit and 1 Gigabit Ethernet ports. With the 1U rackmount form factor, it supports either horizontal or vertical orientation.

The Edge Appliance is essentially a storage transfer device that can also run a Kubernetes cluster and AI inference workloads. With ample stoRage capacity, customers can use it as a cloud storage gateway.

For all intents and purposes, the Edge Appliance is a managed device running Anthos clusters on bare metal hardware. Customers follow the same workflow as installing and configuring Anthos in bare metal environments.

Unlike the rack configuration, clusters run both the control plane and worker nodes locally on the appliance. But, they are registered with the Anthos management plan operating in the nearest Google Cloud region. This configuration allows the edge appliance to run in an offline environment with intermittent cloud connectivity.

Analysis and takeaways

With Anthos and GDC, Google has defined a comprehensive multicloud, hybrid and edge computing strategy. GDC Edge targets CSPs and enterprises with purpose-built hardware offerings.

Telecom operators need a reliable and modern platform to run 5G infrastructure. Google is positioning Anthos as the trusted cloud-native platform for running containerized network functions (CNFs) required for 5G core and radio access (RAN) networks. By providing a combination of managed hardware (rack-based GDC Edge) and software stack (Anthos), Google wants to enable CSPs to deliver 5G Multi-Access Edge Computing (MEC) to enterprises. It has partnered with AT&T, Reliance JIO, TELUS, Indosat Ooredoo, and most recently Bell Canda and Verizon to leverage 5G infrastructure.

Google’s approach is different from Amazon and Microsoft in delivering MEC 5G. Both AWS and Azure have 5G-based zones that act as extensions of their data center footprint. AWS Wavelength and Azure Private MEC allow customers to run workloads in the closest edge location managed by a CSP. Amazon and Microsoft are partnering with telecommunications providers such as AT&T, Verizon, and Vodafone to offer hyperlocal edge zones.

Google is betting big on Anthos as the fabric to run 5G MEC. It partners with leading telecom operators around the world to help them build the 5G infrastructure based on its proven Anthos-based cloud-native infrastructure. Although Google may have a competing bid for AWS Wavelength and Azure Private MEC in the future, its current strategy is to make GDC Edge the preferred 5G MEC platform. This approach puts the CSP at the forefront of its edge computing strategy.

Google finally responded to Azure Stack HCI and AWS Outposts with the GDC Edge appliance. It targets enterprises that need a modern cloud-native platform to run data and compute-intensive workloads at the edge. The Edge Appliance can be deployed in remote locations with intermittent connectivity, unlike the rack configuration.

With Anthos as its cornerstone, Google’s Distributed Cloud strategy looks promising. It aims to gain the enterprise advantage as well as the telecommunications advantage with purpose-built hardware offerings. Google finally has a viable competitor for AWS Wavelength, AWS Outposts, Azure Edge Zones, and Azure Stack.

Leave a Comment