This is what vPODs do to make you lean and agile
Learn how elastic vPODs—part of our implementation of software-defined infrastructure based on Intel® Rack Scale Design—can make your bimodal architecture both agile and lean.
Our hyperscale system gives you vPODs
Ericsson Hyperscale Datacenter System 8000 is a complete hyperscale system for hosting public, private, or hybrid clouds. Based on Intel® Rack Scale Design, it can host a multitude of software-defined vPODs connected across a light-speed optical backplane.
Because the configuration of each vPOD is defined in software, it is very simple to modify or scale a vPOD to make it more suitable for a particular workload. If you need to launch a new web service, you can rapidly configure a virtual datacenter to provision it. If that service requires high performance, you can configure the vPOD with high-performance components. If it requires high network bandwidth, you can draw as much bandwidth as you need from the central pool.
In their basic state, vPODs provide bare metal as a service (BMaaS), so for provisioning purposes, consider a vPOD the same as a bare-metal server. A server-less server, if you will. However, depending on which operating systems or hypervisors you install on them (including OpenStack and VMware), you can use them to offer infrastructure as a service (IaaS) or platform as a service (PaaS).
vPODs can support multi-tenancy through a virtual infrastructure manager (VIM) such as OpenStack or VMware. The VIM manages the virtual machines deployed on a particular vPOD, as if the vPOD were a typical hardware server. Each vPOD contains a number of ports, VLANS, IP subnets, and network services, so it has plenty of capacity for separate, isolated cloud tenants.
vPODs give you a muscular, lean infrastructure
A vPOD is extremely elastic. If at any point it needs more resources, you can simply allocate them from the common pool. When it no longer needs them, you can return them to the pool. This common pool leads to higher utilization rates compared to dedicated hardware that is selected to support peak usage, which results in over-provisioning. Since you are getting more use from the hardware you have, your utilization rate goes up while your capex goes down. Fewer idle systems and less over-provisioning consumes less power, which in turn reduces your utility costs.
Another benefit of the disaggregated system behind Ericsson vPODs is that you can replace individual resources or classes of resources instead of the entire server. Since compute resources have shorter lifecycles than storage resources, for instance, you can not only save money by targeted upgrading, but you can upgrade to the latest hardware sooner.
As a result, you can run your business not only on the most up-to-date components, but also on the components best suited to the needs of your customers and partners, whether those components are older or the latest innovation.
Find out more here
Here is a video of my colleague David Partain talking about vPODs and the Ericsson Command Center: