Feb. 28th, Barcelona – I am very excited about Mobile World Congress (MWC) 2017. This year it’s not about cell phones but rather cellular infrastructure and its transformation to Software Defined Networking and the Cloud. Two of our partners, Ericsson and Dell, are at MWC talking about Pluribus Networks Software Defined Fabrics and how we help the networking layer plug into a Software Defined Infrastructure.
The Pluribus Software Defined Fabric
The Pluribus Software-Defined Fabric runs on OCP-style top of rack switches and is implemented using a distributed control plane that decouples the underlying hardware from fabric services and policies, while providing full visibility into application traffic flowing across the network thus reducing operational complexities and allowing the network to expand and change, independent from the layers above. The Pluribus Fabric provides an abstraction layer and provides advantages similar to a server hypervisor by decoupling the endpoint VNIC from physical switch and physical port.
The VMs and Containers endpoints running on servers are represented by Pluribus Fabric vPORTs (which becomes the other end of the vNIC) which freely move across the Pluribus Fabric and programs the underlying forwarding table of the appropriate switch/port while taking the configured policies and multi-tenancy into account. The Pluribus Fabric programs the Data Path using standard Layer2/3/VXLAN protocols and interworks with legacy infrastructure that helps gradual transformation of a legacy Data Center to a highly agile and efficient software defined environment.
The Pluribus Fabric unifies management models by plugging into a Openstack or VMware Cloud manager to provide full automation by allowing users to manage the leaf-spine POD using the Pluribus CLI as a single-point-of-management, thus drastically reducing an operator’s CAPEX and OPEX. A fully open RESTful API allows for even finer degrees of automation for people who want to take advantage of the full power of network automation, multi-tenancy, and analytics.
As the number of endpoints in the network continues to grow exponentially from tens of thousands of VMs to hundreds of thousands of containers today (and millions of IOT devices tomorrow) each with increasing I/O needs, both Enterprises and Communications Service Provider Data Centers need to embrace a scale-out network which is built on merchant silicon (OCP style H/W) and OPEN protocols provided by the Pluribus Fabric.
Watch the Hyper Scale Data System and Pluribus Fabric at MWC
Our partner Ericsson is showcasing the full solution in their booth at MWC where Fabric is providing full automation for their Hyperscale Data Systems while leveraging the Pluribus Fabric with multi-tenancy to support multiple VPODs with their own cloud managers controlling their environments. The Pluribus Fabric provides a whole new way of pulling rich analytics from the network without additional equipment and is integrated with Ericsson’s Command center via RESTful APIs.
The pictures below show the excitement and crowd Ericsson is drawing at their booth.
Please stop by to discuss with us – we’re here in Hall 2!
About the Author
Sunay is the CTO and a Co-Founder of Pluribus Networks. Prior to Pluribus, Sunay was a Senior Distinguished Engineer for Sun Microsystems, and was the Chief Architect for Kernel/Network Virtualization in Core Solaris OS. Sunay has an extensive 20+ year software background, and was one of the top code contributors to Solaris. Sunay holds over 50 patents encompassing network and server virtualization.