Join the Enterprise CORD mailing list.
Join the CORD team (#e-cord channel) on Slack.
Quickstart
If you are anxious to get started, here's how to deploy E-CORD. You can either go with an emulated setup as described here, or follow the instructions here for an actual hardware-based setup (including bill of materials).
Overview
Description Enterprise CORD (E-CORD) is a first of its kind initiative to offer enterprise connectivity services over metro and wide area networks, using only open source software and commodity hardware.
CORD (Central Office Rearchitected as a Datacenter) combines NFV, SDN, and the elasticity of commodity clouds to bring datacenter economics and cloud agility to the Telco Central Office. An open reference implementation of CORD uses commodity servers and whitebox switches, coupled with open source software that includes OpenStack, Docker, ONOS, and XOS. This reference implementation is a general and extensible platform that supports a variety of domains and business units (e.g., residential, enterprise, mobile), but it is also sufficiently complete to support field trials.
E-CORD builds on the CORD infrastructure to support enterprise customers, and allows service providers to offer enterprise connectivity services (L2 and L3VPN). It can go far beyond these simple connectivity services, as it includes virtual network functions (VNFs) and service composition capabilities to support disruptive cloud-based enterprise services.
In turn, enterprise customers can use E-CORD to rapidly create on-demand networks between any number of endpoints or company branches. These networks are dynamically configurable, implying connection attributes and SLAs can be specified and provisioned on the fly. Furthermore, enterprise customers may choose to run network functions such as firewalls, WAN accelerators, traffic analytic tools, virtual routers, etc. as on-demand services that are provisioned and maintained inside the service provider network.
What key business or technical challenge is addressed by this solution? The technical challenges are twofold. First, software defined control of a converged packet/optical wide area network requires innovative multi-layer and delegated control primitives. Second, carrier grade connectivity services have elaborate service model specifications, and deploying these on white box infrastructure introduces hardware support challenges.
Describe the “open” component(s) that the solution incorporates: Our work leverages and builds further on a fully open source stack.
● Openstack provides a base IaaS capability, and is responsible for creating and provisioning virtual machines (VMs) and virtual networks (VNs). CORD uses OpenStack's Nova, Neutron, Keystone, Ceilometer and Glance subsystems.
● ONOS is the network operating system that manages the whitebox switches and software switches (OvS) in each server. It hosts control programs that implement services and it is responsible for embedding virtual networks in the underlying network.
● XOS is a framework for assembling and composing services. It unifies data plane services supported by OpenStack and Docker, and the control plane services running on ONOS.
● Atrium is the software stack that runs on each whitebox switch. It includes Open Network Linux, the Indigo OpenFlow Agent (OF 1.3), and the OpenFlow Data Plane Abstraction (OFDPA), layered on top of Broadcom merchant silicon. We also present a fully open sourced implementation of MEF Forum (MEF LSO Presto interface) services running on top of commodity hardware using open protocols (OpenFlow etc.).
Further Resources
Roadmap