Who is Driving Network Innovations?
Over the last decade, hyperscale data center architects have consistently built out networks with orders of magnitude improvement in operating and cost metrics compared to traditional designs. Despite their scale, they take advantage of cost/performance improvements faster, and adopt new networking technologies earlier. They have been quietly outpacing the vendor community in innovation. Can aspects of their model be replicated by the rest of us? Absolutely, yes!
While each hyperscale datacenter is unique, design patterns have emerged that are applicable to a broader audience of network architects. Hyperscale networking has attributes that are very attractive to any data center architect:
Open Networking Switch Hardware:
High-performance white-box or brite-box switch hardware built with best of breed ASICs (such as Broadcom Trident-II/II+ and Tomahawk) Choice of hardware vendors reduces CapEx cost and enable more flexibility.
- Moves network intelligence into logically centralized “SDN Controllers” for management and control.
- Drives down management cost and increases access across the network.
Scale-out Pod Designs:
- Enables iterative innovation using Core and Pod designs in data center networking and centralized tool farms for monitoring infrastructure.
- Read the whitepaper on TAP & Tool sharing.
For more information about hyperscale networking, download our whitepaper: Hyperscale Networking for All with Big Cloud Fabric
Bringing Hyperscale-inspired Networking Innovations to Mainstream Data Centers
Big Switch Networks has adopted the same three hyperscale networking principles to deliver next-generation data center networking solutions for mainstream data centers:
- Big Cloud Fabric – next-generation data center switching solution
- Big Monitoring Fabric – next-generation visibility and security solution
Total Cost of Ownership (TCO) Benefits
With Big Switch SDN solutions, customers of any-scale data center experience significant CapEx and OpEx advantage as calculated in the ACG study.
Key Use Cases
Enterprise and service provider customers deploy Big Switch Solutions for specific deployment scenarios:
Big Cloud Fabric
- Physical networking for VMware Software Defined Data Center (SDDC)
- Physical and virtual networking for OpenStack private clouds and network function virtualization (NFV)
- Physical and virtual networking for Container environments
Big Monitoring Fabric
- Pervasive visibility and security across entire organization (data center, campus, remote locations)
- DMZ/Extranet security service chaining
- Monitoring of public cloud (e.g. AWS) and container workloads
Deployments in Existing Data Centers
Big Cloud Fabric is deployed on a pod-by-pod basis in an existing data center. BCF communicates with legacy networks via standards-based routing protocols. BCF also supports inter-pod and/or inter-DC connectivity via VXLAN based Layer-2 extension across Layer-3 core.
Big Monitoring Fabric enables monitoring of existing data centers built with traditional (box-by-box) networks as well as with modern SDN-based pods. Big Mon can monitor any workload (physical, VM, container) traffic and at any link speed (1G, 10G, 25G, 40G and 100G). Big Mon also allows monitoring of campus traffic and remote locations (such as collocated data centers and branch offices).