7300 Series | Platform Overview

Scaling Data Center Performance

The Arista 7300X Series delivers wire speed switching at later 2 and layer 3 to enable dramatically faster and simpler network designs for

data centers that lowers network capital and operational expenses. When used in conjunction with Arista 1G and 10G leaf switches and

Arista’s Multi-Chassis Link Aggregation (MLAG) technology, a pair of 7300X Switches can support over 12,000 Servers with a leaf and

spine active/active L2 network topology. A combination of 16 7300X in a spine at Layer 3 scales the network up to over 16K 10G Servers

in a fully non-blocking, low-latency, two-stage network that provides predictable and consistent application performance. The flexibility

of the L2 and L3 multi-path design options combined with support for open standards provides maximum flexibility, scalability and

network wide virtualization. Arista EOS advanced features provides control, and visibility with single point of management.

Dynamic Bu er Allocation

In cut-through mode, the Arista 7300X series switches forward packets with a latency of less than 2 usec. Upon congestion, the packets

are buffered in shared packet memory that has a total size of 12 Mbytes. Unlike other architectures that have fixed per-port packet

memory, the 7300X Series use Dynamic Buffer Allocation (DBA) to allocate up to 6MB of packet memory to a single port for lossless

forwarding.

Maximum Flexibility for Scale Out Network Designs

Scale out network designs enable solutions to start small and evolve over time. A simple two-way design can grow as wide as 64-way

without significant changes to the architecture. The 7300X Series include enhancements that allow for flexible scale-out designs:

• 64-way ECMP and 64-way MLAG to provide scalable designs and balance traffic evenly across large scale 2 tier leaf-spine designs

• Flow based FDLB architecture to balance large flows and dynamic packet buffering to absorb congestion from microbursts

• Flexible allocation of L2 and L3 forwarding table resources for more design choice

• Wide choice of dense 10GbE and 40GbE modules with broad range of optics and cables for multi-speed flexibility

• VXLAN routing, bridging and gateway for physical to virtualization communication to enable next generation data center designs

• DANZ, sFlow, and multi-port mirroring to detect micro-burst congestion and provide network wide visibility and monitoring

Arista Leaf-Spine Two-Tier and Spline One-Tier Network Architectures

Software De ned Cloud Networks

Arista Software Defined Cloud Networking (SDCN), combines the principles that have made cloud computing the unstoppable force

that it is: automation, self service provisioning, and linear scaling of both performance and economics coupled with the trend in

Software Defined Networking that delivers: network virtualization, custom programmability, simplified architectures, and lower capital

expenditure. This combination creates a best-in-class software foundation for maximizing the value of the network to both the

enterprise and service provider data center. A new architecture for the most mission-critical location within the IT infrastructure that

simplifies management and provisioning, speeds up service delivery, lowers costs and creates opportunities for competitive

differentiation, while putting control and visibility back in the hands of the network and systems administrators.

The Four Pillars of Arista's Software De ned Cloud Networking:

• Universal Cloud Network - scalable standards based MLAG at Layer 2, ECMP for Layer 3 and VXLAN for most flexibility

• Cloud Control - Standards based AEM, ZTP/ZTR, LANZ and DANZ

• Network Wide Virtualization - Multi-vendor API Support with eAPI, VXLAN and NSX, and other encapsulation techniques

• Network Applications and Automated Management - Network applications; single point of management and open - Openflow,

Openstack, OpenVirtualSwitch and OVSDB