Cisco Nexus 9300-FX Series Switches Cisco N9K-C93108TC-FX

Product overview

The Cisco Nexus^® 9300-FX Series switches belongs to the fixed Cisco Nexus 9000 platform based on Cisco Cloud Scale technology. The platform support cost-effective cloud-scale deployments, an increased number of endpoints, and cloud services with wire-rate security and telemetry. The platform is built on modern system architecture designed to provide high performance and meet the evolving needs of highly scalable data centers and growing enterprises.

Cisco Nexus 9300-FX series switches offer a variety of interface options to transparently migrate existing data centers from 100-Mbps, 1-Gbps, and 10-Gbps speeds to 25- Gbps at the server, and from 10- and 40-Gbps speeds to 50- and 100- Gbps at the aggregation layer. The platforms provide investment protection for customers, delivering large buffers, highly flexible Layer 2 and Layer 3 scalability, and performance to meet the changing needs of virtualized data centers and automated cloud environments.

Cisco provides two modes of operation for Cisco Nexus 9000 Series Switches. Organizations can use Cisco NX-OS Software to deploy the switches in standard Cisco Nexus switch environments (NX-OS mode). Organizations can also deploy the infrastructure that is ready to support the Cisco Application Centric Infrastructure (Cisco ACI^™) platform to take full advantage of an automated, policy-based, systems-management approach (ACI mode).

Cisco Nexus 9300-FX Series Switches

Cisco Nexus 93108TC-FX Switch is a 1RU switch that supports 2.16 Tbps of bandwidth and over 1.25bpps. The 48 10GBASE-T downlink ports on the 93108TC-FX can be configured to work as 100-Mbps, 1-Gbps, or 10-Gbps ports. The uplink can support up to six 40- and 100-Gbps ports, or a combination of 1-, 10-, 25-, 40, 50-, and 100-Gbps connectivity, offering flexible migration options.

Features and benefits

The Cisco Nexus 9300-FX series provide the following features and benefits:

● Architectural Flexibility

◦ Industry leading Software Defined Networking Solution Cisco ACI^™support.

◦ Support for standards based VXLAN EVPN fabrics, inclusive of hierarchical multi-site support (refer to VXLAN Network with MP-BGP EVPN Control Plane for more information).

◦ Three-tier BGP architectures, enabling horizontal, non-blocking IPv6 network fabrics at web-scale.

◦ Segment routing allows the network to forward Multiprotocol Label Switching (MPLS) packets and engineer traffic without Resource Reservation Protocol (RSVP) Traffic Engineering (TE). It provides a control-plane alternative for increased network scalability and virtualization.

◦ Comprehensive protocol support for Layer 3 (v4/v6) unicast and multicast routing protocol suites, including BGP, Open Shortest Path First (OSPF), Enhanced Interior Gateway Routing Protocol (EIGRP), Routing Information Protocol Version 2 (RIPv2), Protocol Independent Multicast Sparse Mode (PIM-SM), Source-Specific Multicast (SSM), and Multicast Source Discovery Protocol (MSDP).

● Extensive Programmability

◦ Day zero automation through Power On Auto Provisioning, drastically reducing provisioning time.

◦ Industry leading integrations for leading devops configuration management applications – Ansible, Chef, Puppet, SALT. Extensive Native YANG and industry standard OpenConfig model support through RESTCONF/NETCONF.

◦ Pervasive API’s for all switch CLI functions (JSON based RPC over HTTP/HTTPs).

● High Scalability, Flexibility, and Security

◦ Flexible forwarding tables support up to 2 million shared entries on FX models. Flexible use of TCAM space allows for custom definition of Access Control List (ACL) templates.

◦ IEEE 802.1ae MAC Security (MACsec) support on all ports of 9300-FX models with speed greater than or equal to 10-Gbps, allows traffic encryption at the physical layer and provides secure server, border leaf, and leaf-to-spine connectivity.

● Intelligent Buffer Management

◦ The platform offers Cisco’s innovative intelligent buffer management, that offers capability to distinguish mice and elephant flows and apply different queue management schemes to them based on their network forwarding requirements in the event of link congestion.

◦ Intelligent buffer management functions are:

◦ Approximate Fair Dropping (AFD) with Elephant trap (ETRAP). AFD distinguishes long-lived elephant flows from short-lived mice flows, by using ETRAP. AFD exempts mice flows from the dropping algorithm so that mice flows will get their fair share of bandwidth without being starved by bandwidth-hungry elephant flows. Also, AFD tracks elephant flows and subjects them to the AFD algorithm in the egress queue to grant them their fair share of bandwidth.

◦ ETRAP measures the byte counts of incoming flows and compares this against the user defined ETRAP threshold. After a flow crosses the threshold, it becomes an elephant flow.

◦ Dynamic Packet Prioritization (DPP) provides the capability of separating mice flows and elephant flows into two different queues so that buffer space can be allocated to them independently. Mice flows, sensitive to congestion and latency can take priority queue and avoid re-ordering that allows to elephant flows to take full link bandwidth.

● RDME over Converged Ethernet – RoCE Support

◦ Platform offers lossless transport for RDMA over Converged Ethernet with support of DCB protocols:

◦ Priority-based Flow Control – (PFC) to prevent drops in the network and pause frame propagation per priority class.

◦ Enhanced Transmission Selection – (ETS) to reserve bandwidth per priority class in network contention situation.

◦ Data Center Bridging Exchange Protocol – (DCBX) to discover and exchange priority and bandwidth information with end points.

◦ Platform also supports Explicit Congestion Notification – (ECN) that provides end-to-end notification per IP flow by marking packets that experienced congestion, without dropping traffic. The platform is capable to track ECN statistics of number of marked packet that have experienced congestion.

● LAN and SAN Convergence

◦ Fibre Channel and Fibre Channel over Ethernet (FCoE) N-Port Virtualization (NPV) support enables the network administrator to control domain IDs and points of management on a Fibre Channel network as it scales. This feature enables LAN and SAN converged networks on a lossless, reliable Ethernet network.

● Hardware and Software High Availability

◦ Virtual Port-Channel (vPC) technology provides Layer 2 multipathing through the elimination of Spanning Tree Protocol. It also enables fully utilized bisectional bandwidth and simplified Layer 2 logical topologies without the need to change the existing management and deployment models.

◦ The 64-way Equal-Cost MultiPath (ECMP) routing enables the use of Layer 3 fat-tree designs. This feature helps organizations prevent network bottlenecks, increase resiliency, and add capacity with little network disruption.

◦ Advanced reboot capabilities include hot and cold patching.

◦ The switches use hot-swappable Power-Supply Units (PSUs) and fans with N+1 redundancy.

● Purpose-Built Cisco NX-OS Software Operating System with Comprehensive, Proven Innovations

◦ Single binary image that supports every switch in the Cisco Nexus 9000 series, simplifying image management. The operating system is modular, with a dedicated process for each routing protocol: a design that isolates faults while increasing availability. In the event of a process failure, the process can be restarted without loss of state. The operating system supports hot and cold patching and online diagnostics.

◦ Data Center Network Manager (DCNM) is the network management platform for all NX-OS-enabled deployments, spanning new fabric architectures, IP Fabric for Media, and storage networking deployments for the Cisco Nexus^®-powered data center. Accelerate provisioning from days to minutes, and simplify deployments from day zero through day N. Reduce troubleshooting cycles with graphical operational visibility for topology, network fabric, and infrastructure. Eliminate configuration errors and automate ongoing change in a closed loop, with templated deployment models and configuration compliance alerting with automatic remediation. Real-time health summary for fabric, devices, and topology. Correlated visibility for fabric (underlay, overlay, virtual and physical endpoints), including compute visualization with VMware.

◦ Network traffic monitoring with Cisco Nexus Data Broker builds simple, scalable, and cost-effective network Test Access Points (TAPs) and Cisco Switched Port Analyzer (SPAN) aggregation for network traffic monitoring and analysis.

● Cisco Network Assurance Engine (NAE)

◦ Cisco NAE continuously verifies if the network infrastructure is operating as per policy intent and it leverages the power of mathematical models to reason on behalf of the operator in policy, configuration and dynamic state level. NAE can precisely indicate problems in the network, identify which application or part of network is impacted, root-cause the problem and suggest how to fix it. Its continuous verification approach transforms Day 2 Operations from reactive to proactive mode and it does so without using any packet data. NAE helps avoid outages by predicting the impact of changes, reducing network related IT incidents and shrinking the mean time to repair by up to 66%. NAE also helps assure network security and segmentation compliance. To learn more about NAE, visit https://www.cisco.com/c/en/us/products/data-center-analytics/network-assurance-engine/index.html.

Cisco Nexus 9300-FX Series Switch specifications

Table 3 lists the performance and scalability specifications for the Cisco Nexus 9300-FX series switches. (Check the software release notes for feature support information.)