Juniper Networks QFX5130-32CD

QFX5130 Switches offer a high-density, cost-optimized 1U, 400GbE fixed configuration ideal for data centers where cloud services are being added. These services require higher network bandwidth per rack, along with flexibility, making the 10/25/40/100/400GbE interface options ideal for server and intrafabric connectivity. The QFX5130 is an optimal choice for spine and leaf deployments in enterprise, service provider, and cloud provider data centers.

Organizations requiring scale-out networks to run applications dependent on sophisticated traffic handling with in-band telemetry and traffic steering based on the dynamic state will benefit from Juniper’s compact, value-based solution. Coupled with the widespread adoption of overlay technologies, the QFX5130 Switch lays a strong infrastructure foundation for your evolving business and network needs. With deployment versatility to multiple applications, from custom services delivery in provider networks to breakthrough AI applications and scientific research, the platform brings future-proof flexibility to your network investment.

The QFX5130 comes in one model:

• QFX5130-32CD: data center leaf or spine with 32 x 400GbE and 2 x 10GbE port

Product Description

The Juniper Networks QFX5130 Switch is a next-generation, fixed-configuration spine-and-leaf switch that offers flexible, cost-effective, high-density 400GbE, 100GbE, 50GbE, 40GbE, 25GbE, and 10GbE interfaces for server and intra-fabric connectivity.

A versatile, future-proofed solution for today’s data centers, the QFX5130 leverages the power of a fully programmable chipset to support and deliver a diverse set of use cases. It supports advanced Layer 2, Layer 3, and Ethernet VPN (EVPN)- Virtual Extensible LAN (VXLAN) features. For large public cloud providers—early adopters of high-performance servers to meet explosive workload growth—the QFX5130 supports very large, dense, and fast 400GbE IP fabrics based on proven Internet scale technology. For enterprise customers seeking investment protection, as they transition their server farms from 10GbE to 25GbE, the QFX5130 switch also provides a high radix-native 100GbE/400GbE EVPN-VXLAN spine option at reduced power and a smaller footprint.

The QFX5130 supports diverse use cases such as neural networks for AI applications, including autonomous driving, disaggregated storage, high-frequency trading, packet brokering, and over-the-top streaming services. Delivering 25.6 Tbps of bidirectional bandwidth, the switch is optimally designed for spine-and-leaf deployments in enterprise, high-performance computing (HPC), service providers, and cloud data centers.

The QFX5130-32CD offers 32 ports in a low-profile 1 U form factor. High-speed interfaces support a wide variety of port configurations, including 400GbE, 100GbE, 25GbE, 40GbE, and 10GbE. The QFX5130-32CD is equipped with two AC or DC power supplies, providing 1+1 redundancy when all power supplies are present. Six hot-swappable fans offer back-to-front (AFO) or front-to-back (AFI) airflow options, providing 5+1 redundancy.

The QFX5130 includes an Intel XeonD-1500 processor to drive the control plane, which runs the Junos OS Evolved operating system software.

Highlights

The QFX5130 includes the following capabilities. Please refer to the Specifications section for current shipping features.

• Native 400GbE Configuration
  The QFX5130-32CD offers 32 ports in a 1 U form factor. The high-speed ports support a wide variety of configurations, including 100GbE and 40GbE.
• High-Density Configurations
  The QFX5130 is optimized for high-density fabric deployments, providing options for 32 ports of 400GbE, 100GbE, or 40GbE.
• Flexible Connectivity Options
  The QFX5130 offers a choice of interface speeds for server and intra-fabric connectivity, providing deployment versatility and investment protection.

Key Product Differentiators

Increased Scale and Buffer
The QFX5130 provides enhanced scale with up to 1.24 million routes, 80,000 firewall filters, and 160,000 media access control (MAC) addresses. It supports high numbers of egress IPv4/ IPv6 rules by programming matches in egress ternary content addressable memory (TCAM) along with ingress TCAM.

132MB Shared Packet Buffer
Today’s cloud-native applications have a critical dependency on buffer size to prevent congestion and packet drops. The QFX5130 has a 132 MB shared packet buffer that is allocated dynamically to congested ports.

Programmability
The QFX5130 revolutionizes performance for data center networks by providing a programmable software-defined pipeline in addition to the comprehensive feature set provided in the Juniper Networks QFX5120 Switch line. The QFX5130 uses a compiler-driven switch data plane with full software program control to enable and serve a diverse set of use cases, including in-band telemetry, fine-grained filtering for traffic steering, traffic monitoring, and support for new protocol encapsulations.

Power Efficiency
With its low-power 7 nm process, the QFX5130 consumes a maximum of 973 W, bringing improvements in speed, less power consumption, and higher density on-chip.