VMware NSX Edge节点在虚拟网络中扮演关键角色，通过网络虚拟化提升性能。本文详细测试NSX裸金属边缘节点在无服务运行时，4x100Gbps接口实现388Gbps南北流量吞吐，8节点集群达3Tbps。硬件选择需关注物理网卡、CPU核心数、内存传输速度及PCI插槽兼容性，本地存储优先。测试场景涵盖逻辑拓扑与硬件规格，建议调整环缓冲区大小、禁用流量控制和超线程以优化性能。

🌐 VMware NSX Edge节点通过网络虚拟化在虚拟网络中发挥关键作用，支持高吞吐量服务，对整个生态系统至关重要。

💻 测试显示，NSX裸金属边缘节点在无服务运行时，4x100Gbps接口可实现高达388Gbps的南北流量吞吐，8节点集群总吞吐量可达3Tbps。

🛠 硬件选择需重点考虑物理网卡带宽、CPU核心数（影响吞吐量）、内存传输速度（MT/s）及PCI插槽兼容性，优先使用本地存储并选择支持Ubuntu软件的存储控制器。

📊 性能测试基于特定逻辑拓扑和硬件配置，建议通过调整环缓冲区大小、禁用流量控制和超线程来优化NSX Edge性能。

🔧 优化措施包括增加环缓冲区至4096，默认禁用超线程和流量控制，以及启用流缓存，具体配置可参考官方文档。

Every cloud environment is rooted in virtualization and is defined by three pillars: network virtualization, server virtualization, and storage virtualization. The VMware NSX Edge Node plays an essential role in virtualizing networking and security services. The throughput supported by the NSX Edge Node is critical for the entire ecosystem and network services running on it.

In this blog, we outline NSX Bare Metal Edge performance for customers implementing Bare Metal Edge for their virtual networking infrastructure.  Using NSX Bare Metal Edge (with no services running) with 4x100Gbps interfaces, RFC2544 performance tests yielded a North-South throughput of up to 388 Gbps (97%-line rate) and up to 3 Tbps for the entire cluster (when using 8 Edge Nodes), providing significant throughput for North-South traffic in the virtual network infrastructure.

Please refer to VMware NSX Bare Metal Edge Performance white paper for more information on test and settings used to achieve these results.

Key Hardware Considerations for NSX Bare Metal Edge

The choice of hardware for the NSX Bare Metal Edge is driven by bandwidth requirements and the throughput you want to achieve. Key considerations include:

Physical NIC: Consider the bandwidth, connectivity, and resiliency requirements for the Bare Metal Edge.CPU: NSX Bare Metal Edge supports a broad list of processors from Intel and AMD. The major consideration for the CPU is the number of cores which can impact the throughput the NSX Edge can support.Memory: Selecting memory compatible with the CPU and higher transfer speed (MT/s or mega transfers per second) will influence the maximum throughput.PCI slots: When selecting servers, select servers from a generation that supports the PCI-E generation of NIC cards.Storage: Allocate appropriate disk space for your Bare Metal Edge. Local storage on the Bare Metal Edge is preferred. Also, the storage controller should be supported by the Bare Metal Edge Ubuntu software.

Test case scenario and topology

The performance tests were executed with a Bare Metal Edge in the following scenario:

1. Logical topology:

2. Test Scenario:

3. Achieved Throughput: 

 

4. Hardware specifications used for the above test:

 

NSX Version: 4.0.1.1.0.20598726

BM Edge version: 4.0.1.1.0.20598726

Ring-Buffer size is increased to 4096 for Tx and RX/Hyperthreading is disabled by default/Flow control is disabled.

For performance tuning, consider adjusting ring buffer size, disabling flow control and hyper threading, and enabling flow cache.  More information can be found in the linked document.

Conclusion and analysis:

This blog post outlines some key hardware considerations for maximizing the performance of the NSX Bare Metal Edge, especially for low latency and high throughput environments.

The RFC tests produced the following results:

A single Bare Metal Edge node can achieve speeds of up to 388Gbps for North-South trafficAn NSX Bare Metal Edge cluster can achieve up to 3Tbps for North-South traffic

For detailed study please refer to VMware NSX Bare Metal Edge Performance white paper .

Additional Resources:

Enhanced NSX Edge and Networking Services in NSX 4.0.1.1 blog.Announcing Networking and Advanced Security Enhancement in NSX 4.0.1.1 blogVMware NSX Bare Metal Edge Performance white paper

The post VMware NSX Bare Metal Edge Performance appeared first on Network and Security Virtualization.