Azure Stack HCI 的物理网络要求Physical network requirements for Azure Stack HCI

适用于 Azure Stack HCI 版本 20H2Applies to Azure Stack HCI, version 20H2

本主题讨论物理(结构)网络注意事项和 Azure Stack HCI 的要求,尤其是网络交换机。This topic discusses physical (fabric) network considerations and requirements for Azure Stack HCI, particularly for network switches.


未来 Azure Stack HCI 版本的要求可能会改变。Requirements for future Azure Stack HCI versions may change.

Azure Stack HCI 网络交换机Network switches for Azure Stack HCI

Microsoft 根据下面的“网络交换机要求”部分中标识的标准和协议测试 Azure Stack HCI。Microsoft tests Azure Stack HCI to the standards and protocols identified in the Network switch requirements section below. 虽然 Microsoft 不验证网络交换机,但我们确实会与供应商合作来识别支持 Azure Stack HCI 要求的设备。While Microsoft does not certify network switches, we do work with vendors to identify devices that support Azure Stack HCI requirements.

这些要求也已在 Windows 硬件兼容性计划规范和策略中发布。These requirements are also published in Windows Hardware Compatibility Program Specifications and Policies. 选择“下载规范和策略,版本 1809”,打开 ZIP 文件,打开“WHCP-Components-Peripherals-Specification-1809.pdf”,然后查看“Device.Network.Switch.SDDC”部分。Select Download Specifications and Policies, version 1809, open the ZIP file, open WHCP-Components-Peripherals-Specification-1809.pdf, then see the Device.Network.Switch.SDDC section.


尽管使用此处未列出的技术和协议的其他网络交换机可能有效,但我们无法保证它们将与 Azure Stack HCI 一起运行,并且可能无法帮助排查发生的问题。While other network switches using technologies and protocols not listed here may work, We cannot guarantee they will work with Azure Stack HCI and may be unable to assist in troubleshooting issues that occur.

购买网络交换机时,请与交换机供应商联系,确保设备满足所有 Azure Stack HCI 要求。When purchasing network switches, contact your switch vendor and ensure that the devices meet all Azure Stack HCI requirements. 以下供应商(按字母顺序排序)已确认其交换机支持 Azure Stack HCI 要求:The following vendors (in alphabetical order) have confirmed that their switches support Azure Stack HCI requirements:

VendorVendor 10 GbE10 GbE 25 GbE25 GbE 100 GbE100 GbE
DellDell S41xx 系列S41xx series S52xx 系列S52xx series S52xx 系列S52xx series
LenovoLenovo G8272NE1032G8272, NE1032 NE2572NE2572 NE10032NE10032


当网络交换机供应商就变更通知我们时,我们会更新此列表。We update this list as we are informed of changes by network switch vendors.

如果未包含交换机,请联系交换机供应商,确保交换机型号和交换机操作系统版本支持下一部分中的要求。If your switch is not included, contact your switch vendor to ensure your switch model and switch operating system version support the requirements in the next section.

网络交换机要求Network switch requirements

本部分列出了所有 Azure Stack HCI 部署中所使用的网络交换机必须遵循的行业标准。This section lists industry standards that are mandatory for network switches used in all Azure Stack HCI deployments. 这些标准有助于确保 Azure Stack HCI 群集部署中的节点之间的可靠通信。These standards help ensure reliable communications between nodes in Azure Stack HCI cluster deployments.


用于计算、存储和管理流量的网络适配器需要以太网。Network adapters used for compute, storage, and management traffic require Ethernet. 有关详细信息,请参阅主机网络要求For more information, see Host network requirements.

下面是必需的 IEEE 标准和规范:Here are the mandatory IEEE standards and specifications:

标准:IEEE 802.1QStandard: IEEE 802.1Q

以太网交换机必须符合定义 VLAN 的 IEEE 802.1Q 规范。Ethernet switches must comply with the IEEE 802.1Q specification that defines VLANs. Azure Stack HCI 的多个方面都需要 VLAN,并且所有场景下都需要 VLAN。VLANs are required for several aspects of Azure Stack HCI and are required in all scenarios.

标准:IEEE 802.1QbbStandard: IEEE 802.1Qbb

以太网交换机必须符合定义优先级流控制 (PFC) 的 IEEE 802.1Qbb 规范。Ethernet switches must comply with the IEEE 802.1Qbb specification that defines Priority Flow Control (PFC). 使用数据中心桥接 (DCB) 的情况下需要 PFC。PFC is required where Data Center Bridging (DCB) is used. 由于 DCB 可以在 RoCE 和 iWARP RDMA 场景中使用,因此所有场景中都需要 802.1Qbb。Since DCB can be used in both RoCE and iWARP RDMA scenarios, 802.1Qbb is required in all scenarios. 在不降低交换机功能或端口速度的情况下,至少需要三个服务等级 (CoS) 优先级。A minimum of three Class of Service (CoS) priorities are required without downgrading the switch capabilities or port speeds. 其中至少有一个通信类必须提供无损通信。At least one of these traffic classes must provide lossless communication.

标准:IEEE 802.1QazStandard: IEEE 802.1Qaz

以太网交换机必须符合定义增强传输选择 (ETS) 的 IEEE 802.1Qaz 规范。Ethernet switches must comply with the IEEE 802.1Qaz specification that defines Enhanced Transmission Select (ETS). 使用 DCB 时需要 ETS。ETS is required where DCB is used. 由于 DCB 可以在 RoCE 和 iWARP RDMA 场景中使用,因此所有场景中都需要 802.1Qaz。Since DCB can be used in both RoCE and iWARP RDMA scenarios, 802.1Qaz is required in all scenarios. 在不降低交换机功能或端口速度的情况下,至少需要三个 CoS 优先级。A minimum of three CoS priorities are required without downgrading the switch capabilities or port speed.


超聚合基础结构高度依赖于同一机架内的东-西向 2 层通信,因此需要 ETS。Hyper-converged infrastructure has a high reliance on East-West Layer-2 communication within the same rack and therefore requires ETS. 我们不使用区分服务代码点 (DSCP) 来测试 Azure Stack HCI。We do not test Azure Stack HCI with Differentiated Services Code Point (DSCP).

标准:IEEE 802.1ABStandard: IEEE 802.1AB

以太网交换机必须符合定义链接层发现协议 (LLDP) 的 IEEE 802.1AB 规范。Ethernet switches must comply with the IEEE 802.1AB specification that defines the Link Layer Discovery Protocol (LLDP). Azure Stack HCI 需要 LLDP,并支持物理网络配置故障排除。LLDP is required for Azure Stack HCI and enables troubleshooting of physical networking configurations.

必须动态启用 LLDP Type-Length-Value (TLV) 配置。Configuration of the LLDP Type-Length-Values (TLVs) must be dynamically enabled. 除了启用特定 TLV 以外,交换机不得要求额外配置。Switches must not require additional configuration beyond enablement of a specific TLV. 例如,启用 802.1 子类型 3 应会自动播发交换机端口上所有可用的 VLAN。For example, enabling 802.1 Subtype 3 should automatically advertise all VLANs available on switch ports.

自定义 TLV 要求Custom TLV requirements

LLDP 使组织可定义并编码自己的自定义 TLV。LLDP allows organizations to define and encode their own custom TLVs. 这些称为组织特定的 TLV。These are called Organizationally Specific TLVs. 所有组织特定的 TLV 都以 LLDP TLV 类型值 127 开始。All Organizationally Specific TLVs start with an LLDP TLV Type value of 127. 下表显示了哪些组织特定的自定义 TLV(TLV 类型 127)子类型是必需的:The following table shows which Organizationally Specific Custom TLV (TLV Type 127) subtypes are required:

所需版本Version required 组织Organization TLV 子类型TLV Subtype
20H2 及更高版本20H2 and later IEEE 802.1IEEE 802.1 VLAN 名称(子类型 = 3)VLAN Name (Subtype = 3)
20H2 及更高版本20H2 and later IEEE 802.3IEEE 802.3 最大帧大小(子类型 = 4)Maximum Frame Size (Subtype = 4)

网络流量和体系结构Network traffic and architecture

本部分主要针对网络管理员。This section is predominantly for network administrators.

Azure Stack HCI 可在各种数据中心体系结构中运行,包括 2 层(叶脊)和 3 层(核心聚合访问)。Azure Stack HCI can function in various data center architectures including 2-tier (Spine-Leaf) and 3-tier (Core-Aggregation-Access). 本部分详细介绍了叶脊拓扑中的概念,该拓扑通常用于超聚合基础结构中的工作负载,如 Azure Stack HCI。This section refers more to concepts from the Spine-Leaf topology that is commonly used with workloads in hyper-converged infrastructure such as Azure Stack HCI.

网络模型Network models

网络流量可以按其方向进行分类。Network traffic can be classified by its direction. 传统存储区域网络 (SAN) 环境主要是北-南向,其中流量从计算层跨 3 层 (IP) 边界流向存储层。Traditional Storage Area Network (SAN) environments are heavily North-South where traffic flows from a compute tier to a storage tier across a Layer-3 (IP) boundary. 超聚合基础结构主要是东-西向,其中很大一部分流量停留在 2 层 (VLAN) 边界内。Hyperconverged infrastructure is more heavily East-West where a substantial portion of traffic stays within a Layer-2 (VLAN) boundary.


强烈建议站点中的所有群集节点都位于同一机架上,并连接到同一架顶式 (ToR) 交换机。We highly recommend that all cluster nodes in a site are physically located in the same rack and connected to the same top-of-rack (ToR) switches.

Azure Stack HCI 北-南向流量North-South traffic for Azure Stack HCI

北-南向流量具有以下特征:North-South traffic has the following characteristics:

  • 流量从 ToR 交换机流向脊或从脊流向 ToR 交换机Traffic flows out of a ToR switch to the spine or in from the spine to a ToR switch
  • 流量离开物理机架或跨越 3 层边界 (IP)Traffic leaves the physical rack or crosses a Layer-3 boundary (IP)
  • 包括管理(PowerShell、Windows Admin Center)、计算 (VM) 和站点间拉伸群集流量Includes management (PowerShell, Windows Admin Center), compute (VM), and inter-site stretched cluster traffic
  • 使用以太网交换机连接到物理网络Uses an Ethernet switch for connectivity to the physical network

Azure Stack HCI 东-西向流量East-West traffic for Azure Stack HCI

东-西向流量具有以下特征:East-West traffic has the following characteristics:

  • 流量保留在 ToR 交换机和 2 层边界 (VLAN) 内Traffic remains within the ToR switches and Layer-2 boundary (VLAN)
  • 包括同一群集和(如果使用拉伸群集)同一站点中节点之间的存储流量或实时迁移流量Includes storage traffic or Live Migration traffic between nodes in the same cluster and (if using a stretched cluster) within the same site
  • 可以使用以太网交换机(交换机式)或直接(无交换机)连接,如接下来的两部分所述。May use an Ethernet switch (switched) or a direct (switchless) connection, as described in the next two sections.

使用交换机Using switches

北-南向流量需要使用交换机。North-South traffic requires the use of switches. 除了使用支持 Azure Stack HCI 所需协议的以太网交换机,最重要的方面是正确调整网络结构大小。Besides using an Ethernet switch that supports the required protocols for Azure Stack HCI, the most important aspect is the proper sizing of the network fabric.

必须了解以太网交换机可以支持的“非阻止”结构带宽,并将网络的超额订阅降至最低(或最好消除)。It is imperative to understand the "non-blocking" fabric bandwidth that your Ethernet switches can support and that you minimize (or preferably eliminate) oversubscription of the network.

可以通过正确使用子网和 VLAN 来消除常见的拥塞点和超额订阅,如用于路径冗余的多底盘链路聚合组Common congestion points and oversubscription, such as the Multi-Chassis Link Aggregation Group used for path redundancy, can be eliminated through proper use of subnets and VLANs. 另请参阅主机网络要求Also see Host network requirements.

与你的网络供应商或网络支持团队协作,确保网络交换机已根据要运行的工作负载适当调整大小。Work with your network vendor or network support team to ensure your network switches have been properly sized for the workload you are intending to run.

使用无交换机Using switchless

只要群集中的每个节点都与群集中的每个节点建立冗余连接,Azure Stack HCI 就支持所有群集大小东-西向流量的无交换机(直接)连接。Azure Stack HCI supports switchless (direct) connections for East-West traffic for all cluster sizes so long as each node in the cluster has a redundant connection to every node in the cluster. 这称为“交错”连接。This is called a "full-mesh" connection.


由于所需的网络适配器数,当群集大于 3 个节点时,无交换机部署的好处就会减少。The benefits of switchless deployments diminish with clusters larger than three-nodes due to the number of network adapters required.

无交换机连接的优点Advantages of switchless connections

  • 对于东-西向流量,无需购买交换机。No switch purchase is necessary for East-West traffic. 北-南向流量需要交换机。A switch is required for North-South traffic. 这可能会导致资本支出 (CAPEX) 成本降低,但具体取决于群集中的节点数。This may result in lower capital expenditure (CAPEX) costs but is dependent on the number of nodes in the cluster.
  • 由于没有交换机,因此配置仅限于主机,这可能会减少所需的潜在配置步骤数。Because there is no switch, configuration is limited to the host, which may reduce the potential number of configuration steps needed. 当群集大小增加时,此值会减小。This value diminishes as the cluster size increases.

无交换机连接的缺点Disadvantages of switchless connections

  • 随着群集中节点数的增长,网络适配器的成本可能会超过使用网络交换机的成本。As the number of nodes in the cluster grows, the cost of network adapters could exceed the cost of using network switches.
  • IP 和子网寻址方案需要进行更多规划。More planning is required for IP and subnet addressing schemes.
  • 仅提供本地存储访问。Provides only local storage access. VM 流量、管理流量和需要北-南向访问的其他流量不能使用这些适配器。VM traffic, management traffic, and other traffic requiring North-South access cannot use these adapters.
  • 通常不能扩展到超过三个节点的群集。Generally does not scale well beyond three-node clusters.

后续步骤Next steps