H19-402_V1.0 HCSP-Presales-Data Center Network Planning and Design V1.0 Questions and Answers

Comprehensive and Detailed 150 to 200 words of Explanation From Huawei data center:

Huawei data center materials describe a high-performance network using core technical indicators such as high throughput, low latency, and zero packet loss . These are the actual network characteristics used to evaluate whether a data center fabric can efficiently support AI computing, storage traffic, and east-west service communication. In Huawei’s intelligent lossless network design, the purpose is to build a fabric that forwards traffic at high speed, minimizes delay, and prevents packet loss under heavy load.

By contrast, Higher GPU computing power is not a direct network characteristic. It is an effect or business benefit that can result when the network performs well. Huawei explains that intelligent lossless networking improves AI cluster efficiency and helps computing resources operate more effectively, but GPU power itself belongs to the computing layer, not the network feature set. The network supports better GPU utilization; it does not define GPU computing power as one of its own characteristics.

Therefore, the correct answer is B .

In Huawei M-LAG design, strict requirements ensure stability and consistency between the two participating devices. Option A is false because M-LAG must be established between devices of the same type and model (or at least fully compatible models) . This ensures consistent forwarding behavior, synchronization of MAC/ARP tables, and proper operation of the peer-link and keepalive mechanisms. Using different device types is not supported and may lead to instability.

Option B is correct : unidirectional isolation is relevant only for dual-homed scenarios. If a device is single-homed, this mechanism is not applied.

Option C is correct : the peer-link is a critical connection between M-LAG peers and is typically configured as an Eth-Trunk (link aggregation) to ensure high bandwidth and redundancy.

Option D is also correct : peer-link interfaces are dedicated and cannot be used for other services, ensuring reliable synchronization and control-plane communication.

Huawei best practices emphasize homogeneous device deployment for M-LAG to guarantee predictable and stable operation.

Huawei iMaster NCE-Fabric supports both in-band and out-of-band deployment modes, each with distinct characteristics.

In in-band deployment (A, B) :

The management traffic shares the service network , meaning no separate management network is required.

The controller communicates with device management IPs over the service (data) network .

Redundant links can be configured to ensure high reliability and avoid single points of failure.

Therefore, A and B are correct descriptions .

Option C is false because it incorrectly states that the management and service networks are isolated in in-band mode. In reality, they are NOT isolated —they share the same physical infrastructure, which is a defining feature of in-band deployment.

In out-of-band deployment (D) :

A separate management network is used.

iMaster NCE-Fabric connects to devices via dedicated management interfaces through a management switch , ensuring isolation from service traffic.

Huawei recommends choosing deployment mode based on network scale, security, and reliability requirements .

Therefore, the correct answer is C .

In Huawei CloudFabric and cloud platform architectures (such as those integrated with ManageOne and OpenStack ), the concept of a tenant is used to logically isolate resources such as network, compute, and storage . It is correct that one department can be treated as a tenant , and an enterprise can have multiple tenants representing different departments or business units.

However, the statement is false because it incorrectly claims that the entire enterprise data center can be managed by one tenant administrator . In Huawei’s design:

Each tenant has its own administrator , responsible only for that tenant’s resources.

A higher-level role, such as a cloud administrator or system administrator , manages the entire data center infrastructure across all tenants.

This separation ensures:

Multi-tenancy isolation

Security and access control

Clear responsibility boundaries

Huawei emphasizes role-based access control (RBAC) , where tenant admins cannot manage resources belonging to other tenants or the entire infrastructure.

Therefore, the correct answer is FALSE .

In Huawei networking, Eth-Trunk (link aggregation) can operate in two modes: manual mode and LACP mode . In manual mode , the Eth-Trunk is statically configured by the administrator, and member interfaces are manually added without using the Link Aggregation Control Protocol (LACP) .

In this mode, all member links that are up are considered active by default , and they simultaneously participate in traffic forwarding and load balancing . Traffic distribution is typically based on hash algorithms (e.g., source/destination MAC or IP), ensuring efficient utilization of available bandwidth.

Unlike LACP mode, manual mode does not perform dynamic negotiation or link state detection between devices. Therefore, it requires consistent configuration on both ends to avoid issues such as loops or traffic blackholing. However, it is simpler and can be useful in controlled environments.

In Huawei data center designs, especially in M-LAG scenarios , LACP is generally preferred for better reliability and fault detection. Still, the statement accurately describes manual mode behavior.

Therefore, the statement is TRUE .

Huawei M-LAG 2.0 is designed to provide ultra-fast convergence and high availability in modern data center networks. One of its key enhancements over traditional M-LAG implementations is the ability to achieve fast fault detection and rapid switchover , minimizing service interruption.

In the event of a single point of failure (such as link or device failure), M-LAG 2.0 leverages mechanisms like BFD (Bidirectional Forwarding Detection) and optimized peer-link synchronization to quickly detect failures and redirect traffic. The switchover time is typically around 5 milliseconds , ensuring near hitless failover for critical services.

This ultra-fast convergence is particularly important for applications such as AI workloads, financial systems, and real-time services , where even small delays can impact performance.

Compared to traditional technologies (which may take tens or hundreds of milliseconds), Huawei M-LAG 2.0 significantly improves network reliability, service continuity, and user experience .

Therefore, the correct answer is C (5 ms) .

In Huawei data center and network security architecture, native encryption support is a key differentiator between tunneling technologies and secure communication protocols.

SSL VPN (C) and IPsec VPN (D) both provide built-in encryption mechanisms . SSL VPN uses TLS/SSL protocols to encrypt application-layer traffic, making it suitable for secure remote access. IPsec VPN operates at the network layer and provides confidentiality, integrity, and authentication through protocols such as ESP (Encapsulating Security Payload), making it widely used for site-to-site and data center interconnection security.

On the other hand, VXLAN (A) and GRE (B) are encapsulation/tunneling technologies that do not inherently provide encryption. VXLAN is used for overlay networking (e.g., tenant isolation in CloudFabric), while GRE is used for simple tunneling across IP networks. Both require additional security mechanisms (such as IPsec) if encryption is needed.

Huawei CloudFabric design guidelines clearly separate overlay encapsulation (VXLAN) from security protocols (IPsec/SSL) , emphasizing that encryption must be implemented using dedicated security technologies.

Therefore, the correct answers are C and D .

Huawei data center design documents clearly state that overlay networks (typically based on VXLAN EVPN) are highly versatile and support multiple application scenarios across modern and traditional environments.

In private cloud scenarios , overlay networks enable resource pooling and seamless data center interconnection, allowing flexible workload migration and multi-tenant isolation. For traditional IDC hosting services , overlays provide improved scalability and tenant isolation compared to VLAN-based designs, making them suitable for legacy-to-cloud evolution.

In public cloud environments (IaaS/PaaS/SaaS) , overlay networks are essential for large-scale multi-tenancy, enabling logical network segmentation, automation, and elastic service provisioning. Similarly, in NFV cloud scenarios , overlays integrate with SDN and NFV architectures to support virtualized network functions, service chaining, and dynamic service deployment.

Huawei CloudFabric emphasizes that overlay technology is not limited to a single use case but is a foundational technology across all modern data center architectures. Therefore, all listed options are valid application scenarios.

Huawei’s AI Fabric solution is designed to build a unified, intelligent lossless data center network by integrating traditionally separate network infrastructures into a single converged Ethernet-based fabric.

The three integrated networks are:

Computing network (C): Handles east-west traffic between compute nodes (e.g., AI training clusters, GPU servers).

Storage network (B): Supports high-throughput, low-latency storage access (e.g., distributed storage systems like HDFS or Ceph).

Ethernet network (D): Provides the underlying IP-based transport, enabling unified connectivity and scalability.

Traditionally, InfiniBand (IB) networks were used for high-performance computing due to their low latency and RDMA capabilities. However, Huawei AI Fabric replaces IB with lossless Ethernet (RoCE-based) solutions, allowing all services (compute + storage + management) to run over a single Ethernet fabric .

This convergence reduces:

Network complexity

Capital and operational costs

Management overhead

While improving:

Resource utilization

Scalability

Automation

Therefore, the correct three networks are Storage, Computing, and Ethernet , making B, C, and D correct .

In Huawei CloudFabric architecture, the underlay network is the physical IP fabric, while the overlay network is a logical network built on top of it using technologies like VXLAN and BGP EVPN .

Option A is false because the overlay network does not require bare optical fibers . It operates independently of the physical medium and can run over any IP-based underlay (Ethernet, optical, etc.). The overlay abstracts the physical infrastructure.

Option B is correct : the underlay network is transparent to endpoints (servers, firewalls, routers). These devices only interact with the overlay and are unaware of the underlying transport.

Option C is correct : the overlay has its own forwarding plane (VXLAN encapsulation) and control plane (BGP EVPN) , enabling scalable and automated network virtualization.

Option D is correct : the overlay is a logical network built over the underlay , providing tenant isolation and flexible service deployment.

Huawei best practices emphasize decoupling overlay from underlay , ensuring flexibility, scalability, and simplified operations.

Therefore, the correct answer is A .

In Huawei CloudFabric and modern data center architectures, the underlay and overlay networks are designed as independent layers with clear separation of responsibilities. The underlay network provides basic IP connectivity using standard Layer 3 routing (commonly using protocols such as OSPF, IS-IS, or even static routing), ensuring reliable transport between network devices.

The overlay network, typically implemented using VXLAN with BGP EVPN as the control plane, builds logical Layer 2/Layer 3 services on top of the underlay. Importantly, the overlay does not require the same routing protocol as the underlay. This independence allows flexible design, scalability, and easier evolution of services without modifying the physical infrastructure.

Option A is correct because endpoints (servers, VAS devices) are unaware of the underlay—they only interact with the overlay. Option C is correct as VXLAN is the mainstream overlay encapsulation technology. Option D correctly defines the overlay as a logical abstraction over the physical network.

Thus, statement B is false because Huawei explicitly supports different protocols between underlay and overlay layers.

In Huawei CloudFabric and VXLAN-based overlay networking, the overlay provides abstraction, flexibility, and scalability by decoupling logical services from the physical infrastructure. NVEs (Network Virtualization Edge nodes) can indeed be deployed on physical switches (such as leaf switches), which is a fundamental capability of hardware-based VXLAN fabrics. Additionally, overlay networks are designed to meet the needs of private cloud environments, offering high performance, simplified O & M, and enhanced security through network segmentation (e.g., VXLAN VNIs).

Overlay networks also support access for both virtual machines and physical servers, ensuring consistent connectivity regardless of workload type.

However, statement D is incorrect. In Huawei’s architecture, especially with BGP EVPN-based VXLAN, the control plane is distributed rather than relying on a controller to synchronously deliver flow tables. Devices dynamically learn and exchange forwarding information using EVPN. Even in SDN-based scenarios with iMaster NCE-Fabric, policy delivery is not strictly synchronous flow table pushing in the traditional sense (like OpenFlow).

Therefore, “controller delivers flow tables synchronously” is not a standard capability of Huawei overlay networks, making option D incorrect.

In Huawei CloudFabric design, M-LAG (Multi-Chassis Link Aggregation) is widely used to provide active-active forwarding and high availability at the access and border layers. When border leaf nodes are deployed in an M-LAG pair, they typically connect to upstream PE (Provider Edge) devices in a dual-homing (square topology) manner, ensuring both link-level and device-level redundancy.

However, Huawei design guidelines clearly state that an interconnection link (commonly called a peer-link or bypass link) between M-LAG devices is mandatory. This link is essential for synchronization of forwarding states, MAC address tables, ARP/ND entries, and control plane information between the two devices. It also ensures proper traffic forwarding in failure scenarios, such as when one device loses its uplinks but remains operational.

Without this peer-link, traffic consistency and loop prevention mechanisms cannot function correctly, leading to potential traffic loss or loops. Therefore, even in dual-egress scenarios with PE devices, the bypass/peer link is still required.

Hence, the statement is FALSE.

Huawei’s data center design guidelines emphasize that spine-leaf architecture is a flattened, two-layer fabric designed to overcome the limitations of traditional three-tier networks. One of its key advantages is low and predictable oversubscription ratios , achieved through equal-cost multi-path (ECMP) forwarding and uniform link distribution.

Option A is correct as an advantage because spine-leaf enables resource pooling across zones , eliminating isolated silos and improving utilization. Option C is also a core benefit: the architecture provides high reliability, redundancy, and scalable east-west traffic capacity , which is critical for cloud and distributed applications. Option D reflects the fundamental design principle where each leaf connects to multiple spine switches , ensuring full-mesh reachability and consistent latency.

However, Option B states that the architecture has a high oversubscription ratio , which contradicts Huawei best practices. In fact, spine-leaf is specifically designed to minimize oversubscription , ensuring balanced traffic and predictable performance.

Therefore, B is not an advantage , making it the correct answer.

In Huawei CloudFabric architecture, the underlay network is the physical IP network that provides basic connectivity and routing reachability for overlay services such as VXLAN.

Option A is correct : the underlay acts as the bearer (transport) network for VXLAN traffic, carrying encapsulated packets between VTEPs.

Option B is correct : the underlay includes both NVE (Network Virtualization Edge) devices that perform VXLAN encapsulation/decapsulation and standard IP forwarding devices (e.g., spine switches).

Option C is correct : the underlay has its own independent control plane , typically using IGP (OSPF/IS-IS) or BGP (EBGP) , and operates independently from the overlay (EVPN).

Option D is false because the underlay network is fundamentally responsible for Layer 3 IP reachability between VTEPs. Without proper L3 routing in the underlay, VXLAN tunnels cannot be established.

Huawei best practices emphasize a simple, stable, and highly reliable underlay , as it is the foundation for all overlay services.

Therefore, the correct answer is D .