SONiC decouples the network operating system from the underlying switching hardware, providing a common software foundation across multiple hardware platforms. Its database centric, micro-services architecture uses containerized services to manage configuration, operational state, routing, and hardware programming. This book explores the architecture and operational behavior of SONiC through the step-by-step configuration of a BGP EVPN data center fabric. It combines architectural explanations with practical configurations, database analysis, and lab-tested examples to show how SONiC builds and operates a modern data center network.

This book is all about VXLAN Fabric. It explains the Control Plane (BGP L2VPN EVPN and IPv4 MVPN) and VXLAN Data Plane operation in detail. It also explains how to implement multihoming (vPC, ESI), Firewall services, external connections (IPv4, MPLS), DCI Multi-Site among the other important things.

Modern Deep Learning models can be extremely large, often exceeding the memory capacity of a single GPU or CPU. In these cases, training must be distributed across multiple processors. This introduces the need for high-speed communication between GPUs—both within a single server and across multiple servers. Intra-node GPU communication typically relies on high-speed interconnects like NVLink, with Direct Memory Access operations enabling efficient data transfers between GPUs. Inter-node communication, however, depends on the backend network, either  InfiniBand or Ethernet-based. Synchronization of model parameters across GPUs places strict requirements on the network: high throughput, ultra-low latency, and zero packet loss. Achieving this in an Ethernet fabric is challenging but possible.   This is where datacenter networking meets Deep Learning. Understanding how GPUs communicate and what the network must deliver is essential for designing effective AI data center infrastructures.

A modern SD-WAN solution offers automated and secure device onboarding as well well as Centralized Management and Control Plane. It also supports multiple VPNs over a common underlay network as well as highly secure Direct Cloud/Internet Access and Application-Aware Routing.

This book tries to give a clear picture of how LISP Control-Plane used in Campus Fabric works. If you are considering implementing Campus Fabric, or if you are already done that, you might found this book valuable. Also, if you are preparing to network certification that includes LISP you might want to read this book.

This book explains various VXLAN Fabric models such as Single-ASN, Multi-ASN, Dual-ASN, and Hybrid-ASN. It also introduces L3-Only DCI with MPLS.