Consolidation of LAN and SAN data center networks based on DCB and FCoE protocols

    The purpose of this article is to give the reader a basic understanding of the technologies that made it possible to integrate the two Ethernet networks and Fiber Channel (FC). These networks have been built in parallel for many years and are independently maintained. The Data Center Bridging (DCB) and Fiber Channel over Ethernet (FCoE) protocols combine the functions of both on a single set of equipment, which saves the capital and operational costs of the data center infrastructure.

    Ethernet is without a doubt the most popular networking technology to date. During the existence of Ethernet, the maximum data transfer rate has increased from 10 Mbit / s to 100 Gbit / s. Ethernet has ousted many other protocols from the market due to its simplicity, low cost and widespread support by the network industry. In Ethernet networks, data transmission losses are permissible, which is categorically unacceptable for Fiber Channel networks. DCB is an Ethernet “enhancement” technology that provides lossless data transport. FCoE - FC transport protocol over “enhanced” Ethernet.

    Although DCB and FCoE are used together to build a complete solution, these are two different technologies, and we will consider them separately

    Data Center Bridging Technology (DCB)

    What is required of Ethernet to ensure its applicability for FC transport? This issue has been the subject of close attention of the network industry and the development of standards over the years, and several terms have appeared to refer to a set of Ethernet enhancements for data center needs:
    • CEE (Converged Enhanced Ethernet) - a term proposed by IBM and actively used as part of the standardization process Channel over Ethernet Fibre
    • DCB (Data Center Bridging) - the term used in the process of standardizing the various improvements to Ethernet organization committee IEEE
    • DCE (Data Center Ethernet) - a term used to train Cisco Achen Ethernet architecture for a new generation of data center tasks.

    To refer to “enhanced Ethernet”, the term Data Center Bridging will be used later in the article.

    The main components of the Data Center Bridging solution include:
    • Providing lossless transport (lossless Ethernet). To do this, two conditions must be met:
    o The internal architecture of the switch must ensure lossless data switching . In particular, on Cisco Nexus switches, this is achieved using the VOQ (Virtual Output Queuing) concept , which provides for data transmission through the switching matrix to the output port only if it is able to receive this data

    • There must be mechanismsflow control , which will not allow sending more information of this type to the network than the network can transmit at a particular point in time (similar to what is provided in Fiber Channel networks thanks to the Buffer-to-buffer Credits mechanism). In DCB, a PFC (Priority-based Flow Control, IEEE 802.1Qbb) flow control mechanism was created that functions separately for each traffic class and allows you to pause storage network data transfer without affecting control data and client-server sessions. Lane managementavailable to different types of traffic. This is necessary in order to determine the levels of service provided for different types of traffic in a consolidated network, and thereby make it possible to transfer them together without compromising quality. This problem is solved in the DCB architecture using the ETS (Enhanced Transmission Selection, IEEE 802.1Qaz) mechanism.
    Automatically detect settingsinteracting devices. This is necessary to automatically ensure consistent flow control and dedicated bandwidth settings for different types of traffic, the logical state of the "virtual bands", etc., as well as to determine whether the communicating device supports DCB functions, i.e. defining the DCB “domain” boundary within an Ethernet network The DCBX (Data Center Bridging Exchange) protocol developed by IEEE 802.1Qaz solves this problem.

    Fiber Channel over Ethernet (FCoE) Technology

    Fiber Channel protocol information is transmitted via the “improved” Ethernet in the FCoE architecture with full preservation of the Fiber Channel frame structure - Fiber Channel frames are equipped with additional headers and are placed inside Ethernet frames.
    It should be noted that the requirement for the transmission (encapsulation) of Fiber Channel frames implies two significant additional requirements for FCoE DCB transport:
    Support for large Ethernet frames . Since the maximum size of a Fiber Channel frame exceeds 2 kilobytes, it cannot be encapsulated in a standard Ethernet frame up to 1518 bytes in size, so larger frames, the so-called jumbo frames, are required to transmit Fiber Channel over Ethernet.

    Work at a speed of 10 Gbit / s and higher . Modern servers, as a rule, are connected to the storage network at a speed of 4-8 Gbit / s, therefore, of course, we cannot use speeds of 1 Gbit / s or lower for consolidated transport.

    To date, FCoE together with DCB are widely used, especially at the level of connecting servers to the data center network, allowing you to halve the number of network adapters and switches, and reduce cable infrastructure. I / O consolidation technology is an effective way to reduce the cost of creating and operating a data center, increasing the flexibility and speed of deployment of new services.

    Additional Resources:
    Cisco Data Center Switches Cisco Data Center

    Also popular now: