Concept Guide

For example, instead of deploying an Ethernet network for LAN trac, include additional storage area networks (SANs) to ensure lossless
Fibre Channel trac, and a separate InniBand network for high-performance inter-processor computing within server clusters, only one
DCB-enabled network is required in a data center. The Dell EMC Networking switches that support a unied fabric and consolidate multiple
network infrastructures use a single input/output (I/O) device called a converged network adapter (CNA).
A CNA is a computer input/output device that combines the functionality of a host bus adapter (HBA) with a network interface controller
(NIC). Multiple adapters on dierent devices for several trac types are no longer required.
Data center bridging satises the needs of the following types of data center trac in a unied fabric:
Trac Description
LAN trac LAN trac consists of many ows that are insensitive to latency requirements, while certain applications, such as
streaming video, are more sensitive to latency. Ethernet functions as a best-eort network that may drop packets
in the case of network congestion. IP networks rely on transport protocols (for example, TCP) for reliable data
transmission with the associated cost of greater processing overhead and performance impact LAN trac consists
of a large number of ows that are generally insensitive to latency requirements, while certain applications, such as
streaming video, are more sensitive to latency. Ethernet functions as a best-eort network that may drop packets
in case of network congestion. IP networks rely on transport protocols (for example, TCP) for reliable data
transmission with the associated cost of greater processing overhead and performance impact.
Storage trac Storage trac based on Fibre Channel media uses the Small Computer System Interface (SCSI) protocol for data
transfer. This trac typically consists of large data packets with a payload of 2K bytes that cannot recover from
frame loss. To successfully transport storage trac, data center Ethernet must provide no-drop service with
lossless links.
InterProcess
Communication
(IPC) trac
InterProcess Communication (IPC) trac within high-performance computing clusters to share information. Server
trac is extremely sensitive to latency requirements.
To ensure lossless delivery and latency-sensitive scheduling of storage and service trac and I/O convergence of LAN, storage, and server
trac over a unied fabric, IEEE data center bridging adds the following extensions to a classical Ethernet network:
• 802.1Qbb — Priority-based Flow Control (PFC)
• 802.1Qaz — Enhanced Transmission Selection (ETS)
• 802.1Qau — Congestion Notication
• Data Center Bridging Exchange (DCBx) protocol
NOTE
: Dell EMC Networking OS supports only the PFC, ETS, and DCBx features in data center bridging.
Priority-Based Flow Control
In a data center network, priority-based ow control (PFC) manages large bursts of one trac type in multiprotocol links so that it does not
aect other trac types and no frames are lost due to congestion.
When PFC detects congestion on a queue for a specied priority, it sends a pause frame for the 802.1p priority trac to the transmitting
device. In this way, PFC ensures that PFC-enabled priority trac is not dropped by the switch.
PFC enhances the existing 802.3x pause and 802.1p priority capabilities to enable ow control based on 802.1p priorities (classes of
service). Instead of stopping all trac on a link (as performed by the traditional Ethernet pause mechanism), PFC pauses trac on a link
according to the 802.1p priority set on a trac type. You can create lossless ows for storage and server trac while allowing for loss in
case of LAN trac congestion on the same physical interface.
The following illustration shows how PFC handles trac congestion by pausing the transmission of incoming trac with dot1p priority 4.
Data Center Bridging (DCB)
277