Setup Guide

Configuring Priority-Based Flow Control
Priority-Based Flow Control (PFC) provides a flow control mechanism based on the 802.1p priorities in converged Ethernet traffic
received on an interface and is enabled by default when you enable DCB.
As an enhancement to the existing Ethernet pause mechanism, PFC stops traffic transmission for specified priorities (Class of Service
(CoS) values) without impacting other priority classes. Different traffic types are assigned to different priority classes.
When traffic congestion occurs, PFC sends a pause frame to a peer device with the CoS priority values of the traffic that is to be
stopped. Data Center Bridging Exchange protocol (DCBx) provides the link-level exchange of PFC parameters between peer devices. PFC
allows network administrators to create zero-loss links for Storage Area Network (SAN) traffic that requires no-drop service, while
retaining packet-drop congestion management for Local Area Network (LAN) traffic.
To configure PFC, follow these steps:
1. Create a DCB Map.
CONFIGURATION mode
dcb-map dcb-map-name
The dcb-map-name variable can have a maximum of 32 characters.
2. Create a PFC group.
CONFIGURATION mode
priority-group group-num {bandwidth bandwidth | strict-priority} pfc on
The range for priority group is from 0 to 7.
Set the bandwidth in percentage. The percentage range is from 1 to 100% in units of 1%.
Committed and peak bandwidth is in megabits per second. The range is from 0 to 40000.
Committed and peak burst size is in kilobytes. Default is 50. The range is from 0 to 40000.
The pfc on command enables priority-based flow control.
3. Specify the dot1p priority-to-priority group mapping for each priority.
priority-pgid dot1p0_group_num dot1p1_group_num ...dot1p7_group_num
Priority group range is from 0 to 7. All priorities that map to the same queue must be in the same priority group.
Leave a space between each priority group number. For example: priority-pgid 0 0 0 1 2 4 4 4 in which priority group 0 maps to dot1p
priorities 0, 1, and 2; priority group 1 maps to dot1p priority 3; priority group 2 maps to dot1p priority 4; priority group 4 maps to dot1p
priorities 5, 6, and 7.
Dell EMC Networking OS Behavior: As soon as you apply a DCB policy with PFC enabled on an interface, DCBx starts exchanging
information with PFC-enabled peers. The IEEE802.1Qbb and CEE versions of PFC Type, Length, Value (TLV) are supported. DCBx also
validates PFC configurations that are received in TLVs from peer devices.
NOTE:
You cannot enable PFC and link-level flow control at the same time on an interface.
Configuring Lossless Queues
DCB also supports the manual configuration of lossless queues on an interface when PFC mode is turned off.
Prerequisite: A DCB with PFC configuration is applied to the interface with the following conditions:
• PFC mode is off (no pfc mode on).
• No PFC priority classes are configured (no pfc priority priority-range).
Example:
Port A —> Port B
Port C —> Port B
PFC no-drop queues are configured for queues 3, 4 on Port B. PFC capability is enabled on priorities 3, 4 on PORT A and C.
Port B acting as Egress
During the congestion, [traffic pump on priorities 3 and 4 from PORT A and PORT C is at full line rate], PORT A and C send out the PFCs
to rate the traffic limit. Egress drops are not observed on Port B since traffic flow on priorities is mapped to loss less queues.
Port B acting as Ingress
If the traffic congestion is on PORT B , Egress DROP is on PORT A or C, as the PFC is not enabled on PORT B.
Data Center Bridging (DCB)
241