Administrator Guide

As soon as you apply a DCB map with PFC enabled on an interface, DCBx starts exchanging information with a peer. The IEEE802.1Qbb,
CEE and CIN versions of PFC TLV are supported. DCBx also validates PFC configurations that are received in TLVs from peer devices. By
applying a DCB map with PFC enabled, you enable PFC operations on ingress port traffic. To achieve complete lossless handling of traffic,
configure PFC priorities on all DCB egress ports.
NOTE: DCB maps are supported only on physical Ethernet interfaces.
•
To remove a DCB map, including the PFC configuration it contains, use the no dcb map command in Interface configuration mode.
• To disable PFC operation on an interface, use the no pfc mode on command in DCB-Map configuration mode.
• Traffic may be interrupted when you reconfigure PFC no-drop priorities in a DCB map or re-apply the DCB map to an interface.
• For PFC to be applied, the configured priority traffic must be supported by a PFC peer (as detected by DCBx).
• If you apply a DCB map with PFC disabled (pfc off), you can enable link-level flow control on the interface using the
flowcontrol rx on tx on command. To delete the DCB map, first disable link-level flow control. PFC is then automatically
enabled on the interface because an interface is PFC-enabled by default, when DCB is enabled.
• To ensure no-drop handling of lossless traffic, PFC allows you to configure lossless queues on a port (see Configuring Lossless
Queues).
• When you configure a DCB map with more than the maximum lossless queues configured, an error message is displayed if the PFC
dot1p priorities result in more than two lossless queues.
• When you apply a DCB map, an error message is displayed if link-level flow control is already enabled on an interface. You cannot
enable PFC and link-level flow control at the same time on an interface.
• Configure all the backplane ports of the linecards and RPM0 and RPM1 with same dcb-map configuration.
dcb-map linecard 0 backplane all name
dcb-map linecard all backplane all name
• Dell Networking OS allows you to change the default dot1p priority-queue assignments only if the change satisfies the following
requirements in DCB maps already applied to the interfaces:
• All 802.1p priorities mapped to the same queue must be in the same priority group.
• A maximum of four PFC-enabled, lossless queues are supported on an interface.
Otherwise, the reconfiguration of a default dot1p-queue assignment is rejected.
• To ensure complete no-drop service, apply the same PFC parameters on all PFC-enabled peers.
ETS Configuration Notes
ETS provides a way to optimize bandwidth allocation to outbound 802.1p classes of converged Ethernet traffic. Different traffic types
have different service needs. Using ETS, you can create groups within an 802.1p priority class to configure different treatment for traffics
with different bandwidth, latency, and best-effort needs.
When you configure ETS in a DCB map:
• The DCB map associates a priority group with a PFC operational mode (on or off) and an ETS scheduling and bandwidth allocation.
You can apply a DCB map on multiple egress ports.
• Use the ETS configuration associated with 802.1p priority traffic in a DCB map in DCBx negotiation with ETS peers.
• Traffic in priority groups is assigned to strict-queue or weighted round-robin (WRR) scheduling in an ETS configuration and is
managed using the ETS bandwidth-assignment algorithm. Dell Networking OS de-queues all frames of strict-priority traffic before
servicing any other queues. A queue with strict-priority traffic can starve other queues in the same port.
• ETS-assigned bandwidth allocation and strict-priority scheduling apply only to data queues, not to control queues.
• Dell Networking OS supports hierarchical scheduling on an interface. The control traffic on Dell Networking OS is redirected to control
queues as higher priority traffic with strict priority scheduling. After the control queues drain out, the remaining data traffic is
scheduled to queues according to the bandwidth and scheduler configuration in the DCB map. The available bandwidth calculated by
the ETS algorithm is equal to the link bandwidth after scheduling non-ETS higher-priority traffic.
• The configuration of bandwidth allocation and strict-queue scheduling is not supported at the same time for a priority group.
• Bandwidth assignment: By default, equal bandwidth is assigned to each dot1p priority in a priority group. To configure the bandwidth
assigned to the port queues associated with dot1p priorities in a priority group, use the bandwidth percentage parameter. The sum of
the bandwidth allocated to all priority groups in a DCB map must be 100% of the bandwidth on the link. You must allocate at least 1%
of the total bandwidth to each priority group.
• Scheduling of priority traffic: dot1p priority traffic on the switch is scheduled to the current queue mapping. dot1p priorities within
the same queue must have the same traffic properties and scheduling method.
244
Data Center Bridging (DCB)