Concept Guide

• Trac in priority groups is assigned to strict-queue or weighted round-robin (WRR) scheduling in an ETS conguration and is managed
using the ETS bandwidth-assignment algorithm. Dell EMC Networking OS de-queues all frames of strict-priority trac before servicing
any other queues. A queue with strict-priority trac 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 EMC Networking OS supports hierarchical scheduling on an interface. The control trac on Dell EMC Networking OS is redirected
to control queues as higher priority trac with strict priority scheduling. After the control queues drain out, the remaining data trac is
scheduled to queues according to the bandwidth and scheduler conguration in the DCB map. The available bandwidth calculated by
the ETS algorithm is equal to the link bandwidth after scheduling non-ETS higher-priority trac.
• The conguration 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 congure 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 trac: dot1p priority trac on the switch is scheduled to the current queue mapping. dot1p priorities within the
same queue must have the same trac properties and scheduling method.
• ETS conguration error: If an error occurs in an ETS conguration, the conguration is ignored and the scheduler and bandwidth
allocation settings are reset to the ETS default value: 100% of available bandwidth is allocated to priority group 0 and the bandwidth is
equally assigned to each dot1p priority.
If an error occurs when a port receives a peer’s ETS conguration, the port’s conguration resets to the ETS conguration in the previously
congured DCB map. If no DCB map was previously applied, the port resets to the default ETS parameters.
ETS Prerequisites and Restrictions
On a switch, ETS is enabled by default on Ethernet ports with equal bandwidth assigned to each 802.1p priority. You can change the default
ETS conguration only by using a DCB map.
The following prerequisites and restrictions apply when you congure ETS bandwidth allocation or strict-priority queuing in a DCB map:
• When allocating bandwidth or conguring strict-priority queuing for dot1p priorities in a priority group on a DCBx CIN interface, take
into account the CIN bandwidth allocation and dot1p-queue mapping.
• Because all the priorities mapped to a priority group is scheduled using a single queue, the priorities are treated with rst come rst
served basis.
• Although ETS bandwidth allocation or strict-priority queuing does not support weighted random early detection (WRED), explicit
congestion notication (ECN), rate shaping, and rate limiting because these parameters are not negotiated by DCBx with peer devices,
you can apply a QoS output policy with WRED and/or rate shaping on a DCBx CIN-enabled interface. In this case, the WRED or rate
shaping conguration in the QoS output policy must take into account the bandwidth allocation or queue scheduler congured in the
DCB map.
Priority-Group Conguration Notes
When you congure priority groups in a DCB map:
• A priority group consists of 802.1p priority values that are grouped together for similar bandwidth allocation and scheduling, and that
share the same latency and loss requirements. All 802.1p priorities mapped to the same queue must be in the same priority group.
• In a DCB map, each 802.1p priority must map to a priority group.
• The maximum number of priority groups supported in a DCB map on an interface is equal to the number of data queues (4) on the port.
Each priority group can support more than one data queue.
• You can enable PFC on a maximum of two priority queues on an interface.
• If you congure more than one priority group as strict priority, the higher numbered priority queue is given preference when scheduling
data trac.
294
Data Center Bridging (DCB)