White Papers

Configuring Bandwidth Allocation for DCBx CIN
After you apply an ETS output policy to an interface, if the DCBx version used in your data center network is CIN, you may need
to configure a QoS output policy to overwrite the default CIN bandwidth allocation.
This default setting divides the bandwidth allocated to each port queue equally between the dot1p priority traffic assigned to the
queue.
To create a QoS output policy that allocates different amounts of bandwidth to the different traffic types/ dot1p priorities
assigned to a queue and apply the output policy to the interface, follow these steps.
1. Create a QoS output policy.
CONFIGURATION mode
Dell(conf)#qos-policy-output test12
The maximum 32 alphanumeric characters.
2. Configure the percentage of bandwidth to allocate to the dot1p priority/queue traffic in the associated L2 class map.
QoS OUTPUT POLICY mode
Dell(conf-qos-policy-out)#bandwidth-percentage 100
The default is none.
3. Repeat Step 2 to configure bandwidth percentages for other priority queues on the port.
QoS OUTPUT POLICY mode
Dell(conf-qos-policy-out)#bandwidth-percentage 100
4. Exit QoS Output Policy Configuration mode.
QoS OUTPUT POLICY mode
Dell(conf-if-te-0/1)#exit
5. Enter INTERFACE Configuration mode.
CONFIGURATION mode
interface type slot/port
6. Apply the QoS output policy with the bandwidth percentage for specified priority queues to an egress interface.
INTERFACE mode
Dell(conf-if-te-0/1)#service-policy output test12
Hierarchical Scheduling in ETS Output Policies
ETS supports up to three levels of hierarchical scheduling.
For example, you can apply ETS output policies with the following configurations:
Priority group 1
Assigns traffic to one priority queue with 20% of the link bandwidth and strict-priority scheduling.
Priority group 2 Assigns traffic to one priority queue with 30% of the link bandwidth.
Priority group 3 Assigns traffic to two priority queues with 50% of the link bandwidth and strict-priority scheduling.
In this example, the configured ETS bandwidth allocation and scheduler behavior is as follows:
Unused
bandwidth usage:
Normally, if there is no traffic or unused bandwidth for a priority group, the bandwidth allocated to the
group is distributed to the other priority groups according to the bandwidth percentage allocated to each
group. However, when three priority groups with different bandwidth allocations are used on an interface:
● If priority group 3 has free bandwidth, it is distributed as follows: 20% of the free bandwidth to
priority group 1 and 30% of the free bandwidth to priority group 2.
● If priority group 1 or 2 has free bandwidth, (20 + 30)% of the free bandwidth is distributed to priority
group 3. Priority groups 1 and 2 retain whatever free bandwidth remains up to the (20+ 30)%.
Strict-priority
groups:
If two priority groups have strict-priority scheduling, traffic assigned from the priority group with the
higher priority-queue number is scheduled first. However, when three priority groups are used and two
groups have strict-priority scheduling (such as groups 1 and 3 in the example), the strict priority group
whose traffic is mapped to one queue takes precedence over the strict priority group whose traffic is
mapped to two queues.
Data Center Bridging (DCB) 245