Users Guide

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 congurations:

Priority group 1 Assigns trac to one priority queue with 20% of the link bandwidth and strict-priority scheduling.

Priority group 2 Assigns trac to one priority queue with 30% of the link bandwidth.

Priority group 3 Assigns trac to two priority queues with 50% of the link bandwidth and strict-priority scheduling.

In this example, the congured ETS bandwidth allocation and scheduler behavior is as follows:

Unused bandwidth

usage:

Normally, if there is no trac 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 dierent 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, trac assigned from the priority group with the higher

priority-queue number is scheduled rst. 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 trac is mapped to one

queue takes precedence over the strict priority group whose trac is mapped to two queues.

Therefore, in this example, scheduling trac to priority group 1 (mapped to one strict-priority queue) takes precedence over scheduling

trac to priority group 3 (mapped to two strict-priority queues).

DCBx Operation

The data center bridging exchange protocol (DCBx) is used by DCB devices to exchange conguration information with directly connected

peers using the link layer discovery protocol (LLDP) protocol. DCBx can detect the misconguration of a peer DCB device, and optionally,

congure peer DCB devices with DCB feature settings to ensure consistent operation in a data center network.

DCBx is a prerequisite for using DCB features, such as priority-based ow control (PFC) and enhanced trac selection (ETS), to exchange

link-level congurations in a converged Ethernet environment. DCBx is also deployed in topologies that support lossless operation for FCoE

or iSCSI trac. In these scenarios, all network devices are DCBx-enabled (DCBx is enabled end-to-end).

The following versions of DCBx are supported on an Aggregator: CIN, CEE, and IEEE2.5.

DCBx requires the LLDP to be enabled on all DCB devices.

DCBx Operation

DCBx performs the following operations:

• Discovers DCB conguration (such as PFC and ETS) in a peer device.

• Detects DCB mis-conguration in a peer device; that is, when DCB features are not compatibly congured on a peer device and the

local switch. Mis-conguration detection is feature-specic because some DCB features support asymmetric conguration.

• Recongures a peer device with the DCB conguration from its conguration source if the peer device is willing to accept

conguration.

• Accepts the DCB conguration from a peer if a DCBx port is in “willing” mode to accept a peer’s DCB settings and then internally

propagates the received DCB conguration to its peer ports.

Data Center Bridging (DCB)