Administrator Guide

Valid stack-unit IDs are 0 to 5.
The only valid port-set ID (port-pipe number) is 0.
Dell Networking OS Behavior:
To achieve lossless PFC operation, the PFC port count and queue number used for the reserved buer size that is created must be greater
than or equal to the buer size required for PFC-enabled ports and lossless queues on the switch.
For the PFC buer conguration to take eect, you must reload the stack or a specied stack unit (use the reload command at EXEC
Privilege level).
If you congure the PFC buer on all stack units, delete the startup conguration on both the master and standby, and reload the stack,
the new master (previously standby) generates the following syslog message for each stack unit when it boots up:
PFC_BUFFER_CONFIG_CHANGED is generated for all stack units.
Conguring Enhanced Transmission Selection
ETS provides a way to optimize bandwidth allocation to outbound 802.1p classes of converged Ethernet trac.
Dierent trac types have dierent service needs. Using ETS, you can create groups within an 802.1p priority class to congure dierent
treatment for trac with dierent bandwidth, latency, and best-eort needs.
For example, storage trac is sensitive to frame loss; interprocess communication (IPC) trac is latency-sensitive. ETS allows dierent
trac types to coexist without interruption in the same converged link by:
• Allocating a guaranteed share of bandwidth to each priority group.
• Allowing each group to exceed its minimum guaranteed bandwidth if another group is not fully using its allotted bandwidth.
To congure ETS and apply an ETS dcb-map to an interface, you must follow the steps described in Conguring Priority-Based Flow
Control.
How Enhanced Transmission Selection is Implemented
Enhanced transmission selection (ETS) provides a way to optimize bandwidth allocation to outbound 802.1p classes of converged Ethernet
trac. Dierent trac types have dierent service needs. Using ETS, groups within an 802.1p priority class are auto-congured to provide
dierent treatment for trac with dierent bandwidth, latency, and best-eort needs.
For example, storage trac is sensitive to frame loss; interprocess communication (IPC) trac is latency-sensitive. ETS allows dierent
trac types to coexist without interruption in the same converged link.
NOTE
: The IEEE 802.1Qaz, CEE, and CIN versions of ETS are supported.
ETS is implemented on an Aggregator as follows:
• Trac in priority groups is assigned to strict-queue or WERR scheduling in a dcb-map and is managed using the ETS bandwidth-
assignment algorithm. Dell Networking OS de-qeues 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 scheduling apply only to data queues, not to control queues.
• Dell Networking OS supports hierarchical scheduling on an interface. Dell Networking OS control trac is redirected to control queues
as higher priority trac with strict priority scheduling. After 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.
• By default, equal bandwidth is assigned to each port queue and each dot1p priority in a priority group.
• By default, equal bandwidth is assigned to each priority group in the dcb-map applied to an egress port. The sum of auto-congured
bandwidth allocation to dot1p priority trac in all ETS priority groups is 100%.
• dot1p priority trac on the switch is scheduled according to the default dot1p-queue mapping. dot1p priorities within the same queue
should have the same trac properties and scheduling method.
248
Data Center Bridging (DCB)