White Papers

pauses traffic on a link according to the 802.1p priority set on a traffic type. You can create lossless flows for storage and server
traffic while allowing for loss in case of LAN traffic congestion on the same physical interface.
The following illustration shows how PFC handles traffic congestion by pausing the transmission of incoming traffic with dot1p
priority 3.
Figure 139. Priority-Based Flow Control
In the system, PFC is implemented as follows:
● PFC is supported on specified 802.1p priority traffic (dot1p 0 to 7) and is configured per interface. However, only two
lossless queues are supported on an interface: one for Fibre Channel over Ethernet (FCoE) converged traffic and one for
Internet Small Computer System Interface (iSCSI) storage traffic. Configure the same lossless queues on all ports.
● PFC delay constraints place an upper limit on the transmit time of a queue after receiving a message to pause a specified
priority.
● By default, PFC is enabled on an interface with no dot1p priorities configured. You can configure the PFC priorities if the
switch negotiates with a remote peer using DCBX.
● During DCBX negotiation with a remote peer:
○ If the negotiation succeeds and the port is in DCBX Willing mode to receive a peer configuration, PFC parameters from
the peer are used to configured PFC priorities on the port. If you enable the link-level flow control mechanism on the
interface, DCBX negotiation with a peer is not performed.
○ If the negotiation fails and PFC is enabled on the port, any user-configured PFC input policies are applied. If no PFC input
policy has been previously applied, the PFC default setting is used (no priorities configured). If you do not enable PFC on
an interface, you can enable the 802.3x link-level pause function. By default, the link-level pause is disabled.
● PFC supports buffering to receive data that continues to arrive on an interface while the remote system reacts to the PFC
operation.
● PFC uses the DCB MIB IEEE802.1azd2.5 and the PFC MIB IEEE802.1bb-d2.2.
Enhanced Transmission Selection
Enhanced transmission selection (ETS) supports optimized bandwidth allocation between traffic types in multiprotocol
(Ethernet, FCoE, SCSI) links.
ETS allows you to divide traffic according to its 802.1p priority into different priority groups (traffic classes) and configure
bandwidth allocation and queue scheduling for each group to ensure that each traffic type is correctly prioritized and receives
its required bandwidth. For example, you can prioritize low-latency storage or server cluster traffic in a traffic class to receive
more bandwidth and restrict best-effort LAN traffic assigned to a different traffic class.
Although you can configure strict-priority queue scheduling for a priority group, ETS introduces flexibility that allows the
bandwidth allocated to each priority group to be dynamically managed according to the amount of LAN, storage, and server
traffic in a flow. Unused bandwidth is dynamically allocated to prioritized priority groups. Traffic is queued according to its
802.1p priority assignment, while flexible bandwidth allocation and the configured queue-scheduling for a priority group is
supported.
The following figure shows how ETS allows you to allocate bandwidth when different traffic types are classed according to
802.1p priority and mapped to priority groups.
FC Flex IO Modules
927