-
If PFC is enabled on a port or a port channel, it does not cause a port flap.
-
Ensure that ports or port channels have enough resources before enabling PFC on them.
-
PFC configuration enables PFC in both the send (Tx) and receive (Rx) direction.
-
Only an exact match of the no-drop CoS is considered as a successful negotiation of PFC by the Data Center Bridging Exchange
Protocol (DCBXP).
-
Configuration time quanta of the pause frames is not supported.
-
The configuration does not support pausing selected streams that are mapped to a particular traffic-class queue. All flows
that are mapped to the class are treated as no-drop. It blocks out scheduling for the entire queue, which pauses traffic for
all the streams in the queue. To achieve lossless service for a no-drop class, we highly recommend that you have only the
no-drop class traffic on the queue.
-
For VLAN-tagged packets, priority is always assigned based on the 802.1p field in the VLAN tag and takes precedence over the
assigned internal priority(qos-group). DSCP or IP access-list classification cannot be performed on VLAN-tagged frames
-
When a no-drop class is classified based on 802.1p CoS x and assigned an internal priority value (qos-group) of y, we recommend
that you use the internal priority value x to classify traffic on 802.1p CoS only, and not on any other field. For x, the
packet priority assigned is x if the classification is not based on CoS, which results in packets of the internal priority
that is x and y to map to the same priority x.
-
The PFC feature supports up to three no-drop classes of any MTU size. However, there is a limit on the number of PFC-enabled
interfaces based on the following factors:
-
MTU size of the no-drop class
-
Number of 10G and 40G ports
-
Pause buffer size configuration in the input queuing policies
-
Interface QoS policy takes precedence over the system policy. PFC priority derivation also occurs in the same order.
-
Ensure that you apply the same interface-level QoS policy on all PFC-enabled interfaces for both ingress and egress.
Caution
|
Irrespective of the PFC configuration, we recommend that you stop traffic before you apply or remove the queuing policy that
has strict priority levels at the interface level or the system level.
|
-
To achieve end-to-end lossless service over the network, we recommend that you enable PFC on each interface through which
the no-drop class traffic flows #(Tx/Rx).
-
To achieve lossless service for a no-drop class, it is recommended that you maintain only no-drop class traffic on the egress
queue.
-
We recommend that you change the PFC configuration when there is no traffic; otherwise, packets already in the memory management
unit (MMU) of the system might not get the expected treatment.
-
The buffers required for PFC are best allocated automatically. However, you can change the buffer thresholds by configuring
input queuing policies.
-
For no-drop classes classified based on DSCP/IP access-lists (non CoS based classifications), we highly recommend that you
use the same qos-group value as the match CoS value.
-
Do not enable WRED on a no-drop class because it results in egress queue drops.
-
When you configure a port from the 40 Gigabit Ethernet mode to the 10 Gigabit Ethernet mode or from the 10 Gigabit Ethernet
mode to the 40 Gigabit Ethernet mode, the affected ports will be administratively unavailable and PFC will be disabled on
these ports. To make these ports available, use the no shut command. After the ports are available, PFC will become enabled on them.
-
Beginning with Cisco NX-OS Release 7.0(3)I4(2), the no lldp tlv-select dcbxp command is enhanced so that the PFC is disabled for interfaces on both sides of back-to-back switches.
-
When the 'hardware qos pfc mc-drop' configuration is enabled on Cisco Nexus 3064 switches, and if the no-drop and drop qos-groups
are mapped to the same queue, then flapping the link or removing/adding PFC configurations will result in the drop-multicast
feature not working correctly. This is due to the hardware limitation of having only four multicast queues in Cisco Nexus
3064 switches. To avoid this issue, do one of the following:
-
Specify both of the qos-groups that correspond to a single multicast queue as no-drop.
-
Change the mapping of the multicast queue to qos-groups using the wrr-queue qos-group-map <queue-no> <qos-groups that are no-drop> command.
-
Beginning with Cisco NX-OS Release 7.0(3)I7(8), you can see additional syslog messages for multicast queue drops on no-drop
class when you enable hardware qos pfc mc-drop global configuration on Cisco Nexus 3000 and 3100 switches. However this feature is not supported on Cisco Nexus C3132Q-V,
C31108PC-V, C31108TC-V and C3132C-Z switches.
-
Beginning with Cisco NX-OS Release 7.0(3)I7(4), when PFC is received on a lossy priority group (non-configured), the event
is recorded in the syslog for subsequent analysis.
Cisco Nexus N3000 and N3100 series switches report BCM_UNEXPECTED_PFC_FRAMES syslog whenever PFC frames are received with
unexpected CoS. The syslog contains the approximate count of the unexpected PFC frames received for a particular CoS in the
last two seconds. The packets per second (PPS) metric can be derived by dividing this number by two.
-
Beginning with Cisco NX-OS Release 7.0(3)I7(4), switches can be configured to drop multicast/broadcast traffic on no-drop
configured classes with the hardware qos pfc mc-drop command.
-
Beginning with Cisco NX-OS Release 7.0(3)I7(4), traffic across all no-drop queues and incoming PFC frames for no-drop classes
can be configured to be dropped with the priority-flow-control watch-dog forced on command. (Use the no priority-flow-control watch-dog forced on command to re-enable the traffic for no-drop classes.)
-
When a queue (under an interface) becomes stuck, you can use the priority-flow-control watch-dog-interval on disable-action command to send a message to the syslog that describes the status of the queue instead of shutting the queue (Cisco NX-OS
Release 7.0(3)I7(4) and later).
Example:
switch(config)# interface ethernet 1/12
switch(config-if)# priority-flow-control watch-dog-interval on disable-action