When the decommission entries are not configured, during system initialization, based on the maximum number of ports supported on the device, the total buffer is distributed into per port egress buffer pool for access ports, network ports, access-uplink ports and hybrid ports. Each port on the system gets an equal portion of the available buffers. From the buffers allocated to a port, each queue gets its CBS amount of buffers. The remaining buffers are allocated toward the shared MBS pool per port. All the queues of the port can use the buffers from the shared MBS pool. This model of buffer pool allocation is called per port MBS pool.
With the per port MBS pool, each queue is allocated with a small fixed amount of buffers toward the CBS (Committed burst size) and each port is allocated with a shared pool of buffers toward the MBS (Maximum Burst Size). The queue’s CBS portion of buffers guarantees that the queue does not starve because of lack of buffers.
The buffers allocated toward the MBS pool, allow each port to handle some amount of burst. Per port MBS pool/portion of buffers is shared by all the queues of the port and allows any queue or a small group of queues of the port to absorb larger bursts assuming that, not all the queues receive burst simultaneously. In a typical network, the router/switch in the ingress traffic is usually a mix of packets of different sizes and different flows burst at different time intervals, which allows for better burst absorption capability per queue using shared resources.