Dynamic queue length thresholds for shared-memory packet switches

Abstract

In shared-memory packet switches, buffer management schemes can improve overall loss performance, as well as fairness, by regulating the sharing of memory among the different output port queues. Of the conventional schemes, static threshold (ST) is simple but does not adapt to changing traffic conditions, while pushout (PO) is highly adaptive but difficult to implement. We propose a novel scheme called dynamic threshold (DT) that combines the simplicity of ST and the adaptivity of PO. The key idea is that the maximum permissible length, for any individual queue at any instant of time, is proportional to the unused buffering in the switch. A queue whose length equals or exceeds the current threshold value may accept no more arrivals. An analysis of the DT algorithm shows that a small amount of buffer space is (intentionally) left unallocated, and that the remaining buffer space becomes equally distributed among the active output queues. We use computer simulation to compare the loss performance of DT, ST, and PO. DT control is shown to be more robust to uncertainties and changes in traffic conditions than ST control.Index Terms-Adaptive thresholds, asynchronous transfer mode, buffer allocation, dynamic thresholds, memory management, pushout, queue length thresholds, shared-memory switch.

Dynamic Neural-Based Buffer Management for Queuing Systems With Self-Similar Characteristics

“…Packet arrivals for a partitioned buffer are blocked whenever the partitioned buffer length equals or exceeds the current threshold value. In [23], the authors extend their earlier work of [10] to regulate buffer sharing among traffic classes with different loss priorities.…”

“…Although offering excellent efficiency and fairness characteristics, DPO has proven to have a very high overhead of implementation. Relying on the max-min proposal in [29], the dynamic buffer management scheme in [10] proposes simpler versions of DPO in which the individual partitioned buffer length threshold, at any instant of time, is proportional to the current amount of unused buffering in the main buffer. Packet arrivals for a partitioned buffer are blocked whenever the partitioned buffer length equals or exceeds the current threshold value.…”

Buffer Management in the Sliding-Window (SW) Packet Switch for Priority Switching

“…In the third buffer-management scheme, arriving packets are allowed to enter the buffer as long as there is available space. In the push out (PO) scheme [2] [6], when the buffer fills up, an incoming packet destined to a lightly loaded output port is allowed to enter by overwriting another packet that is already in the buffer at the tail of the longest output queue.…”

“…In the second approach of buffer management, a dynamic threshold regulates the sharing of the buffer space among output ports. In the dynamic threshold (DT) scheme [2] [5], the maximum queue length for output ports, at any instant in time, is proportional to the current amount of unused buffer space in the switch. In the third buffer-management scheme, arriving packets are allowed to enter the buffer as long as there is available space.…”

“…One type of buffer-management scheme places limits on the maximum or minimum amount of buffer space that should be available to any individual output queue. In the static threshold (ST) scheme [2] [3], also called sharing with maximum queue lengths (SMXQ) [4] [5], an arriving packet is admitted only if the queue length at its destination output port is smaller than a given threshold. In the sharing with a minimum allocation (SMA) scheme [4] [5], a minimum amount of buffer space is always reserved for each output port.…”