Method and device for allocating and controlling buffer space of multiple queues

Abstract

The invention discloses a method and a device for allocating and controlling cache space of multiple queues. The invention allocates a share for each queue that needs to allocate cache space to be shared by determining the number of queues that need to allocate cache space to be shared. Cache space, and as the number of queues that need to be allocated cache space to be shared changes, allocate shared cache space for each queue that needs to be allocated cache space to be shared, realizing automatic adjustment and allocation of cache space according to network traffic, saving Hardware resources are conducive to hardware practice, and at the same time, the utilization rate of cache space is improved.

Description

technical field [0001] The present invention relates to the field of buffering, in particular to a method and device for allocating and controlling the buffering space of multiple queues. Background technique [0002] With the popularity of the Internet, information exchange and information sharing have become an indispensable part of people's daily life. With the continuous growth of interactive information (data packets) in the network, it will inevitably cause network congestion. Therefore, how to avoid congestion is particularly important. The congestion avoidance mechanism widely used on the Internet (Internet) is the RED (Random Early Discard) mechanism. The key to the RED mechanism is how to effectively use limited cache resources and perform reasonable discarding, so as to avoid congestion and ensure a smooth network. [0003] In the existing multi-queue cache of the RED device using the RED mechanism, the usual ways of allocating the cache include: method 1, which...

AI Technical Summary

Problems solved by technology

[0004] However, there are unavoidable defects in the above method:

[0005] Defect 1. It is relatively simple to use the above method to divide the cache. However, since the cache of each queue is pre-allocated and fixed after allocation, it cannot be automatically adjusted according to the real-time network traffic of each queue. The cache utilization rate is low and lacks self-adaptation performance, and cannot really achieve the effect of shared cache, because after allocation, the maximum amount of cache that each queue can use is the part allocated to itself;

[0006] Defect 2. Using the above method 2 to share the cache, when the activation queue is small, the cache utilization rate is low, and the algorithm is relatively complicated, which is not conducive to hardware implementation

Images