TM Chip Dynamic Queue Allocation for HQoS Resource Efficiency
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In hierarchical quality of service (HQoS) technology, a fixed quantity of queues allocated to each first-level scheduler leads to idle queues when data types are less than the fixed quantity, resulting in resource wastage, and inadequate scheduling when data types exceed the fixed quantity.
Innovation Solution
A network device with a traffic management (TM) chip that schedules queues from a shared queue resource pool, allowing dynamic allocation and reclamation of queues based on actual requirements, decoupling queue allocation from first-level schedulers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Stability of the object's composition
If a fixed quantity of queues are allocated to each first-level scheduler, then queue allocation is simple and stable, but queue resource utilization is low when data types are less than the fixed quantity
Solution Approach 1:
The patent implements dynamic queue allocation where the quantity of queues allocated to each first-level scheduler is not fixed but can be adjusted based on actual data transmission requirements. The controller dynamically allocates queues from a queue resource pool to different first-level schedulers according to the number of data types each scheduler needs to handle, thereby eliminating idle queues and improving resource utilization while maintaining operational stability through controlled dynamic adjustment.
2Ease of operation
If a fixed quantity of queues are allocated to each first-level scheduler, then queue management is easy, but scheduling flexibility is insufficient when data types exceed the fixed quantity
Solution Approach 1:
The system dynamically adjusts the number of queues allocated to each first-level scheduler based on the actual number of data types that need scheduling. When data types exceed the fixed quantity, the controller can allocate additional queues from the resource pool to meet the scheduling requirements, thereby improving adaptability without significantly complicating queue management through automated control.
Solution Approach 2:
The patent creates a shared queue resource pool that serves multiple first-level schedulers simultaneously. This universal queue pool can be dynamically allocated to any scheduler that needs it, allowing the same queue resources to serve multiple different data types and schedulers, thereby improving scheduling flexibility while maintaining manageable queue operations through centralized control.
3Quantity of substance
If multiple different types of data share one queue, then queue quantity is reduced, but classified scheduling cannot be performed on different types of data
Solution Approach 1:
The patent segments the queue resource pool into multiple queues that can be separately allocated to different first-level schedulers based on data type requirements. Each first-level scheduler can be assigned dedicated queues for specific data types, enabling classified scheduling while maintaining a reasonable total queue quantity through shared resource pool management rather than having completely separate queues for each scheduler.
Data Source
AI summary
This application describes a network device, a controller, a queue management method, and a traffic management chip. The method may be applied to a traffic management chip that uses an HQoS technology, and can include receiving a queue management instruction sent by a controller, where the queue management instruction includes an identifier of a first scheduler and an identifier of a first queue, and the first scheduler is one of multiple first-level schedulers. The method may also include controlling, according to the queue management instruction, scheduling of the first queue by the first scheduler, where a queue scheduled by the first scheduler belongs to a queue resource pool of the TM chip, and the queue resource pool includes at least one to-be-allocated queue. In this application, decoupling between queue allocation and the first-level schedulers is implemented, flexibility of queue allocation is improved, and utilization of queue resources is improved.